{ "bcoid": "GLY_000397", "title": "Rat Protein Submitted Names (UniProtKB)", "description": "The Rat Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for rat [taxid:10116] ...", "filename": "rat_protein_submittednames.csv", "filetype": "csv", "categories": { "species": "Rattus norvegicus", "molecule": "Protein", "tags": "Protein Submitted Names", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "D3ZB44-1...", "Zinc finger ..." ], [ "D3ZB44-1...", "RCG27445..." ] ], "headers": [ "uniprotkb_ca...", "submitted_na..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "submitted_name_full" }, { "type": "string", "label": "submitted_name_short" }, { "type": "string", "label": "ec_name" } ], [ "D3ZB44-1", "Zinc finger protein 324", "", "" ], [ "D3ZB44-1", "RCG27445", "", "" ], [ "D3ZXJ3-1", "Zinc finger protein 78", "", "" ], [ "D3ZB49-1", "Similar to Protein C8orf1 (HT41) (Predicted), isoform CRA_b", "", "" ], [ "D3ZB49-1", "Oxidative stress-induced growth inhibitor family member 2", "", "" ], [ "D3ZB48-1", "Hook microtubule-tethering protein 1", "", "" ], [ "D3ZB48-1", "Hook homolog 1 (Drosophila) (Predicted)", "", "" ], [ "Q04462-1", "Valine--tRNA ligase", "", "" ], [ "A0A0G2JVG5-1", "Trichohyalin-like", "", "" ], [ "A0A0G2JVG6-1", "Uncharacterized protein", "", "" ], [ "A0A096MJY8-1", "Acetyl-CoA acetyltransferase 2-like 1", "", "" ], [ "B2GV58-1", "LSM14A mRNA-processing body assembly factor", "", "" ], [ "A0A096MJY1-1", "Similar to Gpc6 protein (Predicted)", "", "" ], [ "A0A096MJY1-1", "Glypican 6", "", "" ], [ "P56558-1", "UDP-N-acetylglucosamine--peptide N-acetylglucosaminyltransferase 110 kDa subunit", "", "" ], [ "A0A096MJY2-1", "Stomatin-like 3", "", "" ], [ "A0A096MJY2-1", "Stomatin (Epb7.2)-like 3 (Predicted), isoform CRA_a", "", "" ], [ "Q5RJK6-1", "Inositol polyphosphate-1-phosphatase", "", "" ], [ "Q5RJK6-1", "RCG22563", "", "" ], [ "Q63358-1", "Unconventional myosin-IXb", "", "" ], [ "Q63358-1", "Myosin 9b", "", "" ], [ "A0A1W2Q6N1-1", "MPL proto-oncogene, thrombopoietin receptor", "", "" ], [ "D4A4W8-1", "T, brachyury homolog (Mouse) (Predicted), isoform CRA_b", "", "" ], [ "D4A4W8-1", "T-box transcription factor T", "", "" ], [ "D4A4W1-1", "Family with sequence similarity 174, member B", "", "" ], [ "F7EN52-1", "Cyp46a1 protein", "", "" ], [ "F7EN52-1", "Cytochrome P450, family 46, subfamily a, polypeptide 1", "", "" ], [ "D4A4W4-1", "Abhydrolase domain containing 9 (Predicted)", "", "" ], [ "D4A4W4-1", "Epoxide hydrolase 3", "", "" ], [ "D4A4W6-1", "SRA stem-loop-interacting RNA-binding protein", "", "" ], [ "D4A4W6-1", "RCG20695, isoform CRA_b", "", "" ], [ "D4A4W7-1", "Mitochondria-localized glutamic acid-rich protein", "", "" ], [ "D4A4W7-1", "RCG50000, isoform CRA_c", "", "" ], [ "G3V6I3-1", "Coiled-coil domain containing 49 (Predicted)", "", "" ], [ "G3V6I3-1", "CWC25 spliceosome-associated protein homolog", "", "" ], [ "Q8K4K5-1", "Lethal(2) giant larvae protein homolog 1", "", "" ], [ "Q8K4K5-1", "RCG33798, isoform CRA_b", "", "" ], [ "Q4L0E8-1", "Regulator of G-protein signaling 18", "", "" ], [ "G3V6I6-1", "Adiponectin receptor 1", "", "" ], [ "G3V6I6-1", "Adiponectin receptor 1, isoform CRA_a", "", "" ], [ "A0A0G2K5E4-1", "DnaJ heat shock protein family (Hsp40) member A3", "", "" ], [ "G3V6I4-1", "Mitochondrial amidoxime reducing component 1", "", "" ], [ "G3V6I4-1", "RCG20363, isoform CRA_a", "", "" ], [ "P12749-1", "RCG33968, isoform CRA_a", "", "" ], [ "P12749-1", "60S ribosomal protein L26", "", "" ], [ "O08812-1", "Cationic amino acid transporter 3", "", "" ], [ "O08812-1", "Solute carrier family 7 (Cationic amino acid transporter, y+ system), member 3, isoform CRA_b", "", "" ], [ "A0A0G2K0T8-1", "Family with sequence similarity 25, member A", "", "" ], [ "A0A0G2K0T8-1", "RCG42313", "", "" ], [ "A0A0G2K0T4-1", "Uncharacterized protein", "", "" ], [ "Q6P6Q9-1", "Calcium uptake protein 1, mitochondrial", "", "" ], [ "A0A0G2K0T7-1", "Zinc finger protein 35", "", "" ], [ "Q5U1W2-1", "Proline-rich protein 13", "", "" ], [ "D3ZVR6-1", "SMC5-SMC6 complex localization factor 1", "", "" ], [ "D3ZVR6-1", "RCG44470", "", "" ], [ "A0A0G2K1A3-1", "Uncharacterized protein", "", "" ], [ "A0A0G2K1A1-1", "Zinc finger protein 706", "", "" ], [ "A0A0G2K1A1-1", "Uncharacterized protein LOC500855", "", "" ], [ "P33124-1", "Long-chain-fatty-acid--CoA ligase 6", "", "" ], [ "Q6MG12-1", "Hypothetical protein MGC:15854", "", "" ], [ "M0RB72-1", "Proline-rich 15-like", "", "" ], [ "M0RB72-1", "RCG34095", "", "" ], [ "D4A781-1", "Importin 5", "", "" ], [ "A0A0G2K8D0-1", "Similar to immunoglobulin superfamily, member 7", "", "" ], [ "P33568-1", "Retinoblastoma-associated protein", "", "" ], [ "E9PU34-1", "RCG41110", "", "" ], [ "E9PU34-1", "Required for meiotic nuclear division 1 homolog", "", "" ], [ "Q8CJ58-1", "Clarin-1", "", "" ], [ "P07727-1", "Glycine receptor subunit alpha-1", "", "" ], [ "P07727-1", "Glycine alpha 1, truncated", "", "" ], [ "P83748-1", "Serine protease 30", "", "" ], [ "P20420-1", "Neuronal nicotinic acetylcholine receptor alpha5 subunit", "", "" ], [ "P20420-1", "Neuronal acetylcholine receptor subunit alpha-5", "", "" ], [ "A0A0G2JTB2-1", "1,4-alpha-glucan-branching enzyme 1", "", "" ], [ "M0R8G5-1", "IgA-inducing protein", "", "" ], [ "D3ZGR6-1", "Coiled-coil domain-containing 138", "", "" ], [ "D3ZGR7-1", "Telomerase RNA component-interacting RNase", "", "" ], [ "D3ZGR7-1", "RCG51149", "", "" ], [ "D3ZGR5-1", "Ankyrin repeat domain-containing protein 12-like", "", "" ], [ "D3ZIY3-1", "YTH N(6)-methyladenosine RNA-binding protein 3", "", "" ], [ "D3ZIY3-1", "YTH domain family 3 (Predicted), isoform CRA_b", "", "" ], [ "D3ZHU7-1", "Methyl-CpG-binding domain protein 3-like 2", "", "" ], [ "D3ZSP2-1", "NACHT, LRR and PYD domains-containing protein 4B-like", "", "" ], [ "D3ZFP5-1", "Similar to Robo-1", "", "" ] ] }, "readme": "Name\n - Rat Protein Submitted Names (UniProtKB)\n\nVersion\n - 1.11.2\n\nCreated on\n - 2020-03-15T13:43:53.106298\n\nModified on\n - 2020-03-16T11:16:17.615859\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 - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n - \n\nUsability Domain\n - The Rat Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for rat [taxid:10116] 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.. 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\nDescription Domain\n Keywords\n - protein submitted name\n - protein name\n - UniProtKB\n\n Pipeline Steps\n - Step-1: 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\n\nExecution Domain\n Scripts - https://github.com/glygener/glygen-backend-integration/blob/master/pipeline/extractor/extract-from-endpoint.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-rattus-norvegicus.nt\n URI: https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-rattus-norvegicus.nt\n Name: rat_protein_masterlist.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_masterlist.csv\n Output Subdomain\n Name: rat_protein_submittednames.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_submittednames.csv\n Name: rat_protein_submittednames.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_submittednames.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/rat_protein_submittednames.csv" }