{ "bcoid": "GLY_000125", "title": "Human UniProtKB Xref Reactome", "description": "The Human UniProtKB Xref Reactome contains human [taxid:9606] UniProtKB canonical accessions cross-referenced ...", "filename": "human_protein_xref_reactome.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "Reactome cross-references", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P23919-1...", "protein_xref..." ], [ "P23919-1...", "protein_xref..." ] ], "headers": [ "uniprotkb_ca...", "xref_key..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "xref_key" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "xref_label" } ], [ "P23919-1", "protein_xref_reactome", "R-HSA-499943", "Interconversion of nucleotide di- and triphosphates" ], [ "P23919-1", "protein_xref_reactome", "R-HSA-499943", "Interconversion of nucleotide di- and triphosphates" ], [ "Q8NHX9-1", "protein_xref_reactome", "R-HSA-2672351", "Stimuli-sensing channels" ], [ "Q9C0H2-1", "protein_xref_reactome", "R-HSA-2672351", "Stimuli-sensing channels" ], [ "Q9C0H5-1", "protein_xref_reactome", "R-HSA-428543", "Inactivation of CDC42 and RAC1" ], [ "Q9C0H5-1", "protein_xref_reactome", "R-HSA-428543", "Inactivation of CDC42 and RAC1" ], [ "Q9C0H5-1", "protein_xref_reactome", "R-HSA-8980692", "RHOA GTPase cycle" ], [ "Q9C0H5-1", "protein_xref_reactome", "R-HSA-9013026", "RHOB GTPase cycle" ], [ "Q9C0H5-1", "protein_xref_reactome", "R-HSA-9013106", "RHOC GTPase cycle" ], [ "Q9C0H5-1", "protein_xref_reactome", "R-HSA-9013148", "CDC42 GTPase cycle" ], [ "Q9C0H5-1", "protein_xref_reactome", "R-HSA-9013149", "RAC1 GTPase cycle" ], [ "Q9C0H5-1", "protein_xref_reactome", "R-HSA-9013404", "RAC2 GTPase cycle" ], [ "Q9C0H5-1", "protein_xref_reactome", "R-HSA-9013405", "RHOD GTPase cycle" ], [ "Q9C0H5-1", "protein_xref_reactome", "R-HSA-9013408", "RHOG GTPase cycle" ], [ "Q9C0H5-1", "protein_xref_reactome", "R-HSA-9013423", "RAC3 GTPase cycle" ], [ "Q9C0H5-1", "protein_xref_reactome", "R-HSA-9035034", "RHOF GTPase cycle" ], [ "Q9C0H5-1", "protein_xref_reactome", "R-HSA-9013405", "RHOD GTPase cycle" ], [ "Q9C0H5-1", "protein_xref_reactome", "R-HSA-9035034", "RHOF GTPase cycle" ], [ "Q96J66-1", "protein_xref_reactome", "R-HSA-382556", "ABC-family proteins mediated transport" ], [ "Q9NYS7-1", "protein_xref_reactome", "R-HSA-8951664", "Neddylation" ], [ "Q9NYS7-1", "protein_xref_reactome", "R-HSA-8951664", "Neddylation" ], [ "Q9NYS7-1", "protein_xref_reactome", "R-HSA-8951664", "Neddylation" ], [ "Q9NYS7-1", "protein_xref_reactome", "R-HSA-8951664", "Neddylation" ], [ "Q9NYS7-1", "protein_xref_reactome", "R-HSA-8951664", "Neddylation" ], [ "P40424-1", "protein_xref_reactome", "R-HSA-452723", "Transcriptional regulation of pluripotent stem cells" ], [ "P40424-1", "protein_xref_reactome", "R-HSA-452723", "Transcriptional regulation of pluripotent stem cells" ], [ "P40424-1", "protein_xref_reactome", "R-HSA-9013508", "NOTCH3 Intracellular Domain Regulates Transcription" ], [ "P40424-1", "protein_xref_reactome", "R-HSA-5617472", "Activation of anterior HOX genes in hindbrain development during early embryogenesis" ], [ "P40424-1", "protein_xref_reactome", "R-HSA-5617472", "Activation of anterior HOX genes in hindbrain development during early embryogenesis" ], [ "P40424-1", "protein_xref_reactome", "R-HSA-5617472", "Activation of anterior HOX genes in hindbrain development during early embryogenesis" ], [ "P40424-1", "protein_xref_reactome", "R-HSA-5617472", "Activation of anterior HOX genes in hindbrain development during early embryogenesis" ], [ "P40424-1", "protein_xref_reactome", "R-HSA-5617472", "Activation of anterior HOX genes in hindbrain development during early embryogenesis" ], [ "P40424-1", "protein_xref_reactome", "R-HSA-5617472", "Activation of anterior HOX genes in hindbrain development during early embryogenesis" ], [ "P40424-1", "protein_xref_reactome", "R-HSA-5617472", "Activation of anterior HOX genes in hindbrain development during early embryogenesis" ], [ "P40424-1", "protein_xref_reactome", "R-HSA-5617472", "Activation of anterior HOX genes in hindbrain development during early embryogenesis" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-72764", "Eukaryotic Translation Termination" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-72764", "Eukaryotic Translation Termination" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-156827", "L13a-mediated translational silencing of Ceruloplasmin expression" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-156827", "L13a-mediated translational silencing of Ceruloplasmin expression" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-156827", "L13a-mediated translational silencing of Ceruloplasmin expression" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-156902", "Peptide chain elongation" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-156902", "Peptide chain elongation" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-156902", "Peptide chain elongation" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-156902", "Peptide chain elongation" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-72764", "Eukaryotic Translation Termination" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-1799339", "SRP-dependent cotranslational protein targeting to membrane" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-1799339", "SRP-dependent cotranslational protein targeting to membrane" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-1799339", "SRP-dependent cotranslational protein targeting to membrane" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-1799339", "SRP-dependent cotranslational protein targeting to membrane" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-1799339", "SRP-dependent cotranslational protein targeting to membrane" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-192823", "Viral mRNA Translation" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-192823", "Viral mRNA Translation" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-6791226", "Major pathway of rRNA processing in the nucleolus and cytosol" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-2408557", "Selenocysteine synthesis" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-2408557", "Selenocysteine synthesis" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-72689", "Formation of a pool of free 40S subunits" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-72706", "GTP hydrolysis and joining of the 60S ribosomal subunit" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-72706", "GTP hydrolysis and joining of the 60S ribosomal subunit" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-9010553", "Regulation of expression of SLITs and ROBOs" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-9010553", "Regulation of expression of SLITs and ROBOs" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-975957", "Nonsense Mediated Decay (NMD) enhanced by the Exon Junction Complex (EJC)" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-975956", "Nonsense Mediated Decay (NMD) independent of the Exon Junction Complex (EJC)" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-975957", "Nonsense Mediated Decay (NMD) enhanced by the Exon Junction Complex (EJC)" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-975957", "Nonsense Mediated Decay (NMD) enhanced by the Exon Junction Complex (EJC)" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-975957", "Nonsense Mediated Decay (NMD) enhanced by the Exon Junction Complex (EJC)" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-9633012", "Response of EIF2AK4 (GCN2) to amino acid deficiency" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-9633012", "Response of EIF2AK4 (GCN2) to amino acid deficiency" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-9633012", "Response of EIF2AK4 (GCN2) to amino acid deficiency" ], [ "P40429-1", "protein_xref_reactome", "R-HSA-9633012", "Response of EIF2AK4 (GCN2) to amino acid deficiency" ], [ "P03891-1", "protein_xref_reactome", "R-HSA-6799198", "Complex I biogenesis" ], [ "P03891-1", "protein_xref_reactome", "R-HSA-6799198", "Complex I biogenesis" ], [ "P03891-1", "protein_xref_reactome", "R-HSA-6799198", "Complex I biogenesis" ], [ "P03891-1", "protein_xref_reactome", "R-HSA-6799198", "Complex I biogenesis" ], [ "P03891-1", "protein_xref_reactome", "R-HSA-6799198", "Complex I biogenesis" ], [ "P03891-1", "protein_xref_reactome", "R-HSA-611105", "Respiratory electron transport" ], [ "P03897-1", "protein_xref_reactome", "R-HSA-6799198", "Complex I biogenesis" ], [ "P03897-1", "protein_xref_reactome", "R-HSA-6799198", "Complex I biogenesis" ], [ "P03897-1", "protein_xref_reactome", "R-HSA-6799198", "Complex I biogenesis" ], [ "P03897-1", "protein_xref_reactome", "R-HSA-6799198", "Complex I biogenesis" ], [ "P03897-1", "protein_xref_reactome", "R-HSA-6799198", "Complex I biogenesis" ], [ "P03897-1", "protein_xref_reactome", "R-HSA-611105", "Respiratory electron transport" ], [ "P02768-1", "protein_xref_reactome", "R-HSA-159418", "Recycling of bile acids and salts" ], [ "P02768-1", "protein_xref_reactome", "R-HSA-159418", "Recycling of bile acids and salts" ], [ "P02768-1", "protein_xref_reactome", "R-HSA-159418", "Recycling of bile acids and salts" ] ] }, "readme": "Name\n - Human UniProtKB Xref Reactome\n\nVersion\n - 1.11.2\n\nCreated on\n - 2019-03-15T16:14:06.456984\n\nModified on\n - 2022-01-19T11:01:14.071661\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Xavier Holmes [xavierh@email.gwu.edu], Karina Martinez [karinamartinez@gwu.edu], Amanda Bell [amandab2140@gwu.edu], Jonathon Keeney [keeneyjg@gwu.edu], Millicent Quartey [mquartey@email.gwu.edu]\n\nAuthors\n - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n - \n\nUsability Domain\n - The Human UniProtKB Xref Reactome contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Reactome database accessions/identifiers. The dataset is derived from 2019-09 UniProtKB release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n - REACTOME is an open-source, open access, manually curated and peer-reviewed pathway database. \n\nDescription Domain\n Keywords\n - pathways\n - reactions\n - REACTOME\n - cross-reference\n\n Pipeline Steps\n - Step-1: 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. \n\nExecution Domain\n Scripts - https://github.com/GW-HIVE/glygen-backend-integration/blob/master/pipeline/integrator/make-protein-dataset.py\n\n\n Software Prerequisites\n Name: Python\n Version: 2.7.5\n URI: https://www.python.org/download/releases/2.7.5/\n\nI/O Domain\n Input Subdomain\n Name: uniprot-proteome-homo-sapiens.nt\n URI: https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-homo-sapiens.nt\n Output Subdomain\n Name: human_protein_xref_reactome.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_reactome.csv\n Name: human_protein_xref_reactome.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_reactome.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"16\"\n Name: \"motif_start\"\n Description: \"\"\n Unique Values: \"23\"\n Name: \"filter_flags\"\n Description: \"Filter tags/flags assigned to the mutation entries that have passed the mutation filter criteria\"\n Unique Values: \"19\"\n Name: \"sift_prediction\"\n Description: \"The SIFT qualitative prediction is derived from this score such that substitutions with a score < 0.05 are called 'deleterious' and all others are called 'tolerated\"\n Unique Values: \"3\"\n Name: \"somatic_status\"\n Description: \"The status of the variant whether it is germline (somatic status =0) or somatic (somatic status =1) variant\"\n Unique Values: \"1\"\n Name: \"chr_pos\"\n Description: \"Chromosome Position of a gene\"\n Unique Values: \"19\"\n Name: \"chr_id\"\n Description: \"\"\n Unique Values: \"10\"\n Name: \"dbsnp_id\"\n Description: \"\"A reference SNP ID number\"\n Unique Values: \"19\"\n Name: \"evidence_ECO:0000313\"\n Description: \"A type of evidence that is imported information used in an automatic assertion\"\n Unique Values: \"1\"\n Name: \"xref_id\"\n Description: \"ID of the X-ref\"\n Unique Values: \"19\"\n Name: \"mim_id\"\n Description: \"Disease ID from the OMIM database\"\n Unique Values: \"1\"\n Name: \"description\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"begin_aa_pos\"\n Description: \"Start position of the amino acid in the sequence of a protein in UniProtKB\"\n Unique Values: \"18\"\n Name: \"cytogenic_band\"\n Description: \"One of the subregions of a chromosome visible microscopically after special staining\"\n Unique Values: \"14\"\n Name: \"aa_pos\"\n Description: \"Position of the amino acid in canonical sequence of protein in the UniProtKB database\"\n Unique Values: \"18\"\n Name: \"ref_aa\"\n Description: \"Reference amino acid residue\"\n Unique Values: \"9\"\n Name: \"sift_score\"\n Description: \"SIFT predicts whether an amino acid substitution is likely to affect protein function based on sequence homology and the physico-chemical similarity between the alternate amino acids. The data we provide for each amino acid substitution is a score and a qualitative prediction (either 'tolerated' or 'deleterious'). The score is the normalized probability that the amino acid change is tolerated so scores nearer zero are more likely to be deleterious. The qualitative prediction is derived from this score such that substitutions with a score < 0.05 are called 'deleterious' and all others are called 'tolerated\"\n Unique Values: \"10\"\n Name: \"alt_motif\"\n Description: \"Altered motif\"\n Unique Values: \"24\"\n Name: \"disease_xrefs\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"polyphen_score\"\n Description: \"The score assigned to a amino acid substitution by a tool called as PolyPhen (=Polymorphism Phenotyping) which predicts possible impact of an amino acid substitution on the structure and function of a human protein using straightforward physical and comparative considerations. The PolyPhen score ranges from 0.0 (tolerated) to 1.0 (deleterious). Variants with scores of 0.0 are predicted to be benign. Values closer to 1.0 are more confidently predicted to be deleterious\"\n Unique Values: \"1\"\n Name: \"polyphen_prediction\"\n Description: \"\"The PolyPhen prediction values are - greater than 0.908 - \"\"Probably Damaging\"\"; greater than 0.446 and less than or equal to 0.908 - \"\"Possibly Damaging\"\"; less than or equal to 0.446 - \"\"Benign\"\"\"\n Unique Values: \"1\"\n Name: \"is_known_glycoprotein\"\n Description: \"Yes or no flag to denote if a protein is experimentally proven glycoprotein\"\n Unique Values: \"1\"\n Name: \"alt_nt\"\n Description: \"Alternative nucleotide\"\n Unique Values: \"1\"\n Name: \"protein_name\"\n Description: \"Protein name in the UniProtKB\"\n Unique Values: \"16\"\n Name: \"disease_evidence_ECO:0000313\"\n Description: \"The evidence that could be a PMID or a ClinVar ID that associates disease with the variant\"\n Unique Values: \"1\"\n Name: \"effect\"\n Description: \"The effect on glycosylation or N-sequon due to variation at site of glycosylated amino acid.\"\n Unique Values: \"3\"\n Name: \"end_aa_pos\"\n Description: \"End position of the amino acid in the sequence of a protein in UniProtKB\"\n Unique Values: \"18\"\n Name: \"mutation_type\"\n Description: \"Denotes whether mutation was reported with reference to amino acid or nucleotide\"\n Unique Values: \"1\"\n Name: \"disease_description\"\n Description: \"The disease description and/or definition \"\n Unique Values: \"1\"\n Name: \"do_id\"\n Description: \"Disease Ontology identifier\"\n Unique Values: \"1\"\n Name: \"evidence_ECO:0000269\"\n Description: \"A type of experimental evidence that is used in a manual assertion. Usually the values are PMIDs\"\n Unique Values: \"1\"\n Name: \"ref_nt\"\n Description: \"Reference nucleotide\"\n Unique Values: \"4\"\n Name: \"disease\"\n Description: \"The disease name for the cell line\"\n Unique Values: \"1\"\n Name: \"alt_aa\"\n Description: \"Altered amino acid residue\"\n Unique Values: \"10\"\n Name: \"cosmic_id\"\n Description: \"Legacy mutation identifier (COSM) in Catalogue of Somatic Mutations in Cancer (COSMIC) represents existing COSM mutation identifiers. This identifier remains the same between different assemblies (GRCh37 and GRCh38). All the COSM ids at the same genomic location have been collapsed into one representative COSM id. These ids are maintained to help track existing mutations\"\n Unique Values: \"1\"\n Name: \"ref_motif\"\n Description: \"Reference motif\"\n Unique Values: \"20\"\n Name: \"xref_key\"\n Description: \"Source key associated to the xref_id\"\n Unique Values: \"2\"\n Name: \"minor_allelic_frequency\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"gene_name\"\n Description: \"\"Official gene name/symbol assigned to the gene. Human gene name/symbol are approved by the HUGO Gene Nomenclature Committee (HGNC) and mouse gene name are approved by the Mouse Genome Informatics (MGI)\"\n Unique Values: \"17\"\n Name: \"disease_evidence_ECO:0000269\"\n Description: \"The PMID evidence for the association of the disease with the variant.\"\n Unique Values: \"1\"", "downloadurl": "/ln2data/releases/data/v-1.11.2/reviewed/human_protein_xref_reactome.csv" }