{
    "bcoid": "GLY_000470",
    "title": "SARS-CoV2 Protein Citations (UniProtKB)",
    "description": "The SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein Citations dataset contains publication information ...",
    "filename": "sarscov2_protein_citations_uniprotkb.csv",
    "filetype": "csv",
    "categories": {
        "species": "SARS coronavirus (SARS-CoV-2 or 2019-nCoV)",
        "molecule": "Protein",
        "tags": "Protein Citations",
        "file_type": "csv",
        "status": "Reviewed",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "P0DTD2-1...",
                "A new corona..."
            ],
            [
                "P0DTD1-1...",
                "A new corona..."
            ]
        ],
        "headers": [
            "uniprotkb_ca...",
            "title..."
        ],
        "colwidth": [
            "40%",
            "20%"
        ]
    },
    "sampledata": {
        "type": "table",
        "data": [
            [
                {
                    "type": "string",
                    "label": "uniprotkb_canonical_ac"
                },
                {
                    "type": "string",
                    "label": "title"
                },
                {
                    "type": "string",
                    "label": "journal_name"
                },
                {
                    "type": "string",
                    "label": "publication_date"
                },
                {
                    "type": "string",
                    "label": "authors"
                },
                {
                    "type": "string",
                    "label": "xref_key"
                },
                {
                    "type": "string",
                    "label": "xref_id"
                },
                {
                    "type": "string",
                    "label": "src_xref_key"
                },
                {
                    "type": "string",
                    "label": "src_xref_id"
                }
            ],
            [
                "P0DTD2-1",
                "A new coronavirus associated with human respiratory disease in China.",
                "Nature",
                "2020",
                "Hu Y., Liu Y., Wang W., Zhao S., Xu L., Wu F., Yu B., Zhang Y.-L., Zhang Y.-Z., Zhang Y.L., Tian J.H., Zheng J.J., Zhang Y.Z., Chen Y.M., Chen Y.-M., Wang Q.M., Dai F.-H., Holmes E.C., Pei Y.-Y., Song Z.-G., Tao Z.-W., Tian J.-H., Wang Q.-M., Yuan M.-L., Zheng J.-J., Dai F.H., Pei Y.Y., Song Z.G., Tao Z.W., Yuan M.L.",
                "protein_xref_pubmed",
                "32015508",
                "protein_xref_uniprotkb",
                "P0DTD2"
            ],
            [
                "P0DTD1-1",
                "A new coronavirus associated with human respiratory disease in China.",
                "Nature",
                "2020",
                "Hu Y., Liu Y., Wang W., Zhao S., Xu L., Wu F., Yu B., Zhang Y.-L., Zhang Y.-Z., Zhang Y.L., Tian J.H., Zheng J.J., Zhang Y.Z., Chen Y.M., Chen Y.-M., Wang Q.M., Dai F.-H., Holmes E.C., Pei Y.-Y., Song Z.-G., Tao Z.-W., Tian J.-H., Wang Q.-M., Yuan M.-L., Zheng J.-J., Dai F.H., Pei Y.Y., Song Z.G., Tao Z.W., Yuan M.L.",
                "protein_xref_pubmed",
                "32015508",
                "protein_xref_uniprotkb",
                "P0DTD1"
            ],
            [
                "A0A663DJA2-1",
                "A new coronavirus associated with human respiratory disease in China.",
                "Nature",
                "2020",
                "Hu Y., Liu Y., Wang W., Zhao S., Xu L., Wu F., Yu B., Zhang Y.-L., Zhang Y.-Z., Zhang Y.L., Tian J.H., Zheng J.J., Zhang Y.Z., Chen Y.M., Chen Y.-M., Wang Q.M., Dai F.-H., Holmes E.C., Pei Y.-Y., Song Z.-G., Tao Z.-W., Tian J.-H., Wang Q.-M., Yuan M.-L., Zheng J.-J., Dai F.H., Pei Y.Y., Song Z.G., Tao Z.W., Yuan M.L.",
                "protein_xref_pubmed",
                "32015508",
                "protein_xref_uniprotkb",
                "A0A663DJA2"
            ],
            [
                "P0DTD3-1",
                "A new coronavirus associated with human respiratory disease in China.",
                "Nature",
                "2020",
                "Hu Y., Liu Y., Wang W., Zhao S., Xu L., Wu F., Yu B., Zhang Y.-L., Zhang Y.-Z., Zhang Y.L., Tian J.H., Zheng J.J., Zhang Y.Z., Chen Y.M., Chen Y.-M., Wang Q.M., Dai F.-H., Holmes E.C., Pei Y.-Y., Song Z.-G., Tao Z.-W., Tian J.-H., Wang Q.-M., Yuan M.-L., Zheng J.-J., Dai F.H., Pei Y.Y., Song Z.G., Tao Z.W., Yuan M.L.",
                "protein_xref_pubmed",
                "32015508",
                "protein_xref_uniprotkb",
                "P0DTD3"
            ],
            [
                "P0DTC7-1",
                "A new coronavirus associated with human respiratory disease in China.",
                "Nature",
                "2020",
                "Hu Y., Liu Y., Wang W., Zhao S., Xu L., Wu F., Yu B., Zhang Y.-L., Zhang Y.-Z., Zhang Y.L., Tian J.H., Zheng J.J., Zhang Y.Z., Chen Y.M., Chen Y.-M., Wang Q.M., Dai F.-H., Holmes E.C., Pei Y.-Y., Song Z.-G., Tao Z.-W., Tian J.-H., Wang Q.-M., Yuan M.-L., Zheng J.-J., Dai F.H., Pei Y.Y., Song Z.G., Tao Z.W., Yuan M.L.",
                "protein_xref_pubmed",
                "32015508",
                "protein_xref_uniprotkb",
                "P0DTC7"
            ],
            [
                "P0DTC6-1",
                "A new coronavirus associated with human respiratory disease in China.",
                "Nature",
                "2020",
                "Hu Y., Liu Y., Wang W., Zhao S., Xu L., Wu F., Yu B., Zhang Y.-L., Zhang Y.-Z., Zhang Y.L., Tian J.H., Zheng J.J., Zhang Y.Z., Chen Y.M., Chen Y.-M., Wang Q.M., Dai F.-H., Holmes E.C., Pei Y.-Y., Song Z.-G., Tao Z.-W., Tian J.-H., Wang Q.-M., Yuan M.-L., Zheng J.-J., Dai F.H., Pei Y.Y., Song Z.G., Tao Z.W., Yuan M.L.",
                "protein_xref_pubmed",
                "32015508",
                "protein_xref_uniprotkb",
                "P0DTC6"
            ],
            [
                "P0DTC5-1",
                "A new coronavirus associated with human respiratory disease in China.",
                "Nature",
                "2020",
                "Hu Y., Liu Y., Wang W., Zhao S., Xu L., Wu F., Yu B., Zhang Y.-L., Zhang Y.-Z., Zhang Y.L., Tian J.H., Zheng J.J., Zhang Y.Z., Chen Y.M., Chen Y.-M., Wang Q.M., Dai F.-H., Holmes E.C., Pei Y.-Y., Song Z.-G., Tao Z.-W., Tian J.-H., Wang Q.-M., Yuan M.-L., Zheng J.-J., Dai F.H., Pei Y.Y., Song Z.G., Tao Z.W., Yuan M.L.",
                "protein_xref_pubmed",
                "32015508",
                "protein_xref_uniprotkb",
                "P0DTC5"
            ],
            [
                "P0DTC4-1",
                "A new coronavirus associated with human respiratory disease in China.",
                "Nature",
                "2020",
                "Hu Y., Liu Y., Wang W., Zhao S., Xu L., Wu F., Yu B., Zhang Y.-L., Zhang Y.-Z., Zhang Y.L., Tian J.H., Zheng J.J., Zhang Y.Z., Chen Y.M., Chen Y.-M., Wang Q.M., Dai F.-H., Holmes E.C., Pei Y.-Y., Song Z.-G., Tao Z.-W., Tian J.-H., Wang Q.-M., Yuan M.-L., Zheng J.-J., Dai F.H., Pei Y.Y., Song Z.G., Tao Z.W., Yuan M.L.",
                "protein_xref_pubmed",
                "32015508",
                "protein_xref_uniprotkb",
                "P0DTC4"
            ],
            [
                "P0DTC3-1",
                "A new coronavirus associated with human respiratory disease in China.",
                "Nature",
                "2020",
                "Hu Y., Liu Y., Wang W., Zhao S., Xu L., Wu F., Yu B., Zhang Y.-L., Zhang Y.-Z., Zhang Y.L., Tian J.H., Zheng J.J., Zhang Y.Z., Chen Y.M., Chen Y.-M., Wang Q.M., Dai F.-H., Holmes E.C., Pei Y.-Y., Song Z.-G., Tao Z.-W., Tian J.-H., Wang Q.-M., Yuan M.-L., Zheng J.-J., Dai F.H., Pei Y.Y., Song Z.G., Tao Z.W., Yuan M.L.",
                "protein_xref_pubmed",
                "32015508",
                "protein_xref_uniprotkb",
                "P0DTC3"
            ],
            [
                "P0DTC2-1",
                "A new coronavirus associated with human respiratory disease in China.",
                "Nature",
                "2020",
                "Hu Y., Liu Y., Wang W., Zhao S., Xu L., Wu F., Yu B., Zhang Y.-L., Zhang Y.-Z., Zhang Y.L., Tian J.H., Zheng J.J., Zhang Y.Z., Chen Y.M., Chen Y.-M., Wang Q.M., Dai F.-H., Holmes E.C., Pei Y.-Y., Song Z.-G., Tao Z.-W., Tian J.-H., Wang Q.-M., Yuan M.-L., Zheng J.-J., Dai F.H., Pei Y.Y., Song Z.G., Tao Z.W., Yuan M.L.",
                "protein_xref_pubmed",
                "32015508",
                "protein_xref_uniprotkb",
                "P0DTC2"
            ],
            [
                "P0DTC2-1",
                "Cryo-EM structure of the 2019-nCoV spike in the prefusion conformation.",
                "Science",
                "2020",
                "Wang N., McLellan J.S., Graham B.S., Hsieh C.L., Abiona O., Corbett K.S., Goldsmith J.A., Wrapp D.",
                "protein_xref_pubmed",
                "32075877",
                "protein_xref_uniprotkb",
                "P0DTC2"
            ],
            [
                "P0DTC2-1",
                "SARS-CoV-2 cell entry depends on ACE2 and TMPRSS2 and is blocked by a clinically proven protease inhibitor.",
                "Cell",
                "2020",
                "Poehlmann S., Schroeder S., Drosten C., Hoffmann M., Herrler G., Erichsen S., Herrler T., Kleine-Weber H., Krueger N., Mueller M.A., Nitsche A., Schiergens T.S., Wu N.H.",
                "protein_xref_pubmed",
                "32142651",
                "protein_xref_uniprotkb",
                "P0DTC2"
            ],
            [
                "P0DTC2-1",
                "Structure, function, and antigenicity of the SARS-CoV-2 spike glycoprotein.",
                "Cell",
                "2020",
                "Park Y.J., McGuire A.T., Tortorici M.A., Veesler D., Wall A., Walls A.C.",
                "protein_xref_pubmed",
                "32155444",
                "protein_xref_uniprotkb",
                "P0DTC2"
            ],
            [
                "P0DTC1-1",
                "A new coronavirus associated with human respiratory disease in China.",
                "Nature",
                "2020",
                "Hu Y., Liu Y., Wang W., Zhao S., Xu L., Wu F., Yu B., Zhang Y.-L., Zhang Y.-Z., Zhang Y.L., Tian J.H., Zheng J.J., Zhang Y.Z., Chen Y.M., Chen Y.-M., Wang Q.M., Dai F.-H., Holmes E.C., Pei Y.-Y., Song Z.-G., Tao Z.-W., Tian J.-H., Wang Q.-M., Yuan M.-L., Zheng J.-J., Dai F.H., Pei Y.Y., Song Z.G., Tao Z.W., Yuan M.L.",
                "protein_xref_pubmed",
                "32015508",
                "protein_xref_uniprotkb",
                "P0DTC1"
            ],
            [
                "P0DTD8-1",
                "A new coronavirus associated with human respiratory disease in China.",
                "Nature",
                "2020",
                "Hu Y., Liu Y., Wang W., Zhao S., Xu L., Wu F., Yu B., Zhang Y.-L., Zhang Y.-Z., Zhang Y.L., Tian J.H., Zheng J.J., Zhang Y.Z., Chen Y.M., Chen Y.-M., Wang Q.M., Dai F.-H., Holmes E.C., Pei Y.-Y., Song Z.-G., Tao Z.-W., Tian J.-H., Wang Q.-M., Yuan M.-L., Zheng J.-J., Dai F.H., Pei Y.Y., Song Z.G., Tao Z.W., Yuan M.L.",
                "protein_xref_pubmed",
                "32015508",
                "protein_xref_uniprotkb",
                "P0DTD8"
            ],
            [
                "P0DTC9-1",
                "A new coronavirus associated with human respiratory disease in China.",
                "Nature",
                "2020",
                "Hu Y., Liu Y., Wang W., Zhao S., Xu L., Wu F., Yu B., Zhang Y.-L., Zhang Y.-Z., Zhang Y.L., Tian J.H., Zheng J.J., Zhang Y.Z., Chen Y.M., Chen Y.-M., Wang Q.M., Dai F.-H., Holmes E.C., Pei Y.-Y., Song Z.-G., Tao Z.-W., Tian J.-H., Wang Q.-M., Yuan M.-L., Zheng J.-J., Dai F.H., Pei Y.Y., Song Z.G., Tao Z.W., Yuan M.L.",
                "protein_xref_pubmed",
                "32015508",
                "protein_xref_uniprotkb",
                "P0DTC9"
            ],
            [
                "P0DTC8-1",
                "A familial cluster of pneumonia associated with the 2019 novel coronavirus indicating person-to-person transmission: a study of a family cluster.",
                "Lancet",
                "2020",
                "Liu J., Yang J., Chen H., Yuan S., Chan W.M., Cai J.P., Kok K.H., Chu H., Yip C.C., Chan K.H., Yuen K.Y., Chan J.F., Cheng V.C., Hui C.K., Ip J.D., Lo S.K., Poon R.W., Poon V.K., To K.K., Tsoi H.W., Xing F.",
                "protein_xref_pubmed",
                "31986261",
                "protein_xref_uniprotkb",
                "P0DTC8"
            ],
            [
                "P0DTC8-1",
                "A new coronavirus associated with human respiratory disease in China.",
                "Nature",
                "2020",
                "Hu Y., Liu Y., Wang W., Zhao S., Xu L., Wu F., Yu B., Zhang Y.-L., Zhang Y.-Z., Zhang Y.L., Tian J.H., Zheng J.J., Zhang Y.Z., Chen Y.M., Chen Y.-M., Wang Q.M., Dai F.-H., Holmes E.C., Pei Y.-Y., Song Z.-G., Tao Z.-W., Tian J.-H., Wang Q.-M., Yuan M.-L., Zheng J.-J., Dai F.H., Pei Y.Y., Song Z.G., Tao Z.W., Yuan M.L.",
                "protein_xref_pubmed",
                "32015508",
                "protein_xref_uniprotkb",
                "P0DTC8"
            ]
        ]
    },
    "readme": "Name\n   - SARS-CoV2 Protein Citations (UniProtKB)\n\nVersion\n   - 1.7.10\n\nCreated on\n  - 2020-04-19T11:32:35.963024\n\nModified on\n   - 2020-04-19T11:33:03.867613\n\nCreated by\n   - Jeet Vora [jeetvora@gwu.edu], Rahi Navelkar [rsn13@gwu.edu], Robel Kahsay [rykahsay@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 SARS coronavirus (SARS-CoV-2 or 2019-nCoV) Protein Citations dataset contains publication information for sarscov2 [taxid:2697049] UniProtKB accessions that includes PMID, journal name, date and author and title. The dataset is derived from 2020-01 UniProt release. If you use this dataset please provide proper attribution to EMBL-EBI-UniProtKB and GlyGen\n\nDescription Domain\n   Keywords\n   - publications\n   - PMID\n   - journal\n   - citations\n   - authors\n   - UniProtKB\n   - PubMed\n\n   Pipeline Steps\n   - Step-1: The script loads the UniProtKB publication data from the triplestore containing triples from nt file to retrieve the publication information associated with the UniProtKB accession and maps it to the UniProtKB canonical accessions. The script also filters out publications of large scale studies, and high frequency publications pertaining to DNA sequencing, cDNA, chromosomes using blacklisted PMIDs file.\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-sars-cov-2.nt\n      URI: https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-sars-cov-2.nt\n      Name: sarscov2_protein_masterlist.csv\n      URI: https://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_masterlist.csv\n   Output Subdomain\n      Name: sarscov2_protein_citations_uniprotkb.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_citations_uniprotkb.csv\n      Name: sarscov2_protein_citations_uniprotkb.stat.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/sarscov2_protein_citations_uniprotkb.stat.csv\n\nFields\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"\"\n      Unique Values: \"14\"\n      Name: \"xref_id\"\n     Description: \"ID of the X-ref\"\n      Unique Values: \"5\"\n      Name: \"title\"\n     Description: \"Title of the published article in the journal\"\n      Unique Values: \"5\"\n      Name: \"src_xref_key\"\n     Description: \"Source Xref  key\"\n      Unique Values: \"1\"\n      Name: \"src_xref_id\"\n     Description: \"Source X-ref ID\"\n      Unique Values: \"14\"\n      Name: \"journal_name\"\n     Description: \"The name of the journal in which the article is published\"\n      Unique Values: \"4\"\n      Name: \"authors\"\n     Description: \"NA\"\n      Unique Values: \"5\"\n      Name: \"publication_date\"\n     Description: \"Contains the full date on which the issue of the journal was published. Sourced from MEDLINE/PubMed data element(fields) description.\"\n      Unique Values: \"1\"\n      Name: \"xref_key\"\n     Description: \"Source key associated to the  xref_id\"\n      Unique Values: \"1\"",
    "downloadurl": "/ln2data/releases/data/v-1.7.10/reviewed/sarscov2_protein_citations_uniprotkb.csv"
}