{ "bcoid": "GLY_000392", "title": "Human Protein Names (NCBI RefSeq)", "description": "The Human Protein Names (NCBI RefSeq) dataset contains human [taxid:9606] protein names (primary and ...", "filename": "human_protein_proteinnames_refseq.csv", "filetype": "csv", "categories": { "species": "Homo sapiens", "molecule": "Protein", "tags": "Protein Names", "file_type": "csv", "status": "Reviewed", "scope": "internal" }, "minitable": { "content": [ [ "P30613-1...", "NP_000289.1..." ], [ "P30613-1...", "NP_000289.1..." ] ], "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" } ], [ "P30613-1", "NP_000289.1", "pyruvate kinase PKLR isoform 1" ], [ "P30613-1", "NP_000289.1", "pyruvate kinase type L; pyruvate kinase, liver and blood cell; pyruvate kinase 1; pyruvate kinase isozyme R/L; R-type/L-type pyruvate kinase; red cell/liver pyruvate kinase; pyruvate kinase isozymes R/L; pyruvate kinase isozymes L/R; pyruvate kinase PKLR; pyruvate kinase, liver and RBC" ], [ "P30613-1", "NP_000289", "pyruvate kinase PKLR isoform 1" ], [ "P30613-1", "NP_000289", "pyruvate kinase type L; pyruvate kinase, liver and blood cell; pyruvate kinase 1; pyruvate kinase isozyme R/L; R-type/L-type pyruvate kinase; red cell/liver pyruvate kinase; pyruvate kinase isozymes R/L; pyruvate kinase isozymes L/R; pyruvate kinase PKLR; pyruvate kinase, liver and RBC" ], [ "P23919-1", "NP_001158503.1", "thymidylate kinase isoform 2" ], [ "P23919-1", "NP_001158503.1", "deoxythymidylate kinase (thymidylate kinase); dTMP kinase" ], [ "P23919-1", "NP_001158503", "thymidylate kinase isoform 2" ], [ "P23919-1", "NP_001158503", "deoxythymidylate kinase (thymidylate kinase); dTMP kinase" ], [ "Q8NHX4-1", "NP_620712.2", "spermatogenesis-associated protein 3" ], [ "Q8NHX4-1", "NP_620712.2", "testis and spermatogenesis cell apoptosis related gene 1; testis spermatocyte apoptosis-related protein 1; testis and spermatogenesis cell-related protein 1" ], [ "Q8NHX4-1", "NP_620712", "spermatogenesis-associated protein 3" ], [ "Q8NHX4-1", "NP_620712", "testis and spermatogenesis cell apoptosis related gene 1; testis spermatocyte apoptosis-related protein 1; testis and spermatogenesis cell-related protein 1" ], [ "Q8NHX9-1", "NP_620714.2", "two pore calcium channel protein 2" ], [ "Q8NHX9-1", "NP_620714.2", "voltage-dependent calcium channel protein TPC2" ], [ "Q8NHX9-1", "NP_620714", "two pore calcium channel protein 2" ], [ "Q8NHX9-1", "NP_620714", "voltage-dependent calcium channel protein TPC2" ], [ "H3BTG2-1", "NP_001229450.1", "testis-expressed protein 46 precursor" ], [ "H3BTG2-1", "NP_001229450.1", "uncharacterized protein C1orf234; testis-expressed protein 46" ], [ "H3BTG2-1", "NP_001229450", "testis-expressed protein 46 precursor" ], [ "H3BTG2-1", "NP_001229450", "uncharacterized protein C1orf234; testis-expressed protein 46" ], [ "Q9C0H2-1", "NP_079526.1", "protein tweety homolog 3" ], [ "Q9C0H2-1", "NP_079526.1", "hTTY3; tweety homolog 3" ], [ "Q9C0H2-1", "NP_079526", "protein tweety homolog 3" ], [ "Q9C0H2-1", "NP_079526", "hTTY3; tweety homolog 3" ], [ "Q9C0H5-1", "NP_001295136.1", "rho GTPase-activating protein 39 isoform 1" ], [ "Q9C0H5-1", "NP_001295136.1", "crossGAP homolog; RhoGAP93B homolog" ], [ "Q9C0H5-1", "NP_001295136", "rho GTPase-activating protein 39 isoform 1" ], [ "Q9C0H5-1", "NP_001295136", "crossGAP homolog; RhoGAP93B homolog" ], [ "Q9C0H6-1", "NP_061990.2", "kelch-like protein 4 isoform 1" ], [ "Q9C0H6-1", "NP_061990.2", "kelch-like protein 4" ], [ "Q9C0H6-1", "NP_061990", "kelch-like protein 4 isoform 1" ], [ "Q9C0H6-1", "NP_061990", "kelch-like protein 4" ], [ "Q9C0H9-5", "NP_079524.2", "SRC kinase signaling inhibitor 1" ], [ "Q9C0H9-5", "NP_079524.2", "SNAP25-interacting protein; p140Cap; P130Cas-associated protein; SNAP-25-interacting protein" ], [ "Q9C0H9-5", "NP_079524", "SRC kinase signaling inhibitor 1" ], [ "Q9C0H9-5", "NP_079524", "SNAP25-interacting protein; p140Cap; P130Cas-associated protein; SNAP-25-interacting protein" ], [ "Q96J66-1", "NP_115972.2", "ATP-binding cassette sub-family C member 11 isoform a" ], [ "Q96J66-1", "NP_115972.2", "ATP-binding cassette, sub-family C (CFTR/MRP), member 11; multi-resistance protein 8; ATP-binding cassette transporter MRP8; ATP-binding cassette protein C11; multidrug resistance-associated protein 8; ATP-binding cassette transporter sub-family C member 11; ATP-binding cassette sub-family C member 11" ], [ "Q96J66-1", "NP_115972", "ATP-binding cassette sub-family C member 11 isoform a" ], [ "Q96J66-1", "NP_115972", "ATP-binding cassette, sub-family C (CFTR/MRP), member 11; multi-resistance protein 8; ATP-binding cassette transporter MRP8; ATP-binding cassette protein C11; multidrug resistance-associated protein 8; ATP-binding cassette transporter sub-family C member 11; ATP-binding cassette sub-family C member 11" ], [ "Q96J65-1", "NP_150229.2", "multidrug resistance-associated protein 9" ], [ "Q96J65-1", "NP_150229.2", "ATP-binding cassette, sub-family C (CFTR/MRP), member 12; ATP-binding cassette transporter sub-family C member 12; ATP-binding cassette sub-family C member 12" ], [ "Q96J65-1", "NP_150229", "multidrug resistance-associated protein 9" ], [ "Q96J65-1", "NP_150229", "ATP-binding cassette, sub-family C (CFTR/MRP), member 12; ATP-binding cassette transporter sub-family C member 12; ATP-binding cassette sub-family C member 12" ], [ "Q8NC06-1", "XP_016880588.1", "acyl-CoA-binding domain-containing protein 4 isoform X14" ], [ "Q8NC06-1", "XP_016880588", "acyl-CoA-binding domain-containing protein 4 isoform X14" ], [ "Q8NBW4-1", "NP_001269358.1", "sodium-coupled neutral amino acid transporter 9 isoform 4" ], [ "Q8NBW4-1", "NP_001269358.1", "putative sodium-coupled neutral amino acid transporter 9; up-regulated in lung cancer 11" ], [ "Q8NBW4-1", "NP_001269358", "sodium-coupled neutral amino acid transporter 9 isoform 4" ], [ "Q8NBW4-1", "NP_001269358", "putative sodium-coupled neutral amino acid transporter 9; up-regulated in lung cancer 11" ], [ "Q9NYS7-1", "NP_001265486.1", "WD repeat and SOCS box-containing protein 2 isoform 1" ], [ "Q9NYS7-1", "NP_001265486.1", "WSB-2; CS box-containing WD protein; WD repeat and SOCS box-containing protein 2" ], [ "Q9NYS7-1", "NP_001265486", "WD repeat and SOCS box-containing protein 2 isoform 1" ], [ "Q9NYS7-1", "NP_001265486", "WSB-2; CS box-containing WD protein; WD repeat and SOCS box-containing protein 2" ], [ "P40424-1", "NP_001191892.1", "pre-B-cell leukemia transcription factor 1 isoform 3" ], [ "P40424-1", "NP_001191892.1", "pre-B-cell leukemia transcription factor 1; pre-B-cell leukemia homeobox 1; homeobox protein PRL; homeobox protein PBX1" ], [ "P40424-1", "NP_001191892", "pre-B-cell leukemia transcription factor 1 isoform 3" ], [ "P40424-1", "NP_001191892", "pre-B-cell leukemia transcription factor 1; pre-B-cell leukemia homeobox 1; homeobox protein PRL; homeobox protein PBX1" ], [ "P40425-1", "NP_002577.2", "pre-B-cell leukemia transcription factor 2" ], [ "P40425-1", "NP_002577.2", "homeobox 12; pre-B-cell leukemia homeobox 2; homeobox protein PBX2; XXbac-BPG300A18.13" ], [ "P40425-1", "NP_002577", "pre-B-cell leukemia transcription factor 2" ], [ "P40425-1", "NP_002577", "homeobox 12; pre-B-cell leukemia homeobox 2; homeobox protein PBX2; XXbac-BPG300A18.13" ], [ "P40426-1", "NP_001128250.1", "pre-B-cell leukemia transcription factor 3 isoform 2" ], [ "P40426-1", "NP_001128250.1", "pre-B-cell leukemia transcription factor 3; pre-B-cell leukemia homeobox 3; homeobox protein PBX3" ], [ "P40426-1", "NP_001128250", "pre-B-cell leukemia transcription factor 3 isoform 2" ], [ "P40426-1", "NP_001128250", "pre-B-cell leukemia transcription factor 3; pre-B-cell leukemia homeobox 3; homeobox protein PBX3" ], [ "P40429-1", "NP_001257420.1", "60S ribosomal protein L13a isoform 2" ], [ "P40429-1", "NP_001257420.1", "60S ribosomal protein L13a; 23 kDa highly basic protein; tissue specific transplantation antigen 1; large ribosomal subunit protein uL13; epididymis secretory sperm binding protein" ], [ "P40429-1", "NP_001257420", "60S ribosomal protein L13a isoform 2" ], [ "P40429-1", "NP_001257420", "60S ribosomal protein L13a; 23 kDa highly basic protein; tissue specific transplantation antigen 1; large ribosomal subunit protein uL13; epididymis secretory sperm binding protein" ], [ "Q9H2I8-1", "NP_114413.1", "leucine-rich melanocyte differentiation-associated protein isoform 2" ], [ "Q9H2I8-1", "NP_114413.1", "leucine-rich repeat-containing protein C10orf11; leucine-rich melanocyte differentiation-associated protein" ], [ "Q9H2I8-1", "NP_114413", "leucine-rich melanocyte differentiation-associated protein isoform 2" ], [ "Q9H2I8-1", "NP_114413", "leucine-rich repeat-containing protein C10orf11; leucine-rich melanocyte differentiation-associated protein" ], [ "P03891-1", "YP_003024027.1", "NADH dehydrogenase subunit 2" ], [ "P03891-1", "YP_003024027", "NADH dehydrogenase subunit 2" ], [ "P03897-1", "YP_003024033.1", "NADH dehydrogenase subunit 3" ], [ "P03897-1", "YP_003024033", "NADH dehydrogenase subunit 3" ], [ "P02768-1", "NP_000468.1", "albumin preproprotein" ], [ "P02768-1", "NP_000468.1", "serum albumin" ], [ "P02768-1", "NP_000468", "albumin preproprotein" ], [ "P02768-1", "NP_000468", "serum albumin" ], [ "P02760-1", "NP_001624.1", "protein AMBP preproprotein" ], [ "P02760-1", "NP_001624.1", "inter-alpha-trypsin inhibitor light chain; bikunin; growth-inhibiting protein 19; uristatin; protein HC; complex-forming glycoprotein heterogeneous in charge; uronic-acid-rich protein; trypstatin; protein AMBP" ] ] }, "readme": "Name\n - Human Protein Names (NCBI RefSeq)\n\nVersion\n - 1.11.2\n\nCreated on\n - 2020-03-15T13:26:46.282740\n\nModified on\n - 2020-04-10T11:49:01.913927\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 Human Protein Names (NCBI RefSeq) dataset contains human [taxid:9606] 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_9606.gpff\n URI: https://data.glygen.org/ln2wwwdata/source/refseq_protein_all_9606.gpff\n Name: human_protein_xref_refseq.csv\n URI: https://data.glygen.org/ln2wwwdata/reviewed/human_protein_xref_refseq.csv\n Output Subdomain\n Name: human_protein_proteinnames_refseq.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_protein_proteinnames_refseq.csv\n Name: human_protein_proteinnames_refseq.stat.csv\n URI: http://data.glygen.org/ln2wwwdata/reviewed/human_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/human_protein_proteinnames_refseq.csv" }