{
    "bcoid": "GLY_000398",
    "title": "Human Protein Sequence Info (UniProtKB)",
    "description": "The Human Protein Sequence Info (UniProtKB) dataset contains human [taxid:9606] UniProtKB protein fasta ...",
    "filename": "human_protein_sequenceinfo.csv",
    "filetype": "csv",
    "categories": {
        "species": "Homo sapiens",
        "molecule": "Protein",
        "tags": "All Protein Sequence Info",
        "file_type": "csv",
        "status": "Reviewed",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "O75818-1...",
                "X6RLL4-1..."
            ],
            [
                "Q9Y6C9-1...",
                "E9PIE4-1..."
            ]
        ],
        "headers": [
            "uniprotkb_ca...",
            "uniprotkb_is..."
        ],
        "colwidth": [
            "40%",
            "20%"
        ]
    },
    "sampledata": {
        "type": "table",
        "data": [
            [
                {
                    "type": "string",
                    "label": "uniprotkb_canonical_ac"
                },
                {
                    "type": "string",
                    "label": "uniprotkb_isoform_ac"
                },
                {
                    "type": "string",
                    "label": "protein_existence"
                },
                {
                    "type": "string",
                    "label": "sequence_version"
                },
                {
                    "type": "string",
                    "label": "sequence_header"
                }
            ],
            [
                "O75818-1",
                "X6RLL4-1",
                "1",
                "1",
                "tr|X6RLL4-1|X6RLL4_HUMAN Computationally mapped isoform of Ribonuclease P protein subunit p40  OS=Homo sapiens OX=9606 GN=RPP40 PE=1 SV=1 CANONICAL=O75818-1"
            ],
            [
                "Q9Y6C9-1",
                "E9PIE4-1",
                "1",
                "8",
                "tr|E9PIE4-1|MTCH2_HUMAN Computationally mapped isoform of Mitochondrial carrier homolog 2  OS=Homo sapiens OX=9606 GN=MTCH2 PE=1 SV=8 CANONICAL=Q9Y6C9-1"
            ],
            [
                "Q9Y6C9-1",
                "Q9Y6C9-1",
                "1",
                "1",
                "sp|Q9Y6C9-1|MTCH2_HUMAN Isoform 1 of Mitochondrial carrier homolog 2  OS=Homo sapiens OX=9606 GN=MTCH2 PE=1 SV=1 CANONICAL=Q9Y6C9-1"
            ],
            [
                "Q658T7-1",
                "Q658T7-1",
                "5",
                "2",
                "sp|Q658T7-1|F90A2_HUMAN Isoform 1 of Putative protein FAM90A2P  OS=Homo sapiens OX=9606 GN=FAM90A2P PE=5 SV=2 CANONICAL=Q658T7-1"
            ],
            [
                "Q658T7-1",
                "Q658T7-2",
                "5",
                "2",
                "sp|Q658T7-2|F90A2_HUMAN Isoform 2 of Putative protein FAM90A2P  OS=Homo sapiens OX=9606 GN=FAM90A2P PE=5 SV=2 CANONICAL=Q658T7-1"
            ],
            [
                "Q8TDG4-1",
                "E3W980-1",
                "1",
                "1",
                "tr|E3W980-1|E3W980_HUMAN Computationally mapped isoform of Helicase POLQ-like  OS=Homo sapiens OX=9606 GN=HELQ PE=1 SV=1 CANONICAL=Q8TDG4-1"
            ],
            [
                "P30613-1",
                "P30613-1",
                "1",
                "2",
                "sp|P30613-1|KPYR_HUMAN Isoform 1 of Pyruvate kinase PKLR  OS=Homo sapiens OX=9606 GN=PKLR PE=1 SV=2 CANONICAL=P30613-1"
            ],
            [
                "P30613-1",
                "P30613-2",
                "1",
                "2",
                "sp|P30613-2|KPYR_HUMAN Isoform 2 of Pyruvate kinase PKLR  OS=Homo sapiens OX=9606 GN=PKLR PE=1 SV=2 CANONICAL=P30613-1"
            ],
            [
                "P30613-1",
                "A0A0G2JLC7-1",
                "1",
                "1",
                "tr|A0A0G2JLC7-1|KPYR_HUMAN Computationally mapped isoform of Pyruvate kinase PKLR  OS=Homo sapiens OX=9606 GN=PKLR PE=1 SV=1 CANONICAL=P30613-1"
            ],
            [
                "P30613-1",
                "F8W6W2-1",
                "1",
                "2",
                "tr|F8W6W2-1|KPYR_HUMAN Computationally mapped isoform of Pyruvate kinase PKLR  OS=Homo sapiens OX=9606 GN=PKLR PE=1 SV=2 CANONICAL=P30613-1"
            ],
            [
                "P50213-1",
                "H0YKD0-1",
                "1",
                "1",
                "tr|H0YKD0-1|H0YKD0_HUMAN Computationally mapped isoform of Isocitrate dehydrogenase [NAD] subunit alpha, mitochondrial  OS=Homo sapiens OX=9606 GN=IDH3A PE=1 SV=1 CANONICAL=P50213-1"
            ],
            [
                "A0A1B0GX78-1",
                "A0A0J9YY10-1",
                "4",
                "3",
                "tr|A0A0J9YY10-1|A0A0J9YY10_HUMAN Computationally mapped isoform of T cell receptor beta variable 12-5  OS=Homo sapiens OX=9606 GN=TRBV12-5 PE=4 SV=3 CANONICAL=A0A1B0GX78-1"
            ],
            [
                "Q9NPB8-1",
                "A0A0J9YY12-1",
                "1",
                "1",
                "tr|A0A0J9YY12-1|A0A0J9YY12_HUMAN Computationally mapped isoform of Glycerophosphocholine phosphodiesterase GPCPD1  OS=Homo sapiens OX=9606 GN=GPCPD1 PE=1 SV=1 CANONICAL=Q9NPB8-1"
            ],
            [
                "Q5MIZ7-1",
                "Q5MIZ7-1",
                "1",
                "2",
                "sp|Q5MIZ7-1|P4R3B_HUMAN Isoform 1 of Serine/threonine-protein phosphatase 4 regulatory subunit 3B  OS=Homo sapiens OX=9606 GN=PPP4R3B PE=1 SV=2 CANONICAL=Q5MIZ7-1"
            ],
            [
                "Q5MIZ7-1",
                "Q5MIZ7-2",
                "1",
                "2",
                "sp|Q5MIZ7-2|P4R3B_HUMAN Isoform 2 of Serine/threonine-protein phosphatase 4 regulatory subunit 3B  OS=Homo sapiens OX=9606 GN=PPP4R3B PE=1 SV=2 CANONICAL=Q5MIZ7-1"
            ],
            [
                "Q5MIZ7-1",
                "Q5MIZ7-3",
                "1",
                "2",
                "sp|Q5MIZ7-3|P4R3B_HUMAN Isoform 3 of Serine/threonine-protein phosphatase 4 regulatory subunit 3B  OS=Homo sapiens OX=9606 GN=PPP4R3B PE=1 SV=2 CANONICAL=Q5MIZ7-1"
            ],
            [
                "Q5MIZ7-1",
                "Q5MIZ7-4",
                "1",
                "2",
                "sp|Q5MIZ7-4|P4R3B_HUMAN Isoform 4 of Serine/threonine-protein phosphatase 4 regulatory subunit 3B  OS=Homo sapiens OX=9606 GN=PPP4R3B PE=1 SV=2 CANONICAL=Q5MIZ7-1"
            ],
            [
                "Q5MIZ7-1",
                "Q5MIZ7-5",
                "1",
                "2",
                "sp|Q5MIZ7-5|P4R3B_HUMAN Isoform 5 of Serine/threonine-protein phosphatase 4 regulatory subunit 3B  OS=Homo sapiens OX=9606 GN=PPP4R3B PE=1 SV=2 CANONICAL=Q5MIZ7-1"
            ],
            [
                "Q9NV96-1",
                "E5RG19-1",
                "1",
                "1",
                "tr|E5RG19-1|E5RG19_HUMAN Computationally mapped isoform of Cell cycle control protein 50A  OS=Homo sapiens OX=9606 GN=TMEM30A PE=1 SV=1 CANONICAL=Q9NV96-1"
            ],
            [
                "Q99687-1",
                "U3KQJ9-1",
                "4",
                "1",
                "tr|U3KQJ9-1|U3KQJ9_HUMAN Computationally mapped isoform of Homeobox protein Meis3  OS=Homo sapiens OX=9606 GN=MEIS3 PE=4 SV=1 CANONICAL=Q99687-1"
            ],
            [
                "Q969N2-1",
                "A0A1W2PQ29-1",
                "1",
                "1",
                "tr|A0A1W2PQ29-1|A0A1W2PQ29_HUMAN Computationally mapped isoform of GPI transamidase component PIG-T  OS=Homo sapiens OX=9606 GN=PIGT PE=1 SV=1 CANONICAL=Q969N2-1"
            ],
            [
                "P05093-1",
                "A0A1W2PQ28-1",
                "1",
                "1",
                "tr|A0A1W2PQ28-1|A0A1W2PQ28_HUMAN Computationally mapped isoform of Steroid 17-alpha-hydroxylase/17,20 lyase  OS=Homo sapiens OX=9606 GN=CYP17A1 PE=1 SV=1 CANONICAL=P05093-1"
            ],
            [
                "A0A1W2PQ27-1",
                "A0A1W2PQ27-1",
                "3",
                "1",
                "tr|A0A1W2PQ27-1|A0A1W2PQ27_HUMAN Isoform 1 of RNA polymerase II subunit A C-terminal domain phosphatase SSU72  OS=Homo sapiens OX=9606 GN=SSU72P7 PE=3 SV=1 CANONICAL=A0A1W2PQ27-1"
            ],
            [
                "O60285-1",
                "F8VXF0-1",
                "1",
                "1",
                "tr|F8VXF0-1|F8VXF0_HUMAN Computationally mapped isoform of NUAK family SNF1-like kinase 1  OS=Homo sapiens OX=9606 GN=NUAK1 PE=1 SV=1 CANONICAL=O60285-1"
            ],
            [
                "P14136-1",
                "A0A1W2PQ25-1",
                "1",
                "1",
                "tr|A0A1W2PQ25-1|A0A1W2PQ25_HUMAN Computationally mapped isoform of Glial fibrillary acidic protein  OS=Homo sapiens OX=9606 GN=GFAP PE=1 SV=1 CANONICAL=P14136-1"
            ],
            [
                "P09471-1",
                "A0A1W2PQ24-1",
                "1",
                "1",
                "tr|A0A1W2PQ24-1|A0A1W2PQ24_HUMAN Computationally mapped isoform of Guanine nucleotide-binding protein G(o) subunit alpha  OS=Homo sapiens OX=9606 GN=GNAO1 PE=1 SV=1 CANONICAL=P09471-1"
            ],
            [
                "Q9Y312-1",
                "A0A7P0T8J7-1",
                "4",
                "1",
                "tr|A0A7P0T8J7-1|A0A7P0T8J7_HUMAN Computationally mapped isoform of Protein AAR2 homolog  OS=Homo sapiens OX=9606 GN=AAR2 PE=4 SV=1 CANONICAL=Q9Y312-1"
            ],
            [
                "Q9UNP4-1",
                "A0A1W2PQ22-1",
                "4",
                "1",
                "tr|A0A1W2PQ22-1|A0A1W2PQ22_HUMAN Computationally mapped isoform of Lactosylceramide alpha-2,3-sialyltransferase  OS=Homo sapiens OX=9606 GN=ST3GAL5 PE=4 SV=1 CANONICAL=Q9UNP4-1"
            ],
            [
                "Q7RTN6-1",
                "A0A1W2PQ20-1",
                "1",
                "1",
                "tr|A0A1W2PQ20-1|A0A1W2PQ20_HUMAN Computationally mapped isoform of STE20-related kinase adapter protein alpha  OS=Homo sapiens OX=9606 GN=STRADA PE=1 SV=1 CANONICAL=Q7RTN6-1"
            ],
            [
                "Q5SRE7-1",
                "H7C3M4-1",
                "1",
                "1",
                "tr|H7C3M4-1|H7C3M4_HUMAN Computationally mapped isoform of Phytanoyl-CoA dioxygenase domain-containing protein 1  OS=Homo sapiens OX=9606 GN=PHYHD1 PE=1 SV=1 CANONICAL=Q5SRE7-1"
            ],
            [
                "Q2PZI1-1",
                "H7C3M5-1",
                "1",
                "1",
                "tr|H7C3M5-1|H7C3M5_HUMAN Computationally mapped isoform of Probable C-mannosyltransferase DPY19L1  OS=Homo sapiens OX=9606 GN=DPY19L1 PE=1 SV=1 CANONICAL=Q2PZI1-1"
            ],
            [
                "Q5VT40-1",
                "H7C3M6-1",
                "1",
                "1",
                "tr|H7C3M6-1|H7C3M6_HUMAN Computationally mapped isoform of Protein FAM78B  OS=Homo sapiens OX=9606 GN=FAM78B PE=1 SV=1 CANONICAL=Q5VT40-1"
            ],
            [
                "O94887-1",
                "H7C3M7-1",
                "1",
                "2",
                "tr|H7C3M7-1|H7C3M7_HUMAN Computationally mapped isoform of FERM, ARHGEF and pleckstrin domain-containing protein 2  OS=Homo sapiens OX=9606 GN=FARP2 PE=1 SV=2 CANONICAL=O94887-1"
            ],
            [
                "O95672-1",
                "H7C3M0-1",
                "1",
                "1",
                "tr|H7C3M0-1|H7C3M0_HUMAN Computationally mapped isoform of Endothelin-converting enzyme-like 1  OS=Homo sapiens OX=9606 GN=ECEL1 PE=1 SV=1 CANONICAL=O95672-1"
            ],
            [
                "Q9Y448-1",
                "H0YKD4-1",
                "4",
                "1",
                "tr|H0YKD4-1|H0YKD4_HUMAN Computationally mapped isoform of Small kinetochore-associated protein  OS=Homo sapiens OX=9606 GN=KNSTRN PE=4 SV=1 CANONICAL=Q9Y448-1"
            ],
            [
                "P39023-1",
                "H7C3M2-1",
                "1",
                "1",
                "tr|H7C3M2-1|H7C3M2_HUMAN Computationally mapped isoform of 60S ribosomal protein L3  OS=Homo sapiens OX=9606 GN=RPL3 PE=1 SV=1 CANONICAL=P39023-1"
            ],
            [
                "Q8TC84-1",
                "H7C3M3-1",
                "1",
                "1",
                "tr|H7C3M3-1|H7C3M3_HUMAN Computationally mapped isoform of Fibronectin type 3 and ankyrin repeat domains protein 1  OS=Homo sapiens OX=9606 GN=FANK1 PE=1 SV=1 CANONICAL=Q8TC84-1"
            ],
            [
                "Q13241-1",
                "F6WZH4-1",
                "1",
                "1",
                "tr|F6WZH4-1|F6WZH4_HUMAN Computationally mapped isoform of Natural killer cells antigen CD94  OS=Homo sapiens OX=9606 GN=KLRD1 PE=1 SV=1 CANONICAL=Q13241-1"
            ],
            [
                "Q13283-1",
                "A0A7I2YQH0-1",
                "1",
                "1",
                "tr|A0A7I2YQH0-1|A0A7I2YQH0_HUMAN Computationally mapped isoform of Ras GTPase-activating protein-binding protein 1  OS=Homo sapiens OX=9606 GN=G3BP1 PE=1 SV=1 CANONICAL=Q13283-1"
            ],
            [
                "Q12815-1",
                "F8VXF3-1",
                "1",
                "1",
                "tr|F8VXF3-1|F8VXF3_HUMAN Computationally mapped isoform of Tastin  OS=Homo sapiens OX=9606 GN=TROAP PE=1 SV=1 CANONICAL=Q12815-1"
            ],
            [
                "Q8IZS7-1",
                "H0YFK3-1",
                "4",
                "1",
                "tr|H0YFK3-1|H0YFK3_HUMAN Computationally mapped isoform of C-type lectin-like domain family 1  OS=Homo sapiens OX=9606 GN=CLECL1 PE=4 SV=1 CANONICAL=Q8IZS7-1"
            ],
            [
                "Q86W67-1",
                "H7C3M9-1",
                "3",
                "1",
                "tr|H7C3M9-1|H7C3M9_HUMAN Computationally mapped isoform of Protein FAM228A  OS=Homo sapiens OX=9606 GN=FAM228A PE=3 SV=1 CANONICAL=Q86W67-1"
            ],
            [
                "P68400-1",
                "A0A2R8YCC9-1",
                "4",
                "1",
                "tr|A0A2R8YCC9-1|A0A2R8YCC9_HUMAN Computationally mapped isoform of Casein kinase II subunit alpha  OS=Homo sapiens OX=9606 GN=CSNK2A1 PE=4 SV=1 CANONICAL=P68400-1"
            ],
            [
                "P29122-1",
                "A0A7I2YQH5-1",
                "1",
                "1",
                "tr|A0A7I2YQH5-1|A0A7I2YQH5_HUMAN Computationally mapped isoform of Proprotein convertase subtilisin/kexin type 6  OS=Homo sapiens OX=9606 GN=PCSK6 PE=1 SV=1 CANONICAL=P29122-1"
            ],
            [
                "P51788-1",
                "A0A1B0GVL9-1",
                "1",
                "1",
                "tr|A0A1B0GVL9-1|CLCN2_HUMAN Computationally mapped isoform of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=1 CANONICAL=P51788-1"
            ],
            [
                "P51788-1",
                "A0A1B0GVU4-1",
                "1",
                "1",
                "tr|A0A1B0GVU4-1|CLCN2_HUMAN Computationally mapped isoform of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=1 CANONICAL=P51788-1"
            ],
            [
                "P51788-1",
                "A0A1B0GUY6-1",
                "1",
                "1",
                "tr|A0A1B0GUY6-1|CLCN2_HUMAN Computationally mapped isoform of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=1 CANONICAL=P51788-1"
            ],
            [
                "P51788-1",
                "H7C0Q8-1",
                "1",
                "1",
                "tr|H7C0Q8-1|CLCN2_HUMAN Computationally mapped isoform of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=1 CANONICAL=P51788-1"
            ],
            [
                "P51788-1",
                "A0A1B0GVW7-1",
                "1",
                "1",
                "tr|A0A1B0GVW7-1|CLCN2_HUMAN Computationally mapped isoform of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=1 CANONICAL=P51788-1"
            ],
            [
                "P51788-1",
                "A0A1B0GTY0-1",
                "1",
                "1",
                "tr|A0A1B0GTY0-1|CLCN2_HUMAN Computationally mapped isoform of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=1 CANONICAL=P51788-1"
            ],
            [
                "P51788-1",
                "P51788-1",
                "1",
                "2",
                "sp|P51788-1|CLCN2_HUMAN Isoform 1 of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=2 CANONICAL=P51788-1"
            ],
            [
                "P51788-1",
                "P51788-2",
                "1",
                "2",
                "sp|P51788-2|CLCN2_HUMAN Isoform 2 of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=2 CANONICAL=P51788-1"
            ],
            [
                "P51788-1",
                "P51788-3",
                "1",
                "2",
                "sp|P51788-3|CLCN2_HUMAN Isoform 3 of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=2 CANONICAL=P51788-1"
            ],
            [
                "P51788-1",
                "P51788-4",
                "1",
                "2",
                "sp|P51788-4|CLCN2_HUMAN Isoform 4 of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=2 CANONICAL=P51788-1"
            ],
            [
                "P51788-1",
                "P51788-5",
                "1",
                "2",
                "sp|P51788-5|CLCN2_HUMAN Isoform 5 of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=2 CANONICAL=P51788-1"
            ],
            [
                "P51788-1",
                "A0A1B0GTJ3-1",
                "1",
                "1",
                "tr|A0A1B0GTJ3-1|CLCN2_HUMAN Computationally mapped isoform of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=1 CANONICAL=P51788-1"
            ],
            [
                "P51788-1",
                "A0A1B0GUZ8-1",
                "1",
                "1",
                "tr|A0A1B0GUZ8-1|CLCN2_HUMAN Computationally mapped isoform of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=1 CANONICAL=P51788-1"
            ],
            [
                "P51788-1",
                "A0A1B0GWC8-1",
                "1",
                "1",
                "tr|A0A1B0GWC8-1|CLCN2_HUMAN Computationally mapped isoform of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=1 CANONICAL=P51788-1"
            ],
            [
                "P51788-1",
                "A0A1B0GV52-1",
                "1",
                "1",
                "tr|A0A1B0GV52-1|CLCN2_HUMAN Computationally mapped isoform of Chloride channel protein 2  OS=Homo sapiens OX=9606 GN=CLCN2 PE=1 SV=1 CANONICAL=P51788-1"
            ],
            [
                "P23919-1",
                "P23919-2",
                "1",
                "4",
                "sp|P23919-2|KTHY_HUMAN Isoform 2 of Thymidylate kinase  OS=Homo sapiens OX=9606 GN=DTYMK PE=1 SV=4 CANONICAL=P23919-1"
            ],
            [
                "P23919-1",
                "H7BZ20-1",
                "1",
                "1",
                "tr|H7BZ20-1|KTHY_HUMAN Computationally mapped isoform of Thymidylate kinase  OS=Homo sapiens OX=9606 GN=DTYMK PE=1 SV=1 CANONICAL=P23919-1"
            ],
            [
                "P23919-1",
                "H7C3A4-1",
                "1",
                "1",
                "tr|H7C3A4-1|KTHY_HUMAN Computationally mapped isoform of Thymidylate kinase  OS=Homo sapiens OX=9606 GN=DTYMK PE=1 SV=1 CANONICAL=P23919-1"
            ],
            [
                "P23919-1",
                "H7C312-1",
                "1",
                "1",
                "tr|H7C312-1|KTHY_HUMAN Computationally mapped isoform of Thymidylate kinase  OS=Homo sapiens OX=9606 GN=DTYMK PE=1 SV=1 CANONICAL=P23919-1"
            ],
            [
                "P23919-1",
                "P23919-1",
                "1",
                "4",
                "sp|P23919-1|KTHY_HUMAN Isoform 1 of Thymidylate kinase  OS=Homo sapiens OX=9606 GN=DTYMK PE=1 SV=4 CANONICAL=P23919-1"
            ],
            [
                "P23919-1",
                "G5E9E9-1",
                "1",
                "1",
                "tr|G5E9E9-1|KTHY_HUMAN Computationally mapped isoform of Thymidylate kinase  OS=Homo sapiens OX=9606 GN=DTYMK PE=1 SV=1 CANONICAL=P23919-1"
            ],
            [
                "Q8NHX4-1",
                "H7C3E6-1",
                "2",
                "1",
                "tr|H7C3E6-1|SPTA3_HUMAN Computationally mapped isoform of Spermatogenesis-associated protein 3  OS=Homo sapiens OX=9606 GN=SPATA3 PE=2 SV=1 CANONICAL=Q8NHX4-1"
            ],
            [
                "Q8NHX4-1",
                "H7C283-1",
                "2",
                "1",
                "tr|H7C283-1|SPTA3_HUMAN Computationally mapped isoform of Spermatogenesis-associated protein 3  OS=Homo sapiens OX=9606 GN=SPATA3 PE=2 SV=1 CANONICAL=Q8NHX4-1"
            ],
            [
                "Q8NHX4-1",
                "F8WDD9-1",
                "2",
                "1",
                "tr|F8WDD9-1|SPTA3_HUMAN Computationally mapped isoform of Spermatogenesis-associated protein 3  OS=Homo sapiens OX=9606 GN=SPATA3 PE=2 SV=1 CANONICAL=Q8NHX4-1"
            ],
            [
                "Q8NHX4-1",
                "Q8NHX4-1",
                "2",
                "2",
                "sp|Q8NHX4-1|SPTA3_HUMAN Isoform 1 of Spermatogenesis-associated protein 3  OS=Homo sapiens OX=9606 GN=SPATA3 PE=2 SV=2 CANONICAL=Q8NHX4-1"
            ],
            [
                "Q8NHX4-1",
                "A0A2R8Y5R0-1",
                "2",
                "1",
                "tr|A0A2R8Y5R0-1|SPTA3_HUMAN Computationally mapped isoform of Spermatogenesis-associated protein 3  OS=Homo sapiens OX=9606 GN=SPATA3 PE=2 SV=1 CANONICAL=Q8NHX4-1"
            ],
            [
                "Q8NHX9-1",
                "Q8NHX9-1",
                "1",
                "2",
                "sp|Q8NHX9-1|TPC2_HUMAN Isoform 1 of Two pore calcium channel protein 2  OS=Homo sapiens OX=9606 GN=TPCN2 PE=1 SV=2 CANONICAL=Q8NHX9-1"
            ],
            [
                "Q8NHX9-1",
                "A0A1B0GTM1-1",
                "1",
                "1",
                "tr|A0A1B0GTM1-1|TPC2_HUMAN Computationally mapped isoform of Two pore calcium channel protein 2  OS=Homo sapiens OX=9606 GN=TPCN2 PE=1 SV=1 CANONICAL=Q8NHX9-1"
            ],
            [
                "Q8NHX9-1",
                "A0A1B0GUM5-1",
                "1",
                "1",
                "tr|A0A1B0GUM5-1|TPC2_HUMAN Computationally mapped isoform of Two pore calcium channel protein 2  OS=Homo sapiens OX=9606 GN=TPCN2 PE=1 SV=1 CANONICAL=Q8NHX9-1"
            ],
            [
                "Q8NHX9-1",
                "E7ETX0-1",
                "1",
                "1",
                "tr|E7ETX0-1|TPC2_HUMAN Computationally mapped isoform of Two pore calcium channel protein 2  OS=Homo sapiens OX=9606 GN=TPCN2 PE=1 SV=1 CANONICAL=Q8NHX9-1"
            ],
            [
                "O94993-1",
                "B4DXW7-1",
                "1",
                "1",
                "tr|B4DXW7-1|B4DXW7_HUMAN Computationally mapped isoform of cDNA FLJ53881, highly similar to Transcription factor SOX-30  OS=Homo sapiens OX=9606 GN=SOX30 PE=1 SV=1 CANONICAL=O94993-1"
            ],
            [
                "Q9NXR8-1",
                "Q9NXR8-1",
                "1",
                "2",
                "sp|Q9NXR8-1|ING3_HUMAN Isoform 1 of Inhibitor of growth protein 3  OS=Homo sapiens OX=9606 GN=ING3 PE=1 SV=2 CANONICAL=Q9NXR8-1"
            ],
            [
                "Q9NXR8-1",
                "Q9NXR8-2",
                "1",
                "2",
                "sp|Q9NXR8-2|ING3_HUMAN Isoform 2 of Inhibitor of growth protein 3  OS=Homo sapiens OX=9606 GN=ING3 PE=1 SV=2 CANONICAL=Q9NXR8-1"
            ],
            [
                "Q9NXR8-1",
                "Q9NXR8-3",
                "1",
                "2",
                "sp|Q9NXR8-3|ING3_HUMAN Isoform 3 of Inhibitor of growth protein 3  OS=Homo sapiens OX=9606 GN=ING3 PE=1 SV=2 CANONICAL=Q9NXR8-1"
            ],
            [
                "Q9NXR8-1",
                "E7ET07-1",
                "1",
                "1",
                "tr|E7ET07-1|ING3_HUMAN Computationally mapped isoform of Inhibitor of growth protein 3  OS=Homo sapiens OX=9606 GN=ING3 PE=1 SV=1 CANONICAL=Q9NXR8-1"
            ],
            [
                "Q9NXR8-1",
                "A0A0C4DG38-1",
                "1",
                "1",
                "tr|A0A0C4DG38-1|ING3_HUMAN Computationally mapped isoform of Inhibitor of growth protein 3  OS=Homo sapiens OX=9606 GN=ING3 PE=1 SV=1 CANONICAL=Q9NXR8-1"
            ],
            [
                "P10242-1",
                "E9PN43-1",
                "1",
                "1",
                "tr|E9PN43-1|E9PN43_HUMAN Computationally mapped isoform of Transcriptional activator Myb  OS=Homo sapiens OX=9606 GN=MYB PE=1 SV=1 CANONICAL=P10242-1"
            ],
            [
                "Q9GZW8-1",
                "E9PN40-1",
                "3",
                "1",
                "tr|E9PN40-1|E9PN40_HUMAN Computationally mapped isoform of Membrane-spanning 4-domains subfamily A member 7  OS=Homo sapiens OX=9606 GN=MS4A7 PE=3 SV=1 CANONICAL=Q9GZW8-1"
            ],
            [
                "O14817-1",
                "E9PN41-1",
                "1",
                "1",
                "tr|E9PN41-1|E9PN41_HUMAN Computationally mapped isoform of Tetraspanin-4  OS=Homo sapiens OX=9606 GN=TSPAN4 PE=1 SV=1 CANONICAL=O14817-1"
            ],
            [
                "Q9C0H5-1",
                "Q9C0H5-1",
                "1",
                "2",
                "sp|Q9C0H5-1|RHG39_HUMAN Isoform 1 of Rho GTPase-activating protein 39  OS=Homo sapiens OX=9606 GN=ARHGAP39 PE=1 SV=2 CANONICAL=Q9C0H5-1"
            ]
        ]
    },
    "readme": "Name\n   - Human Protein Sequence Info (UniProtKB)\n\nVersion\n   - 1.11.2\n\nCreated on\n  - 2020-03-15T14:32:07.364795\n\nModified on\n   - 2020-04-10T11:49:57.046096\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   - Maria Martin [martin@ebi.ac.uk], Preethi Vasudev [pvasudev@ebi.ac.uk]\n\nChecksum\n   - \n\nUsability Domain\n   - The Human Protein Sequence Info (UniProtKB) dataset contains human [taxid:9606] UniProtKB protein fasta sequence information that includes sequence version and fasta header. 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\nDescription Domain\n   Keywords\n   - protein sequence info\n   - fasta header\n   - UniProtKB\n\n   Pipeline Steps\n   - Step-1: The script loads the UniProtKB sequence for all human isoform accessions data from the triplestore containing triples from nt file and extracts it into a dataset in a fasta format\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   Output Subdomain\n      Name: human_protein_sequenceinfo.csv\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/human_protein_sequenceinfo.csv\n      Name: human_protein_sequenceinfo.stat.csv\n      URI: http://data.glygen.org/ln2data/releases/data/v-1.11.2/reviewed/human_protein_human_sequenceinfo.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_sequenceinfo.csv"
}