{ "bcoid": "GLY_000266", "title": "Rat UniProtKB Xref Bgee", "description": "The Rat UniProtKB Xref Bgee dataset contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced ...", "filename": "rat_protein_xref_bgee.csv", "filetype": "csv", "categories": { "species": "Rattus norvegicus", "molecule": "Protein", "tags": "Bgee cross-references", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "D3ZB44-1...", "protein_xref..." ], [ "D3ZXJ3-1...", "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" } ], [ "D3ZB44-1", "protein_xref_bgee", "ENSRNOG00000027436", "Expressed in liver and 19 other tissues" ], [ "D3ZXJ3-1", "protein_xref_bgee", "ENSRNOG00000015322", "Expressed in thymus and 20 other tissues" ], [ "D3ZB49-1", "protein_xref_bgee", "ENSRNOG00000009358", "Expressed in quadriceps femoris and 20 other tissues" ], [ "D3ZB48-1", "protein_xref_bgee", "ENSRNOG00000026226", "Expressed in testis and 20 other tissues" ], [ "Q5RJZ1-1", "protein_xref_bgee", "ENSRNOG00000027513", "Expressed in liver and 21 other tissues" ], [ "Q04462-1", "protein_xref_bgee", "ENSRNOG00000000867", "Expressed in testis and 22 other tissues" ], [ "A0A0G2JVG5-1", "protein_xref_bgee", "ENSRNOG00000030948", "Expressed in testis and 3 other tissues" ], [ "A0A0G2JVG6-1", "protein_xref_bgee", "ENSRNOG00000053366", "Expressed in frontal cortex and 20 other tissues" ], [ "Q99372-1", "protein_xref_bgee", "ENSRNOG00000001469", "Expressed in esophagus and 20 other tissues" ], [ "A0A096MJY8-1", "protein_xref_bgee", "ENSRNOG00000013975", "Expressed in testis and 21 other tissues" ], [ "A0A096MJY4-1", "protein_xref_bgee", "ENSRNOG00000033134", "Expressed in frontal cortex and 20 other tissues" ], [ "B2GV58-1", "protein_xref_bgee", "ENSRNOG00000021133", "Expressed in thymus and 21 other tissues" ], [ "A0A096MJY1-1", "protein_xref_bgee", "ENSRNOG00000046660", "Expressed in heart and 20 other tissues" ], [ "A0A0G2KA92-1", "protein_xref_bgee", "ENSRNOG00000012716", "Expressed in spleen and 21 other tissues" ], [ "P56558-1", "protein_xref_bgee", "ENSRNOG00000003359", "Expressed in thymus and 21 other tissues" ], [ "A0A096MJY2-1", "protein_xref_bgee", "ENSRNOG00000011006", "Expressed in quadriceps femoris and 14 other tissues" ], [ "A0A0G2K4P4-1", "protein_xref_bgee", "ENSRNOG00000011376", "Expressed in testis and 21 other tissues" ], [ "Q5RJK6-1", "protein_xref_bgee", "ENSRNOG00000012375", "Expressed in kidney and 21 other tissues" ], [ "P01946-1", "protein_xref_bgee", "ENSRNOG00000029886", "Expressed in spleen and 20 other tissues" ], [ "Q63358-1", "protein_xref_bgee", "ENSRNOG00000016256", "Expressed in spleen and 21 other tissues" ], [ "Q5M9G9-1", "protein_xref_bgee", "ENSRNOG00000052477", "Expressed in duodenum and 21 other tissues" ], [ "P30936-1", "protein_xref_bgee", "ENSRNOG00000007332", "Expressed in thymus and 21 other tissues" ], [ "P02767-1", "protein_xref_bgee", "ENSRNOG00000016275", "Expressed in liver and 21 other tissues" ], [ "D4A4W8-1", "protein_xref_bgee", "ENSRNOG00000012229", "Expressed in testis and 8 other tissues" ], [ "D4A4W9-1", "protein_xref_bgee", "ENSRNOG00000038045", "Expressed in thymus and 21 other tissues" ], [ "D4A4W0-1", "protein_xref_bgee", "ENSRNOG00000048005", "Expressed in adult mammalian kidney and 1 other tissue" ], [ "D4A4W1-1", "protein_xref_bgee", "ENSRNOG00000012369", "Expressed in lung and 20 other tissues" ], [ "D4A4W2-1", "protein_xref_bgee", "ENSRNOG00000038055", "Expressed in testis and 17 other tissues" ], [ "F7EN52-1", "protein_xref_bgee", "ENSRNOG00000007147", "Expressed in frontal cortex and 19 other tissues" ], [ "D4A4W4-1", "protein_xref_bgee", "ENSRNOG00000027319", "Expressed in esophagus and 19 other tissues" ], [ "D4A4W5-1", "protein_xref_bgee", "ENSRNOG00000003781", "Expressed in duodenum and 17 other tissues" ], [ "D4A4W6-1", "protein_xref_bgee", "ENSRNOG00000012314", "Expressed in brain and 22 other tissues" ], [ "D4A4W7-1", "protein_xref_bgee", "ENSRNOG00000011923", "Expressed in female gonad and 20 other tissues" ], [ "G3V6I3-1", "protein_xref_bgee", "ENSRNOG00000004091", "Expressed in brain and 20 other tissues" ], [ "P21932-1", "protein_xref_bgee", "ENSRNOG00000003999", "Expressed in brain and 21 other tissues" ], [ "Q8K4K5-1", "protein_xref_bgee", "ENSRNOG00000003948", "Expressed in brain and 20 other tissues" ], [ "Q4L0E8-1", "protein_xref_bgee", "ENSRNOG00000003959", "Expressed in spleen and 21 other tissues" ], [ "G3V6I6-1", "protein_xref_bgee", "ENSRNOG00000004143", "Expressed in skeletal muscle tissue and 20 other tissues" ], [ "A0A0G2K5E4-1", "protein_xref_bgee", "ENSRNOG00000003855", "Expressed in skeletal muscle tissue and 20 other tissues" ], [ "G3V6I4-1", "protein_xref_bgee", "ENSRNOG00000004101", "Expressed in liver and 20 other tissues" ], [ "P12749-1", "protein_xref_bgee", "ENSRNOG00000004214", "Expressed in thymus and 20 other tissues" ], [ "O08812-1", "protein_xref_bgee", "ENSRNOG00000004133", "Expressed in brain and 18 other tissues" ], [ "P11980-1", "protein_xref_bgee", "ENSRNOG00000011329", "Expressed in skeletal muscle tissue and 21 other tissues" ], [ "A0A0G2K0T8-1", "protein_xref_bgee", "ENSRNOG00000055025", "Expressed in esophagus and 17 other tissues" ], [ "A0A0G2K0T4-1", "protein_xref_bgee", "ENSRNOG00000059654", "Expressed in frontal cortex and 17 other tissues" ], [ "Q6P6Q9-1", "protein_xref_bgee", "ENSRNOG00000043436", "Expressed in lung and 20 other tissues" ], [ "Q63544-1", "protein_xref_bgee", "ENSRNOG00000058006", "Expressed in esophagus and 22 other tissues" ], [ "A0A0G2K0T7-1", "protein_xref_bgee", "ENSRNOG00000049137", "Expressed in testis and 20 other tissues" ], [ "P28648-1", "protein_xref_bgee", "ENSRNOG00000007650", "Expressed in adult mammalian kidney and 21 other tissues" ], [ "Q5U1W2-1", "protein_xref_bgee", "ENSRNOG00000042094", "Expressed in duodenum and 21 other tissues" ], [ "D3ZVR6-1", "protein_xref_bgee", "ENSRNOG00000040279", "Expressed in thymus and 21 other tissues" ], [ "A0A0G2K1A3-1", "protein_xref_bgee", "ENSRNOG00000008398", "Expressed in thymus and 12 other tissues" ], [ "A0A0G2K1A1-1", "protein_xref_bgee", "ENSRNOG00000060956", "Expressed in pancreas and 22 other tissues" ], [ "P01237-1", "protein_xref_bgee", "ENSRNOG00000017374", "Expressed in Ammon's horn and 2 other tissues" ], [ "P33124-1", "protein_xref_bgee", "ENSRNOG00000026745", "Expressed in frontal cortex and 20 other tissues" ], [ "P01230-1", "protein_xref_bgee", "ENSRNOG00000047040", "Expressed in testis and 21 other tissues" ], [ "Q6MG12-1", "protein_xref_bgee", "ENSRNOG00000000812", "Expressed in brain and 22 other tissues" ], [ "M0RB72-1", "protein_xref_bgee", "ENSRNOG00000049162", "Expressed in jejunum and 18 other tissues" ], [ "D4A781-1", "protein_xref_bgee", "ENSRNOG00000010989", "Expressed in testis and 20 other tissues" ], [ "M0RB75-1", "protein_xref_bgee", "ENSRNOG00000049221", "Expressed in brain and 21 other tissues" ], [ "A0A0G2K8D0-1", "protein_xref_bgee", "ENSRNOG00000048771", "Expressed in lung and 21 other tissues" ], [ "Q9JHY1-1", "protein_xref_bgee", "ENSRNOG00000004414", "Expressed in lung and 21 other tissues" ], [ "P33568-1", "protein_xref_bgee", "ENSRNOG00000016029", "Expressed in thymus and 21 other tissues" ], [ "P31646-1", "protein_xref_bgee", "ENSRNOG00000012876", "Expressed in liver and 17 other tissues" ], [ "E9PU34-1", "protein_xref_bgee", "ENSRNOG00000019501", "Expressed in liver and 22 other tissues" ], [ "Q02874-1", "protein_xref_bgee", "ENSRNOG00000011523", "Expressed in thymus and 21 other tissues" ], [ "P08699-1", "protein_xref_bgee", "ENSRNOG00000010645", "Expressed in jejunum and 21 other tissues" ], [ "P56558-1", "protein_xref_bgee", "ENSRNOG00000003359", "Expressed in thymus and 21 other tissues" ], [ "P08011-1", "protein_xref_bgee", "ENSRNOG00000007743", "Expressed in liver and 21 other tissues" ], [ "Q8CJ58-1", "protein_xref_bgee", "ENSRNOG00000042477", "Expressed in brain and 5 other tissues" ], [ "P54690-1", "protein_xref_bgee", "ENSRNOG00000015514", "Expressed in brain and 22 other tissues" ], [ "Q99JD4-1", "protein_xref_bgee", "ENSRNOG00000009161", "Expressed in cerebellum and 21 other tissues" ], [ "P07727-1", "protein_xref_bgee", "ENSRNOG00000013588", "Expressed in cerebellum and 9 other tissues" ], [ "Q99JD2-1", "protein_xref_bgee", "ENSRNOG00000014973", "Expressed in testis and 22 other tissues" ], [ "Q7TP40-1", "protein_xref_bgee", "ENSRNOG00000028411", "Expressed in cerebellum and 20 other tissues" ], [ "P83748-1", "protein_xref_bgee", "ENSRNOG00000033266", "Expressed in duodenum and 15 other tissues" ], [ "P18508-1", "protein_xref_bgee", "ENSRNOG00000003241", "Expressed in brain and 14 other tissues" ], [ "P20420-1", "protein_xref_bgee", "ENSRNOG00000013610", "Expressed in brain and 14 other tissues" ], [ "A0A0G2JTB2-1", "protein_xref_bgee", "ENSRNOG00000051232", "Expressed in liver and 22 other tissues" ], [ "M0R8G6-1", "protein_xref_bgee", "ENSRNOG00000060408", "Expressed in spleen and 13 other tissues" ], [ "F1M9T2-1", "protein_xref_bgee", "ENSRNOG00000010824", "Expressed in female gonad and 20 other tissues" ], [ "M0R8G5-1", "protein_xref_bgee", "ENSRNOG00000049067", "Expressed in frontal cortex and 17 other tissues" ], [ "Q02293-1", "protein_xref_bgee", "ENSRNOG00000007660", "Expressed in cerebellum and 21 other tissues" ], [ "D3ZGR6-1", "protein_xref_bgee", "ENSRNOG00000028581", "Expressed in testis and 21 other tissues" ] ] }, "readme": "Name\n - Rat UniProtKB Xref Bgee\n\nVersion\n - 1.11.2\n\nCreated on\n - 2019-09-06T14:06:38.992721\n\nModified on\n - 2020-04-10T12:07:42.440257\n\nCreated by\n - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@gwu.edu], Xavier Holmes [xavierh@email.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 UniProtKB Xref Bgee dataset contains rat [taxid:10116] UniProtKB canonical accessions cross-referenced to Bgee database accessions/identifiers. 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 - Bgee is a database to retrieve and compare gene expression patterns in multiple animal species, produced from multiple data types (RNA-Seq, Affymetrix, in situ hybridization, and EST data) and from multiple data sets.\n\nDescription Domain\n Keywords\n - gene expression\n - Bgee\n - cross-reference\n\n Pipeline Steps\n - Step-1: The script loads the UniProtKB canonical accessions that are cross-referenced to Bgee database accessions/identifiers from the triplestore containing triples from nt file and extracts the data as a csv dataset\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: 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_xref_bgee.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_bgee.csv\n Name: rat_protein_xref_bgee.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/rat_protein_xref_bgee.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_xref_bgee.csv" }