{ "provenance_domain": { "name": "Fruitfly Protein Isoform sequences (UniProtKB)", "version": "v-x.x.x", "created": "2022-08-30T12:21:27.326808", "modified": "2022-09-26T09:08:12.539404", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Isoform sequences (UniProtKB) dataset contains fruitfly [taxid:7227] protein fasta sequences for the fruitfly isoform accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "All Protein Sequences", "category_name": "tag" }, { "category_value": "fasta", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein isoform sequences", "fasta", "UniProtKB" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB fasta sequence for all fruitfly isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_allsequences.fasta", "filename": "fruitfly_protein_allsequences.fasta" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "fasta", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_allsequences.fasta", "filename": "fruitfly_protein_allsequences.fasta" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_allsequences.stat.csv", "filename": "fruitfly_protein_allsequences.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000634/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "9aca4ef9e033b4a5684e0531e854d9d9c3ceb476b470ab81d6378da0b9f3fa4e" } { "provenance_domain": { "name": "Fruitfly Protein Alternative Name (UniProtKB)", "version": "v-x.x.x", "created": "2022-08-30T13:19:31.385999", "modified": "2022-09-26T09:08:12.445889", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Alternative Name (UniProtKB) dataset contains UniProtKB alternative names for fruitfly [taxid:7227] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Protein Alternative Names", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein alternative name", "UniProtKB" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB alternative names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_altnames.csv", "filename": "fruitfly_protein_altnames.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_altnames.csv", "filename": "fruitfly_protein_altnames.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_altnames.stat.csv", "filename": "fruitfly_protein_altnames.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000635/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "8839ab6e8b03cb56c1a34c97c5a34d32efaf3355307336468890dea862d2eedd" } { "provenance_domain": { "name": "Fruitfly Protein Binary Interactions (IntAct)", "version": "v-x.x.x", "created": "2022-09-06T12:13:07.540218", "modified": "2022-09-26T09:08:12.548920", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Binary Interaction (IntAct) dataset contains fruitfly [taxid:10116] binary interaction data for UniProtKB canonical accession from IntAct database. The data is quality filtered by UniProt from IntAct and contains information about the interactors, number of experiments, IntAct Ids etc. If you use this dataset please provide proper attribution to UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Binary Interaction", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "Binary Interactions", "IntAct", "UniProtKB" ], "pipeline_steps": [ { "step_number": 0, "name": "make-protein-dataset.py", "description": "The script loads the binary interactions data for UniProtKB canonical interactions from the triplestore and extracts it as a dataset in csv format", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_binary_interactions.csv", "filename": "fruitfly_protein_binary_interactions.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_binary_interactions.csv", "filename": "fruitfly_protein_binary_interactions.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_binary_interactions.stat.csv", "filename": "fruitfly_protein_binary_interactions.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000691/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "a810498ae19086659cf2675e3ded72936f745ef96a174837e214eabde96f80d1", "error_domain": { "empirical_error": {}, "algorithmic_error": {} } } { "provenance_domain": { "name": "Fruitfly Protein Canonical sequences (UniProtKB)", "version": "v-x.x.x", "created": "2022-08-30T14:04:28.411067", "modified": "2022-09-26T09:08:12.757432", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Canonical (UniProtKB) Sequences dataset contains fruitfly [taxid:7227] canonical protein fasta sequences from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Canonical Protein fasta Sequences", "category_name": "tag" }, { "category_value": "fasta", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein sequence", "fasta", "UniProtKB canonical accessions" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB fasta sequence for all fruitfly canonical accessions data from the triplestore containing triples from nt file and extracts it into a dataset as fasta format", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/v-x.x.x/reviewed/fruitfly_protein_canonicalsequences.fasta", "filename": "fruitfly_protein_canonicalsequences.fasta" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "fasta", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_canonicalsequences.fasta", "filename": "fruitfly_protein_canonicalsequences.fasta" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_canonicalsequences.stat.csv", "filename": "fruitfly_protein_canonicalsequences.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000636/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "0ea77d132fb9e44312e66fd8e8fddba453302345a0e6d8b3d0943d00e7faaa95" } { "object_id": "https://biocomputeobject.org/GLY_000742/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "a10d7486e02cfa80987f3c7d6ce6b707ee3b87aa", "provenance_domain": { "name": "Fruitfly Protein Citations (Reactome)", "version": "v-x.x.x", "license": "https://creativecommons.org/licenses/by/4.0/", "created": "2019-11-30T12:49:42.900057", "modified": "2022-09-26T09:05:27.638299", "contributors": [ { "name": "Jeet Vora", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jeetvora@gwu.edu" }, { "name": "Robel Kahsay", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "rykahsay@gwu.edu" }, { "name": "Maria Martin", "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "email": "martin@ebi.ac.uk" }, { "name": "Preethi Vasudev", "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "email": "pvasudev@ebi.ac.uk" }, { "name": "Karina Martinez", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "review": [] }, "usability_domain": [ "The Fruitfly Protein Reactions (Reactome) dataset contains reactions information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Reactions Reactome", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "Reactome", "Pathway", "Reactions", "PMID" ], "pipeline_steps": [ { "name": "make-protein-dataset.py", "version": "", "step_number": 1, "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_citations_reactome.csv", "filename": "fruitfly_protein_citations_reactome.csv" } ], "prerequisite": [], "description": "The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format" } ] }, "execution_domain": { "external_data_endpoints": [], "environment_variables": {}, "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ] }, "parametric_domain": [ { "step": "", "value": "", "param": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_protein_reactions_reactome.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_reactions_reactome.csv" } }, { "uri": { "filename": "fruitfly_protein_xref_reactome.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_reactome.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_citations_reactome.csv", "filename": "fruitfly_protein_citations_reactome.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_citations_reactome.stat.csv", "filename": "fruitfly_protein_citations_reactome.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} } } { "provenance_domain": { "name": "Fruitfly Protein Citations (UniProtKB)", "version": "v-x.x.x", "created": "2022-08-30T14:17:09.307325", "modified": "2022-09-26T09:08:12.727097", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Citations dataset contains publication information for fruitfly [taxid:7227] UniProtKB accessions that includes PMID, journal name, date and author and title. Publications of large scale studies, and high frequency publications pertaining to genome sequencing, cDNA, chromosomes have been filtered out as per https://data.glygen.org/ln2data/releases/data/v-1.12.3/compiled/fruitfly_protein_blacklisted_pmids_uniprotkb.csv. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Protein Citations", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "publications", "PMID", "journal", "citations", "authors", "UniProtKB", "PubMed" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file.", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/compiled/fruitfly_protein_blacklisted_pmids_uniprotkb.csv", "filename": "fruitfly_protein_blacklisted_pmids_uniprotkb.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_citations_uniprotkb.csv", "filename": "fruitfly_protein_citations_uniprotkb.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_citations_uniprotkb.csv", "filename": "fruitfly_protein_citations_uniprotkb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_citations_uniprotkb.stat.csv", "filename": "fruitfly_protein_citations_uniprotkb.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000637/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "c602995925caab09f524b5c2d8fab9feef2e28871ac49f0620b8ef94aa1798fa" } { "provenance_domain": { "name": "Fruitfly Protein Enzyme Annotation (UniProtKB)", "version": "v-x.x.x", "created": "2022-08-30T14:44:26.008676", "modified": "2022-09-26T09:08:12.523790", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Enzyme Annotation (UniProtKB) dataset contains fruitfly [taxid:7227] enzyme annotations for UniProtKB canonical accessions. The dataset contains ec numbers and enzyme activity that describes the enzymatic reactions. The dataset is derived form 2019-09 UniprotKB release. If you use this dataset please give proper attribution to UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "enzyme annotation", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "enzyme annotation", "enzyme ", "UniProtKB", "enzyme activity", "EC number" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script extracts the enzyme annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_enzyme_annotation_uniprotkb.csv", "filename": "fruitfly_protein_enzyme_annotation_uniprotkb.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_enzyme_annotation_uniprotkb.csv", "filename": "fruitfly_protein_enzyme_annotation_uniprotkb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_enzyme_annotation_uniprotkb.stat.csv", "filename": "fruitfly_protein_enzyme_annotation_uniprotkb.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000638/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "5cc46d1524fef2b3ca558d97b4b6df3827d6865c4a0497dc9ccbbb5cdb622767", "error_domain": { "empirical_error": {}, "algorithmic_error": {} } } { "provenance_domain": { "name": "Fruitfly Protein Function (UniProtKB)", "version": "v-x.x.x", "created": "2022-08-30T14:58:43.098400", "modified": "2022-09-26T09:08:12.461522", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Function (UniProtKB) dataset contains biological function annotation for fruitfly [taxid:7227] protein accessions from the UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. " ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Protein Function", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein function", "UniProtKB" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB function annotations triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_function_uniprotkb.csv", "filename": "fruitfly_protein_function_uniprotkb.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_function_uniprotkb.csv", "filename": "fruitfly_protein_function_uniprotkb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_function_uniprotkb.stat.csv", "filename": "fruitfly_protein_function_uniprotkb.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000639/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "0d5572d6ca592a6cbae36645a2b5785dba7a467f526d61007d8e4a961f251486" } { "provenance_domain": { "name": "Fruitfly Gene Locus (Ensembl)", "version": "v-x.x.x", "created": "2020-04-10T11:29:22.824792", "modified": "2022-09-26T09:08:12.732452", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Gene Locus (Ensembl) contains fruitfly [taxid:7227] UniProtKB canonical accessions mapped to the corresponding ensembl Gene ID, chromosome ID along with the gene's start and end position on the chromosome. The dataset is derived from 2019-09 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Gene Coordinates", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "gene coordinates", "chromosome", "start position", "end position", "Ensembl", "strand" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are mapped to ENSEMBL Gene identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_genelocus.csv", "filename": "fruitfly_protein_genelocus.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv" } }, { "uri": { "filename": "Drosophila_melanogaster.BDGP6.32.104.gtf", "uri": "/data/shared/glyds/downloads/ucsc/gtf/Drosophila_melanogaster.BDGP6.32.104.gtf" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_genelocus.csv", "filename": "fruitfly_protein_genelocus.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_genelocus.stat.csv", "filename": "fruitfly_protein_genelocus.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000640/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "dc9ba57eb818e56b7043ef762289622ec5b3dc7060c76bd03cf8b82081bc1e7a" } { "provenance_domain": { "name": "Fruitfly Gene Names (NCBI RefSeq)", "version": "v-x.x.x", "created": "2022-08-30T15:40:57.216837", "modified": "2022-09-26T09:08:12.476226", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "affiliation": "", "contribution": [ "contributedBy" ], "name": "Not Applicable", "email": "" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Gene Names (NCBI RefSeq) dataset contains fruitfly [taxid:7227] gene Names/names (primary gene name and gene synonyms) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Protein Information", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein gene names", "NCBI RefSeq" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script parses the NCBI RefSeq gpff files to extract the gene Names/names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_refseq.csv", "filename": "fruitfly_protein_xref_refseq.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/refseq_protein_all_7227.gpff", "filename": "refseq_protein_all_7227.gpff" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_genenames_refseq.csv", "filename": "fruitfly_protein_genenames_refseq.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_protein_xref_refseq.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_refseq.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_genenames_refseq.csv", "filename": "fruitfly_protein_genenames_refseq.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_genenames_refseq.stat.csv", "filename": "fruitfly_protein_genenames_refseq.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000642/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "9822ab66b005a1525e242bd8f7a96fd43f7779dbbd511f2d52bbce8b1c0ede88" } { "provenance_domain": { "name": "Fruitfly Gene Names (UniProtKB)", "version": "v-x.x.x", "created": "", "modified": "2022-09-26T09:08:12.751848", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Gene Names (UniProtKB) dataset contains UniProtKB gene Names/names for fruitfly [taxid:7227] proteins. It contains the recommended gene symbol, alternative gene symbol and ORF gene names assigned by the Gene Name Nomenclature commitees. (for more info - https://www.uniprot.org/help/gene_name). If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Gene Names", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein alternative name", "UniProtKB" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB gene Names for protein accessions from the triplestore containing triples from nt file and extracts the alternative protein names into csv dataset file", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_genenames_uniprotkb.csv", "filename": "fruitfly_protein_genenames_uniprotkb.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_genenames_uniprotkb.csv", "filename": "fruitfly_protein_genenames_uniprotkb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_genenames_uniprotkb.stat.csv", "filename": "fruitfly_protein_genenames_uniprotkb.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000641/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "082b310fbd13d0250f9cca4cbe06e72421931e681136423d7cb9f26e2b29f78a" } { "provenance_domain": { "name": "Fruitfly Glycohydrolases", "version": "v-x.x.x", "created": "2022-09-06T11:23:37.687653", "modified": "2022-09-26T09:08:12.673905", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Glycohydrolases dataset contains a list of fruitfly [taxid:7227] glycohydrolases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam.If you use this dataset please provide proper attribution to UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Glycohydrolases", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "glycohydrolase", "glycosidase", "EC Number", "CAZy" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script maps and replaces the UniProtKB accession to the UniProtKB canonical accession", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/compiled/fruitfly_protein_glycohydrolase.csv", "filename": "fruitfly_protein_glycohydrolase.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_glycohydrolase.csv", "filename": "fruitfly_protein_glycohydrolase.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_protein_glycohydrolase.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/compiled/fruitfly_protein_glycohydrolase.csv" } }, { "uri": { "filename": "fruitfly_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_glycohydrolase.csv", "filename": "fruitfly_protein_glycohydrolase.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_glycohydrolase.stat.csv", "filename": "fruitfly_protein_glycohydrolase.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000685/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "04ae7a53313b73f1aa1ea1e98afb8396a3f5405565df21fb38132be48214c369" } { "provenance_domain": { "name": "Fruitfly N-Glycosylation Sequon", "version": "v-x.x.x", "created": "2022-08-30T16:10:07.494670", "modified": "2022-09-26T09:08:12.486880", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly N-Glycosylation Sequon dataset contains N-glycosylation sequon or motif or consensus sequence for fruitfly [taxid:7227] UniProtKB canonical sequences identified by the script. The script identifies the N-glycosylation sequon pattern - Asn-X-Ser/Thr , where X is any amino acid except proline (Pro) for UniProtKB accessions. " ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "N-Glycosylation Sequon", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "n-glycosylation sequon", "NXS/T", "n-glycosylation motif", "n-glycosylation consensus sequence" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script uses the PS Scan tool (accession- PS00001) from ProSite to extracts the N-glycosylation pattern/sequon/motif N-{P}-[ST]-{P} where P is not a proline from the UniProtKB canonical sequences. More info - https://prosite.expasy.org/PDOC00001, https://prosite.expasy.org/PS00001 and extracts as a csv.", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_canonicalsequences.fasta", "filename": "fruitfly_protein_canonicalsequences.fasta" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_glycosylation_motifs.csv", "filename": "fruitfly_protein_glycosylation_motifs.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_protein_canonicalsequences.fasta", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_canonicalsequences.fasta" } }, { "uri": { "filename": "prosite.dat", "uri": "/data/shared/glyds/downloads/prosite/prosite.dat" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_glycosylation_motifs.csv", "filename": "fruitfly_protein_glycosylation_motifs.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_glycosylation_motifs.stat.csv", "filename": "fruitfly_protein_glycosylation_motifs.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000643/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "a65ba4c3f4e8152a387b0e23ffaaf8fb9f510c67a41c6007cbda036d396f89c0", "error_domain": { "empirical_error": {}, "algorithmic_error": {} } } { "provenance_domain": { "name": "Fruitfly Glycosyltransferases", "version": "v-x.x.x", "created": "2022-09-06T11:20:50.205601", "modified": "2022-09-26T09:08:12.697120", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "authoredBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Glycosyltransferases dataset contains a list of fruitfly [taxid:7227] Glycosyltransferases derived from UniProtKB database using advanced search and other databases including CAZy, InterPro and Pfam.If you use this dataset please provide proper attribution to UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Glycosyltransferases", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "GT", "gycosyltransferase", "CAZy" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script maps and replaces the UniProtKB accession to the UniProtKB canonical accession", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/compiled/fruitfly_protein_glycosyltransferase.csv", "filename": "fruitfly_protein_glycosyltransferase.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_glycosyltransferase.csv", "filename": "fruitfly_protein_glycosyltransferase.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_protein_glycosyltransferase.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/compiled/fruitfly_protein_glycosyltransferase.csv" } }, { "uri": { "filename": "fruitfly_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_glycosyltransferase.csv", "filename": "fruitfly_protein_glycosyltransferase.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_glycosyltransferase.stat.csv", "filename": "fruitfly_protein_glycosyltransferase.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000684/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "eebd51d5b8474c44e7ba6529a61380606b75cce0167f278c6b4c4127d1e33227" } { "provenance_domain": { "name": "Fruitfly Gene Ontology (GO)", "version": "v-x.x.x", "created": "2022-08-30T16:13:56.875825", "modified": "2022-09-26T09:08:12.556119", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Gene Ontology (GO) dataset contains fruitfly [taxid:7227] Gene Ontology Id and name, categories and evidence information for UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. " ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Gene Ontology (Go)", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "go id", "go name", "molecular function", "biological process", "cellular component", "Gene Ontology (GO)" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script extracts the GO Id, name, category and evidence from the triplestore of NT file and maps it to the UniProtKB canonical sequences. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_go_annotation.csv", "filename": "fruitfly_protein_go_annotation.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_go_annotation.csv", "filename": "fruitfly_protein_go_annotation.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_go_annotation.stat.csv", "filename": "fruitfly_protein_go_annotation.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000644/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "875a0d80e2b858c1eed9e89108698e27008268c0f746c49b8564b75a29b32424", "error_domain": { "empirical_error": {}, "algorithmic_error": {} } } { "provenance_domain": { "name": "Fruitfly Protein Information (NCBI RefSeq)", "version": "v-x.x.x", "created": "2022-08-30T16:17:01.573604", "modified": "2022-09-26T09:08:12.614356", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Information (NCBI RefSeq) dataset contains fruitfly [taxid:7227] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Protein Information", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein information", "protein length", "NCBI RefSeq", "protein summary" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_refseq.csv", "filename": "fruitfly_protein_xref_refseq.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/refseq_protein_all_7227.gpff", "filename": "refseq_protein_all_7227.gpff" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_info_refseq.csv", "filename": "fruitfly_protein_info_refseq.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_protein_xref_refseq.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_refseq.csv" } }, { "uri": { "filename": "refseq_protein_all_7227.gpff", "uri": "/data/shared/glyds/downloads/ncbi/refseq/2023_07_13/refseq_protein_all_7227.gpff" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_info_refseq.csv", "filename": "fruitfly_protein_info_refseq.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_info_refseq.stat.csv", "filename": "fruitfly_protein_info_refseq.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000645/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "71970c32a09f635d4f2110efe282a55e89fe374ac8bab691e3c362984b80ad6a" } { "provenance_domain": { "name": "Fruitfly Protein Information (UniProtKB)", "version": "v-x.x.x", "created": "2022-08-30T16:19:56.970676", "modified": "2022-09-26T09:08:12.657372", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Information dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with their UniProtKB entry [id/mnemonic] name and properties such as mass and length. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Protein Information", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "UniProtKB entry id", "UniProtKB mnemonic name", "protein length", "protein mass" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB entry id/mnemonic name, protein mass and length for all canonical accessions from the triplestore containing triples from nt file and extracts it into a dataset as a csv format", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_info_uniprotkb.csv", "filename": "fruitfly_protein_info_uniprotkb.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_info_uniprotkb.csv", "filename": "fruitfly_protein_info_uniprotkb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_info_uniprotkb.stat.csv", "filename": "fruitfly_protein_info_uniprotkb.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000646/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "af0421819e8e048a159bd27e5f98ac89d5740f9451f1175847c8e4eb90eb707b" } { "provenance_domain": { "name": "Fruitfly Proteome Masterlist (UniProtKB)", "version": "v-x.x.x", "created": "2022-08-30T16:22:11.325302", "modified": "2022-09-26T09:08:12.709716", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Proteome Masterlist dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions mapped to the reviewed (SwissProt) and unreviewed (TrEMBL) UniProtKB isoforms via gene grouping. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Protein Canonical Accessions", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "canonical accessions", "gene name", "protein isoforms", "complete proteome", "UniProtKB" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB proteome data from the triplestore containing triples from nt file to map UniProtKB canonical accessions to reviewed and unreviewed isoforms via gene grouping", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.stat.csv", "filename": "fruitfly_protein_masterlist.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000647/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "4b0f1a024196bd3b5bee08f040cb59abf8cd7386455ab7e1b640989d88c05df7" } { "provenance_domain": { "name": "Fruitfly NCBI Protein Linkouts", "version": "v-x.x.x", "created": "2022-09-14T12:25:39.026264", "modified": "2022-09-26T09:08:12.707824", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly NCBI Protein Linkouts contains fruitfly [taxid:7227] NCBI RefSeq accessions with their corresponding GlyGen protein detail page URLs. The dataset is formatted as per NCBI non-bib. linkouts guidelines where 10277 is the GlyGen's provider ID." ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "NCBI Gene Linkouts", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "NCBI Protein Linkouts", "RefSeq" ], "pipeline_steps": [ { "step_number": 1, "name": "make-species-agnostic-dataset.py", "description": "The script loads the RefSeq accessions, RefSeq protein name and based on the RefSeq-UniprotKB accession mapping generates the GlyGen protein detail page URLs. The script also enters the other fields as defined by the NCBI Protein Linkouts to generate a csv dataset", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/v-x.x.x/reviewed/fruitfly_protein_xref_refseq.csv", "filename": "fruitfly_protein_xref_refseq.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/v-x.x.x/reviewed/fruitfly_protein_ncbi_linkouts.csv", "filename": "fruitfly_protein_ncbi_linkouts.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_protein_proteinnames_refseq.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_proteinnames_refseq.csv" } }, { "uri": { "filename": "fruitfly_protein_xref_refseq.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_refseq.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_ncbi_linkouts.csv", "filename": "fruitfly_protein_ncbi_linkouts.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_ncbi_linkouts.stat.csv", "filename": "fruitfly_protein_ncbi_linkouts.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000702/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "33206360f5b05686faac549d2cc4eac397578a663c5cbe112d493ec07e33603a" } { "provenance_domain": { "name": "Fruitfly EBI-UniProtKB NT file", "version": "v-x.x.x", "created": "2022-08-31T10:27:25.026993", "modified": "2022-09-26T09:08:12.581897", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly EBI-UniProtKB NT file contains proteome data for fruitfly [taxid:7227] from UniProtKB and other EMBL-EBI resources as per the GlyGen specifications in the NT format. T If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "EMBL-EBI-GlyGen-NT File", "category_name": "tag" }, { "category_value": "nt", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "NT", "proteome", "EMBL-EBI" ], "pipeline_steps": [ { "step_number": 0, "name": "", "description": "The NT file requires no processing after it is received from EMBL-EBI-UniProtKB", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/fruitfly_protein_ntdata.nt", "filename": "fruitfly_protein_ntdata.nt" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "nt", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_ntdata.nt", "filename": "fruitfly_protein_ntdata.nt" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_ntdata.stat.csv", "filename": "fruitfly_protein_ntdata.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000648/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "b229c20d8db1099235625df0f7f4d382902e9e159c58b137604e473722a90b9b" } { "provenance_domain": { "name": "Fruitfly Reaction Participants (Reactome)", "version": "v-x.x.x", "created": "2022-09-06T11:52:53.037427", "modified": "2022-09-26T09:08:12.689154", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "\"The Fruitfly Protein Reaction Participants (Reactome) dataset contains reactions participants information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen\"" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Reaction Participants (Reactome)", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "Reactome", "Participant" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the Reactome participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_reactions_reactome.csv", "filename": "fruitfly_protein_reactions_reactome.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "database_accession.tsv", "uri": "/data/shared/glyds/downloads/chebi/2023_07_13/database_accession.tsv" } }, { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_participants_reactome.csv", "filename": "fruitfly_protein_participants_reactome.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_participants_reactome.stat.csv", "filename": "fruitfly_protein_participants_reactome.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000688/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "a1a6a43688159a434b1544177d54b585a327bdb4a330a1441728507291dbf019", "error_domain": { "empirical_error": {}, "algorithmic_error": {} } } { "provenance_domain": { "name": "Fruitfly Reaction Participants (Rhea)", "version": "v-x.x.x", "created": "2022-09-06T12:06:00.142793", "modified": "2022-09-26T09:08:12.687423", "contributors": [ { "affiliation": "", "contribution": [ "createdBy" ], "name": "", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Reaction Participants (Rhea) dataset contains reactions participants information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction IDs, participant ID, participant name, role, xref ID etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Reaction Participants (Rhea)", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "Rhea", "Participants", "Reactions" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the Rhea participant data from the triplestore containing triples from nt file to retrieve the information extracts the dataset in the csv format.", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_reactions_rhea.csv", "filename": "fruitfly_protein_reactions_rhea.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_participants_rhea.csv", "filename": "fruitfly_protein_participants_rhea.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_participants_rhea.stat.csv", "filename": "fruitfly_protein_participants_rhea.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000689/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "194c281f30daa3e29dbfa3e7192a0813f3ee75133a9ac18a7b89ec32e558dceb", "error_domain": { "empirical_error": {}, "algorithmic_error": {} } } { "provenance_domain": { "name": "Fruitfly Pathways (Reactome)", "version": "v-x.x.x", "created": "2022-09-06T12:11:33.921445", "modified": "2022-09-26T09:08:12.630687", "contributors": [ { "affiliation": "", "contribution": [ "createdBy" ], "name": "", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "This dataset contains fruitfly [taxid:7227] pathway information from Reactome database and mapped to the UniProtKB canonical accessions. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen", "Reactome is an open-source, open access, manually curated and peer-reviewed pathway database. " ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Reactome Pathway", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "pathways", "reactions", "REACTOME" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the Reactome Pathways for UniProtKB canonical accessions from the triplestore containing triples from nt file and extracts the data as a csv dataset", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_pathways_reactome.csv", "filename": "fruitfly_protein_pathways_reactome.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_pathways_reactome.csv", "filename": "fruitfly_protein_pathways_reactome.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_pathways_reactome.stat.csv", "filename": "fruitfly_protein_pathways_reactome.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000690/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "f74efd421552a6f75b2034bd4cf8965136f3de9b2606b53c3097198a224a82a9" } { "provenance_domain": { "name": "Protein Resource Ontology [Fruitfly]", "version": "v-x.x.x", "created": "2022-09-14T12:16:23.572102", "modified": "2022-09-26T09:08:12.615962", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "Georgetown University", "contribution": [ "contributedBy" ], "name": "Darren Natale", "email": "dan5@georgetown.edu" }, { "affiliation": "UniCarbKB", "contribution": [ "contributedBy" ], "name": "Matthew Campbell ", "email": "m.campbell2@griffith.edu.au" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "This dataset provides the Protein Resource Ontology (PRO) identifiers associated with the proteoforms generated based on the protein, site, glycan information for fruitfly [taxid:7227] proteins. " ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "PRO ontology", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "Proteoforms", "PRO", "UniCarbKB" ], "pipeline_steps": [ { "step_number": 0, "name": "", "description": "The source file was downloaded from the contributors (Darren Natale) and a python script was used to convert the source file into a csv format.", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/GlyGen_table_to_PRO.obo", "filename": "GlyGen_table_to_PRO.obo" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_pro_annotation.csv", "filename": "fruitfly_protein_pro_annotation.csv" } ] } ] }, "execution_domain": { "script": [], "script_driver": "", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "GlyGen_table_to_PRO.obo", "uri": "/data/shared/glyds/downloads/pro/pro_08_28_2020/GlyGen_table_to_PRO.obo" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_pro_annotation.csv", "filename": "fruitfly_protein_pro_annotation.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_pro_annotation.stat.csv", "filename": "fruitfly_protein_pro_annotation.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000700/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "be25d2157f2b9ca65d9cc8e24ecf932558fa7f2724a17968a26dd7bfd54856ba", "error_domain": { "empirical_error": {}, "algorithmic_error": {} } } { "provenance_domain": { "name": "Fruitfly Protein Names (NCBI RefSeq)", "version": "v-x.x.x", "created": "2022-08-31T10:35:44.201343", "modified": "2022-09-26T09:08:12.585707", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Names (NCBI RefSeq) dataset contains fruitfly [taxid:7227] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Protein Names", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein names", "NCBI RefSeq" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion to the UniProtKB Canonical accessions", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_refseq.csv", "filename": "fruitfly_protein_xref_refseq.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/refseq_protein_all_7227.gpff", "filename": "refseq_protein_all_7227.gpff" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_info_refseq.csv", "filename": "fruitfly_protein_info_refseq.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_protein_xref_refseq.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_refseq.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_proteinnames_refseq.csv", "filename": "fruitfly_protein_proteinnames_refseq.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_proteinnames_refseq.stat.csv", "filename": "fruitfly_protein_proteinnames_refseq.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000649/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "1e408748e3cdf44c5c96986b070a0d7d22738863503a1fabbccd1c82e28465a1" } { "provenance_domain": { "name": "Fruitfly Protein PTM Annotation (UniProtKB)", "version": "v-x.x.x", "created": "2022-08-31T10:58:38.192589", "modified": "2022-09-26T09:08:12.662574", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein PTM Annotation (UniProtKB) dataset contains fruitfly [taxid:7227] PTM annotations for UniProtKB canonical accessions. The annotation is the curated statements of mainly about glycosylation and phosphorylation. If you use this dataset please give proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "PTM annotation", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "ptm annotation", "glycosylation", "phosphorylation" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script extracts the ptm annotation strings from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_ptm_annotation_uniprotkb.csv", "filename": "fruitfly_protein_ptm_annotation_uniprotkb.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_ptm_annotation_uniprotkb.csv", "filename": "fruitfly_protein_ptm_annotation_uniprotkb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_ptm_annotation_uniprotkb.stat.csv", "filename": "fruitfly_protein_ptm_annotation_uniprotkb.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000650/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "ffe94e195534eb97b220033fb2bf49257052588a084027a7b62604bba98d237a", "error_domain": { "empirical_error": {}, "algorithmic_error": {} } } { "provenance_domain": { "name": "Fruitfly Protein Reactions (Reactome)", "version": "v-x.x.x", "created": "2022-09-06T11:25:28.437609", "modified": "2022-09-26T09:08:12.647223", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Reactions (Reactome) dataset contains reactions information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction participants, pathway ID, reaction ID, PMID etc from Reactome database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Reactome and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Reactions Reactome", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "Reactome", "Pathway", "Reactions", "PMID" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the Reactome reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Reactome IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_reactions_reactome.csv", "filename": "fruitfly_protein_reactions_reactome.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_reactions_reactome.csv", "filename": "fruitfly_protein_reactions_reactome.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_reactions_reactome.stat.csv", "filename": "fruitfly_protein_reactions_reactome.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000686/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "a3f3dd49f53d0bf8fa6cb4ceaf71294170d59c3a21562b6616cc1d6838fc9aa3" } { "provenance_domain": { "name": "Fruitfly Reactions Rhea", "version": "v-x.x.x", "created": "2022-09-06T11:37:59.766468", "modified": "2022-09-26T09:08:12.541950", "contributors": [ { "affiliation": "", "contribution": [ "createdBy" ], "name": "", "email": "jeetvora@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Reactions (Rhea) dataset contains reactions information for pathways for fruitfly [taxid:7227] UniProtKB accessions that includes reaction participants ID, reaction ID, pathway ID, summary etc from Rhea database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB, Rhea and GlyGen\"" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Reactions Rhea", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "Rhea", "Reactions", "Participants", "Enzymes" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the Rhea reaction data from the triplestore containing triples from nt file to retrieve the information associated with the Rhea reaction IDs and maps it to the UniProtKB canonical accessions and extracts the dataset in the csv format", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_reactions_rhea.csv", "filename": "fruitfly_protein_reactions_rhea.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_reactions_rhea.csv", "filename": "fruitfly_protein_reactions_rhea.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_reactions_rhea.stat.csv", "filename": "fruitfly_protein_reactions_rhea.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000687/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "e5fa00983429c60017501708496d7cc697577dcb27e02d237d631213d5a2be32", "error_domain": { "empirical_error": {}, "algorithmic_error": {} } } { "provenance_domain": { "name": "Fruitfly Protein Recommended Names (UniProtKB)", "version": "v-x.x.x", "created": "2022-08-31T11:01:36.870249", "modified": "2022-09-26T09:08:12.703732", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Recommended Names (UniProtKB) dataset contains UniProtKB recommended names for fruitfly [taxid:7227] proteins. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Protein Recommended Names", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein recommended name", "protein name", "UniProtKB" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB recommended names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_recnames.csv", "filename": "fruitfly_protein_recnames.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py", "filename": "extract-from-endpoint.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_recnames.csv", "filename": "fruitfly_protein_recnames.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_recnames.stat.csv", "filename": "fruitfly_protein_recnames.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000651/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "5cb7b693df8da5b260ce9bb58549ffa92901a1be29cb60c3eaeff044b6555fba" } { "provenance_domain": { "name": "Fruitfly Protein Sequence Info (UniProtKB)", "version": "v-x.x.x", "created": "2022-08-31T11:03:51.938138", "modified": "2022-09-26T09:08:12.552687", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Sequence Info (UniProtKB) dataset contains fruitfly [taxid:7227] UniProtKB protein fasta sequence information that includes sequence version and fasta header. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "All Protein Sequence Info", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein sequence info", "fasta header", "UniProtKB" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB sequence for all fruitfly isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_sequenceinfo.csv", "filename": "fruitfly_protein_sequenceinfo.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "fasta", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_sequenceinfo.csv", "filename": "fruitfly_protein_sequenceinfo.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_sequenceinfo.stat.csv", "filename": "fruitfly_protein_sequenceinfo.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000652/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "b777edc1f2bb0ae99e5926162edf75cb02a5e015acb85fb516d4ff6a22b83b67" } { "provenance_domain": { "name": "Fruitfly Protein Signal Peptide", "version": "v-x.x.x", "created": "2022-08-31T11:05:56.022652", "modified": "2022-08-31T11:06:45.732251", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Signal Peptide dataset contains fruitfly [taxid:7227] signal peptide information for the UniProtKB canonical accessions. The dataset contains protein information, signal peptide sequence, signal peptide length, signal peptide start and end position, cleaved protein sequence, eco ids and PMIDs. The dataset contains related files in the output subdomain that includes processed protein sequence files in fasta format viz. Signal peptide sequence, protein sequence after signal peptide is cleaved, and full protein sequences of the proteins that contain signal peptide. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. " ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Reviewed", "category_name": "status" } ] } } ], "description_domain": { "keywords": [ "signal peptide", "ptm processing", "UniProtKB" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script extracts the signal peptide information from the triplestore and maps to the UniProtKB canonical accessions. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_signalp_annotation.csv", "filename": "fruitfly_protein_signalp_annotation.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_signalp_peptidesequences.fasta", "filename": "fruitfly_protein_signalp_peptidesequences.fasta" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_signalp_cleavedsequences.fasta", "filename": "fruitfly_protein_signalp_cleavedsequences.fasta" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_signalp_fullsequences.fasta", "filename": "fruitfly_protein_signalp_fullsequences.fasta" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } }, { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } }, { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } }, { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_signalp_annotation.csv", "filename": "fruitfly_protein_signalp_annotation.csv" } }, { "mediatype": "fasta", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_signalp_peptidesequences.fasta", "filename": "fruitfly_protein_signalp_peptidesequences.fasta" } }, { "mediatype": "fasta", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_signalp_cleavedsequences.fasta", "filename": "fruitfly_protein_signalp_cleavedsequences.fasta" } }, { "mediatype": "fasta", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_signalp_fullsequences.fasta", "filename": "fruitfly_protein_signalp_fullsequences.fasta" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_signalp_annotation.stat.csv", "filename": "fruitfly_protein_signalp_annotation.stat.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_signalp_peptidesequences.stat.csv", "filename": "fruitfly_protein_signalp_peptidesequences.stat.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_signalp_cleavedsequences.stat.csv", "filename": "fruitfly_protein_signalp_cleavedsequences.stat.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_signalp_fullsequences.stat.csv", "filename": "fruitfly_protein_signalp_fullsequences.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000653/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "574a0c92ca61ec70369653eed6552450" } { "provenance_domain": { "name": "Fruitfly Protein Site Annotation", "version": "v-x.x.x", "created": "2022-08-31T11:08:19.037259", "modified": "2022-09-26T09:08:12.471396", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Site Annotation (UniProtKB) dataset contains fruitfly [taxid:7227] site annotations for UniProtKB canonical accessions. The dataset contains information about UniProtKB annotations with their amino acid range. If you use this dataset please give proper attribution to UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "site annotation", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "site annotation", "amino acid range", "UniProtKB" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script extracts the site annotation triples from the triplestore for the UniProtKB canonical sequnces asnd extracts as a dataset in a csv format", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_site_annotation_uniprotkb.csv", "filename": "fruitfly_protein_site_annotation_uniprotkb.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv" } }, { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_site_annotation_uniprotkb.csv", "filename": "fruitfly_protein_site_annotation_uniprotkb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_site_annotation_uniprotkb.stat.csv", "filename": "fruitfly_protein_site_annotation_uniprotkb.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000654/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "3d0207a5f507b87f1554729affb9a03fde68cb4df46fa2bc475929166084750e", "error_domain": { "empirical_error": {}, "algorithmic_error": {} } } { "provenance_domain": { "name": "Fruitfly Protein Submitted Names (UniProtKB)", "version": "v-x.x.x", "created": "2022-08-31T11:11:10.067141", "modified": "2022-09-26T09:08:12.491498", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for fruitfly [taxid:7227] UniProtKB/TrEMBL proteins accessions. In UniProt, UniProtKB/TrEMBL entries usually have 'Submitted name' which may later be improved by automatic annotation procedures but if not, it remains as provided by the submitter until the entry is manually annotated and integrated to UniProtKB/Swiss-Prot. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Protein Submitted Names", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein submitted name", "protein name", "UniProtKB" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB submitted names for protein accessions from the triplestore containing triples from nt file and extracts the recommended names into csv dataset file", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_submittednames.csv", "filename": "fruitfly_protein_submittednames.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/extract-from-endpoint.py", "filename": "extract-from-endpoint.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_submittednames.csv", "filename": "fruitfly_protein_submittednames.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_submittednames.stat.csv", "filename": "fruitfly_protein_submittednames.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000655/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "dc531b0ac981f0c41fe72aa81f826cd500e47705d7053526e4c07aec86612ef0" } { "provenance_domain": { "name": "Fruitfly Transcript Locus (Ensembl Transcript coordinates)", "version": "v-x.x.x", "created": "2022-08-31T11:17:02.109861", "modified": "2022-09-26T09:08:12.734263", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Transcript Locus (Ensembl Transcript coordinates)s contains UniProtKB fruitfly [taxid:7227] canonical accessions mapped to their isoforms with further mapping to the corresponding ENSEMBL Transcript ID, Peptide ID, chromosome ID along with the transcripts' start and end position. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. " ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Transcript Coordinates", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "transcript locus", "ensembl transcript id", "ensembl peptide id", "chromosome", "Ensembl" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB accessions that are mapped to UniProtKB isoforms and ENSEMBL Transcript and Peptide identifiers from the triplestore containing triples from nt file and maps it to the UniProtKB canonical accession to finally extract the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlistcsv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_transcriptlocus.csv", "filename": "fruitfly_protein_transcriptlocus.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_transcriptlocus.csv", "filename": "fruitfly_protein_transcriptlocus.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_transcriptlocus.stat.csv", "filename": "fruitfly_protein_transcriptlocus.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000656/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "d43f1a2e3583c0018f7d0c1cf5407240c1fe76cc02418fa96f952cb87f5d1994" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref Bgee", "version": "v-x.x.x", "created": "2022-08-31T12:38:17.932566", "modified": "2022-09-26T09:08:12.750012", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref Bgee dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ", "Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets." ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Bgee", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "gene expression", "Bgee", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_bgee.csv", "filename": "fruitfly_protein_xref_bgee.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_bgee.csv", "filename": "fruitfly_protein_xref_bgee.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_bgee.stat.csv", "filename": "fruitfly_protein_xref_bgee.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000657/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "948ab88c72eb470b305c9ac9bce4355b3e717ca4569c205ac76b4a81cf6b6ac4" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref BRENDA", "version": "v-x.x.x", "created": "2022-08-31T12:42:59.923930", "modified": "2022-09-26T09:08:12.451387", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniprotKB Xref BRENDA contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to BRENDA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen", "BRENDA is an information system representing one of the most comprehensive enzyme repositories. It is an electronic resource that comprises molecular and biochemical information on enzymes that have been classified by the IUBMB." ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Brenda", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "enzyme", "ec number", "BRENDA", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to BRENDA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_brenda.csv", "filename": "fruitfly_protein_xref_brenda.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_brenda.csv", "filename": "fruitfly_protein_xref_brenda.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_brenda.stat.csv", "filename": "fruitfly_protein_xref_brenda.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000658/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "70a178d6aa80df08701e41958d0dcfbe001406e9d02cef64e930c243be9afeaa" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref CAZy", "version": "v-x.x.x", "created": "2022-08-31T12:46:03.864774", "modified": "2022-09-26T09:08:12.533507", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniprotKB Xref CAZy contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to CAZy database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen", "CAZy is a database of Carbohydrate-Active enZYmes (CAZymes). The database contains a classification and associated information about enzymes involved in the synthesis, metabolism, and recognition of complex carbohydrates." ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Cazy", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "carbohydrate family", "CAZy", "glycosyltransferase", "glycohydrolase", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to CAZy database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_cazy.csv", "filename": "fruitfly_protein_xref_cazy.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_cazy.csv", "filename": "fruitfly_protein_xref_cazy.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_cazy.stat.csv", "filename": "fruitfly_protein_xref_cazy.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000659/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "7ca9e80ae8327c41f52e475db77309b7bff5989ad75b4909bf8ded8268f63f57" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref CDD", "version": "v-x.x.x", "created": "2022-08-31T12:47:56.887721", "modified": "2022-09-26T09:08:12.728533", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref CDD contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to CDD database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen", "The Conserved Domain Database is a database of well-annotated multiple sequence alignment models and derived database search models, for ancient domains and full-length proteins." ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Cdd cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein domains", "CDD", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to CDD database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_cdd.csv", "filename": "fruitfly_protein_xref_cdd.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_cdd.csv", "filename": "fruitfly_protein_xref_cdd.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_cdd.stat.csv", "filename": "fruitfly_protein_xref_cdd.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000660/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "c55c6194dc4c2adca7c3fe5627527e41bd5edbc799f477a4b482bc9be5c095d6" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref ChEMBL", "version": "v-x.x.x", "created": "2022-08-31T13:04:19.896737", "modified": "2022-09-26T09:08:12.756205", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniprotKB Xref ChEMBL contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to ChEMBL database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen", " ChEMBL or ChEMBLdb is a manually curated chemical database of bioactive molecules with drug-like properties." ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Chembl cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "bioactivity", "ChEMBL", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to ChEMBL database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_chembl.csv", "filename": "fruitfly_protein_xref_chembl.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_chembl.csv", "filename": "fruitfly_protein_xref_chembl.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_chembl.stat.csv", "filename": "fruitfly_protein_xref_chembl.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000661/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "a845c9183e758c37e84668231e384999c714822db244a5e75384ae0921053e0c" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref FlyBase", "version": "v-x.x.x", "created": "2022-09-01T11:43:42.773513", "modified": "2022-09-26T09:08:12.448259", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref FlyBase contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to FlyBase database accessions/identifiers. If you use this dataset please provide proper attribution to FlyBase and GlyGen", "FlyBase is a database for Drosophila gene and genomes. https://flybase.org/" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "FlyBase cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "Drosophila", "FlyBase", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to flybase database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_flybase.csv", "filename": "fruitfly_protein_xref_flybase.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_flybase.csv", "filename": "fruitfly_protein_xref_flybase.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_flybase.stat.csv", "filename": "fruitfly_protein_xref_flybase.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000674/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "3e60c3e36cc8004cc5e2e15e6f9179240d24b8d55a50519431c5d28ac921e146" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref NCBI Gene", "version": "v-x.x.x", "created": "2022-08-31T13:07:41.419400", "modified": "2022-09-26T09:08:12.444004", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref NCBI Gene dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to NCBI Gene database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen", "NCBI Gene integrates information from a wide range of species. A record may include nomenclature, Reference Sequences (RefSeqs), maps, pathways, variations, phenotypes, and links to genome-, phenotype-, and locus-specific resources worldwide." ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Ncbi Gene cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "gene id", "NCBI gene", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI Gene database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_geneid.csv", "filename": "fruitfly_protein_xref_geneid.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_geneid.csv", "filename": "fruitfly_protein_xref_geneid.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_geneid.stat.csv", "filename": "fruitfly_protein_xref_geneid.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000662/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "a90424f85acbfc4557d98748f916e09490607d1beefe210e62826c4a2deb81d4" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref IntAct", "version": "v-x.x.x", "created": "2022-08-31T13:13:10.878546", "modified": "2022-09-26T09:08:12.540727", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref IntAct dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to IntAct database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ", "IntAct provides a freely available, open source database system and analysis tools for molecular interaction data. All interactions are derived from literature curation or direct user submissions and are freely available. The IntAct Team also produce the Complex Portal. " ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Intact", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "molecular interaction data", "protein-protein interaction", "IntAct", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to IntAct database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_intact.csv", "filename": "fruitfly_protein_xref_intact.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_intact.csv", "filename": "fruitfly_protein_xref_intact.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_intact.stat.csv", "filename": "fruitfly_protein_xref_intact.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000663/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "708bb3749e7da25eed2a9273e3dc5a164eca0bf815bd3e8e9554f097373e1714", "error_domain": { "empirical_error": {}, "algorithmic_error": {} } } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref InterPro", "version": "v-x.x.x", "created": "2022-08-31T13:16:01.810293", "modified": "2022-09-26T09:08:12.565997", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref InterPro contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to InterPro database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen", "InterPro is a database of protein families, domains and functional sites in which identifiable features found in known proteins can be applied to new protein sequences in order to functionally characterise them." ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Interpro cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein family", "protein domain", "protein functional site", "InterPro", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB accessions that are cross-referenced to InterPro database accessions/identifiers from the triplestore containing triples from nt file and maps to the UniProtKB canonical accessions and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_interpro.csv", "filename": "fruitfly_protein_xref_interpro.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_interpro.csv", "filename": "fruitfly_protein_xref_interpro.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_interpro.stat.csv", "filename": "fruitfly_protein_xref_interpro.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000664/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "913e0289c02dc9529768b091121305725755f6154d1c154a518e64793eb875ce" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref KEGG PATHWAY", "version": "v-x.x.x", "created": "2022-08-31T13:17:32.978920", "modified": "2022-09-26T09:08:12.598531", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref KEGG PATHWAY contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to KEGG PATHWAY database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen", "KEGG PATHWAY is a collection of manually drawn pathway maps representing our knowledge on the molecular interaction, reaction and relation networks." ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Kegg Pathway cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "pathways", "reactions", "KEGG Pathway", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to KEGG PATHWAY database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_kegg.csv", "filename": "fruitfly_protein_xref_kegg.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_kegg.csv", "filename": "fruitfly_protein_xref_kegg.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_kegg.stat.csv", "filename": "fruitfly_protein_xref_kegg.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000665/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "aada2dff37c90cffeba34ab51cc9de0e40e0e4ff0a51f0244e8773b0a0d74d3c" } { "object_id": "https://biocomputeobject.org/GLY_000735/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "", "provenance_domain": { "name": "Fruitfly UniProtKB Xref O-GlcNAcAtlas", "version": "v-x.x.x", "created": "2023-03-14T18:15:28.807Z", "modified": "2023-03-14T18:46:17.321Z", "embargo": { "start_time": "", "end_time": "" }, "contributors": [ { "name": "Jeet Vora", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jeetvora@gwu.edu" }, { "name": "Karina Martinez", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "karinamartinez@gwu.edu" }, { "name": "Robel Kahsay", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "rykahsay@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref O-GlcNAcAtlas dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to O-GlcNAcAtlas database accessions/identifiers. If you use this dataset please provide proper attribution to O-GlcNAcAtlas and GlyGen. O-GlcNAcAtlas is a a rigorously curated database for experimentally identified O-GlcNAc sites/proteins (https://oglcnac.org/atlas/)" ], "description_domain": { "keywords": [ "Cross-references", "Drosophila", "O-GlcNAcAtlas" ], "platform": [], "pipeline_steps": [ { "name": "make-protein-dataset.py", "version": "", "step_number": 1, "input_list": [ { "uri": "", "filename": "" } ], "output_list": [ { "filename": "", "uri": "" } ], "prerequisite": [], "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAcAtlas database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset." } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv" } } ], "output_subdomain": [ { "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_oglcnac_atlas.csv", "filename": "fruitfly_protein_xref_oglcnac_atlas.csv" }, "mediatype": "csv" }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_oglcnac_atlas.stat.csv", "filename": "fruitfly_protein_xref_oglcnac_atlas.stat.csv" } } ] }, "parametric_domain": [ { "step": "", "param": "", "value": "" } ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "O-GlcNAcAtlas cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ] } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref O-GlcNAc (MCW)", "version": "v-x.x.x", "created": "2022-08-31T13:46:26.989814", "modified": "2022-09-26T09:08:12.591263", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": "Stephanie Olivier-Van Stichelen", "email": "solivier@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": "Eugenia Wulff-Fuentes", "email": "ewulff@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": " Rex R. Berendt", "email": "rberendt@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": " Logan Massman", "email": "lmassman@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": "Laura Danner", "email": "ldanner@mcw.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "httpss://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref O-GlcNAc (MCW) contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to O-GlcNAc (MCW) database accessions/identifiers. If you use this dataset please provide proper attribution to O-GlcNAc (MCW) and GlyGen. O - GlcNAc(MCW) is a database for O - GlcNAc glycosylation information. https://www.oglcnac.mcw.edu/" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "O-GlcNAc (MCW) cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "Drosophila", "O-GlcNAc (MCW)", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to O-GlcNAc database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv", "filename": "fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_oglcnac_db.csv", "filename": "fruitfly_protein_xref_oglcnac_db.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_oglcnac_db.csv", "filename": "fruitfly_protein_xref_oglcnac_db.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_oglcnac_db.stat.csv", "filename": "fruitfly_protein_xref_oglcnac_db.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000673/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "27036f799b95dc8820d76b2780c464c30eec8417d9af315e9c7014eea77890dd" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref OMA", "version": "v-x.x.x", "created": "2022-08-31T13:20:12.938783", "modified": "2022-09-26T09:08:12.686484", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref OMA contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to OMA database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen", "The OMA (Orthologous MAtrix) project is a method and database for the inference of orthologs among complete genomes." ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Oma cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "orthologs", "OMA", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to OMA database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_oma.csv", "filename": "fruitfly_protein_xref_oma.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_oma.csv", "filename": "fruitfly_protein_xref_oma.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_oma.stat.csv", "filename": "fruitfly_protein_xref_oma.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000666/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "ec08ab4875adc8165fa6992f97f3788bf2a2273aa1d8c4ff1103879c81604bac" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref OrthoDB", "version": "v-x.x.x", "created": "2022-08-31T13:25:53.921490", "modified": "2022-09-26T09:08:12.688276", "contributors": [ { "affiliation": "", "contribution": [ "createdBy" ], "name": "", "email": "jeetvora@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref OrthoDB contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to OrthoDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen", " OrthoDB is a comprehensive catalog of orthologs, i.e. descendants from a single gene of the last common ancestor of a specific phylogeny radiation termed level-of-orthology." ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Orthodb cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "orthologs", "OrthoDB", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to OrthoDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_orthodb.csv", "filename": "fruitfly_protein_xref_orthodb.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_orthodb.csv", "filename": "fruitfly_protein_xref_orthodb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_orthodb.stat.csv", "filename": "fruitfly_protein_xref_orthodb.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000667/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "f7f6d8335416a42c5e75263c1a062b0a9ca235de21005d57a466421c804bf3f7" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref PANTHER", "version": "v-x.x.x", "created": "2022-08-31T13:34:27.210052", "modified": "2022-09-26T09:08:12.543006", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref PANTHER contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to PANTHER database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen", "The PANTHER classification system is a large curated biological database of gene/protein families and their functionally related subfamilies that can be used to classify and identify the function of gene products." ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Panther cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein family", "PANTHER", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to PANTHER database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_panther.csv", "filename": "fruitfly_protein_xref_panther.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_panther.csv", "filename": "fruitfly_protein_xref_panther.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_panther.stat.csv", "filename": "fruitfly_protein_xref_panther.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000668/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "9664ee1bd460aa590f5f3663e8666c3f6cda9eceac154ccd3b684e4c5583b642" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref PDB", "version": "v-x.x.x", "created": "2022-08-31T13:40:29.038163", "modified": "2022-09-26T09:08:12.651444", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref PDB contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to PDB database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ", "The Protein Data Bank is a database for the three-dimensional structural data of large biological molecules, such as proteins and nucleic acids. " ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Pdb cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein 3D structure", "RCSB PDB", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to RCSB PDB database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_pdb.csv", "filename": "fruitfly_protein_xref_pdb.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_pdb.csv", "filename": "fruitfly_protein_xref_pdb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_pdb.stat.csv", "filename": "fruitfly_protein_xref_pdb.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000669/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "de7e1ba091f5f28adee579192ad95523abb2f90588251b8954636c929398fa04" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref Pfam", "version": "v-x.x.x", "created": "2022-08-31T13:42:50.669379", "modified": "2022-09-26T09:08:12.679882", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref Pfam contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Pfam database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ", "Pfam is a database of protein families that includes their annotations and multiple sequence alignments generated using hidden Markov models. " ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Pfam cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein family", "Pfam", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to Pfam database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_pfam.csv", "filename": "fruitfly_protein_xref_pfam.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_pfam.csv", "filename": "fruitfly_protein_xref_pfam.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_pfam.stat.csv", "filename": "fruitfly_protein_xref_pfam.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000670/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "8fe2601bc6e81c0964b498200cb5cd17f0d9d36a8873ee5fb7e33afbe1ef3800" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref PRO", "version": "v-x.x.x", "created": "2022-08-31T13:44:37.770122", "modified": "2022-09-26T09:08:12.692039", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniprotKB Xref PRO contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to PRO database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ", "PRO provides an ontological representation of protein-related entities by explicitly defining them and showing the relationships between them. " ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Pro cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein ontology", "PRO", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to PRO database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_pro.csv", "filename": "fruitfly_protein_xref_pro.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_pro.csv", "filename": "fruitfly_protein_xref_pro.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_pro.stat.csv", "filename": "fruitfly_protein_xref_pro.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000671/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "c674e7bb2192e30cac7035c66f6d07ded61edec94599390143ea34b4d7921c56" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref Reactome", "version": "v-x.x.x", "created": "2022-08-31T13:46:26.989814", "modified": "2022-09-26T09:08:12.574776", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref Reactome contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen", "REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. " ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Reactome cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "pathways", "reactions", "REACTOME", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to REACTOME database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_reactome.csv", "filename": "fruitfly_protein_xref_reactome.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_reactome.csv", "filename": "fruitfly_protein_xref_reactome.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_reactome.stat.csv", "filename": "fruitfly_protein_xref_reactome.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000672/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "c25667b5526de26c1d5d26fdb5296b08fb5616d45c1ac0d9ad3dd0e18a3671b9" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref RefSeq", "version": "v-x.x.x", "created": "2022-09-14T12:24:23.479851", "modified": "2022-09-26T09:08:12.557748", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniprotKB Xref RefSeq contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to RefSeq database accessions/identifiers. The script extracts one-to-one UniProtKB isoform ac to RefSeq ac and also UniProtKB ac to RefSeq ac where there is no UniProtKB isoforms other than the canonical ac. The dataset is contributed by EMBL-EBI-UniProtKB and processed by GlyGen. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ", " NCBI RefSeq is a comprehensive, integrated, non-redundant, well-annotated set of reference sequences including genomic, transcript, and protein. " ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Refseq cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "protein accessions", "RefSeq", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to NCBI RefSeq database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-homo-sapiens.nt", "filename": "uniprot-proteome-homo-sapiens.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/v-x.x.x/reviewed/fruitfly_protein_xref_refseq.csv", "filename": "fruitfly_protein_xref_refseq.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_refseq.csv", "filename": "fruitfly_protein_xref_refseq.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_refseq.stat.csv", "filename": "fruitfly_protein_xref_refseq.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000701/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "91f3355ff05669536eab066d7c019ab49b2f873f0076aaec4c7fb8b0aeba63bd" } { "provenance_domain": { "name": "Fruitfly UniProtKB Xref Rhea", "version": "v-x.x.x", "created": "2022-09-06T16:53:49.310443", "modified": "2022-09-26T09:08:12.763780", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly UniProtKB Xref Rhea contains fruitfly [taxid:7227] UniProtKB canonical accessions cross-referenced to Rhea database accessions/identifiers. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen. ", "Rhea" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Rhea cross-references", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "reactions", "Rhea", "cross-reference" ], "pipeline_steps": [ { "step_number": 1, "name": "make-protein-dataset.py", "description": "The script loads the UniProtKB canonical accessions that are cross-referenced to Rhea database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_rhea.csv", "filename": "fruitfly_protein_xref_rhea.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-protein-dataset.py", "filename": "make-protein-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_rhea.csv", "filename": "fruitfly_protein_xref_rhea.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_rhea.stat.csv", "filename": "fruitfly_protein_xref_rhea.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000698/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "8aa969c203e8d703248b63b0f1dbe46608040079395cf76c0e349ce65dfb3c66" } { "provenance_domain": { "name": "Fruitfly UniProtKB xref UniProtKB", "version": "v-x.x.x", "created": "2022-09-06T16:55:15.307877", "modified": "2022-09-26T09:08:12.721639", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "UniProtKB", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [], "pipeline_steps": [] }, "execution_domain": { "script": [], "script_driver": "", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_uniprotkb.csv", "filename": "fruitfly_protein_xref_uniprotkb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_xref_uniprotkb.stat.csv", "filename": "fruitfly_protein_xref_uniprotkb.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000699/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "310855064bd4424bb8f55052816046a7dad3ce6666fcd78c1b09baa41b42229e", "error_domain": { "empirical_error": {}, "algorithmic_error": {} } } { "object_id": "https://biocomputeobject.org/GLY_000675/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "19911a5bd442791bc835732ddb4eb6eb2c6dd12fe21487d6b61251dd3a76dc36", "provenance_domain": { "name": "Fruitfly Proteoform Citations (GlyConnect)", "version": "v-x.x.x", "created": "2022-09-02T10:28:05.203794", "modified": "2023-03-14T17:09:38.835Z", "embargo": { "start_time": "", "end_time": "" }, "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "GlyConnect", "contribution": [ "contributedBy" ], "name": "Frederique Lisacek", "email": "frederique.lisacek@sib.swiss" }, { "affiliation": "GlyConnect", "contribution": [ "contributedBy" ], "name": "Julien Mariethoz", "email": "julien.mariethoz@sib.swiss" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "httpss://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Proteoform Citations (GlyConnect) dataset provides citation details corresponding to the PubMed ID (PMID) from file httpss://data.glygen.org/GLYDS000329. The script accesses the NCBI ENTREZ infrastructure to retrieve the publication information of the given PMID. The dataset is contributed by GlyGen and processed by GlyGen. If you use this dataset please provide proper attribution to GlyConnect (httpss://glyconnect.expasy.org/)." ], "description_domain": { "keywords": [ "PMID", "journal", "citations", "authors", "GlyConnect", "PubMed" ], "platform": [], "pipeline_steps": [ { "step_number": 1, "name": "make-proteoform-dataset.py", "description": "The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv", "filename": "fruitfly_proteoform_glycosylation_sites_glyconnect.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv", "filename": "fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_proteoform_glycosylation_sites_glyconnect.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv", "filename": "fruitfly_proteoform_citations_glycosylation_sites_glyconnect.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_sites_glyconnect.stat.csv", "filename": "fruitfly_proteoform_citations_glycosylation_sites_glyconnect.stat.csv" } } ] }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "Protein Citations", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ] } { "object_id": "https://biocomputeobject.org/GLY_000715/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "", "provenance_domain": { "name": "Fruitfly O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas)", "version": "v-x.x.x", "created": "2023-02-27T21:08:01.227Z", "modified": "2023-03-06T20:17:44.645Z", "embargo": { "start_time": "", "end_time": "" }, "contributors": [ { "name": "Jeet Vora", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jeetvora@gwu.edu" }, { "name": "Karina Martinez", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "karinamartinez@gwu.edu" }, { "name": "Robel Kahsay", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "rykahsay@gwu.edu" }, { "name": "Jungfeng Ma", "contribution": [ "contributedBy" ], "affiliation": "Georgetown University Medical Center, Georgetown University", "email": "junfeng.ma@georgetown.edu ", "orcid": "" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly O-GlcNAc Glycosylation Citations (O-GlcNAc Atlas) dataset contains details of the publication present in the dataset Fruitfly O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) https://data.glygen.org/GLY_000711, contributed by Jungfeng Ma's group." ], "description_domain": { "keywords": [ "O-GlcNAc", "Publications", "Citations", "PubMed" ], "platform": [], "pipeline_steps": [ { "name": "make-proteoform-dataset.py", "version": "", "step_number": 1, "input_list": [], "output_list": [], "prerequisite": [], "description": "The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. " } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv" } } ], "output_subdomain": [ { "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv", "filename": "fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.csv" }, "mediatype": "csv" }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv", "filename": "fruitfly_proteoform_citations_glycosylation_sites_oglcnac_atlas.stat.csv" } } ] }, "parametric_domain": [ { "step": "", "param": "", "value": "" } ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.1.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "Protein Citations O-GlcNAc (O-GlcNAc Atlas)", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ] } { "object_id": "https://biocomputeobject.org/GLY_000676/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "300f6fc14a258484c8d5dc851657617a876ced72f997973cba6858ed747f971a", "provenance_domain": { "name": "Fruitfly Proteoform O-GlcNAc Glycosylation Citations (MCW)", "version": "v-x.x.x", "created": "2022-09-02T10:30:49.524483", "modified": "2023-03-14T17:10:40.590Z", "embargo": { "start_time": "", "end_time": "" }, "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": "Stephanie Olivier-Van Stichelen", "email": "solivier@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": "Eugenia Wulff-Fuentes", "email": "ewulff@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": " Rex R. Berendt", "email": "rberendt@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": " Logan Massman", "email": "lmassman@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": "Laura Danner", "email": "ldanner@mcw.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "httpss://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly O-GlcNAc Glycosylation Citations (MCW) dataset contains details of the publication present in the dataset Fruitfly O-GlcNAc Glycosylation Sites (MCW) httpss://data.glygen.org/GLY_000517, contributed by Stephanie Olivier's group." ], "description_domain": { "keywords": [ "O-GlcNAc", "Publications", "Citations", "PubMed", "MCW", "Glycosylation" ], "platform": [], "pipeline_steps": [ { "step_number": 1, "name": "make-proteoform-dataset.py", "description": "The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv", "filename": "fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_o_glcnac_mcw.csv", "filename": "fruitfly_proteoform_citations_glycosylation_o_glcnac_mcw.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv", "filename": "fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv", "filename": "fruitfly_proteoform_citations_glycosylation_sites_oglcnac_mcw.stat.csv" } } ] }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "Protein Citations O-GlcNAc (MCW)", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ] } { "object_id": "https://biocomputeobject.org/GLY_000677/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "9685182ba40514fb894ef9bf2c47c20d0d24ecc1081f248067acdad2b1a68a8e", "provenance_domain": { "name": "Fruitfly Proteoform Glycosylation Citations (UniProtKB)", "version": "v-x.x.x", "created": "2022-09-02T10:55:15.390409", "modified": "2023-03-14T17:11:16.449Z", "embargo": { "start_time": "", "end_time": "" }, "contributors": [ { "affiliation": "", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "httpss://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [], "description_domain": { "keywords": [ "publications", "PMID", "journal", "citations", "authors", "UniProtKB", "PubMed", "Glycosylation" ], "platform": [], "pipeline_steps": [ { "step_number": 1, "name": "make-proteoform-dataset.py", "description": "The script extracts the PMID from the dataset and uses the Entrez API to retrieve the publication details and extracts in a csv dataset. ", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv", "filename": "fruitfly_proteoform_glycosylation_sites_uniprotkb.csv" } ], "output_list": [ { "uri": "http://data.glygen.org/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv", "filename": "fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv" } ] } ] }, "execution_domain": { "script": [], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_proteoform_glycosylation_sites_uniprotkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv", "filename": "fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv", "filename": "fruitfly_proteoform_citations_glycosylation_sites_uniprotkb.stat.csv" } } ] }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "Protein Citations UniProtKB", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ] } { "object_id": "https://biocomputeobject.org/GLY_000678/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "35a790a87de80c791432b16ab1a698a5d21d78537425882c070987ef089b898a", "provenance_domain": { "name": "Fruitfly Proteoform Phosphorylation Citations (iPTMnet)", "version": "v-x.x.x", "created": "2022-09-02T13:26:18.780372", "modified": "2023-03-14T17:11:57.540Z", "embargo": { "start_time": "", "end_time": "" }, "contributors": [ { "affiliation": "", "contribution": [ "createdBy" ], "name": "", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [], "description_domain": { "keywords": [ "PMID", "journal", "citations", "authors", "iPTMnet", "PubMed", "Phosphorylation" ], "platform": [], "pipeline_steps": [ { "step_number": 1, "name": "make-proteoform-dataset.py", "description": "The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.csv", "filename": "fruitfly_proteoform_phosphorylation_sites_iptmnet.csv" } ], "output_list": [ { "uri": "http://data.glygen.org/v-x.x.x/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv", "filename": "fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_proteoform_phosphorylation_sites_iptmnet.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv", "filename": "fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv", "filename": "fruitfly_proteoform_citations_phosphorylation_sites_iptmnet.stat.csv" } } ] }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "Phosphorylation Citations (iPTMnet)", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ] } { "object_id": "https://biocomputeobject.org/GLY_000679/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "04fb205a124ba1f2c61d22468f1e402ea54a15d085ae73d67dbf798296c88e3e", "provenance_domain": { "name": "Fruitfly Proteoform Phosphorylation Citations (UniProtKB)", "version": "v-x.x.x", "created": "2022-09-02T13:32:35.505543", "modified": "2023-03-14T17:12:29.696Z", "embargo": { "start_time": "", "end_time": "" }, "contributors": [ { "affiliation": "", "contribution": [ "createdBy" ], "name": "", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [], "description_domain": { "keywords": [ "publications", "PMID", "journal", "citations", "authors", "UniProtKB", "PubMed", "Phosphorylation" ], "platform": [], "pipeline_steps": [ { "step_number": 1, "name": "make-proteoform-dataset.py", "description": "The script parses the input file for PMIDs and accesses the NCBI Entrez infrastructure to download the publication information of the corresponding PMIDs", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv", "filename": "fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv" } ], "output_list": [ { "uri": "http://data.glygen.org/v-x.x.x/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv", "filename": "fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv", "filename": "fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv", "filename": "fruitfly_proteoform_citations_phosphorylation_sites_uniprotkb.stat.csv" } } ] }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Protein", "category_name": "molecule" }, { "category_value": "Phosphorylation Citations UniProtKB", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ] } { "provenance_domain": { "name": "Fruitfly Glycosylation Sites (GlyConnect) ", "version": "v-x.x.x", "created": "2022-08-16T12:24:13.810189", "modified": "2022-09-26T09:08:12.690956", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "GlyConnect", "contribution": [ "contributedBy" ], "name": "Frederique Lisacek", "email": "frederique.lisacek@sib.swiss" }, { "affiliation": "GlyConnect", "contribution": [ "contributedBy" ], "name": "Julien Mariethoz", "email": "julien.mariethoz@sib.swiss" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Glycosylation Sites (GlyConnect) dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with information on reported glycans in GlyConnect database (https://glyconnect.expasy.org/; PMID: 30574787).A json file was derived through GlyConnect API (https://glyconnect.expasy.org/api/docs/index.html?url=/api/assets/swagger.json#/Glycosylation/listGlycosylationsAsJson) (Query: taxonomy:Drosophila melanogaster). If you use this dataset please provide proper attribution to GlyConnect and GlyGen. Please note that this dataset does not contain protein or sites information just the glycans" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "Glycosylation Sites", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "glycosylation", "reported glycosylation" ], "pipeline_steps": [ { "step_number": 1, "name": "make-proteoform-dataset.py", "description": "The script loads the glycosylation information from the input JSON file and extracts the data. The QC checks filter out: 1) any rows where the UniProtKB accession is not included in the GlyGen protein list (https://data.glygen.org/GLYDS000001) and/or 2) if the given glycosylation position and amino acid does not match to the amino acid on the .fasta sequence provided in the latest UniProtKB release for that protein (However it does pass if the amino acid +glyco-site is empty (as these records correspond to the \"not reported\" glyco-sites and/or 3) If the glycosylation type does not associate to the glycostlation based on amino acid (i.e if a N-linked is associated with Ser/Thr residue, etc). 4) If the glyco-site is not reported and the glycosylation type is ambigious (c-Linked/o-linked) and/or 5) if the saccharide (GlyTouCan) is not present in the GlyGen glycan masterlist. All the flagged entries are added in the log file (fruitfly_proteoform_glycosylation_sites_glyconnect.1.log) In this dataset the script only extracts the glycan information. CURRENTLY - THE ABOVE QC STEP IS NOT DONE AS THE DATA DOES NOT HAVE PROTEIN AND SITES.", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/glyconnect_fruitfly.json", "filename": "glyconnect_fruitfly.json" }, { "uri": "https:/data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https:/data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/glycan_masterlist.csv", "filename": "glycan_masterlist.csv" } ], "output_list": [ { "uri": "https:/data.glygen.org/ln2data/releases/data/v-x.x.x/logs/fruitfly_proteoform_glycosylation_sites_glyconnect.1.log", "filename": "fruitfly_proteoform_glycosylation_sites_glyconnect.1.log" }, { "uri": "https:/data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv", "filename": "fruitfly_proteoform_glycosylation_sites_glyconnect.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "n_sequon_info.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/misc/n_sequon_info.csv" } }, { "uri": { "filename": "sample_mapping.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/misc/sample_mapping.csv" } }, { "uri": { "filename": "cellosaurus.txt", "uri": "/data/shared/glyds/downloads/cellosaurus/2023_07_13/cellosaurus.txt" } }, { "uri": { "filename": "glycosylations?taxonomy=Drosophila melanogaster", "uri": "/data/shared/glyds/downloads/glyconnect/2023_07_13/glycosylations?taxonomy=Drosophila melanogaster" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.csv", "filename": "fruitfly_proteoform_glycosylation_sites_glyconnect.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_glyconnect.stat.csv", "filename": "fruitfly_proteoform_glycosylation_sites_glyconnect.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000630/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "acf6c3f56dce3dd4a373f606e053789982ae6e91310eb248ec7955f3b5a2f10c" } { "object_id": "https://biocomputeobject.org/GLY_000711/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "", "provenance_domain": { "name": "Fruitfly O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)", "version": "v-x.x.x", "created": "2023-02-24T16:22:06.506Z", "modified": "2023-03-06T20:15:27.506Z", "embargo": { "start_time": "", "end_time": "" }, "contributors": [ { "name": "Jeet Vora", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jeetvora@gwu.edu" }, { "name": "Karina Martinez", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "karinamartinez@gwu.edu" }, { "name": "Robel Kahsay", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "rykahsay@gwu.edu" }, { "name": "Jungfeng Ma", "contribution": [ "contributedBy" ], "affiliation": "Georgetown University Medical Center, Georgetown University", "email": "junfeng.ma@georgetown.edu ", "orcid": "" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas) contains fruitfly (taxid:7227) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO." ], "description_domain": { "keywords": [ "", "O-GlcNAc", "Serine" ], "platform": [], "pipeline_steps": [ { "name": "make-proteoform-dataset.py", "version": "", "step_number": 1, "input_list": [ { "uri": "", "filename": "" } ], "output_list": [ { "uri": "", "filename": "" } ], "prerequisite": [], "description": "The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script also maps the sample type to correct sample term id and sample term name. " } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_protein_info_uniprotkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_info_uniprotkb.csv" } }, { "uri": { "filename": "fruitfly_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv" } }, { "uri": { "filename": "fruitfly_protein_recnames.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_recnames.csv" } }, { "uri": { "filename": "sample_mapping.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/misc/sample_mapping.csv" } }, { "uri": { "filename": "ambiguous_sites_version_2.0.csv", "uri": "/data/shared/glyds/downloads/atlas_oglcnac/2022_10_20/ambiguous_sites_version_2.0.csv" } }, { "uri": { "filename": "unambiguous_sites_version_2.0.csv", "uri": "/data/shared/glyds/downloads/atlas_oglcnac/2022_10_20/unambiguous_sites_version_2.0.csv" } }, { "uri": { "filename": "cellosaurus.txt", "uri": "/data/shared/glyds/downloads/cellosaurus/2023_07_13/cellosaurus.txt" } } ], "output_subdomain": [ { "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv", "filename": "fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.csv" }, "mediatype": "csv" }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv", "filename": "fruitfly_proteoform_glycosylation_sites_oglcnac_atlas.stat.csv" } } ] }, "parametric_domain": [ { "step": "", "param": "", "value": "" } ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "O-GlcNAc Glycosylation Sites (O-GlcNAc Atlas)", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ] } { "object_id": "https://biocomputeobject.org/GLY_000633/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "a2cf4e4f9fb8b2c855e5b233c91ae8c991e8345bd609700baa275892de58d966", "provenance_domain": { "name": "Fruitfly O-GlcNAc Glycosylation Sites (MCW)", "version": "v-x.x.x", "created": "2022-08-16T20:56:25.251283", "modified": "2023-03-14T17:08:38.688Z", "embargo": { "start_time": "", "end_time": "" }, "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": "Stephanie Olivier-Van Stichelen", "email": "solivier@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": "Eugenia Wulff-Fuentes", "email": "ewulff@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": " Rex R. Berendt", "email": "rberendt@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": " Logan Massman", "email": "lmassman@mcw.edu" }, { "affiliation": "Medical College of Wisconsin", "contribution": [ "contributedBy" ], "name": "Laura Danner", "email": "ldanner@mcw.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly O-GlcNAc Glycosylation Sites (MCW) contains fruitfly (taxid:7227) O-GlcNAc modifications on Serine and Threonine extracted from the publication and mapped to the UniProtKB canonical accession and fasta sequence. The GlyTouCan ID for the O-GlcNAc is G49108TO. The dataset also contains other information such as O-GlcNAc score, the count and the techniques used to determine the O-GlcNAc modification and the peptide sequence from the -5 to +5 postion of the modified residue. The dataset also containes disclaimer and notes where the position of sites in publication and in the fasta sequence varies.", "The dataset is contributed from The O-GlcNAc Database maintained by Stephanie Olivier's lab ", "Wulff-Fuentes E, Berendt RR, Massman L, Danner L, Malard F, Vora J, Kahsay R, and Olivier-Van Stichelen S, The Fruitfly O-GlcNAcome Database and Meta-Analysis. Scientific Data 8, 25 (2021) ", "QC check - The python script is used to process each protein entry of the database table and perform quality control (QC). In the QC checks, the reported UniProtKB accessions in the database are matched with the GlyGen\u2019s fruitfly protein masterlist of UniProtKB canonical accessions to ensure all of the proteins belong to fruitfly species. Next, the O-GlcNAc site data that contained the amino acid residue and its position are mapped to the GlyGen\u2019s fasta sequence for the corresponding fruitfly UniProtKB canonical proteins. The amino acid residues and positions that don't match with the fasta sequence of the canonical protein were flagged and excluded from the table. Similarly, the protein entries that don't have any site information are also excluded. The entries that passed all the quality control steps are exported as a final csv dataset file whereas the excluded entries are exported in a log file with the reasons for exclusion for further manual verification.", "DISCLAIMER - For each entry, an O-GlcNAc score was attributed to each O-GlcNAcylated protein, reflecting the confidence in the protein\u2019s O-GlcNAcylation identification. The score combined the number of articles and techniques used and the availability of some O-GlcNAcylation sites. Interestingly, a O-GlcNAc score of 3 or under, means that (1) no sites were identified, (2) only one technique was used, and (3) 1-2 articles were associated with the entry. Often identified from large-scale proteomics studies, at least an extra-validation step would be highly recommended to confirm their O-GlcNAcylation." ], "description_domain": { "keywords": [ "O-GlcNAc" ], "platform": [], "pipeline_steps": [ { "step_number": 1, "name": "make-proteoform-dataset.py", "description": "The script maps the UniProtKB accesions to the UniProtKB Canonical accessions and also checks the position and amino acid of O-GlcNAc modified residue against UniProtKB Canonical sequences. The script that processes this dataset matches the amino acid and position with the latest release fasta file as a QC check to eliminate the incorrect entries. The script also adds the -5 and +5 amino acids from the modified residue in the peptide field.", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/fruitfly_o-glcnacome_mcw.csv", "filename": "fruitfly_o-glcnacome_mcw.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_allsequences.fasta", "filename": "fruitfly_protein_allsequences.fasta" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv", "filename": "fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/logs/fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.log", "filename": "fruitfly_proteoform_glycosylation_sites_o_glcnac_mcw.log" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_protein_info_uniprotkb.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_info_uniprotkb.csv" } }, { "uri": { "filename": "fruitfly_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv" } }, { "uri": { "filename": "fruitfly_protein_recnames.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_recnames.csv" } }, { "uri": { "filename": "sample_mapping.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/misc/sample_mapping.csv" } }, { "uri": { "filename": "cellosaurus.txt", "uri": "/data/shared/glyds/downloads/cellosaurus/2023_07_13/cellosaurus.txt" } }, { "uri": { "filename": "fruitfly_o_glcnacome_mcw.csv", "uri": "/data/shared/glyds/downloads/mcw_oglcnac/2023_07_18/fruitfly_o_glcnacome_mcw.csv" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv", "filename": "fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv", "filename": "fruitfly_proteoform_glycosylation_sites_oglcnac_mcw.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "O-GlcNAc Glycosylation Sites (MCW)", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ] } { "provenance_domain": { "name": "Fruitfly Glycosylation Sites (UniProtKB)", "version": "v-x.x.x", "created": "2022-09-06T09:50:57.220135", "modified": "2022-09-26T09:08:12.457590", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Glycosylation Sites (UniProtKB) dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with information on reported and predicted glycosylation sites in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "Glycosylation Sites", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "glycosylation", "reported glycosylation", "predicted glycosylation", "UniProtKB", "PubMed", "Evidence and conclusion Ontology" ], "pipeline_steps": [ { "step_number": 1, "name": "make-proteoform-dataset.py", "description": "The script loads the glycosylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv", "filename": "fruitfly_proteoform_glycosylation_sites_uniprotkb.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "glycosylation_subtype.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/misc/glycosylation_subtype.csv" } }, { "uri": { "filename": "n_sequon_info.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/misc/n_sequon_info.csv" } }, { "uri": { "filename": "sample_mapping.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/misc/sample_mapping.csv" } }, { "uri": { "filename": "cellosaurus.txt", "uri": "/data/shared/glyds/downloads/cellosaurus/2023_07_13/cellosaurus.txt" } }, { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.csv", "filename": "fruitfly_proteoform_glycosylation_sites_uniprotkb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_glycosylation_sites_uniprotkb.stat.csv", "filename": "fruitfly_proteoform_glycosylation_sites_uniprotkb.stat.csv" } } ] }, "error_domain": { "empirical_error": {}, "algorithmic_error": {} }, "object_id": "https://biocomputeobject.org/GLY_000681/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "b4405205af0a98bd7407e488edca7a60a324d6f85cd9107238ee8973cdcb8084" } { "provenance_domain": { "name": "Fruitfly Phosphorylation Sites (iPTMNet)", "version": "v-x.x.x", "created": "2022-09-06T09:56:04.354720", "modified": "2022-09-26T09:08:12.740578", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "This dataset contains fruitfly [taxid:7227] phosphorylation sites from iPTMNet database. The protein and sites are mapped to UniProtKB canonical accessions and fasta sequence. If you use this dataset please provide proper attribution to iPTMnet-GlyGen." ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "Phosphorylation Sites (iPTMnet)", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "iPTMnet", "Phosphorylation sites" ], "pipeline_steps": [ { "step_number": 0, "name": "make-proteoform-dataset.py", "description": "The script extracts the phosphorylation information from the source dataset as per taxid and extracts as a csv dataset. The protein accession and sites are mapped to the UniProtKB canonical accession and fasta sequence.", "version": "1", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/source/ptm.txt", "filename": "ptm.txt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.csv", "filename": "fruitfly_proteoform_phosphorylation_sites_iptmnet.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "parametric_domain": [ { "param": "", "value": "", "step": "" } ], "io_domain": { "input_subdomain": [ { "uri": { "filename": "fruitfly_protein_masterlist.csv", "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv" } }, { "uri": { "filename": "ptm.txt", "uri": "/data/shared/glyds/downloads/iptmnet/2023_07_18/ptm.txt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.csv", "filename": "fruitfly_proteoform_phosphorylation_sites_iptmnet.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_phosphorylation_sites_iptmnet.stat.csv", "filename": "fruitfly_proteoform_phosphorylation_sites_iptmnet.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000683/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "7535720e5c5a64f7336a898cc11d4fba6176666cd7b5fa8cc2fbea54e9eaef60", "error_domain": { "empirical_error": {}, "algorithmic_error": {} } } { "provenance_domain": { "name": "Fruitfly Phosphorylation Sites (UniProtKB)", "version": "v-x.x.x", "created": "2022-09-06T09:53:09.953304", "modified": "2022-09-26T09:08:12.741565", "contributors": [ { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Jeet Vora", "email": "jeetvora@gwu.edu" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Robel Kahsay", "email": "rykahsay@gwu.edu" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Maria Martin", "email": "martin@ebi.ac.uk" }, { "affiliation": "EMBL-EBI-UniProt", "contribution": [ "contributedBy" ], "name": "Preethi Vasudev", "email": "pvasudev@ebi.ac.uk" }, { "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "name": "Karina Martinez", "email": "karinamartinez@gwu.edu" }, { "name": "Jingyue Wu", "affiliation": "The George Washington University", "contribution": [ "createdBy" ], "email": "jingyue.wu@email.gwu.edu" } ], "license": "https://creativecommons.org/licenses/by/4.0/" }, "usability_domain": [ "The Fruitfly Phosphorylation Sites (UniProtKB) dataset contains fruitfly [taxid:7227] UniProtKB canonical accessions with information on reported and predicted phosphoryation sites with evidence in UniProtKB database. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen" ], "extension_domain": [ { "extension_schema": "https://www.w3id.org/biocompute/extension_domain/1.2.0/dataset/dataset_extension.json", "dataset_extension": { "additional_license": { "data_license": "https://creativecommons.org/licenses/by/4.0/", "script_license": "https://www.gnu.org/licenses/gpl-3.0.en.html" }, "dataset_categories": [ { "category_value": "Drosophila melanogaster", "category_name": "species" }, { "category_value": "Proteoform", "category_name": "molecule" }, { "category_value": "Phosphorylation Sites", "category_name": "tag" }, { "category_value": "csv", "category_name": "file_type" }, { "category_value": "Reviewed", "category_name": "status" }, { "category_value": "internal", "category_name": "scope" } ] } } ], "description_domain": { "keywords": [ "phosphoryation Sites", "ptm processing", "UniProtKB" ], "pipeline_steps": [ { "step_number": 1, "name": "make-proteoform-dataset.py", "description": "The script loads the phosphorylation information from the triplestore conatining triples from the nt file and extracts as a csv dataset", "version": "", "prerequisite": [], "input_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_protein_masterlist.csv", "filename": "fruitfly_protein_masterlist.csv" }, { "uri": "https://data.glygen.org/v-x.x.x/source/uniprot-proteome-drosophila-melanogaster.nt", "filename": "uniprot-proteome-drosophila-melanogaster.nt" } ], "output_list": [ { "uri": "https://data.glygen.org/ln2data/releases/data/v-x.x.x/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv", "filename": "fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv" } ] } ] }, "execution_domain": { "script": [ { "uri": { "uri": "https://github.com/glygener/glygen-backend-integration/blob/master/dataset-maker/make-proteoform-dataset.py", "filename": "make-proteoform-dataset.py" } } ], "script_driver": "manual", "software_prerequisites": [ { "version": "2.7.5", "name": "Python", "uri": { "uri": "https://www.python.org/download/releases/2.7.5/" } } ], "external_data_endpoints": [], "environment_variables": {} }, "io_domain": { "input_subdomain": [ { "uri": { "filename": "uniprot-proteome-drosophila-melanogaster.nt", "uri": "/data/shared/glyds/downloads/ebi/2023_07_11/uniprot-proteome-drosophila-melanogaster.nt" } } ], "output_subdomain": [ { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv", "filename": "fruitfly_proteoform_phosphorylation_sites_uniprotkb.csv" } }, { "mediatype": "csv", "uri": { "uri": "https:/data.glygen.org/ln2releases/data/v-x.x.x/reviewed/fruitfly_proteoform_phosphorylation_sites_uniprotkb.stat.csv", "filename": "fruitfly_proteoform_phosphorylation_sites_uniprotkb.stat.csv" } } ] }, "object_id": "https://biocomputeobject.org/GLY_000682/v-x.x.x", "spec_version": "https://w3id.org/ieee/ieee-2791-schema/2791object.json", "etag": "cc7a5efff9f464667a74a58e7202eeb72cb79d1da458b19f67cc17cf4645ea04", "error_domain": { "empirical_error": {}, "algorithmic_error": {} } }