{ "bcoid": "GLY_000091", "title": "Mouse UniProtKB Xref Bgee", "description": "The Mouse UniProtKB Xref Bgee contains mouse [taxid:10090] UniProtKB canonical accessions cross-referenced ...", "filename": "mouse_protein_xref_bgee.csv", "filetype": "csv", "categories": { "species": "Mus musculus", "molecule": "Protein", "tags": "Bgee", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q8BH24-1...", "protein_xref..." ], [ "Q8BH27-1...", "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" } ], [ "Q8BH24-1", "protein_xref_bgee", "ENSMUSG00000068040", "Expressed in humerus cartilage element and 294 other tissues" ], [ "Q8BH27-1", "protein_xref_bgee", "ENSMUSG00000039270", "Expressed in utricle of membranous labyrinth and 263 other tissues" ], [ "Q8BH26-1", "protein_xref_bgee", "ENSMUSG00000046675", "Expressed in islet of Langerhans and 78 other tissues" ], [ "E9Q287-1", "protein_xref_bgee", "ENSMUSG00000043635", "Expressed in cortical plate and 75 other tissues" ], [ "Q922G0-1", "protein_xref_bgee", "ENSMUSG00000032449", "Expressed in metanephric cortical collecting duct and 308 other tissues" ], [ "O35453-1", "protein_xref_bgee", "ENSMUSG00000001249", "Expressed in proximal tubule and 232 other tissues" ], [ "Q80T32-1", "protein_xref_bgee", "ENSMUSG00000044017", "Expressed in urinary bladder and 160 other tissues" ], [ "B2RXV4-1", "protein_xref_bgee", "ENSMUSG00000066595", "Expressed in small intestine and 257 other tissues" ], [ "P62492-1", "protein_xref_bgee", "ENSMUSG00000004771", "Expressed in kidney and 320 other tissues" ], [ "E9Q3P4-1", "protein_xref_bgee", "ENSMUSG00000026605", "Expressed in primary oocyte and 228 other tissues" ], [ "P63166-1", "protein_xref_bgee", "ENSMUSG00000026021", "Expressed in embryonic facial prominence and 91 other tissues" ], [ "A0A087WPJ1-1", "protein_xref_bgee", "ENSMUSG00000056912", "Expressed in spermatid and 51 other tissues" ], [ "B2RX88-1", "protein_xref_bgee", "ENSMUSG00000056763", "Expressed in metanephric cortical collecting duct and 279 other tissues" ], [ "A0A087WRQ3-1", "protein_xref_bgee", "ENSMUSG00000076758", "Expressed in thymus and 23 other tissues" ], [ "A5H0M4-1", "protein_xref_bgee", "ENSMUSG00000063932", "Expressed in spermatocyte and 15 other tissues" ], [ "P03899-1", "protein_xref_bgee", "ENSMUSG00000064360", "Expressed in thymus and 71 other tissues" ], [ "O35153-1", "protein_xref_bgee", "ENSMUSG00000025484", "Expressed in pancreas and 305 other tissues" ], [ "P03893-1", "protein_xref_bgee", "ENSMUSG00000064345", "Expressed in muscle tissue and 71 other tissues" ], [ "Q9QYH9-1", "protein_xref_bgee", "ENSMUSG00000005824", "Expressed in granulocyte and 52 other tissues" ], [ "P52479-1", "protein_xref_bgee", "ENSMUSG00000031826", "Expressed in epiblast (generic) and 316 other tissues" ], [ "P02762-1", "protein_xref_bgee", "ENSMUSG00000078673", "Expressed in liver and 35 other tissues" ], [ "Q9QYH6-1", "protein_xref_bgee", "ENSMUSG00000025151", "Expressed in placenta and 331 other tissues" ], [ "Q08AU7-1", "protein_xref_bgee", "ENSMUSG00000025141", "Expressed in muscle tissue and 98 other tissues" ], [ "Q5EBH1-1", "protein_xref_bgee", "ENSMUSG00000026430", "Expressed in thymus and 282 other tissues" ], [ "O35309-1", "protein_xref_bgee", "ENSMUSG00000026946", "Expressed in jejunum and 259 other tissues" ], [ "Q80YU0-1", "protein_xref_bgee", "ENSMUSG00000055882", "Expressed in testis and 52 other tissues" ], [ "Q8BTY1-1", "protein_xref_bgee", "ENSMUSG00000039648", "Expressed in esophagus and 302 other tissues" ], [ "Q5SRT8-1", "protein_xref_bgee", "ENSMUSG00000044707", "Expressed in embryonic post-anal tail and 187 other tissues" ], [ "P70419-1", "protein_xref_bgee", "ENSMUSG00000026994", "Expressed in parotid gland and 227 other tissues" ], [ "Q9EP78-1", "protein_xref_bgee", "ENSMUSG00000037347", "Expressed in proximal tubule and 182 other tissues" ], [ "Q9EP79-1", "protein_xref_bgee", "ENSMUSG00000060816", "Expressed in testis and 7 other tissues" ], [ "Q3URK3-1", "protein_xref_bgee", "ENSMUSG00000047146", "Expressed in embryonic stem cell and 230 other tissues" ], [ "Q9EP72-1", "protein_xref_bgee", "ENSMUSG00000055943", "Expressed in liver and 296 other tissues" ], [ "Q9EP73-1", "protein_xref_bgee", "ENSMUSG00000016496", "Expressed in blood and 136 other tissues" ], [ "Q9EP71-1", "protein_xref_bgee", "ENSMUSG00000022246", "Expressed in renal corpuscle and 287 other tissues" ], [ "Q9EP75-1", "protein_xref_bgee", "ENSMUSG00000024292", "Expressed in jejunum and 79 other tissues" ], [ "Q8VF62-1", "protein_xref_bgee", "ENSMUSG00000066749", "Expressed in zygote and 15 other tissues" ], [ "Q8CHS4-1", "protein_xref_bgee", "ENSMUSG00000064247", "Expressed in substantia nigra and 179 other tissues" ], [ "D3YWQ0-1", "protein_xref_bgee", "ENSMUSG00000038665", "Expressed in cerebral cortex and 103 other tissues" ], [ "P30282-1", "protein_xref_bgee", "ENSMUSG00000034165", "Expressed in thymus and 321 other tissues" ], [ "P97411-1", "protein_xref_bgee", "ENSMUSG00000062995", "Expressed in spermatid and 275 other tissues" ], [ "Q3UHI0-1", "protein_xref_bgee", "ENSMUSG00000058690", "Expressed in dorsal root ganglion and 297 other tissues" ], [ "Q80TT2-1", "protein_xref_bgee", "ENSMUSG00000047507", "Expressed in hypothalamus and 143 other tissues" ], [ "S4R213-1", "protein_xref_bgee", "ENSMUSG00000070683", "Expressed in retinal neural layer and 15 other tissues" ], [ "Q91VV4-1", "protein_xref_bgee", "ENSMUSG00000027901", "Expressed in lymph node and 190 other tissues" ], [ "P53702-1", "protein_xref_bgee", "ENSMUSG00000031352", "Expressed in myocardium of ventricle and 303 other tissues" ], [ "Q9Z2V6-1", "protein_xref_bgee", "ENSMUSG00000008855", "Expressed in olfactory bulb and 307 other tissues" ], [ "O08911-1", "protein_xref_bgee", "ENSMUSG00000022610", "Expressed in muscle tissue and 245 other tissues" ], [ "Q9CWR2-1", "protein_xref_bgee", "ENSMUSG00000055067", "Expressed in embryo and 196 other tissues" ], [ "Q80WC9-1", "protein_xref_bgee", "ENSMUSG00000055923", "Expressed in indifferent gonad and 256 other tissues" ], [ "O08912-1", "protein_xref_bgee", "ENSMUSG00000000420", "Expressed in embryo and 352 other tissues" ], [ "O08915-1", "protein_xref_bgee", "ENSMUSG00000024847", "Expressed in ear vesicle and 309 other tissues" ], [ "O08914-1", "protein_xref_bgee", "ENSMUSG00000034171", "Expressed in cardiac ventricle and 246 other tissues" ], [ "O08917-1", "protein_xref_bgee", "ENSMUSG00000059714", "Expressed in granulocyte and 338 other tissues" ], [ "O08918-1", "protein_xref_bgee", "ENSMUSG00000029385", "Expressed in thymus and 304 other tissues" ], [ "Q80WC1-1", "protein_xref_bgee", "ENSMUSG00000038538", "Expressed in spleen and 271 other tissues" ], [ "Q80WC7-1", "protein_xref_bgee", "ENSMUSG00000029722", "Expressed in cerebellum and 290 other tissues" ], [ "Q9JHY4-1", "protein_xref_bgee", "ENSMUSG00000018211", "Expressed in right kidney and 95 other tissues" ], [ "Q8BYW1-1", "protein_xref_bgee", "ENSMUSG00000030047", "Expressed in granulocyte and 166 other tissues" ], [ "G5E8Q8-1", "protein_xref_bgee", "ENSMUSG00000056492", "Expressed in right lung and 254 other tissues" ], [ "Q8C0L9-1", "protein_xref_bgee", "ENSMUSG00000027346", "Expressed in gastrocnemius and 312 other tissues" ], [ "Q8BTJ4-1", "protein_xref_bgee", "ENSMUSG00000023961", "Expressed in substantia nigra and 266 other tissues" ], [ "P59708-1", "protein_xref_bgee", "ENSMUSG00000037361", "Expressed in vestibular organ and 311 other tissues" ], [ "Q3TX08-1", "protein_xref_bgee", "ENSMUSG00000001909", "Expressed in spermatocyte and 309 other tissues" ], [ "E9PYR1-1", "protein_xref_bgee", "ENSMUSG00000066640", "Expressed in superior cervical ganglion and 116 other tissues" ], [ "P04760-1", "protein_xref_bgee", "ENSMUSG00000026253", "Expressed in lens of camera-type eye and 94 other tissues" ], [ "P59808-1", "protein_xref_bgee", "ENSMUSG00000015305", "Expressed in urinary bladder urothelium and 306 other tissues" ], [ "F8VQK3-1", "protein_xref_bgee", "ENSMUSG00000041624", "Expressed in cerebral cortex and 73 other tissues" ], [ "Q91UZ1-1", "protein_xref_bgee", "ENSMUSG00000039943", "Expressed in saliva-secreting gland and 302 other tissues" ], [ "Q91UZ1-1", "protein_xref_bgee", "ENSMUSG00000039943", "Expressed in saliva-secreting gland and 302 other tissues" ], [ "Q9R1N9-1", "protein_xref_bgee", "ENSMUSG00000058806", "Expressed in cardiac ventricle and 224 other tissues" ], [ "A2AT96-1", "protein_xref_bgee", "ENSMUSG00000075161", "Expressed in proximal tubule and 3 other tissues" ], [ "Q9D387-1", "protein_xref_bgee", "ENSMUSG00000027270", "Expressed in medial vestibular nucleus and 165 other tissues" ], [ "Q3V3Q4-1", "protein_xref_bgee", "ENSMUSG00000066677", "Expressed in spleen and 53 other tissues" ], [ "B1ASB6-1", "protein_xref_bgee", "ENSMUSG00000028784", "Expressed in secondary oocyte and 46 other tissues" ], [ "Q9D516-1", "protein_xref_bgee", "ENSMUSG00000004994", "Expressed in testis and 175 other tissues" ], [ "Q9D517-1", "protein_xref_bgee", "ENSMUSG00000001211", "Expressed in retinal neural layer and 331 other tissues" ], [ "Q9D515-1", "protein_xref_bgee", "ENSMUSG00000067909", "Expressed in spermatid and 8 other tissues" ], [ "Q9D513-1", "protein_xref_bgee", "ENSMUSG00000024155", "Expressed in testis and 77 other tissues" ], [ "Q9D8K8-1", "protein_xref_bgee", "ENSMUSG00000018677", "Expressed in blood and 350 other tissues" ], [ "Q9D518-1", "protein_xref_bgee", "ENSMUSG00000027209", "Expressed in testis and 157 other tissues" ], [ "Q9D519-1", "protein_xref_bgee", "ENSMUSG00000059663", "Expressed in spermatid and 10 other tissues" ], [ "Q61161-1", "protein_xref_bgee", "ENSMUSG00000024948", "Expressed in granulocyte and 267 other tissues" ], [ "Q8K2M0-1", "protein_xref_bgee", "ENSMUSG00000020775", "Expressed in adrenal gland and 308 other tissues" ] ] }, "readme": "Name\n - Mouse UniProtKB Xref Bgee\n\nVersion\n - 1.11.2\n\nCreated on\n - 2019-01-23T17:21:05.959744\n\nModified on\n - 2020-04-10T12:36:19.326409\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 Mouse UniProtKB Xref Bgee contains mouse [taxid:10090] 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-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_xref_bgee.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/mouse_protein_xref_bgee.csv\n Name: mouse_protein_xref_bgee.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/mouse_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/mouse_protein_xref_bgee.csv" }