{ "bcoid": "GLY_000393", "title": "Mouse Protein Names (NCBI RefSeq)", "description": "The Mouse Protein Names (NCBI RefSeq) dataset contains mouse [taxid:10090] protein names (primary and ...", "filename": "mouse_protein_proteinnames_refseq.csv", "filetype": "csv", "categories": { "species": "Mus musculus", "molecule": "Protein", "tags": "Protein Names", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "Q8BH24-1...", "NP_598608.2..." ], [ "Q8BH24-1...", "NP_598608.2..." ] ], "headers": [ "uniprotkb_ca...", "refseq_ac..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "refseq_ac" }, { "type": "string", "label": "refseq_protein_name" } ], [ "Q8BH24-1", "NP_598608.2", "transmembrane 9 superfamily member 4 precursor" ], [ "Q8BH24-1", "NP_598608.2", "transmembrane 9 superfamily protein member 4" ], [ "Q8BH24-1", "NP_598608", "transmembrane 9 superfamily member 4 precursor" ], [ "Q8BH24-1", "NP_598608", "transmembrane 9 superfamily protein member 4" ], [ "Q8BH27-1", "NP_766282.1", "multiple epidermal growth factor-like domains protein 9 precursor" ], [ "Q8BH27-1", "NP_766282.1", "EGF-like-domain, multiple 5; EGF-like protein 5; multiple EGF-like domains protein 9; epidermal growth factor-like protein 5; multiple epidermal growth factor-like domains protein 9" ], [ "Q8BH27-1", "NP_766282", "multiple epidermal growth factor-like domains protein 9 precursor" ], [ "Q8BH27-1", "NP_766282", "EGF-like-domain, multiple 5; EGF-like protein 5; multiple EGF-like domains protein 9; epidermal growth factor-like protein 5; multiple epidermal growth factor-like domains protein 9" ], [ "Q8BH26-1", "NP_001311444.1", "transmembrane protein 251 isoform 2" ], [ "Q8BH26-1", "NP_001311444.1", "UPF0694 transmembrane protein C14orf109 homolog" ], [ "Q8BH26-1", "NP_001311444", "transmembrane protein 251 isoform 2" ], [ "Q8BH26-1", "NP_001311444", "UPF0694 transmembrane protein C14orf109 homolog" ], [ "Q80T32-1", "NP_001334415.1", "adhesion G-protein coupled receptor D1 isoform 2 precursor" ], [ "Q80T32-1", "NP_001334415.1", "G-protein coupled receptor PGR25; probable G-protein coupled receptor 133; G protein coupled receptor Gpr133" ], [ "Q80T32-1", "NP_001334415", "adhesion G-protein coupled receptor D1 isoform 2 precursor" ], [ "Q80T32-1", "NP_001334415", "G-protein coupled receptor PGR25; probable G-protein coupled receptor 133; G protein coupled receptor Gpr133" ], [ "B2RXV4-1", "NP_001074728.1", "feline leukemia virus subgroup C receptor-related protein 1 isoform 1" ], [ "B2RXV4-1", "NP_001074728.1", "major facilitator superfamily domain containing 7B; feline leukemia virus subgroup C receptor-related protein 1" ], [ "B2RXV4-1", "NP_001074728", "feline leukemia virus subgroup C receptor-related protein 1 isoform 1" ], [ "B2RXV4-1", "NP_001074728", "major facilitator superfamily domain containing 7B; feline leukemia virus subgroup C receptor-related protein 1" ], [ "E9Q3P4-1", "NP_001074832.2", "centromere protein F" ], [ "E9Q3P4-1", "NP_001074832.2", "leucine, glutamic acid, lysine family 1 protein; centromere autoantigen F" ], [ "E9Q3P4-1", "NP_001074832", "centromere protein F" ], [ "E9Q3P4-1", "NP_001074832", "leucine, glutamic acid, lysine family 1 protein; centromere autoantigen F" ], [ "A5H0M4-1", "NP_081894.1", "POTE ankyrin domain family member A isoform 2" ], [ "A5H0M4-1", "NP_081894.1", "gonad specific ankyrin repeat protein" ], [ "A5H0M4-1", "NP_081894", "POTE ankyrin domain family member A isoform 2" ], [ "A5H0M4-1", "NP_081894", "gonad specific ankyrin repeat protein" ], [ "P03899-1", "NP_904335.1", "NADH dehydrogenase subunit 3" ], [ "P03899-1", "NP_904335", "NADH dehydrogenase subunit 3" ], [ "O35153-1", "NP_061212.3", "BET1-like protein" ], [ "O35153-1", "NP_061212.3", "GOS-15; soluble N-ethylmaleimide-sensitive factor attachment protein (SNARE) 15; golgi SNARE, 15 kD; vesicle transport protein GOS15; golgi SNARE with a size of 15 kDa; blocked early in transport 1 homolog-like" ], [ "O35153-1", "NP_061212", "BET1-like protein" ], [ "O35153-1", "NP_061212", "GOS-15; soluble N-ethylmaleimide-sensitive factor attachment protein (SNARE) 15; golgi SNARE, 15 kD; vesicle transport protein GOS15; golgi SNARE with a size of 15 kDa; blocked early in transport 1 homolog-like" ], [ "P03893-1", "NP_904329.1", "NADH dehydrogenase subunit 2" ], [ "P03893-1", "NP_904329", "NADH dehydrogenase subunit 2" ], [ "Q9QYH9-1", "NP_062291.1", "tumor necrosis factor ligand superfamily member 14" ], [ "Q9QYH9-1", "NP_062291.1", "tumor necrosis factor ligand 1d" ], [ "Q9QYH9-1", "NP_062291", "tumor necrosis factor ligand superfamily member 14" ], [ "Q9QYH9-1", "NP_062291", "tumor necrosis factor ligand 1d" ], [ "P52479-1", "NP_001297559.1", "ubiquitin carboxyl-terminal hydrolase 10 isoform 2" ], [ "P52479-1", "NP_001297559.1", "ubiquintin c-terminal hydrolase related polypeptide; ubiquitin specific protease 10; ubiquitin carboxyl-terminal hydrolase 10; ubiquitin thioesterase 10; deubiquitinating enzyme 10; ubiquitin-specific-processing protease 10; ubiquitin thiolesterase 10" ], [ "P52479-1", "NP_001297559", "ubiquitin carboxyl-terminal hydrolase 10 isoform 2" ], [ "P52479-1", "NP_001297559", "ubiquintin c-terminal hydrolase related polypeptide; ubiquitin specific protease 10; ubiquitin carboxyl-terminal hydrolase 10; ubiquitin thioesterase 10; deubiquitinating enzyme 10; ubiquitin-specific-processing protease 10; ubiquitin thiolesterase 10" ], [ "P02762-1", "NP_001128599.1", "major urinary protein 11 precursor" ], [ "P02762-1", "NP_001128599.1", "MUP 6; major urinary protein 17; major urinary protein 14; MUP11 and MUP8; Major urinary proteins 11 and 8; major urinary protein 11; Major urinary protein 6; Alpha-2U-globulin; Group 1, BS6" ], [ "P02762-1", "NP_001128599", "major urinary protein 11 precursor" ], [ "P02762-1", "NP_001128599", "MUP 6; major urinary protein 17; major urinary protein 14; MUP11 and MUP8; Major urinary proteins 11 and 8; major urinary protein 11; Major urinary protein 6; Alpha-2U-globulin; Group 1, BS6" ], [ "Q9QYH6-1", "NP_062765.1", "melanoma-associated antigen D1" ], [ "Q9QYH6-1", "NP_062765.1", "melanoma antigen, family D, 1; MAGE-D1 antigen; neurotrophin receptor-interacting MAGE homolog" ], [ "Q9QYH6-1", "NP_062765", "melanoma-associated antigen D1" ], [ "Q9QYH6-1", "NP_062765", "melanoma antigen, family D, 1; MAGE-D1 antigen; neurotrophin receptor-interacting MAGE homolog" ], [ "Q08AU9-1", "NP_001156945.1", "UPF0450 protein C17orf58 homolog isoform 1 precursor" ], [ "Q08AU9-1", "NP_001156945.1", "UPF0450 protein C17orf58 homolog" ], [ "Q08AU9-1", "NP_001156945", "UPF0450 protein C17orf58 homolog isoform 1 precursor" ], [ "Q08AU9-1", "NP_001156945", "UPF0450 protein C17orf58 homolog" ], [ "Q08AU7-1", "NP_001191749.1", "myeloid-associated differentiation marker-like protein 2 isoform 2" ], [ "Q08AU7-1", "NP_001191749.1", "myeloid-associated differentiation marker-like protein 2" ], [ "Q08AU7-1", "NP_001191749", "myeloid-associated differentiation marker-like protein 2 isoform 2" ], [ "Q08AU7-1", "NP_001191749", "myeloid-associated differentiation marker-like protein 2" ], [ "Q5EBH1-1", "NP_001298023.1", "ras association domain-containing protein 5 isoform 2" ], [ "Q5EBH1-1", "NP_001298023.1", "novel ras effector 1; Rap1-binding protein; new ras effector 1; regulator for cell adhesion and polarization enriched in lymphoid tissues; ras association domain-containing protein 5" ], [ "Q5EBH1-1", "NP_001298023", "ras association domain-containing protein 5 isoform 2" ], [ "Q5EBH1-1", "NP_001298023", "novel ras effector 1; Rap1-binding protein; new ras effector 1; regulator for cell adhesion and polarization enriched in lymphoid tissues; ras association domain-containing protein 5" ], [ "Q80YU0-1", "NP_899004.1", "protein ABHD16B" ], [ "Q80YU0-1", "NP_899004.1", "abhydrolase domain-containing protein 16B; alpha/beta hydrolase domain-containing protein 16B" ], [ "Q80YU0-1", "NP_899004", "protein ABHD16B" ], [ "Q80YU0-1", "NP_899004", "abhydrolase domain-containing protein 16B; alpha/beta hydrolase domain-containing protein 16B" ], [ "Q5SRT8-1", "NP_001038995.1", "cyclin-J-like protein" ], [ "Q5SRT8-1", "NP_001038995", "cyclin-J-like protein" ], [ "P70414-1", "NP_035536.2", "sodium/calcium exchanger 1 isoform A precursor" ], [ "P70414-1", "NP_035536.2", "Na/Ca exchanger; Na(+)/Ca(2+)-exchange protein 1; sodium/calcium exchanger 1; solute carrier family 8 member 1" ], [ "P70414-1", "NP_035536", "sodium/calcium exchanger 1 isoform A precursor" ], [ "P70414-1", "NP_035536", "Na/Ca exchanger; Na(+)/Ca(2+)-exchange protein 1; sodium/calcium exchanger 1; solute carrier family 8 member 1" ], [ "A0A0U1RNG7-1", "XP_006507673.1", "BTB/POZ domain-containing protein KCTD14 isoform X3" ], [ "A0A0U1RNG7-1", "XP_006507673", "BTB/POZ domain-containing protein KCTD14 isoform X3" ], [ "P70419-1", "NP_056551.2", "polypeptide N-acetylgalactosaminyltransferase 3" ], [ "P70419-1", "NP_056551.2", "UDP-N-acetyl-alpha-D-galactosamine:polypeptide N-acetylgalactosaminyltransferase 3; ppGaNTase-T3; galNAc-T3; pp-GaNTase 3; polypeptide GalNAc transferase 3; protein-UDP acetylgalactosaminyltransferase 3; UDP-GalNAc:polypeptide N-acetylgalactosaminyltransferase 3" ], [ "P70419-1", "NP_056551", "polypeptide N-acetylgalactosaminyltransferase 3" ], [ "P70419-1", "NP_056551", "UDP-N-acetyl-alpha-D-galactosamine:polypeptide N-acetylgalactosaminyltransferase 3; ppGaNTase-T3; galNAc-T3; pp-GaNTase 3; polypeptide GalNAc transferase 3; protein-UDP acetylgalactosaminyltransferase 3; UDP-GalNAc:polypeptide N-acetylgalactosaminyltransferase 3" ], [ "Q9EP78-1", "NP_068361.1", "carbohydrate sulfotransferase 7 precursor" ], [ "Q9EP78-1", "NP_068361.1", "carbohydrate sulfotransferase 7; chondroitin 6-sulfotransferase 2; N-acetylglucosamine 6-O-sulfotransferase 1; galactose/N-acetylglucosamine/N-acetylglucosamine 6-O-sulfotransferase 5; N-acetylglucosamine 6-O-sulfotransferase 4" ], [ "Q9EP78-1", "NP_068361", "carbohydrate sulfotransferase 7 precursor" ], [ "Q9EP78-1", "NP_068361", "carbohydrate sulfotransferase 7; chondroitin 6-sulfotransferase 2; N-acetylglucosamine 6-O-sulfotransferase 1; galactose/N-acetylglucosamine/N-acetylglucosamine 6-O-sulfotransferase 5; N-acetylglucosamine 6-O-sulfotransferase 4" ] ] }, "readme": "Name\n - Mouse Protein Names (NCBI RefSeq)\n\nVersion\n - 1.11.2\n\nCreated on\n - 2020-03-15T13:29:07.339002\n\nModified on\n - 2020-03-16T11:18:46.916940\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 - \n\nChecksum\n - \n\nUsability Domain\n - The Mouse Protein Names (NCBI RefSeq) dataset contains mouse [taxid:10090] protein names (primary and other alternative/synonym protein names) from NCBI RefSeq database. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. The dataset is derived from NCBI RefSeq Release 96, September 9, 2019. If you use this dataset please provide proper attribution to NCBI RefSeq and GlyGen\n\nDescription Domain\n Keywords\n - protein names\n - NCBI RefSeq\n\n Pipeline Steps\n - Step-1: The script parses the NCBI RefSeq gpff files to extract the protein names and then maps the NCBI RefSeq accesion 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: refseq_protein_all_10090.gpff\n URI: https://data.glygen.org/ln2data/releases/data/v-1.11.2/source/refseq_protein_all_10090.gpff\n Name: mouse_protein_xref_refseq.csv\n URI: https://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/mouse_protein_xref_refseq.csv\n Output Subdomain\n Name: mouse_protein_proteinnames_refseq.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/mouse_protein_proteinnames_refseq.csv\n Name: mouse_protein_proteinnames_refseq.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/mouse_protein_proteinnames_refseq.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_proteinnames_refseq.csv" }