{ "bcoid": "GLY_000461", "title": "Rat Germline Mutation", "description": "The Rat Germline Mutation dataset contains rat [taxid:10116] germline mutation data from EBI Variant ...", "filename": "rat_protein_mutation_germline.csv", "filetype": "csv", "categories": { "species": "Rattus norvegicus", "molecule": "Protein", "tags": "Germline Mutations", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q9JLM2-1...", "114..." ], [ "Q9JLM2-1...", "114..." ] ], "headers": [ "uniprotkb_ca...", "aa_pos..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "aa_pos" }, { "type": "string", "label": "gene_name" }, { "type": "string", "label": "protein_name" }, { "type": "string", "label": "dbsnp_id" }, { "type": "string", "label": "cosmic_id" }, { "type": "string", "label": "description" }, { "type": "string", "label": "evidence_ECO:0000269" }, { "type": "string", "label": "evidence_ECO:0000313" }, { "type": "string", "label": "cytogenic_band" }, { "type": "string", "label": "chr_id" }, { "type": "string", "label": "chr_pos" }, { "type": "string", "label": "ref_nt" }, { "type": "string", "label": "alt_nt" }, { "type": "string", "label": "ref_aa" }, { "type": "string", "label": "alt_aa" }, { "type": "string", "label": "begin_aa_pos" }, { "type": "string", "label": "end_aa_pos" }, { "type": "string", "label": "minor_allelic_frequency" }, { "type": "string", "label": "mutation_type" }, { "type": "string", "label": "polyphen_score" }, { "type": "string", "label": "polyphen_prediction" }, { "type": "string", "label": "sift_score" }, { "type": "string", "label": "sift_prediction" }, { "type": "string", "label": "somatic_status" }, { "type": "string", "label": "disease" }, { "type": "string", "label": "disease_description" }, { "type": "string", "label": "disease_evidence_ECO:0000269" }, { "type": "string", "label": "disease_evidence_ECO:0000313" }, { "type": "string", "label": "xref_key" }, { "type": "string", "label": "xref_id" }, { "type": "string", "label": "mim_id" }, { "type": "string", "label": "do_id" }, { "type": "string", "label": "filter_flags" }, { "type": "string", "label": "glyco_annotation" } ], [ "Q9JLM2-1", "114", "Cd244", "Natural killer cell receptor 2B4", "rs105970872", "", "", "", "", "13q24", "13", "89984233", "A", "T", "R", "S", "114", "114", "", "missense", "", "", "1.0", "tolerated", "0", "", "", "", "", "protein_xref_dbsnp", "rs105970872", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-gain (NQR->NQS).", "glycancount:0, pmidcount:0" ], [ "Q9JLM2-1", "114", "Cd244", "Natural killer cell receptor 2B4", "rs105970872", "", "", "", "", "13q24", "13", "89984233", "A", "T", "R", "S", "114", "114", "", "missense", "", "", "1.0", "tolerated", "0", "", "", "", "", "protein_xref_ensembl", "rs105970872", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-gain (NQR->NQS).", "glycancount:0, pmidcount:0" ], [ "E9PU17-1", "341", "Abca17", "ATP-binding cassette sub-family A member 17", "rs198808071", "", "", "", "", "10q12", "10", "13695815", "T", "G", "T", "P", "341", "341", "", "missense", "", "", "1.0", "tolerated", "0", "", "", "", "", "protein_xref_dbsnp", "rs198808071", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-loss (NTT->NPT).", "glycancount:0, pmidcount:0" ], [ "E9PU17-1", "341", "Abca17", "ATP-binding cassette sub-family A member 17", "rs198808071", "", "", "", "", "10q12", "10", "13695815", "T", "G", "T", "P", "341", "341", "", "missense", "", "", "1.0", "tolerated", "0", "", "", "", "", "protein_xref_ensembl", "rs198808071", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-loss (NTT->NPT).", "glycancount:0, pmidcount:0" ], [ "Q9JLM2-1", "114", "Cd244", "Natural killer cell receptor 2B4", "rs105970872", "", "", "", "", "13q24", "13", "89984233", "A", "T", "R", "S", "114", "114", "", "missense", "", "", "1.0", "tolerated", "0", "", "", "", "", "protein_xref_dbsnp", "rs105970872", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-gain (NQR->NQS).", "glycancount:0, pmidcount:0" ], [ "Q9JLM2-1", "114", "Cd244", "Natural killer cell receptor 2B4", "rs105970872", "", "", "", "", "13q24", "13", "89984233", "A", "T", "R", "S", "114", "114", "", "missense", "", "", "1.0", "tolerated", "0", "", "", "", "", "protein_xref_ensembl", "rs105970872", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-gain (NQR->NQS).", "glycancount:0, pmidcount:0" ], [ "O88277-1", "1059", "Fat2", "Protocadherin Fat 2", "rs198188269", "", "", "", "", "10q22", "10", "40654687", "C", "T", "D", "N", "1059", "1059", "", "missense", "", "", "", "", "0", "", "", "", "", "protein_xref_dbsnp", "rs198188269", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-gain (DDS->NDS).", "glycancount:0, pmidcount:0" ], [ "O88277-1", "1059", "Fat2", "Protocadherin Fat 2", "rs198188269", "", "", "", "", "10q22", "10", "40654687", "C", "T", "D", "N", "1059", "1059", "", "missense", "", "", "", "", "0", "", "", "", "", "protein_xref_ensembl", "rs198188269", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-gain (DDS->NDS).", "glycancount:0, pmidcount:0" ], [ "O88279-1", "408", "Slit1", "Slit homolog 1 protein", "rs8154684", "", "", "", "", "1q54", "1", "260893908", "A", "G", "S", "P", "408", "408", "", "missense", "", "", "0.01", "deleterious", "0", "", "", "", "", "protein_xref_dbsnp", "rs8154684", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-loss (NLS->NLP).", "glycancount:0, pmidcount:0" ], [ "O88279-1", "408", "Slit1", "Slit homolog 1 protein", "rs8154684", "", "", "", "", "1q54", "1", "260893908", "A", "G", "S", "P", "408", "408", "", "missense", "", "", "0.01", "deleterious", "0", "", "", "", "", "protein_xref_ensembl", "rs8154684", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-loss (NLS->NLP).", "glycancount:0, pmidcount:0" ], [ "O88279-1", "408", "Slit1", "Slit homolog 1 protein", "rs8154684", "", "", "", "", "1q54", "1", "260893908", "A", "G", "S", "P", "408", "408", "", "missense", "", "", "0.01", "deleterious", "0", "", "", "", "", "protein_xref_dbsnp", "rs8154684", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-loss (NLS->NLP).", "glycancount:0, pmidcount:0" ], [ "O88279-1", "408", "Slit1", "Slit homolog 1 protein", "rs8154684", "", "", "", "", "1q54", "1", "260893908", "A", "G", "S", "P", "408", "408", "", "missense", "", "", "0.01", "deleterious", "0", "", "", "", "", "protein_xref_ensembl", "rs8154684", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-loss (NLS->NLP).", "glycancount:0, pmidcount:0" ], [ "Q64612-1", "894", "Ptprv", "Receptor-type tyrosine-protein phosphatase V", "rs106600798", "", "", "", "", "13q13", "13", "51946098", "A", "G", "M", "T", "894", "894", "", "missense", "", "", "0.72", "tolerated", "0", "", "", "", "", "protein_xref_dbsnp", "rs106600798", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-gain (NLM->NLT).", "glycancount:0, pmidcount:0" ], [ "Q64612-1", "894", "Ptprv", "Receptor-type tyrosine-protein phosphatase V", "rs106600798", "", "", "", "", "13q13", "13", "51946098", "A", "G", "M", "T", "894", "894", "", "missense", "", "", "0.72", "tolerated", "0", "", "", "", "", "protein_xref_ensembl", "rs106600798", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-gain (NLM->NLT).", "glycancount:0, pmidcount:0" ], [ "O88778-1", "748", "Bsn", "Protein bassoon", "rs199280064", "", "", "", "", "8q32", "8", "116893632", "C", "T", "S", "N", "748", "748", "", "missense", "", "", "", "", "0", "", "", "", "", "protein_xref_dbsnp", "rs199280064", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-gain (SGS->NGS).", "glycancount:0, pmidcount:0" ], [ "O88778-1", "748", "Bsn", "Protein bassoon", "rs199280064", "", "", "", "", "8q32", "8", "116893632", "C", "T", "S", "N", "748", "748", "", "missense", "", "", "", "", "0", "", "", "", "", "protein_xref_ensembl", "rs199280064", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-gain (SGS->NGS).", "glycancount:0, pmidcount:0" ], [ "Q9WTS8-1", "273", "Fcna", "Ficolin (Collagen/fibrinogen domain containing) 1", "rs8146711", "", "", "", "", "3p13", "3", "2850355", "G", "A", "T", "M", "273", "273", "", "missense", "", "", "0.12", "tolerated", "0", "", "", "", "", "protein_xref_dbsnp", "rs8146711", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-loss (NDT->NDM).", "glycancount:0, pmidcount:0" ], [ "Q9WTS8-1", "273", "Fcna", "Ficolin (Collagen/fibrinogen domain containing) 1", "rs8146711", "", "", "", "", "3p13", "3", "2850355", "G", "A", "T", "M", "273", "273", "", "missense", "", "", "0.12", "tolerated", "0", "", "", "", "", "protein_xref_ensembl", "rs8146711", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-loss (NDT->NDM).", "glycancount:0, pmidcount:0" ], [ "Q6TXF5-1", "273", "Lrrc66", "Leucine-rich repeat-containing protein 66", "rs199145123", "", "", "", "", "14p11", "14", "37150267", "C", "T", "P", "S", "273", "273", "", "missense", "", "", "1.0", "tolerated", "0", "", "", "", "", "protein_xref_dbsnp", "rs199145123", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-gain (NTP->NTS).", "glycancount:0, pmidcount:0" ], [ "Q6TXF5-1", "273", "Lrrc66", "Leucine-rich repeat-containing protein 66", "rs199145123", "", "", "", "", "14p11", "14", "37150267", "C", "T", "P", "S", "273", "273", "", "missense", "", "", "1.0", "tolerated", "0", "", "", "", "", "protein_xref_ensembl", "rs199145123", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-gain (NTP->NTS).", "glycancount:0, pmidcount:0" ], [ "Q700K0-1", "917", "Sspo", "SCO-spondin", "rs198757490", "", "", "", "", "4q24", "4", "78089681", "T", "C", "I", "T", "917", "917", "", "missense", "", "", "", "", "0", "", "", "", "", "protein_xref_dbsnp", "rs198757490", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-gain (NCI->NCT).", "glycancount:0, pmidcount:0" ], [ "Q700K0-1", "917", "Sspo", "SCO-spondin", "rs198757490", "", "", "", "", "4q24", "4", "78089681", "T", "C", "I", "T", "917", "917", "", "missense", "", "", "", "", "0", "", "", "", "", "protein_xref_ensembl", "rs198757490", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-gain (NCI->NCT).", "glycancount:0, pmidcount:0" ], [ "Q700K0-1", "2150", "Sspo", "SCO-spondin", "rs107361784", "", "", "", "", "4q24", "4", "78099423", "C", "T", "S", "L", "2150", "2150", "", "missense", "", "", "", "", "0", "", "", "", "", "protein_xref_dbsnp", "rs107361784", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-loss (NLS->NLL).", "glycancount:0, pmidcount:0" ], [ "Q700K0-1", "2150", "Sspo", "SCO-spondin", "rs107361784", "", "", "", "", "4q24", "4", "78099423", "C", "T", "S", "L", "2150", "2150", "", "missense", "", "", "", "", "0", "", "", "", "", "protein_xref_ensembl", "rs107361784", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-loss (NLS->NLL).", "glycancount:0, pmidcount:0" ], [ "Q9EPF2-1", "510", "Mcam", "Cell surface glycoprotein MUC18", "rs8170139", "", "", "", "", "8q22", "8", "48478726", "A", "T", "N", "Y", "510", "510", "", "missense", "", "", "0.02", "deleterious", "0", "", "", "", "", "protein_xref_dbsnp", "rs8170139", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-loss (NTT->YTT).", "glycancount:0, pmidcount:0" ], [ "Q9EPF2-1", "510", "Mcam", "Cell surface glycoprotein MUC18", "rs8170139", "", "", "", "", "8q22", "8", "48478726", "A", "T", "N", "Y", "510", "510", "", "missense", "", "", "0.02", "deleterious", "0", "", "", "", "", "protein_xref_ensembl", "rs8170139", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-loss (NTT->YTT).", "glycancount:0, pmidcount:0" ], [ "Q9EPF2-1", "510", "Mcam", "Isoform 2 of Cell surface glycoprotein MUC18", "rs8170139", "", "", "", "", "8q22", "8", "48478726", "A", "T", "N", "Y", "510", "510", "", "missense", "", "", "0.02", "deleterious", "0", "", "", "", "", "protein_xref_dbsnp", "rs8170139", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-loss (NTT->YTT).", "glycancount:0, pmidcount:0" ], [ "Q9EPF2-1", "510", "Mcam", "Isoform 2 of Cell surface glycoprotein MUC18", "rs8170139", "", "", "", "", "8q22", "8", "48478726", "A", "T", "N", "Y", "510", "510", "", "missense", "", "", "0.02", "deleterious", "0", "", "", "", "", "protein_xref_ensembl", "rs8170139", "", "", "Germline mutation passed 1 out of 1 filters: n-glyco-sequon-loss (NTT->YTT).", "glycancount:0, pmidcount:0" ] ] }, "readme": "Name\n - Rat Germline Mutation\n\nVersion\n - 1.7.13\n\nCreated on\n - 2020-04-03T17:25:56.930719\n\nModified on\n - 2020-04-03T17:39:26.052681\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@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 Germline Mutation dataset contains rat [taxid:10116] germline mutation data from EBI Variant Data API. Only nonsynonymous single-nucleotide variations (nsSNVs) germline mutations are integrated. The dataset is from 2019-11 UniProtKB release .If you use this dataset provide proper attribution to GlyGen and EBI-EMBL-UniProtKB.\n\nDescription Domain\n Keywords\n - single-nucleotide variations (nsSNVs)\n - germline mutations\n - dbSNP\n - disease\n - ClinVar\n\n Pipeline Steps\n - Step-1: The script extracts the gernline (somatic_staus = 0) mutation data from the input file and maps the UniProtKB accession to the UniProtKB canonical accessions\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: dbSNP-rattus-norvegicus.tsv\n URI: https://data.glygen.org/ln2wwwdata/source/dbSNP-rattus-norvegicus.tsv\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_mutation_germline.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_mutation_germline.csv\n Name: rat_protein_mutation_germline.stat.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/rat_protein_mutation_germline.stat.csv\n\nFields\n Name: \"uniprotkb_canonical_ac\"\n Description: \"\"\n Unique Values: \"10\"\n Name: \"filter_flags\"\n Description: \"Filter tags/flags assigned to the mutation entries that have passed the mutation filter criteria\"\n Unique Values: \"11\"\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: \"11\"\n Name: \"chr_id\"\n Description: \"\"\n Unique Values: \"7\"\n Name: \"dbsnp_id\"\n Description: \"\"A reference SNP ID number\"\n Unique Values: \"11\"\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: \"11\"\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: \"10\"\n Name: \"cytogenic_band\"\n Description: \"One of the subregions of a chromosome visible microscopically after special staining\"\n Unique Values: \"10\"\n Name: \"aa_pos\"\n Description: \"Position of the amino acid in canonical sequence of protein in the UniProtKB database\"\n Unique Values: \"10\"\n Name: \"glyco_annotation\"\n Description: \"\"\n Unique Values: \"1\"\n Name: \"ref_aa\"\n Description: \"Reference amino acid residue\"\n Unique Values: \"8\"\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: \"6\"\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: \"alt_nt\"\n Description: \"Alternative nucleotide\"\n Unique Values: \"4\"\n Name: \"protein_name\"\n Description: \"Protein name in the UniProtKB\"\n Unique Values: \"11\"\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: \"end_aa_pos\"\n Description: \"End position of the amino acid in the sequence of a protein in UniProtKB\"\n Unique Values: \"10\"\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: \"7\"\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: \"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: \"10\"\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-1.7.13/reviewed/rat_protein_mutation_germline.csv" }