{ "bcoid": "GLY_000404", "title": "Human UniProtKB Xref Pharos", "description": "The Human UniProtKB Xref Pharos dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced ...", "filename": "human_protein_xref_pharos.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "Pharos cross-references", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P30613-1...", "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" } ], [ "P30613-1", "protein_xref_pharos", "P30613", "Pyruvate kinase PKLR" ], [ "P23919-1", "protein_xref_pharos", "P23919", "Thymidylate kinase" ], [ "Q8NHX4-1", "protein_xref_pharos", "Q8NHX4", "Spermatogenesis-associated protein 3" ], [ "Q8NHX9-1", "protein_xref_pharos", "Q8NHX9", "Two pore calcium channel protein 2" ], [ "H3BTG2-1", "protein_xref_pharos", "H3BTG2", "Testis-expressed protein 46" ], [ "Q9C0H2-1", "protein_xref_pharos", "Q9C0H2", "Protein tweety homolog 3" ], [ "Q9C0H5-1", "protein_xref_pharos", "Q9C0H5", "Rho GTPase-activating protein 39" ], [ "Q9C0H6-1", "protein_xref_pharos", "Q9C0H6", "Kelch-like protein 4" ], [ "Q9C0H9-5", "protein_xref_pharos", "Q9C0H9", "SRC kinase signaling inhibitor 1" ], [ "Q96J66-1", "protein_xref_pharos", "Q96J66", "ATP-binding cassette sub-family C member 11" ], [ "Q96J65-1", "protein_xref_pharos", "Q96J65", "Multidrug resistance-associated protein 9" ], [ "Q9NYS7-1", "protein_xref_pharos", "Q9NYS7", "WD repeat and SOCS box-containing protein 2" ], [ "P40424-1", "protein_xref_pharos", "P40424", "Pre-B-cell leukemia transcription factor 1" ], [ "P40425-1", "protein_xref_pharos", "P40425", "Pre-B-cell leukemia transcription factor 2" ], [ "P40426-1", "protein_xref_pharos", "P40426", "Pre-B-cell leukemia transcription factor 3" ], [ "P40429-1", "protein_xref_pharos", "P40429", "60S ribosomal protein L13a" ], [ "Q9H2I8-1", "protein_xref_pharos", "Q9H2I8", "Leucine-rich melanocyte differentiation-associated protein" ], [ "P03891-1", "protein_xref_pharos", "P03891", "NADH-ubiquinone oxidoreductase chain 2" ], [ "P03897-1", "protein_xref_pharos", "P03897", "NADH-ubiquinone oxidoreductase chain 3" ], [ "P02768-1", "protein_xref_pharos", "P02768", "Serum albumin" ], [ "P02760-1", "protein_xref_pharos", "P02760", "Protein AMBP" ], [ "P02763-1", "protein_xref_pharos", "P02763", "Alpha-1-acid glycoprotein 1" ], [ "P02765-1", "protein_xref_pharos", "P02765", "Alpha-2-HS-glycoprotein" ], [ "P82921-1", "protein_xref_pharos", "P82921", "28S ribosomal protein S21, mitochondrial" ], [ "P02766-1", "protein_xref_pharos", "P02766", "Transthyretin" ], [ "Q9P2J5-1", "protein_xref_pharos", "Q9P2J5", "Leucine--tRNA ligase, cytoplasmic" ], [ "H0YL14-1", "protein_xref_pharos", "H0YL14", "Transmembrane protein 250" ], [ "Q9P2J8-1", "protein_xref_pharos", "Q9P2J8", "Zinc finger protein 624" ], [ "O43399-1", "protein_xref_pharos", "O43399", "Tumor protein D54" ], [ "Q9BXR3-1", "protein_xref_pharos", "Q69384", "Endogenous retrovirus group K member 6 Env polyprotein" ], [ "Q9BXR3-1", "protein_xref_pharos", "Q69383", "Endogenous retrovirus group K member 6 Rec protein" ], [ "Q5VVP1-1", "protein_xref_pharos", "Q5VVP1", "Spermatogenesis-associated protein 31A6" ], [ "Q9BZG1-1", "protein_xref_pharos", "Q9BZG1", "Ras-related protein Rab-34" ], [ "Q9BZG2-1", "protein_xref_pharos", "Q9BZG2", "Testicular acid phosphatase" ], [ "Q9BZG8-1", "protein_xref_pharos", "Q9BZG8", "2-(3-amino-3-carboxypropyl)histidine synthase subunit 1" ], [ "Q6NUK4-1", "protein_xref_pharos", "Q6NUK4", "Receptor expression-enhancing protein 3" ], [ "P01236-1", "protein_xref_pharos", "P01236", "Prolactin" ], [ "Q8N865-1", "protein_xref_pharos", "Q8N865", "Uncharacterized protein C7orf31" ], [ "Q6NX49-1", "protein_xref_pharos", "Q6NX49", "Zinc finger protein 544" ], [ "P09001-1", "protein_xref_pharos", "P09001", "39S ribosomal protein L3, mitochondrial" ], [ "P53708-1", "protein_xref_pharos", "P53708", "Integrin alpha-8" ], [ "Q6NX45-1", "protein_xref_pharos", "Q6NX45", "Zinc finger protein 774" ], [ "Q9H963-1", "protein_xref_pharos", "Q9H963", "Putative zinc finger protein 702" ], [ "Q14568-1", "protein_xref_pharos", "Q14568", "Heat shock protein HSP 90-alpha A2" ], [ "Q9H967-1", "protein_xref_pharos", "Q9H967", "WD repeat-containing protein 76" ], [ "Q14563-1", "protein_xref_pharos", "Q14563", "Semaphorin-3A" ], [ "Q14562-1", "protein_xref_pharos", "Q14562", "ATP-dependent RNA helicase DHX8" ], [ "Q14566-1", "protein_xref_pharos", "Q14566", "DNA replication licensing factor MCM6" ], [ "Q14565-1", "protein_xref_pharos", "Q14565", "Meiotic recombination protein DMC1/LIM15 homolog" ], [ "A6NIR3-1", "protein_xref_pharos", "A6NIR3", "Arf-GAP with GTPase, ANK repeat and PH domain-containing protein 5" ], [ "Q6ZMG9-1", "protein_xref_pharos", "Q6ZMG9", "Ceramide synthase 6" ], [ "Q86VY4-1", "protein_xref_pharos", "Q86VY4", "Testis-specific Y-encoded-like protein 5" ], [ "Q86VY9-1", "protein_xref_pharos", "Q86VY9", "Transmembrane protein 200A" ], [ "P19075-1", "protein_xref_pharos", "P19075", "Tetraspanin-8" ], [ "O60729-1", "protein_xref_pharos", "O60729", "Dual specificity protein phosphatase CDC14B" ], [ "A6NCL1-1", "protein_xref_pharos", "A6NCL1", "Geminin coiled-coil domain-containing protein 1" ], [ "Q8WUF8-1", "protein_xref_pharos", "Q8WUF8", "Protein FAM172A" ], [ "Q96BT1-1", "protein_xref_pharos", "Q96BT1", "Putative uncharacterized protein C3orf49" ], [ "Q8WUF5-1", "protein_xref_pharos", "Q8WUF5", "RelA-associated inhibitor" ], [ "Q96BT3-1", "protein_xref_pharos", "Q96BT3", "Centromere protein T" ], [ "Q96BT7-1", "protein_xref_pharos", "Q96BT7", "Alkylated DNA repair protein alkB homolog 8" ], [ "Q99519-1", "protein_xref_pharos", "Q99519", "Sialidase-1" ], [ "O15417-1", "protein_xref_pharos", "O15417", "Trinucleotide repeat-containing gene 18 protein" ], [ "Q96RU7-1", "protein_xref_pharos", "Q96RU7", "Tribbles homolog 3" ], [ "Q96RU3-1", "protein_xref_pharos", "Q96RU3", "Formin-binding protein 1" ], [ "Q96RU2-1", "protein_xref_pharos", "Q96RU2", "Ubiquitin carboxyl-terminal hydrolase 28" ], [ "Q96RU8-1", "protein_xref_pharos", "Q96RU8", "Tribbles homolog 1" ], [ "Q9ULV4-1", "protein_xref_pharos", "Q9ULV4", "Coronin-1C" ], [ "Q9Y5A7-1", "protein_xref_pharos", "Q9Y5A7", "NEDD8 ultimate buster 1" ], [ "Q9Y5A6-1", "protein_xref_pharos", "Q9Y5A6", "Zinc finger and SCAN domain-containing protein 21" ], [ "Q13643-1", "protein_xref_pharos", "Q13643", "Four and a half LIM domains protein 3" ], [ "Q13642-2", "protein_xref_pharos", "Q13642", "Four and a half LIM domains protein 1" ], [ "Q13641-1", "protein_xref_pharos", "Q13641", "Trophoblast glycoprotein" ], [ "Q9Y5A9-1", "protein_xref_pharos", "Q9Y5A9", "YTH domain-containing family protein 2" ], [ "Q02127-1", "protein_xref_pharos", "Q02127", "Dihydroorotate dehydrogenase (quinone), mitochondrial" ], [ "Q6ZRV3-1", "protein_xref_pharos", "Q6ZRV3", "Putative uncharacterized protein encoded by LINC00696" ], [ "Q6ZRV2-1", "protein_xref_pharos", "Q6ZRV2", "Protein FAM83H" ], [ "Q5T6X5-1", "protein_xref_pharos", "Q5T6X5", "G-protein coupled receptor family C group 6 member A" ], [ "A8MZ59-2", "protein_xref_pharos", "A8MZ59", "Leucine-twenty homeobox" ], [ "Q9Y3T6-1", "protein_xref_pharos", "Q9Y3T6", "R3H and coiled-coil domain-containing protein 1" ], [ "P16520-1", "protein_xref_pharos", "P16520", "Guanine nucleotide-binding protein G(I)/G(S)/G(T) subunit beta-3" ], [ "Q8NCJ5-1", "protein_xref_pharos", "Q8NCJ5", "SPRY domain-containing protein 3" ], [ "Q9Y296-1", "protein_xref_pharos", "Q9Y296", "Trafficking protein particle complex subunit 4" ], [ "Q9Y297-1", "protein_xref_pharos", "Q9Y297", "F-box/WD repeat-containing protein 1A" ] ] }, "readme": "Name\n - Human UniProtKB Xref Pharos\n\nVersion\n - 1.11.2\n\nCreated on\n - 2020-03-20T14:14:17.733990\n\nModified on\n - 2022-01-13T16:15:59.676887\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@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 - Tudor I Oprea [TOprea@salud.unm.edu], Paul Barrett [paul.barrett@nih.gov], Ajay Pillai [ajay.pillai3@nih.gov]\n\nChecksum\n - \n\nUsability Domain\n - The Human UniProtKB Xref Pharos dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced to Pharos UniProtKB accessions. The data is from Pharos API based on TCRD version 5.4.0. If you use this dataset please provide proper attribution to Pharos and GlyGen\n - Pharos is the user interface to the Knowledge Management Center (KMC) for the Illuminating the Druggable Genome (IDG) program funded by the National Institutes of Health.\n - The goal of KMC is to develop a comprehensive, integrated knowledge-base for the Druggable Genome (DG) to illuminate the uncharacterized and/or poorly annotated portion of the DG, focusing on three of the most commonly drug-targeted protein families: G-protein-coupled receptors (GPCRs), ion channels (ICs) and kinases\n - Nguyen, D.-T., Mathias, S. et al, Pharos: Collating Protein Information to Shed Light on the Druggable Genome , Nucl. Acids Res.i>, 2017, 45(D1), D995-D1002. DOI: 10.1093/nar/gkw1072\n - https://pharos.nih.gov/about\n\nDescription Domain\n Keywords\n - Pharos\n - Illuminating the Druggable Genome\n - drug-targeted protein families\n - G-protein-coupled receptors (GPCRs)\n - ion channels (ICs)\n - kinases\n\n Pipeline Steps\n - Step-1: The script extracts the UniProtKB accessions and protein name from the Pharos API and maps to the GlyGen's UniProtKB canonical accessions (masterlist) to generate a csv dataset. The accessions that are not mapped are logged in the log 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: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_masterlist.csv\n Name: pharos_protein_all_9606.json\n URI: https://data.glygen.org/ln2wwwdata/source/pharos_protein_all_9606.json\n Output Subdomain\n Name: human_protein_xref_pharos.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_hgnc.csv\n Name: glygen_pharos_xref_mapping.log\n URI: http://data.glygen.org/ln2wwwdata/logs/glygen_pharos_xref_mapping.log\n Name: human_protein_xref_pharos.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_pharos.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_pharos.csv" }