{ "bcoid": "GLY_000090", "title": "Human UniProtKB Xref Bgee", "description": "The Human UniProtKB Xref Bgee dataset contains human [taxid:9606] UniProtKB canonical accessions cross-referenced ...", "filename": "human_protein_xref_bgee.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "Bgee", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "O75818-1...", "protein_xref..." ], [ "Q14697-1...", "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" } ], [ "O75818-1", "protein_xref_bgee", "ENSG00000124787", "Expressed in left adrenal gland and 208 other tissues" ], [ "Q14697-1", "protein_xref_bgee", "ENSG00000089597", "Expressed in stromal cell of endometrium and 246 other tissues" ], [ "P30613-1", "protein_xref_bgee", "ENSG00000143627", "Expressed in liver and 139 other tissues" ], [ "Q8TEU7-1", "protein_xref_bgee", "ENSG00000158987", "Expressed in corpus callosum and 219 other tissues" ], [ "Q92994-1", "protein_xref_bgee", "ENSG00000185024", "Expressed in sural nerve and 184 other tissues" ], [ "P23769-1", "protein_xref_bgee", "ENSG00000179348", "Expressed in endometrium and 234 other tissues" ], [ "O75962-1", "protein_xref_bgee", "ENSG00000038382", "Expressed in stomach and 233 other tissues" ], [ "P23919-1", "protein_xref_bgee", "ENSG00000168393", "Expressed in ventricular zone and 191 other tissues" ], [ "Q8NHX4-1", "protein_xref_bgee", "ENSG00000173699", "Expressed in testis and 94 other tissues" ], [ "Q8NHX9-1", "protein_xref_bgee", "ENSG00000162341", "Expressed in amniotic fluid and 198 other tissues" ], [ "H3BTG2-1", "protein_xref_bgee", "ENSG00000227868", "Expressed in left testis and 103 other tissues" ], [ "Q92614-1", "protein_xref_bgee", "ENSG00000196535", "Expressed in gastrocnemius and 118 other tissues" ], [ "P10242-1", "protein_xref_bgee", "ENSG00000118513", "Expressed in oviduct epithelium and 147 other tissues" ], [ "Q9GZW8-1", "protein_xref_bgee", "ENSG00000166927", "Expressed in spleen and 170 other tissues" ], [ "Q9C0H2-1", "protein_xref_bgee", "ENSG00000136295", "Expressed in ventricular zone and 182 other tissues" ], [ "Q9C0H5-1", "protein_xref_bgee", "ENSG00000147799", "Expressed in sural nerve and 163 other tissues" ], [ "Q9C0H6-1", "protein_xref_bgee", "ENSG00000102271", "Expressed in corpus callosum and 129 other tissues" ], [ "Q9C0H9-5", "protein_xref_bgee", "ENSG00000277363", "Expressed in cerebellar vermis and 151 other tissues" ], [ "Q8N6H7-1", "protein_xref_bgee", "ENSG00000149182", "Expressed in stomach and 239 other tissues" ], [ "Q96J66-1", "protein_xref_bgee", "ENSG00000121270", "Expressed in sural nerve and 89 other tissues" ], [ "Q9BTE7-1", "protein_xref_bgee", "ENSG00000137692", "Expressed in secondary oocyte and 217 other tissues" ], [ "Q96J65-1", "protein_xref_bgee", "ENSG00000140798", "Expressed in testis and 59 other tissues" ], [ "P25705-1", "protein_xref_bgee", "ENSG00000152234", "Expressed in parietal pleura and 253 other tissues" ], [ "Q6UW68-1", "protein_xref_bgee", "ENSG00000105518", "Expressed in right lobe of liver and 212 other tissues" ], [ "Q9BUZ4-1", "protein_xref_bgee", "ENSG00000076604", "Expressed in adult mammalian kidney and 221 other tissues" ], [ "Q8NC06-1", "protein_xref_bgee", "ENSG00000181513", "Expressed in right lobe of liver and 172 other tissues" ], [ "Q8IYT4-1", "protein_xref_bgee", "ENSG00000167216", "Expressed in sural nerve and 143 other tissues" ], [ "P10242-1", "protein_xref_bgee", "ENSG00000118513", "Expressed in oviduct epithelium and 147 other tissues" ], [ "A6NC51-1", "protein_xref_bgee", "ENSG00000180061", "Expressed in duodenum and 108 other tissues" ], [ "Q13829-1", "protein_xref_bgee", "ENSG00000109079", "Expressed in right lobe of liver and 246 other tissues" ], [ "Q8NBW4-1", "protein_xref_bgee", "ENSG00000177058", "Expressed in secondary oocyte and 200 other tissues" ], [ "Q9NYS7-1", "protein_xref_bgee", "ENSG00000176871", "Expressed in dorsolateral prefrontal cortex and 250 other tissues" ], [ "P40424-1", "protein_xref_bgee", "ENSG00000185630", "Expressed in endocervix and 249 other tissues" ], [ "P40425-1", "protein_xref_bgee", "ENSG00000204304", "Expressed in left lobe of thyroid gland and 233 other tissues" ], [ "P40426-1", "protein_xref_bgee", "ENSG00000167081", "Expressed in intestine and 224 other tissues" ], [ "P40429-1", "protein_xref_bgee", "ENSG00000142541", "Expressed in left ovary and 113 other tissues" ], [ "Q9H2I8-1", "protein_xref_bgee", "ENSG00000148655", "Expressed in muscle tissue and 188 other tissues" ], [ "P03891-1", "protein_xref_bgee", "ENSG00000198763", "Expressed in left adrenal gland and 114 other tissues" ], [ "Q15326-1", "protein_xref_bgee", "ENSG00000015171", "Expressed in cauda epididymis and 264 other tissues" ], [ "Q9H079-1", "protein_xref_bgee", "ENSG00000134152", "Expressed in placenta and 228 other tissues" ], [ "P03897-1", "protein_xref_bgee", "ENSG00000198840", "Expressed in muscle layer of sigmoid colon and 118 other tissues" ], [ "P02768-1", "protein_xref_bgee", "ENSG00000163631", "Expressed in right lobe of liver and 133 other tissues" ], [ "P02760-1", "protein_xref_bgee", "ENSG00000106927", "Expressed in liver and 114 other tissues" ], [ "P02763-1", "protein_xref_bgee", "ENSG00000229314", "Expressed in liver and 115 other tissues" ], [ "P02765-1", "protein_xref_bgee", "ENSG00000145192", "Expressed in liver and 133 other tissues" ], [ "P82921-1", "protein_xref_bgee", "ENSG00000266472", "Expressed in metanephros and 225 other tissues" ], [ "Q9Y228-1", "protein_xref_bgee", "ENSG00000009790", "Expressed in granulocyte and 172 other tissues" ], [ "P02766-1", "protein_xref_bgee", "ENSG00000118271", "Expressed in pigmented layer of retina and 148 other tissues" ], [ "Q9H6T0-1", "protein_xref_bgee", "ENSG00000103067", "Expressed in lower esophagus mucosa and 184 other tissues" ], [ "O95208-1", "protein_xref_bgee", "ENSG00000072134", "Expressed in corpus callosum and 236 other tissues" ], [ "Q4G0P3-1", "protein_xref_bgee", "ENSG00000157423", "Expressed in bronchial epithelial cell and 149 other tissues" ], [ "P43146-1", "protein_xref_bgee", "ENSG00000187323", "Expressed in forebrain and 115 other tissues" ], [ "Q86W25-1", "protein_xref_bgee", "ENSG00000173572", "Expressed in oocyte and 10 other tissues" ], [ "Q9Y2T1-1", "protein_xref_bgee", "ENSG00000168646", "Expressed in female gonad and 188 other tissues" ], [ "Q9BTE0-1", "protein_xref_bgee", "ENSG00000109065", "Expressed in left adrenal gland and 232 other tissues" ], [ "P49640-1", "protein_xref_bgee", "ENSG00000106038", "Expressed in lymph node and 180 other tissues" ], [ "Q6E0U4-1", "protein_xref_bgee", "ENSG00000161249", "Expressed in skin of leg and 164 other tissues" ], [ "Q96Q35-1", "protein_xref_bgee", "ENSG00000155749", "Expressed in testis and 129 other tissues" ], [ "P49789-1", "protein_xref_bgee", "ENSG00000189283", "Expressed in pigmented layer of retina and 150 other tissues" ], [ "Q9P2J5-1", "protein_xref_bgee", "ENSG00000133706", "Expressed in kidney and 237 other tissues" ], [ "P13804-1", "protein_xref_bgee", "ENSG00000140374", "Expressed in oocyte and 246 other tissues" ], [ "Q5ZPR3-1", "protein_xref_bgee", "ENSG00000103855", "Expressed in stromal cell of endometrium and 201 other tissues" ], [ "Q9NQU5-1", "protein_xref_bgee", "ENSG00000137843", "Expressed in prefrontal cortex and 119 other tissues" ], [ "H0YL14-1", "protein_xref_bgee", "ENSG00000238227", "Expressed in stomach and 197 other tissues" ], [ "Q9BVP2-1", "protein_xref_bgee", "ENSG00000163938", "Expressed in urinary bladder and 237 other tissues" ], [ "Q9GZS3-1", "protein_xref_bgee", "ENSG00000140395", "Expressed in pituitary gland and 241 other tissues" ], [ "Q9HBL0-1", "protein_xref_bgee", "ENSG00000079308", "Expressed in blood vessel layer and 255 other tissues" ], [ "P31749-1", "protein_xref_bgee", "ENSG00000142208", "Expressed in left adrenal gland and 233 other tissues" ], [ "Q9P2J8-1", "protein_xref_bgee", "ENSG00000197566", "Expressed in sural nerve and 190 other tissues" ], [ "O43399-1", "protein_xref_bgee", "ENSG00000101150", "Expressed in blood and 240 other tissues" ], [ "Q9Y2H2-1", "protein_xref_bgee", "ENSG00000198825", "Expressed in pons and 239 other tissues" ], [ "P36402-1", "protein_xref_bgee", "ENSG00000081059", "Expressed in thymus and 249 other tissues" ], [ "Q96L93-1", "protein_xref_bgee", "ENSG00000089177", "Expressed in sural nerve and 221 other tissues" ], [ "Q969W1-1", "protein_xref_bgee", "ENSG00000171307", "Expressed in parotid gland and 213 other tissues" ], [ "Q9Y2Q1-1", "protein_xref_bgee", "ENSG00000197134", "Expressed in testis and 125 other tissues" ], [ "Q86YW0-1", "protein_xref_bgee", "ENSG00000139151", "Expressed in sperm and 86 other tissues" ], [ "P29353-1", "protein_xref_bgee", "ENSG00000160691", "Expressed in left coronary artery and 246 other tissues" ], [ "Q5VVP1-1", "protein_xref_bgee", "ENSG00000185775", "Expressed in right testis and 9 other tissues" ], [ "Q86SE5-1", "protein_xref_bgee", "ENSG00000184672", "Expressed in frontal cortex and 143 other tissues" ], [ "Q9BZG1-1", "protein_xref_bgee", "ENSG00000109113", "Expressed in metanephros and 207 other tissues" ], [ "Q9BZG2-1", "protein_xref_bgee", "ENSG00000142513", "Expressed in amniotic fluid and 125 other tissues" ], [ "Q9BZG8-1", "protein_xref_bgee", "ENSG00000108963", "Expressed in pituitary gland and 114 other tissues" ], [ "Q6NUK4-1", "protein_xref_bgee", "ENSG00000165476", "Expressed in epithelial cell of pancreas and 225 other tissues" ], [ "P00738-1", "protein_xref_bgee", "ENSG00000257017", "Expressed in liver and 219 other tissues" ] ] }, "readme": "Name\n - Human UniProtKB Xref Bgee\n\nVersion\n - 1.11.2\n\nCreated on\n - 2019-01-23T17:21:05.959744\n\nModified on\n - 2020-04-10T11:31:45.477452\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 Human UniProtKB Xref Bgee dataset contains human [taxid:9606] 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-homo-sapiens.nt\n URI: https://data.glygen.org/ln2data/releases/data/v-1.11.2/source/uniprot-proteome-homo-sapiens.nt\n Name: human_protein_masterlist.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/human_protein_masterlist.csv\n Output Subdomain\n Name: human_protein_xref_bgee.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/human_protein_xref_bgee.csv\n Name: human_protein_xref_bgee.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/human_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/human_protein_xref_bgee.csv" }