{ "bcoid": "GLY_000336", "title": "Mouse Xref GlycoProtDB", "description": "The Mouse (TaxID:10090) Xref GlycoProtDB contains x-refs to IDs present in the GlycoProtDB database ...", "filename": "mouse_protein_xref_glycoprotdb.csv", "filetype": "csv", "categories": { "species": "Mus musculus", "molecule": "Protein", "tags": "GlycoProtDB cross-references", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q8BH24-1...", "protein_xref..." ], [ "Q8BH27-1...", "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" } ], [ "Q8BH24-1", "protein_xref_glycoprotdb", "GPDB0006196", "Transmembrane 9 superfamily member 4" ], [ "Q8BH27-1", "protein_xref_glycoprotdb", "GPDB0006197", "Multiple epidermal growth factor-like domains protein 9" ], [ "P70412-1", "protein_xref_glycoprotdb", "GPDB0003775", "CUB and zona pellucida-like domain-containing protein 1" ], [ "P70419-1", "protein_xref_glycoprotdb", "GPDB0003776", "Polypeptide N-acetylgalactosaminyltransferase 3" ], [ "Q9EP78-1", "protein_xref_glycoprotdb", "GPDB0007489", "Carbohydrate sulfotransferase 7" ], [ "Q9EP73-1", "protein_xref_glycoprotdb", "GPDB0007488", "Programmed cell death 1 ligand 1" ], [ "G5E8Q8-1", "protein_xref_glycoprotdb", "GPDB0002934", "Adhesion G protein-coupled receptor F5" ], [ "P50429-1", "protein_xref_glycoprotdb", "GPDB0003660", "Arylsulfatase B" ], [ "P50429-1", "protein_xref_glycoprotdb", "GPDB0003661", "Isoform 2 of Arylsulfatase B" ], [ "Q8BTJ4-1", "protein_xref_glycoprotdb", "GPDB0006382", "Bis(5'-adenosyl)-triphosphatase enpp4" ], [ "Q8BTJ4-1", "protein_xref_glycoprotdb", "GPDB0006383", "Isoform 2 of Bis(5'-adenosyl)-triphosphatase enpp4" ], [ "P21661-1", "protein_xref_glycoprotdb", "GPDB0003478", "Neuroendocrine convertase 2" ], [ "Q8CB67-1", "protein_xref_glycoprotdb", "GPDB0006599", "Low-density lipoprotein receptor-related protein 11" ], [ "Q3TNL8-1", "protein_xref_glycoprotdb", "GPDB0004304", "Inositol 1,4,5-trisphosphate receptor-interacting protein" ], [ "Q3TNL8-1", "protein_xref_glycoprotdb", "GPDB0004305", "Isoform 2 of Inositol 1,4,5-trisphosphate receptor-interacting protein" ], [ "Q99J85-1", "protein_xref_glycoprotdb", "GPDB0002439", "Neuronal pentraxin receptor" ], [ "Q8BR76-1", "protein_xref_glycoprotdb", "GPDB0002283", "Meckelin (Fragment)" ], [ "P06909-1", "protein_xref_glycoprotdb", "GPDB0002282", "Complement factor H" ], [ "Q9D306-1", "protein_xref_glycoprotdb", "GPDB0002165", "Alpha-1,3-mannosyl-glycoprotein 4-beta-N-acetylglucosaminyltransferase C (Fragment)" ], [ "Q9WUZ9-1", "protein_xref_glycoprotdb", "GPDB0007798", "Ectonucleoside triphosphate diphosphohydrolase 5" ], [ "Q8BTH8-1", "protein_xref_glycoprotdb", "GPDB0001463", "Casein kinase I isoform gamma-1 (Fragment)" ], [ "Q9ESN3-1", "protein_xref_glycoprotdb", "GPDB0007533", "Transmembrane protein 8A" ], [ "Q9ESN3-1", "protein_xref_glycoprotdb", "GPDB0007534", "Isoform Beta of Transmembrane protein 8A" ], [ "O88307-1", "protein_xref_glycoprotdb", "GPDB0003201", "Sortilin-related receptor" ], [ "O70362-1", "protein_xref_glycoprotdb", "GPDB0006967", "Glycosylphosphatidylinositol specific phospholipase D1" ], [ "Q8VCU1-1", "protein_xref_glycoprotdb", "GPDB0006965", "Carboxylesterase 3B" ], [ "Q8VCU1-1", "protein_xref_glycoprotdb", "GPDB0006966", "Isoform 2 of Carboxylesterase 3B" ], [ "Q67BT3-1", "protein_xref_glycoprotdb", "GPDB0005671", "Solute carrier family 13 member 5" ], [ "F8VPK8-1", "protein_xref_glycoprotdb", "GPDB0001208", "Protein Pcdh9 (Fragment)" ], [ "P27467-1", "protein_xref_glycoprotdb", "GPDB0003528", "Protein Wnt-3a" ], [ "Q8VEK0-1", "protein_xref_glycoprotdb", "GPDB0006987", "Cell cycle control protein 50A" ], [ "P21803-1", "protein_xref_glycoprotdb", "GPDB0002551", "Fibroblast growth factor receptor 2 (Fragment)" ], [ "Q3UHK1-1", "protein_xref_glycoprotdb", "GPDB0004791", "Proton myo-inositol cotransporter" ], [ "Q61614-1", "protein_xref_glycoprotdb", "GPDB0005507", "Endothelin-1 receptor" ], [ "P43006-1", "protein_xref_glycoprotdb", "GPDB0003624", "Excitatory amino acid transporter 2" ], [ "P43006-1", "protein_xref_glycoprotdb", "GPDB0003625", "Isoform Glt-1A of Excitatory amino acid transporter 2" ], [ "P43006-1", "protein_xref_glycoprotdb", "GPDB0003626", "Isoform Glt-1B of Excitatory amino acid transporter 2" ], [ "P16294-1", "protein_xref_glycoprotdb", "GPDB0003428", "Coagulation factor IX" ], [ "Q80V53-1", "protein_xref_glycoprotdb", "GPDB0001712", "Carbohydrate sulfotransferase 14" ], [ "J3QNS5-1", "protein_xref_glycoprotdb", "GPDB0002999", "Protein Mfsd4b4" ], [ "P14427-1", "protein_xref_glycoprotdb", "GPDB0003385", "H-2 class I histocompatibility antigen, D-K alpha chain" ], [ "P14429-1", "protein_xref_glycoprotdb", "GPDB0003387", "H-2 class I histocompatibility antigen, Q7 alpha chain" ], [ "P01901-1", "protein_xref_glycoprotdb", "GPDB0003386", "H-2 class I histocompatibility antigen, K-Q alpha chain (Fragment)" ], [ "Q8BMD6-1", "protein_xref_glycoprotdb", "GPDB0006292", "Transmembrane protein 260" ], [ "Q8BMD6-1", "protein_xref_glycoprotdb", "GPDB0006293", "Isoform 2 of Transmembrane protein 260" ], [ "Q9R0M4-1", "protein_xref_glycoprotdb", "GPDB0007711", "Podocalyxin" ], [ "Q9R0M0-1", "protein_xref_glycoprotdb", "GPDB0007709", "Cadherin EGF LAG seven-pass G-type receptor 2" ], [ "Q9R0M0-1", "protein_xref_glycoprotdb", "GPDB0007710", "Isoform 2 of Cadherin EGF LAG seven-pass G-type receptor 2" ], [ "Q91ZV7-1", "protein_xref_glycoprotdb", "GPDB0001603", "Plexin domain-containing protein 1" ], [ "Q8BLK3-1", "protein_xref_glycoprotdb", "GPDB0001130", "Limbic system-associated membrane protein" ], [ "Q8R2S8-1", "protein_xref_glycoprotdb", "GPDB0006862", "CD177 antigen" ], [ "P22437-1", "protein_xref_glycoprotdb", "GPDB0003487", "Prostaglandin G/H synthase 1" ], [ "O35451-1", "protein_xref_glycoprotdb", "GPDB0003110", "Cyclic AMP-dependent transcription factor ATF-6 beta" ], [ "Q9EPK8-1", "protein_xref_glycoprotdb", "GPDB0007493", "Transient receptor potential cation channel subfamily V member 4" ], [ "Q9EPK6-1", "protein_xref_glycoprotdb", "GPDB0007492", "Nucleotide exchange factor SIL1" ], [ "Q9JLF7-1", "protein_xref_glycoprotdb", "GPDB0007609", "Toll-like receptor 5" ], [ "P01867-1", "protein_xref_glycoprotdb", "GPDB0003255", "Ig gamma-2B chain C region" ], [ "P01867-1", "protein_xref_glycoprotdb", "GPDB0003256", "Isoform 2 of Ig gamma-2B chain C region" ], [ "O55026-1", "protein_xref_glycoprotdb", "GPDB0003161", "Isoform Short of Ectonucleoside triphosphate diphosphohydrolase 2" ], [ "O55026-1", "protein_xref_glycoprotdb", "GPDB0003160", "Ectonucleoside triphosphate diphosphohydrolase 2" ], [ "O54998-1", "protein_xref_glycoprotdb", "GPDB0003157", "Peptidyl-prolyl cis-trans isomerase FKBP7" ], [ "O54990-1", "protein_xref_glycoprotdb", "GPDB0003150", "Prominin-1" ], [ "O54990-1", "protein_xref_glycoprotdb", "GPDB0003151", "Isoform 2 of Prominin-1" ], [ "O54990-1", "protein_xref_glycoprotdb", "GPDB0003152", "Isoform 3 of Prominin-1" ], [ "O54990-1", "protein_xref_glycoprotdb", "GPDB0003153", "Isoform 4 of Prominin-1" ], [ "O54990-1", "protein_xref_glycoprotdb", "GPDB0003154", "Isoform 5 of Prominin-1" ], [ "O54990-1", "protein_xref_glycoprotdb", "GPDB0003155", "Isoform 6 of Prominin-1" ], [ "O54991-1", "protein_xref_glycoprotdb", "GPDB0003156", "Contactin-associated protein 1" ], [ "E9PVB5-1", "protein_xref_glycoprotdb", "GPDB0001645", "Tetratricopeptide repeat protein 17" ], [ "P63056-1", "protein_xref_glycoprotdb", "GPDB0003740", "Noelin-3" ], [ "P63056-1", "protein_xref_glycoprotdb", "GPDB0003741", "Isoform 2 of Noelin-3" ], [ "Q6S9I3-1", "protein_xref_glycoprotdb", "GPDB0005868", "Kng2 protein" ], [ "Q6S9I3-1", "protein_xref_glycoprotdb", "GPDB0005869", "HMW-kininogen-II variant" ], [ "Q6S9I3-1", "protein_xref_glycoprotdb", "GPDB0005870", "HMW kininogen-II" ], [ "Q7TQH7-1", "protein_xref_glycoprotdb", "GPDB0006005", "Low-density lipoprotein receptor-related protein 10" ], [ "Q80TR1-1", "protein_xref_glycoprotdb", "GPDB0002974", "Adhesion G protein-coupled receptor L1" ], [ "P11627-1", "protein_xref_glycoprotdb", "GPDB0003354", "Neural cell adhesion molecule L1" ], [ "Q91Y57-1", "protein_xref_glycoprotdb", "GPDB0007102", "Sialic acid-binding Ig-like lectin 12" ], [ "Q8BPX9-1", "protein_xref_glycoprotdb", "GPDB0006335", "Solute carrier family 15 member 3" ], [ "Q9D3A9-1", "protein_xref_glycoprotdb", "GPDB0001459", "Protein tweety homolog" ], [ "Q9Z1M0-1", "protein_xref_glycoprotdb", "GPDB0005782", "P2X purinoceptor 7" ], [ "P04186-1", "protein_xref_glycoprotdb", "GPDB0002743", "Complement factor B" ], [ "Q64302-1", "protein_xref_glycoprotdb", "GPDB0005628", "Transmembrane 4 L6 family member 1" ], [ "Q9JL06-1", "protein_xref_glycoprotdb", "GPDB0007595", "Lysophosphatidic acid receptor 2" ] ] }, "readme": "Name\n - Mouse Xref GlycoProtDB\n\nVersion\n - 1.11.2\n\nCreated on\n - 2020-02-10T14:47:12.024589\n\nModified on\n - 2020-04-09T18:03:03.346761\n\nCreated by\n - Rahi Navelkar [rsn13@gwu.edu], Jeet Vora [jeetvora@gwu.edu], Robel Kahsay [rykahsay@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 - Kiyoko F. Aoki-Kinoshita [kkiyoko@soka.ac.jp]\n\nChecksum\n - \n\nUsability Domain\n - The Mouse (TaxID:10090) Xref GlycoProtDB contains x-refs to IDs present in the GlycoProtDB database (https://acgg.asia/gpdb2/index). If you use this dataset please provide proper attribution to GlycoProtDB and GlyGen. \n\nDescription Domain\n Keywords\n - GlycoProtDB\n - cross-reference\n\n Pipeline Steps\n - Step-1: The input file was received directly from the author (Kiyoko F. Aoki-Kinoshita). all the accessions from the input file were checked in the UniProtKB through ID mapping tool. It was found that all the UniProtKB accessions belonged to the Mouse [TaxID:10090] species. The QC checks mapped the UniProtKB accessions to UniProtKB canonical accessions. Any GlycoProtDB ID which was mapped to a protein outside GlyGen protein master list was excluded from the output file.\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: protein_xref_glycoprotdb.csv\n URI: https://data.glygen.org/ln2wwwdata/source/protein_xref_glycoprotdb.csv\n Name: mouse_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_masterlist.csv\n Output Subdomain\n Name: mouse_protein_xref_glycoprotdb.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_glycoprotdb.csv\n Name: mouse_protein_xref_glycoprotdb.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_glycoprotdb.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/mouse_protein_xref_glycoprotdb.csv" }