{ "bcoid": "GLY_000022", "title": "Mouse Protein Information (NCBI RefSeq)", "description": "The Mouse Protein Information (NCBI RefSeq) dataset contains mouse [taxid:10090] protein information ...", "filename": "mouse_protein_info_refseq.csv", "filetype": "csv", "categories": { "species": "Mus musculus", "molecule": "Protein", "tags": "Protein Information", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P03888-1...", "NP_904328.1..." ], [ "P03893-1...", "NP_904329.1..." ] ], "headers": [ "uniprotkb_ca...", "p_refseq_ac_..." ], "colwidth": [ "40%", "20%" ] }, "sampledata": { "type": "table", "data": [ [ { "type": "string", "label": "uniprotkb_canonical_ac" }, { "type": "string", "label": "p_refseq_ac_best_match" }, { "type": "string", "label": "refseq_protein_name" }, { "type": "string", "label": "refseq_protein_length" }, { "type": "string", "label": "refseq_protein_summary" } ], [ "P03888-1", "NP_904328.1", "NADH dehydrogenase subunit 1", "318", "" ], [ "P03893-1", "NP_904329.1", "NADH dehydrogenase subunit 2", "345", "" ], [ "P00397-1", "NP_904330.1", "cytochrome c oxidase subunit I", "514", "" ], [ "P00405-1", "NP_904331.1", "cytochrome c oxidase subunit II", "227", "" ], [ "P03930-1", "NP_904332.1", "ATP synthase F0 subunit 8", "67", "" ], [ "P00848-1", "NP_904333.1", "ATP synthase F0 subunit 6", "226", "" ], [ "P00416-1", "NP_904334.1", "cytochrome c oxidase subunit III", "261", "" ], [ "P03899-1", "NP_904335.1", "NADH dehydrogenase subunit 3", "115", "" ], [ "P03903-1", "NP_904336.1", "NADH dehydrogenase subunit 4L", "98", "" ], [ "P03911-1", "NP_904337.1", "NADH dehydrogenase subunit 4", "459", "" ], [ "P03921-1", "NP_904338.1", "NADH dehydrogenase subunit 5", "607", "" ], [ "P03925-1", "NP_904339.1", "NADH dehydrogenase subunit 6", "172", "" ], [ "P00158-1", "NP_904340.1", "cytochrome b", "381", "" ], [ "Q3U687-1", "NP_444447.1", "interferon induced protein with tetratricopeptide repeats 1B like 2", "466", "" ], [ "Q9CZP3-1", "NP_001077427.1", "zinc finger protein 655 isoform b", "181", "" ], [ "H7BX78-1", "NP_001028623.1", "zinc finger protein 408 isoform 2", "610", "" ], [ "A2AE21-1", "NP_899008.2", "zinc finger protein 300 isoform 2", "645", "" ], [ "Q9D9N2-1", "NP_001075140.1", "claudin 34B2 precursor", "209", "" ], [ "Q7TSV0-1", "NP_001035040.1", "zinc finger protein 606 isoform 2", "87", "" ], [ "Q9DCP4-1", "NP_001153110.1", "uncharacterized protein LOC74088 isoform 2", "199", "" ], [ "A2ANY3-1", "NP_001162062.1", "uncharacterized protein LOC67715 isoform 1 precursor", "279", "" ], [ "B1AUN2-1", "NP_780344.2", "translation initiation factor eIF-2B subunit gamma isoform 2", "445", "" ], [ "E9Q492-1", "NP_001012311.2", "piggyBac transposable element-derived protein 1 isoform b", "378", "" ], [ "J3KMM7-1", "NP_001230020.1", "uncharacterized protein LOC381272 isoform 2", "78", "" ], [ "Q3V0S8-1", "NP_001155900.1", "uncharacterized protein LOC69324 isoform 1", "276", "" ], [ "Q99N18-1", "NP_598888.1", "cytochrome P450, family 4, subfamily f, polypeptide 15 isoform 1", "534", "" ], [ "Q8BNV8-1", "NP_001107028.1", "triggering receptor expressed in myeloid cells 4 isoform b precursor", "160", "" ], [ "A2ARW8-1", "NP_001268957.1", "novel KRAB box and zinc finger, C2H2 type domain containing protein isoform 2", "69", "" ], [ "E9Q9T0-1", "NP_082872.2", "fibrosin-1-like protein isoform 2", "593", "" ], [ "Q3SYJ2-1", "NP_082924.2", "proline-rich protein 27 isoform 2 precursor", "344", "" ], [ "E0CZ26-1", "NP_001153337.1", "BTB/POZ domain-containing protein KCTD18 isoform 2", "262", "" ], [ "E9QAA1-1", "NP_663459.2", "zinc finger protein 758 isoform 1", "551", "" ], [ "Q3UH45-1", "NP_001074526.1", "tectonin beta-propeller repeat-containing protein 2 isoform 1", "1423", "" ], [ "Q3TQS0-1", "NP_001272825.1", "calreticulin 4 isoform c", "313", "" ], [ "Q8K193-1", "NP_001297581.1", "claudin 34C1 isoform 2", "257", "" ], [ "E9Q492-1", "NP_001156391.1", "piggyBac transposable element-derived protein 1 isoform a", "415", "" ], [ "Q3UTQ6-1", "NP_001039018.1", "Kruppel-like zinc finger protein", "422", "" ], [ "E9Q4M0-1", "NP_766202.3", "transmembrane protein 44 isoform 2", "433", "" ], [ "D3Z6F0-1", "NP_001095075.1", "uncharacterized protein LOC667373 isoform 2", "470", "" ], [ "Q80ZX2-1", "NP_001139352.1", "zinc finger protein 790", "779", "" ], [ "Q8VI97-1", "NP_001153406.1", "2'-5' oligoadenylate synthetase 1H isoform 2", "239", "" ], [ "Q8BY68-1", "NP_001116067.1", "purinergic receptor P2Y G-protein coupled 10-like", "352", "" ], [ "Q8BV16-1", "NP_766622.2", "zinc finger protein 398 isoform 2", "511", "" ], [ "Q8C7I4-1", "NP_001162131.1", "apolipoprotein L 9b", "310", "" ], [ "Q9D5W6-1", "NP_001157705.1", "solute carrier organic anion transporter family, member 6d1 isoform 2", "650", "" ], [ "J3QML9-1", "NP_001241673.1", "uncharacterized protein LOC319887 isoform 1", "246", "" ], [ "E9PYY6-1", "NP_001106859.1", "sodium-dependent glucose transporter 1 isoform c", "156", "" ], [ "Q9D1U5-1", "NP_001294953.1", "cutA divalent cation tolerance homolog-like isoform 2", "111", "" ], [ "A0A1B0GT64-1", "NP_001019797.2", "zinc finger protein 873 isoform 2", "630", "" ], [ "A0A571BEN1-1", "NP_001239301.1", "myosin-binding protein C, slow-type isoform 1", "1127", "" ], [ "Q6AXF8-1", "NP_598895.2", "HMG domain-containing protein 3 isoform 2", "1254", "" ], [ "Q6S9I3-1", "NP_958763.1", "kininogen 2 isoform 1 precursor", "644", "" ], [ "B2RXC8-1", "NP_742156.2", "serine/threonine-protein phosphatase 2A regulatory subunit B'' subunit alpha isoform 2", "530", "" ], [ "Q6S9I3-1", "NP_001095880.1", "kininogen 2 isoform 3 precursor", "462", "" ], [ "E0CX23-1", "NP_001289282.1", "UBAP1-MVB12-associated (UMA)-domain containing protein 1 isoform 1", "159", "" ], [ "A0A1D5RLF0-1", "NP_001289933.1", "F-box and WD-40 domain protein 27 isoform 2", "209", "" ], [ "Q8HWE5-1", "NP_715641.1", "MHC I like leukocyte 2 isoform short precursor", "340", "" ], [ "Q24JP3-1", "NP_958753.2", "protein FAM178B isoform C", "379", "" ], [ "Q6PFE7-1", "NP_067411.1", "tomoregulin-1 isoform 2 precursor", "372", "" ], [ "A0A2R8VKG2-1", "NP_001028519.2", "UPF0606 protein KIAA1549L homolog isoform 2", "1414", "" ], [ "Q14BI1-1", "NP_001103710.1", "sodium/potassium/calcium exchanger 2 isoform 2", "711", "" ], [ "E9Q9Y3-1", "NP_001161841.1", "uncharacterized protein LOC75453 isoform 1", "381", "" ], [ "E9Q9Y3-1", "NP_083568.2", "uncharacterized protein LOC75453 isoform 2", "183", "" ], [ "A0A0N4SWI3-1", "NP_001161410.1", "uncharacterized protein isoform b", "463", "" ], [ "D3Z3H0-1", "NP_705808.1", "INO80 complex subunit E isoform 2", "205", "" ], [ "A2AJB9-1", "NP_001263377.1", "epididymal-specific lipocalin-6 isoform 1 precursor", "245", "" ], [ "Q9CQ47-1", "NP_080009.1", "uncharacterized protein LOC66732", "274", "" ], [ "Q05AC5-1", "NP_080524.2", "uncharacterized protein LOC67575", "485", "" ], [ "A0A571BEV3-1", "NP_083506.1", "glutamate-rich protein 6B isoform 2", "220", "" ], [ "A2CG24-1", "NP_001157327.1", "testis-expressed basic protein 1 isoform 2", "286", "" ], [ "E9PY36-1", "NP_001074250.1", "uncharacterized protein C13orf46 homolog isoform 2", "219", "" ], [ "E9QAE1-1", "NP_795931.2", "nck-associated protein 5 isoform 3", "406", "" ], [ "Q24JP3-1", "NP_001119518.1", "protein FAM178B isoform A", "523", "" ], [ "E9Q3H6-1", "NP_001074509.1", "coenzyme Q-binding protein COQ10 homolog A, mitochondrial isoform 1", "259", "" ], [ "B8QI36-1", "NP_001138327.1", "liprin-alpha-4 isoform 1", "1187", "" ], [ "D3YV92-1", "NP_081873.2", "protein FAM71D isoform 2", "393", "" ], [ "A9Q7H1-1", "NP_001171368.1", "RIKEN cDNA 9830107B12 isoform 3 precursor", "149", "" ], [ "G3X972-1", "NP_001161745.1", "protein transport protein Sec24C isoform 2", "1020", "" ], [ "E9Q3R6-1", "NP_001158048.1", "zinc finger protein 169 isoform b", "136", "" ], [ "E9Q3R6-1", "NP_001158047.1", "zinc finger protein 169 isoform a", "731", "" ], [ "Q9JJT2-1", "NP_001129535.1", "GDNF family receptor alpha-4 isoform 1 precursor", "293", "This gene encodes a transmembrane protein that functions as the receptor for persephin, a member of the glial cell line derived neurotrophic factors. The encoded protein undergoes proteolytic processing to generate a glycosylphosphatidylinositol-anchored cell surface coreceptor that forms a complex with the receptor tyrosine kinase Ret. A complete lack of the encoded protein impairs production of thyroid calcitonin and increases the rate of bone formation in young mice. [provided by RefSeq, Jul 2016]. " ], [ "Q8BKP2-1", "NP_001276830.1", "zinc finger protein 189", "608", "" ], [ "Q8VCG1-1", "NP_001153118.1", "deoxyuridine 5'-triphosphate nucleotidohydrolase, mitochondrial isoform 1", "200", "" ], [ "A2A590-1", "NP_081433.2", "keratin associated protein 1-5", "122", "" ] ] }, "readme": "Name\n - Mouse Protein Information (NCBI RefSeq)\n\nVersion\n - 1.11.2\n\nCreated on\n - 2019-01-23T17:21:05.888176\n\nModified on\n - 2022-01-12T15:58:42.909330\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 - Not Applicable []\n\nChecksum\n - \n\nUsability Domain\n - The Mouse Protein Information (NCBI RefSeq) dataset contains mouse [taxid:10090] protein information such as protein accession, name, length and protein function summary from NCBI RefSeq database. 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 information\n - protein length\n - protein summary\n - NCBI RefSeq\n\n Pipeline Steps\n - Step-1: The script parses the NCBI RefSeq gpff files to extract the accession, length, protein summary 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_info_refseq.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/mouse_protein_info_refseq.csv\n Name: mouse_protein_info_refseq.stat.csv\n URI: http://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/mouse_protein_info_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_info_refseq.csv" }