{ "bcoid": "GLY_000396", "title": "Mouse Protein Submitted Names (UniProtKB)", "description": "The Mouse Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for mouse [taxid:10090] ...", "filename": "mouse_protein_submittednames.csv", "filetype": "csv", "categories": { "species": "Mus musculus", "molecule": "Protein", "tags": "Protein Submitted Names", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "E9Q287-1...", "A disintegri..." ], [ "Q922G0-1...", "Solute carri..." ] ], "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" } ], [ "E9Q287-1", "A disintegrin-like and metallopeptidase (reprolysin type) with thrombospondin type 1 motif, 3", "", "" ], [ "Q922G0-1", "Solute carrier family 25 member 36", "", "" ], [ "O35453-1", "Serine protease hepsin", "", "" ], [ "Q80T32-1", "Gpr133 protein", "", "" ], [ "Q80T32-1", "Adhesion G-protein-coupled receptor D1", "", "" ], [ "P62492-1", "Ras-related protein Rab-11A", "", "" ], [ "E9Q3P4-1", "Centromere protein F", "", "" ], [ "P63166-1", "Small ubiquitin-related modifier 1", "", "" ], [ "A0A087WPJ1-1", "RIKEN cDNA 1700017N19 gene", "", "" ], [ "B2RX88-1", "Centrosome and spindle pole-associated protein 1", "", "" ], [ "A0A087WRQ3-1", "T cell receptor alpha variable 1", "", "" ], [ "A5H0M4-1", "POTE ankyrin domain family, member G", "", "" ], [ "A5H0M4-1", "GSARP1", "", "" ], [ "Q9CWR0-1", "Rho guanine nucleotide exchange factor 25", "", "" ], [ "A2RSJ4-1", "UHRF1-binding protein 1-like", "", "" ], [ "Q91YE9-1", "Cytosolic 5'-nucleotidase 1B", "", "" ], [ "Q02853-1", "Stromelysin-3", "", "" ], [ "Q6DYE8-1", "Ectonucleotide pyrophosphatase/phosphodiesterase family member 3", "", "" ], [ "P36536-1", "GTP-binding protein SAR1a", "", "" ], [ "Q9R092-1", "17-beta-hydroxysteroid dehydrogenase type 6", "", "" ], [ "A0A0U1RNG7-1", "Potassium channel tetramerisation domain-containing 14", "", "" ], [ "O35309-1", "N-myc-interactor", "", "" ], [ "Q8BTY1-1", "Kynurenine--oxoglutarate transaminase 1", "", "" ], [ "Q61216-1", "MRE11A homolog A, double strand break repair nuclease", "", "" ], [ "Q9JHX3-1", "Interleukin-21 receptor", "", "" ], [ "Q3TLD5-1", "Unconventional prefoldin RPB5 interactor", "", "" ], [ "A0A0U1RNG7-1", "Potassium channel tetramerisation domain-containing 14", "", "" ], [ "Q9QYC7-1", "Vitamin K-dependent gamma-carboxylase", "", "" ], [ "P10852-1", "4F2 cell-surface antigen heavy chain", "", "" ], [ "Q8K2F8-1", "Protein LSM14 homolog A", "", "" ], [ "B2RRA8-1", "Zinc finger protein 114", "", "" ], [ "Q3UMR0-1", "Ankyrin repeat domain-containing protein 27", "", "" ], [ "Q8CHS4-1", "PI-PLC X domain-containing protein 1", "", "" ], [ "P30282-1", "G1/S-specific cyclin-D3", "", "" ], [ "P97411-1", "Islet cell autoantigen 1", "", "" ], [ "Q3UHI0-1", "Serine-rich coiled-coil domain-containing protein 2", "", "" ], [ "Q80TT2-1", "BAI1-associated protein 3", "", "" ], [ "S4R213-1", "Lactamase, beta-like 1", "", "" ], [ "Q91VV4-1", "DENN domain-containing protein 2D", "", "" ], [ "Q9CWR2-1", "Histone-lysine N-methyltransferase SMYD3", "", "" ], [ "Q9D0M3-1", "Cytochrome c1, heme protein, mitochondrial", "", "" ], [ "Q9WTP3-1", "SAM pointed domain-containing Ets transcription factor", "", "" ], [ "B8JJZ7-1", "Zinc finger protein 81", "", "" ], [ "A0A3Q4EGJ1-1", "Predicted gene 5155", "", "" ], [ "D3YVV3-1", "Ankyrin repeat domain 29", "", "" ], [ "P33587-1", "Vitamin K-dependent protein C", "", "" ], [ "Q8BXQ6-1", "Aminopeptidase O", "", "" ], [ "Q8C0L9-1", "Glycerophosphocholine phosphodiesterase GPCPD1", "", "" ], [ "Q3TX08-1", "tRNA (guanine(26)-N(2))-dimethyltransferase", "", "" ], [ "E9PYR1-1", "F-box and leucine-rich repeat protein 18", "", "" ], [ "P04760-1", "Acetylcholine receptor subunit gamma", "", "" ], [ "P59808-1", "SAM and SH3 domain-containing protein 1", "", "" ], [ "Q91UZ1-1", "Phospholipase C, beta 4", "", "" ], [ "Q61418-1", "H(+)/Cl(-) exchange transporter 4", "", "" ], [ "Q9D387-1", "Lysosome-associated membrane glycoprotein 5", "", "" ], [ "P25425-1", "POU domain, class 2, transcription factor 1", "", "" ], [ "B1ASB6-1", "SPOC domain-containing protein 1", "", "" ], [ "Q9D515-1", "Slx-like 1", "", "" ], [ "Q9D8K8-1", "Solute carrier family 25 member 39", "", "" ], [ "Q9D519-1", "Spermatogenesis-associated multipass transmembrane protein 2b", "", "" ], [ "Q61161-1", "Mitogen-activated protein kinase kinase kinase kinase 2", "", "" ], [ "O55087-1", "Myocyte enhancer factor 2B", "", "" ], [ "O55087-1", "Myocyte-specific enhancer factor 2B", "", "" ], [ "P70331-1", "MyoD family inhibitor", "", "" ], [ "F6ZPB0-1", "Predicted gene 21981", "", "" ], [ "F6ZPB0-1", "Prickle planar cell polarity protein 4", "", "" ], [ "Q9R210-1", "Transcription factor EB", "", "" ], [ "P58462-1", "Forkhead box protein P1", "", "" ], [ "P58462-1", "Forkhead box protein P1", "", "" ], [ "Q8BLQ7-1", "Cationic amino acid transporter 4", "", "" ], [ "Q8K2A8-1", "Dol-P-Man:Man(5)GlcNAc(2)-PP-Dol alpha-1,3-mannosyltransferase", "", "" ], [ "Q8BWU3-1", "Protein FAM131A", "", "" ], [ "Q7TQ33-1", "RGM domain family member B", "", "" ], [ "Q9Z1T1-1", "AP-3 complex subunit beta-1", "", "" ], [ "P70323-1", "T-box transcription factor TBX1", "", "" ], [ "Q8CHC4-1", "Synaptojanin-1", "", "" ], [ "Q8K2J4-1", "Coiled-coil domain-containing protein 14", "", "" ], [ "A0A0G2JEU8-1", "T cell receptor alpha variable 13N-1", "", "" ], [ "Q80VU4-1", "Neurotrophin 5", "", "" ], [ "L0N7N1-1", "Kinesin-like protein KIF14", "", "" ], [ "L0N7N1-1", "Truncated kinesin family member 14", "", "" ], [ "Q9R061-1", "Cytosolic Fe-S cluster assembly factor NUBP2", "", "" ], [ "P59672-1", "Ankyrin repeat and SAM domain containing 1", "", "" ], [ "Q497P9-1", "Predicted gene 5941", "", "" ] ] }, "readme": "Name\n - Mouse Protein Submitted Names (UniProtKB)\n\nVersion\n - 1.11.2\n\nCreated on\n - 2020-03-15T13:39:36.626348\n\nModified on\n - 2020-03-16T11:15:40.779396\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 Mouse Protein Submitted Names (UniProtKB) dataset contains UniProtKB submitted names for mouse [taxid:10090] 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-mus-musculus.nt\n URI: https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-mus-musculus.nt\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_submittednames.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_submittednames.csv\n Name: mouse_protein_submittednames.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/mouse_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/mouse_protein_submittednames.csv" }