{
    "bcoid": "GLY_000418",
    "title": "SARS-CoV1 Protein Citations (UniProtKB)",
    "description": "The SARS coronavirus (SARS-CoV-1) Protein Citations dataset contains publication information for sarscov1 ...",
    "filename": "sarscov1_protein_citations_uniprotkb.csv",
    "filetype": "csv",
    "categories": {
        "species": "SARS coronavirus (SARS-CoV-1)",
        "molecule": "Protein",
        "tags": "Protein Citations",
        "file_type": "csv",
        "status": "Reviewed",
        "scope": "internal"
    },
    "minitable": {
        "content": [
            [
                "P59596-1...",
                "Severe acute..."
            ],
            [
                "P59596-1...",
                "Characteriza..."
            ]
        ],
        "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"
                }
            ],
            [
                "P59596-1",
                "Severe acute respiratory syndrome coronavirus protein 7a interacts with hSGT.",
                "Biochem. Biophys. Res. Commun.",
                "2006",
                "Hong W., Shen S., Khan S., Tan T.H.P., Chou C.-F., Fielding B.C., Gunalan V., Lim S.G., Tan Y.-J.",
                "protein_xref_pubmed",
                "16580632",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "Characterization of a novel coronavirus associated with severe acute respiratory syndrome.",
                "Science",
                "2003",
                "Sanchez A., Chen Q., DeRisi J.L., Wang D., Guenther S., Nix W.A., Anderson L.J., Drosten C., Lowe L., Tong S., Chen M.-H., Burns C., Bankamp B., Bellini W.J., Campagnoli R., Erdman D.D., Fouchier R., Frace M., Holloway B., Icenogle J.P., Ksiazek T.G., Liffick S., Limor J., Maher K., McCaustland K., Monroe S.S., Oberste M.S., Olsen-Rasmussen M., Osterhaus A.D.M.E., Pallansch M.A., Penaranda S., Peret T.C.T., Rollin P.E., Rota P.A., Tamin A.",
                "protein_xref_pubmed",
                "12730500",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "The genome sequence of the SARS-associated coronavirus.",
                "Science",
                "2003",
                "Jones S., Li Y., Marra M.A., McDonald H., Brooks-Wilson A., Cloutier A., Ward D., Yang G.S., Feldmann H., Stroher U., Freeman D., Siddiqui A., Petric M., Chan S.Y., Brunham R.C., Flick R., Griffith O.L., Khattra J., Astell C.R., Holt R.A., Upton C., Normand S., Robertson A.G., Gray M., Mayo M., Schein J.E., Grolla A., Asano J.K., Petrescu A.S., Smailus D.E., Stott J.M., Bernard K., Montgomery S.B., Plummer F., Andonov A., Artsob H., Barber S.A., Bastien N., Booth T.F., Bowness D., Butterfield Y.S.N., Coughlin S.M., Czub M., Drebot M., Fernando L., Garbutt M., Girn N., Jones S.J.M., Kabani A., Krajden M., Leach S.R., Meyers A., Pandoh P.K., Roper R.L., Skowronski D.M., Tipples G.A., Tyler S., Vogrig R., Watson B.",
                "protein_xref_pubmed",
                "12730501",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "Comparative full-length genome sequence analysis of 14 SARS coronavirus isolates and common mutations associated with putative origins of infection.",
                "Lancet",
                "2003",
                "Zhang T., Ren E.C., Lim L., Stanton L.W., Ruan Y., Liu E.T., Ng M.L., Vega V.B., Chiu K.P., Ng P., Wei C.L., Chan K.P., Chia J.-M., Leo S.Y., Ling A.E., Long P.M., Ng L.F.P., Oon L.E.L., Se Thoe S.Y., Thoreau H.",
                "protein_xref_pubmed",
                "12781537",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "Coronavirus genomic-sequence variations and the epidemiology of the severe acute respiratory syndrome.",
                "N. Engl. J. Med.",
                "2003",
                "Tsui S.K.W., Chim S.S.C., Lo Y.M.D.",
                "protein_xref_pubmed",
                "12853594",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "The complete genome sequence of severe acute respiratory syndrome coronavirus strain HKU-39849 (HK-39).",
                "Exp. Biol. Med.",
                "2003",
                "Li J., Zheng B., Wang C.Y., Guan Y., Chen J.D., Zeng F.Y., Wang P.Y., Chan C.W., Chan K.H., Chan M.N., Chow K.Y.C., Hon C.C.C., Hui R.K.H., Leung F.C., Li V.Y.Y., Peiris J.S.M., Poon L.L.M., Yuen K.Y.",
                "protein_xref_pubmed",
                "12876307",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "Mechanisms and enzymes involved in SARS coronavirus genome expression.",
                "J. Gen. Virol.",
                "2003",
                "Bayer S., Thiel V., Ziebuhr J., Gorbalenya A.E., Snijder E.J., Doerr H.W., Hertzig T., Ivanov K.A., Putics A., Rabenau H., Schelle B., Weissbrich B.",
                "protein_xref_pubmed",
                "12917450",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "Isolation and characterization of viruses related to the SARS coronavirus from animals in southern China.",
                "Science",
                "2003",
                "Guan Y., Guan Y.J., Lim W., Zheng B.J., Chan K.W., Liu X.L., Zhang L.J., Butt K.M., Cheung C.L., He Y.Q., Li P.H., Luo S.W., Peiris J.S.M., Poon L.L.M., Shortridge K.F., Wong K.L., Yuen K.Y., Zhuang Z.X.",
                "protein_xref_pubmed",
                "12958366",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "A novel severe acute respiratory syndrome coronavirus protein, U274, is transported to the cell surface and undergoes endocytosis.",
                "J. Virol.",
                "2004",
                "Hong W., Shen S., Tan T.H.P., Fielding B.C., Lim S.G., Tan Y.-J., Goh P.-Y., Ooi E.-E., Tan H.-C., Teng E.",
                "protein_xref_pubmed",
                "15194747",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P59596-1",
                "Subcellular localization and membrane association of SARS-CoV 3a protein.",
                "Virus Res.",
                "2005",
                "Chen J., Li J., Wang S., Yao Z., Zhao Z., Yang Z., Yuan X., Dong B., Chen B., Shan Y., Cong Y.",
                "protein_xref_pubmed",
                "15763150",
                "protein_xref_uniprotkb",
                "P59596"
            ],
            [
                "P0C6U8-1",
                "Characterization of a novel coronavirus associated with severe acute respiratory syndrome.",
                "Science",
                "2003",
                "Sanchez A., Chen Q., DeRisi J.L., Wang D., Guenther S., Nix W.A., Anderson L.J., Drosten C., Lowe L., Tong S., Chen M.-H., Burns C., Bankamp B., Bellini W.J., Campagnoli R., Erdman D.D., Fouchier R., Frace M., Holloway B., Icenogle J.P., Ksiazek T.G., Liffick S., Limor J., Maher K., McCaustland K., Monroe S.S., Oberste M.S., Olsen-Rasmussen M., Osterhaus A.D.M.E., Pallansch M.A., Penaranda S., Peret T.C.T., Rollin P.E., Rota P.A., Tamin A.",
                "protein_xref_pubmed",
                "12730500",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "The genome sequence of the SARS-associated coronavirus.",
                "Science",
                "2003",
                "Jones S., Li Y., Marra M.A., McDonald H., Brooks-Wilson A., Cloutier A., Ward D., Yang G.S., Feldmann H., Stroher U., Freeman D., Siddiqui A., Petric M., Chan S.Y., Brunham R.C., Flick R., Griffith O.L., Khattra J., Astell C.R., Holt R.A., Upton C., Normand S., Robertson A.G., Gray M., Mayo M., Schein J.E., Grolla A., Asano J.K., Petrescu A.S., Smailus D.E., Stott J.M., Bernard K., Montgomery S.B., Plummer F., Andonov A., Artsob H., Barber S.A., Bastien N., Booth T.F., Bowness D., Butterfield Y.S.N., Coughlin S.M., Czub M., Drebot M., Fernando L., Garbutt M., Girn N., Jones S.J.M., Kabani A., Krajden M., Leach S.R., Meyers A., Pandoh P.K., Roper R.L., Skowronski D.M., Tipples G.A., Tyler S., Vogrig R., Watson B.",
                "protein_xref_pubmed",
                "12730501",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Coronavirus main proteinase (3CLpro) structure: basis for design of anti-SARS drugs.",
                "Science",
                "2003",
                "Anand K., Hilgenfeld R., Mesters J.R., Ziebuhr J., Wadhwani P.",
                "protein_xref_pubmed",
                "12746549",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Comparative full-length genome sequence analysis of 14 SARS coronavirus isolates and common mutations associated with putative origins of infection.",
                "Lancet",
                "2003",
                "Zhang T., Ren E.C., Lim L., Stanton L.W., Ruan Y., Liu E.T., Ng M.L., Vega V.B., Chiu K.P., Ng P., Wei C.L., Chan K.P., Chia J.-M., Leo S.Y., Ling A.E., Long P.M., Ng L.F.P., Oon L.E.L., Se Thoe S.Y., Thoreau H.",
                "protein_xref_pubmed",
                "12781537",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Coronavirus genomic-sequence variations and the epidemiology of the severe acute respiratory syndrome.",
                "N. Engl. J. Med.",
                "2003",
                "Tsui S.K.W., Chim S.S.C., Lo Y.M.D.",
                "protein_xref_pubmed",
                "12853594",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "The complete genome sequence of severe acute respiratory syndrome coronavirus strain HKU-39849 (HK-39).",
                "Exp. Biol. Med.",
                "2003",
                "Li J., Zheng B., Wang C.Y., Guan Y., Chen J.D., Zeng F.Y., Wang P.Y., Chan C.W., Chan K.H., Chan M.N., Chow K.Y.C., Hon C.C.C., Hui R.K.H., Leung F.C., Li V.Y.Y., Peiris J.S.M., Poon L.L.M., Yuen K.Y.",
                "protein_xref_pubmed",
                "12876307",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Mechanisms and enzymes involved in SARS coronavirus genome expression.",
                "J. Gen. Virol.",
                "2003",
                "Bayer S., Thiel V., Ziebuhr J., Gorbalenya A.E., Snijder E.J., Doerr H.W., Hertzig T., Ivanov K.A., Putics A., Rabenau H., Schelle B., Weissbrich B.",
                "protein_xref_pubmed",
                "12917450",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Structural genomics of the SARS coronavirus: cloning, expression, crystallization and preliminary crystallographic study of the Nsp9 protein.",
                "Acta Crystallogr. D",
                "2003",
                "Ferron F., Campanacci V., Cambillau C., Egloff M.-P., Canard B., Longhi S., Snijder E.J., Bremond N., Dobbe J.C., Durousseau C., Rancurel C., Salomoni A., Tocque F.",
                "protein_xref_pubmed",
                "12925794",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Isolation and characterization of viruses related to the SARS coronavirus from animals in southern China.",
                "Science",
                "2003",
                "Guan Y., Guan Y.J., Lim W., Zheng B.J., Chan K.W., Liu X.L., Zhang L.J., Butt K.M., Cheung C.L., He Y.Q., Li P.H., Luo S.W., Peiris J.S.M., Poon L.L.M., Shortridge K.F., Wong K.L., Yuen K.Y., Zhuang Z.X.",
                "protein_xref_pubmed",
                "12958366",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Severe acute respiratory syndrome-associated coronavirus genotype and its characterization.",
                "Chin. Med. J.",
                "2003",
                "Chen S., Hu S., Li L., Li M., Lu Y., Wang S., Wang X., Wang Z., Yu Y., Zhang M., Zhang Y., Zhu H., Lu Q., Mei L., Yan J., Cheng S., Wu N., Bao Q., Yao J., Yao P., Weng J., Bo X., Wo J.",
                "protein_xref_pubmed",
                "14527350",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Phylogeny of the SARS coronavirus.",
                "Science",
                "2003",
                "Mora M., Abrignani S., Han J.H., Becker S., Censini S., Covacci A., Guidotti S., Klenk H.-D., Rappuoli R., Donati C., Doerr H.W., Eickmann M., Masignani V., Scarselli M., Song H.C., Stadler K.",
                "protein_xref_pubmed",
                "14645828",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "The nsp9 replicase protein of SARS-coronavirus, structure and functional insights.",
                "Structure",
                "2004",
                "Sutton G., Stuart D.I., Grimes J.M., Gilbert R., Carter L., Walter T., Davidson A., Walsh M., Owens R., Berrow N., Alderton D., Diprose J., Fry E., Nettleship J., Poon L.L.M., Sainsbury S., Siddell S.",
                "protein_xref_pubmed",
                "14962394",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "The severe acute respiratory syndrome-coronavirus replicative protein nsp9 is a single-stranded RNA-binding subunit unique in the RNA virus world.",
                "Proc. Natl. Acad. Sci. U.S.A.",
                "2004",
                "Ferron F., Campanacci V., Cambillau C., Egloff M.-P., Canard B., Longhi S., Gorbalenya A.E., Snijder E.J., Dutartre H., Rancurel C.",
                "protein_xref_pubmed",
                "15007178",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Identification and characterization of severe acute respiratory syndrome coronavirus replicase proteins.",
                "J. Virol.",
                "2004",
                "Lu X., Subbarao K., McAuliffe J., Denison M.R., Prentice E.",
                "protein_xref_pubmed",
                "15331731",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Identification of severe acute respiratory syndrome coronavirus replicase products and characterization of papain-like protease activity.",
                "J. Virol.",
                "2004",
                "Smith C.M., Baker S.C., Severson K.M., Bechill J., Harcourt B.H., Jukneliene D., Kanjanahaluethai A., Rota P.A.",
                "protein_xref_pubmed",
                "15564471",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Insights into SARS-CoV transcription and replication from the structure of the nsp7-nsp8 hexadecamer.",
                "Nat. Struct. Mol. Biol.",
                "2005",
                "Li X., Xu X., Sun F., Rao Z., Zhai Y., Pang H., Bartlam M.",
                "protein_xref_pubmed",
                "16228002",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Structural basis of severe acute respiratory syndrome coronavirus ADP-ribose-1''-phosphate dephosphorylation by a conserved domain of nsP3.",
                "Structure",
                "2005",
                "Stevens R.C., Kuhn P., Velasquez J., Subramanian V., Buchmeier M.J., Joseph J.S., Neuman B.W., Clayton T., Griffith M., Moy K., Saikatendu K.S.",
                "protein_xref_pubmed",
                "16271890",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Severe acute respiratory syndrome coronavirus papain-like protease: structure of a viral deubiquitinating enzyme.",
                "Proc. Natl. Acad. Sci. U.S.A.",
                "2006",
                "Stevens R.C., Baker S.C., Mesecar A.D., Santarsiero B.D., Saikatendu K.S., Barretto N., Ratia K.",
                "protein_xref_pubmed",
                "16581910",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Crystal structure of nonstructural protein 10 from the severe acute respiratory syndrome coronavirus reveals a novel fold with two zinc-binding motifs.",
                "J. Virol.",
                "2006",
                "Stevens R.C., Kuhn P., Velasquez J., Subramanian V., Brooun A., Buchmeier M.J., Joseph J.S., Neuman B.W., Griffith M., Moy K., Saikatendu K.S., Yadav M.K.",
                "protein_xref_pubmed",
                "16873246",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Dodecamer structure of severe acute respiratory syndrome coronavirus nonstructural protein nsp10.",
                "J. Virol.",
                "2006",
                "Joachimiak A., Yang H., Su D., Sun F., Rao Z., Zhai Y., Zhang X.C., Zhang R., Bartlam M., Lou Z.",
                "protein_xref_pubmed",
                "16873247",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "A second, non-canonical RNA-dependent RNA polymerase in SARS coronavirus.",
                "EMBO J.",
                "2006",
                "Ferron F., Guillemot J.-C., Egloff M.-P., Bourhis J.-M., Canard B., Gorbalenya A.E., Imbert I., Bussetta C., Coutard B.",
                "protein_xref_pubmed",
                "17024178",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Novel beta-barrel fold in the nuclear magnetic resonance structure of the replicase nonstructural protein 1 from the severe acute respiratory syndrome coronavirus.",
                "J. Virol.",
                "2007",
                "Wuthrich K., Herrmann T., Johnson M.A., Geralt M., Almeida M.S.",
                "protein_xref_pubmed",
                "17202208",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Selectivity in ISG15 and ubiquitin recognition by the SARS coronavirus papain-like protease.",
                "Arch. Biochem. Biophys.",
                "2007",
                "Lindner H.A., Menard R., Qi H., Ziomek E., Lachance P., Lytvyn V.",
                "protein_xref_pubmed",
                "17692280",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Severe acute respiratory syndrome coronavirus papain-like protease ubiquitin-like domain and catalytic domain regulate antagonism of IRF3 and NF-kappaB signaling.",
                "J. Virol.",
                "2009",
                "Mesecar A.D., Johnston R.E., Baric R.S., Frieman M., Ratia K.",
                "protein_xref_pubmed",
                "19369340",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "SARS coronavirus nsp1 protein induces template-dependent endonucleolytic cleavage of mRNAs: viral mRNAs are resistant to nsp1-induced RNA cleavage.",
                "PLoS Pathog.",
                "2011",
                "Huang C., Makino S., Narayanan K., Semler B.L., Rozovics J.M., Lokugamage K.G.",
                "protein_xref_pubmed",
                "22174690",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P0C6U8-1",
                "Severe acute respiratory syndrome coronavirus protein nsp1 is a novel eukaryotic translation inhibitor that represses multiple steps of translation initiation.",
                "J. Virol.",
                "2012",
                "Huang C., Makino S., Narayanan K., Lokugamage K.G.",
                "protein_xref_pubmed",
                "23035226",
                "protein_xref_uniprotkb",
                "P0C6U8"
            ],
            [
                "P59594-1",
                "Angiotensin-converting enzyme 2 is a functional receptor for the SARS coronavirus.",
                "Nature",
                "2003",
                "Li W., Moore M.J., Berne M.A., Choe H., Farzan M., Greenough T.C., Luzuriaga K., Somasundaran M., Sui J., Sullivan J.L., Vasilieva N., Wong S.-K.",
                "protein_xref_pubmed",
                "14647384",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Receptor and viral determinants of SARS-coronavirus adaptation to human ACE2.",
                "EMBO J.",
                "2005",
                "Zhang C., Li W., He Y., Moore M.J., Choe H., Farzan M., Guan Y., Huang I.-C., Kuhn J.H., Luo S., Marasco W.A., Murakami A., Sui J., Vasilieva N., Wong S.-K., Xu K.",
                "protein_xref_pubmed",
                "15791205",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "CD209L (L-SIGN) is a receptor for severe acute respiratory syndrome coronavirus.",
                "Proc. Natl. Acad. Sci. U.S.A.",
                "2004",
                "Mason R.J., Holmes K.V., Wentworth D.E., Achenbach J.E., Ambrosino D.M., Babcock G.J., Demartini J.C., Gillim-Ross L., Hemmila E.M., Jeffers S.A., Thackray L.B., Thomas W.D. Jr., Tusell S.M., Young M.D.",
                "protein_xref_pubmed",
                "15496474",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Characterization of a novel coronavirus associated with severe acute respiratory syndrome.",
                "Science",
                "2003",
                "Sanchez A., Chen Q., DeRisi J.L., Wang D., Guenther S., Nix W.A., Anderson L.J., Drosten C., Lowe L., Tong S., Chen M.-H., Burns C., Bankamp B., Bellini W.J., Campagnoli R., Erdman D.D., Fouchier R., Frace M., Holloway B., Icenogle J.P., Ksiazek T.G., Liffick S., Limor J., Maher K., McCaustland K., Monroe S.S., Oberste M.S., Olsen-Rasmussen M., Osterhaus A.D.M.E., Pallansch M.A., Penaranda S., Peret T.C.T., Rollin P.E., Rota P.A., Tamin A.",
                "protein_xref_pubmed",
                "12730500",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "The genome sequence of the SARS-associated coronavirus.",
                "Science",
                "2003",
                "Jones S., Li Y., Marra M.A., McDonald H., Brooks-Wilson A., Cloutier A., Ward D., Yang G.S., Feldmann H., Stroher U., Freeman D., Siddiqui A., Petric M., Chan S.Y., Brunham R.C., Flick R., Griffith O.L., Khattra J., Astell C.R., Holt R.A., Upton C., Normand S., Robertson A.G., Gray M., Mayo M., Schein J.E., Grolla A., Asano J.K., Petrescu A.S., Smailus D.E., Stott J.M., Bernard K., Montgomery S.B., Plummer F., Andonov A., Artsob H., Barber S.A., Bastien N., Booth T.F., Bowness D., Butterfield Y.S.N., Coughlin S.M., Czub M., Drebot M., Fernando L., Garbutt M., Girn N., Jones S.J.M., Kabani A., Krajden M., Leach S.R., Meyers A., Pandoh P.K., Roper R.L., Skowronski D.M., Tipples G.A., Tyler S., Vogrig R., Watson B.",
                "protein_xref_pubmed",
                "12730501",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Comparative full-length genome sequence analysis of 14 SARS coronavirus isolates and common mutations associated with putative origins of infection.",
                "Lancet",
                "2003",
                "Zhang T., Ren E.C., Lim L., Stanton L.W., Ruan Y., Liu E.T., Ng M.L., Vega V.B., Chiu K.P., Ng P., Wei C.L., Chan K.P., Chia J.-M., Leo S.Y., Ling A.E., Long P.M., Ng L.F.P., Oon L.E.L., Se Thoe S.Y., Thoreau H.",
                "protein_xref_pubmed",
                "12781537",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Coronavirus genomic-sequence variations and the epidemiology of the severe acute respiratory syndrome.",
                "N. Engl. J. Med.",
                "2003",
                "Tsui S.K.W., Chim S.S.C., Lo Y.M.D.",
                "protein_xref_pubmed",
                "12853594",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "The complete genome sequence of severe acute respiratory syndrome coronavirus strain HKU-39849 (HK-39).",
                "Exp. Biol. Med.",
                "2003",
                "Li J., Zheng B., Wang C.Y., Guan Y., Chen J.D., Zeng F.Y., Wang P.Y., Chan C.W., Chan K.H., Chan M.N., Chow K.Y.C., Hon C.C.C., Hui R.K.H., Leung F.C., Li V.Y.Y., Peiris J.S.M., Poon L.L.M., Yuen K.Y.",
                "protein_xref_pubmed",
                "12876307",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Mechanisms and enzymes involved in SARS coronavirus genome expression.",
                "J. Gen. Virol.",
                "2003",
                "Bayer S., Thiel V., Ziebuhr J., Gorbalenya A.E., Snijder E.J., Doerr H.W., Hertzig T., Ivanov K.A., Putics A., Rabenau H., Schelle B., Weissbrich B.",
                "protein_xref_pubmed",
                "12917450",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Isolation and characterization of viruses related to the SARS coronavirus from animals in southern China.",
                "Science",
                "2003",
                "Guan Y., Guan Y.J., Lim W., Zheng B.J., Chan K.W., Liu X.L., Zhang L.J., Butt K.M., Cheung C.L., He Y.Q., Li P.H., Luo S.W., Peiris J.S.M., Poon L.L.M., Shortridge K.F., Wong K.L., Yuen K.Y., Zhuang Z.X.",
                "protein_xref_pubmed",
                "12958366",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Molecular modelling of S1 and S2 subunits of SARS coronavirus spike glycoprotein.",
                "Biochem. Biophys. Res. Commun.",
                "2003",
                "Anselmi F., Bernini A., Causarono V., Chiellini S., Ciutti A., Finetti F., Menciassi N., Niccolai N., Prischi F., Spiga O.",
                "protein_xref_pubmed",
                "14511651",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "A 193-amino acid fragment of the SARS coronavirus S protein efficiently binds angiotensin-converting enzyme 2.",
                "J. Biol. Chem.",
                "2004",
                "Li W., Moore M.J., Choe H., Farzan M., Wong S.K.",
                "protein_xref_pubmed",
                "14670965",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "A novel severe acute respiratory syndrome coronavirus protein, U274, is transported to the cell surface and undergoes endocytosis.",
                "J. Virol.",
                "2004",
                "Hong W., Shen S., Tan T.H.P., Fielding B.C., Lim S.G., Tan Y.-J., Goh P.-Y., Ooi E.-E., Tan H.-C., Teng E.",
                "protein_xref_pubmed",
                "15194747",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Oligomerization of the SARS-CoV S glycoprotein: dimerization of the N-terminus and trimerization of the ectodomain.",
                "Biochem. Biophys. Res. Commun.",
                "2004",
                "Dimitrov D.S., Feng Y., Xiao X., Chakraborti S.",
                "protein_xref_pubmed",
                "15313178",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Crystal structure of severe acute respiratory syndrome coronavirus spike protein fusion core.",
                "J. Biol. Chem.",
                "2004",
                "Liu Y., Xu Y., Gao G.F., Rao Z., Pang H., Lou Z., Tien P.",
                "protein_xref_pubmed",
                "15345712",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "The spike protein of severe acute respiratory syndrome (SARS) is cleaved in virus infected Vero-E6 cells.",
                "Cell Res.",
                "2004",
                "Li L., Lin Y., Tian L., Wang X.Y., Yang S., Yu H., Shen X., Wu J.R., Pei G., Sun B., Zhu X.L., Xie Y.H., Wu Y.D., Yang R.F., Dai E.H., Gan X.Q., Ji Y.Y., Jiang H.L., Jiang W.H., Lin G.M., Ma Z.H., Shang B., Wu X.D.",
                "protein_xref_pubmed",
                "15450134",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Characterization of the heptad repeat regions, HR1 and HR2, and design of a fusion core structure model of the spike protein from severe acute respiratory syndrome (SARS) coronavirus.",
                "Biochemistry",
                "2004",
                "Li X., Liu Y., Bell J.I., Xu Y., Gao G.F., Bai Z., Rao Z., Zhu J., Ni L., Pang H., Liu Y.', Qin L., Su N., Lou Z., Yuan F., Cole D.K., Tien P.",
                "protein_xref_pubmed",
                "15518555",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Structure of a proteolytically resistant core from the severe acute respiratory syndrome coronavirus S2 fusion protein.",
                "Proc. Natl. Acad. Sci. U.S.A.",
                "2004",
                "Ingallinella P., Bianchi E., Carfi A., Bruckmann C., Pessi A., Supekar V.M.",
                "protein_xref_pubmed",
                "15604146",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Cross-host evolution of severe acute respiratory syndrome coronavirus in palm civet and human.",
                "Proc. Natl. Acad. Sci. U.S.A.",
                "2005",
                "Anderson L., Chen F., Gao Y., Li H., Tang H., Kong X., Wang M., Chen J.D., Lin J.Y., Liang G., Fang L., Liu Y.F., Zhou D.H., Cheng F., Liao M., Zheng K., Jiang L.Y., Chen S.J., Xiang H., Li L.H., Du L., Yu X.J., Wang S.Y., Hao P., Zhao G.P., Ren Y.Q., Danchin A., Liang W.J., Tong S., Wu C.I., Fontanet A., Xu R.H., Zheng H.J., Bernini A., Chen Q.X., Chern S.W., Di B., Gao Y.W., Guo Z.M., He J.F., He L.J., He W.Z., Lei L.C., Li Y.X., Luo H.M., Manuguerra J.C., Niccolai N., Pan C.M., Pan H.Y., Qin P.Z., Song H.D., Spiga O., Tu C.C., Wu X.W., Xuan H., Yu Y.D., Zhang G.W., Zheng H.Y., Zhou H.Q.",
                "protein_xref_pubmed",
                "15695582",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Differential maturation and subcellular localization of severe acute respiratory syndrome coronavirus surface proteins S, M and E.",
                "J. Gen. Virol.",
                "2005",
                "Chan C., Kam J., Chu K., Nal B., Altmeyer R., Crescenzo-Chaigne B., Escriou N., Kien F., Siu L., Staropoli I., Tse J., Yuen K.Y., van der Werf S.",
                "protein_xref_pubmed",
                "15831954",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Identification and characterization of the putative fusion peptide of the severe acute respiratory syndrome-associated coronavirus spike protein.",
                "J. Virol.",
                "2005",
                "Wimley W.C., Gallaher W.R., Garry R.F., Rausch J.M., Sainz B. Jr.",
                "protein_xref_pubmed",
                "15890958",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Inhibitors of cathepsin L prevent severe acute respiratory syndrome coronavirus entry.",
                "Proc. Natl. Acad. Sci. U.S.A.",
                "2005",
                "Bates P., Rennekamp A.J., Simmons G., Reeves J.D., Diamond S.L., Gosalia D.N.",
                "protein_xref_pubmed",
                "16081529",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Structure of SARS coronavirus spike receptor-binding domain complexed with receptor.",
                "Science",
                "2005",
                "Li W., Li F., Farzan M., Harrison S.C.",
                "protein_xref_pubmed",
                "16166518",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Furin cleavage of the SARS coronavirus spike glycoprotein enhances cell-cell fusion but does not affect virion entry.",
                "Virology",
                "2006",
                "Nunberg J.H., Follis K.E., York J.",
                "protein_xref_pubmed",
                "16519916",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Structures and polymorphic interactions of two heptad-repeat regions of the SARS virus S2 protein.",
                "Structure",
                "2006",
                "Liu J., Lu M., Deng Y., Zheng Q., Yong W.",
                "protein_xref_pubmed",
                "16698550",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Severe acute respiratory syndrome coronavirus 7a accessory protein is a viral structural protein.",
                "J. Virol.",
                "2006",
                "Huang C., Makino S., Ito N., Tseng C.-T.K.",
                "protein_xref_pubmed",
                "16840309",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Palmitoylation of the cysteine-rich endodomain of the SARS-coronavirus spike glycoprotein is important for spike-mediated cell fusion.",
                "Virology",
                "2007",
                "Farzan M., Chouljenko V.N., Kousoulas K.G., Knipe D.M., Colgrove R., Iyer A., Petit C.M.",
                "protein_xref_pubmed",
                "17134730",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "The cytoplasmic tail of the severe acute respiratory syndrome coronavirus spike protein contains a novel endoplasmic reticulum retrieval signal that binds COPI and promotes interaction with membrane protein.",
                "J. Virol.",
                "2007",
                "Li J., Machamer C.E., McBride C.E.",
                "protein_xref_pubmed",
                "17166901",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "Activation of the SARS coronavirus spike protein via sequential proteolytic cleavage at two distinct sites.",
                "Proc. Natl. Acad. Sci. U.S.A.",
                "2009",
                "Belouzard S., Chu V.C., Whittaker G.R.",
                "protein_xref_pubmed",
                "19321428",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59594-1",
                "The SARS coronavirus E protein interacts with PALS1 and alters tight junction formation and epithelial morphogenesis.",
                "Mol. Biol. Cell",
                "2010",
                "Margolis B., Bruzzone R., Chan W.L., Liu C.J., Nal B., Peiris J.S., Schlueter M.A., Siu Y.L., Teoh K.T.",
                "protein_xref_pubmed",
                "20861307",
                "protein_xref_uniprotkb",
                "P59594"
            ],
            [
                "P59595-1",
                "High-resolution structure of HLA-A*1101 in complex with SARS nucleocapsid peptide.",
                "Acta Crystallogr. D",
                "2005",
                "Blicher T., Buus S., Gajhede M., Kastrup J.S.",
                "protein_xref_pubmed",
                "16041067",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "Novel immunodominant peptide presentation strategy: a featured HLA-A*2402-restricted cytotoxic T-lymphocyte epitope stabilized by intrachain hydrogen bonds from severe acute respiratory syndrome coronavirus nucleocapsid protein.",
                "J. Virol.",
                "2010",
                "Gao F., Liu J., Xie J., Gao G.F., Iwamoto A., Li T., Qi J., Wu P., Vavricka C.J., Kawana-Tachikawa A.",
                "protein_xref_pubmed",
                "20844028",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "Characterization of a novel coronavirus associated with severe acute respiratory syndrome.",
                "Science",
                "2003",
                "Sanchez A., Chen Q., DeRisi J.L., Wang D., Guenther S., Nix W.A., Anderson L.J., Drosten C., Lowe L., Tong S., Chen M.-H., Burns C., Bankamp B., Bellini W.J., Campagnoli R., Erdman D.D., Fouchier R., Frace M., Holloway B., Icenogle J.P., Ksiazek T.G., Liffick S., Limor J., Maher K., McCaustland K., Monroe S.S., Oberste M.S., Olsen-Rasmussen M., Osterhaus A.D.M.E., Pallansch M.A., Penaranda S., Peret T.C.T., Rollin P.E., Rota P.A., Tamin A.",
                "protein_xref_pubmed",
                "12730500",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "The genome sequence of the SARS-associated coronavirus.",
                "Science",
                "2003",
                "Jones S., Li Y., Marra M.A., McDonald H., Brooks-Wilson A., Cloutier A., Ward D., Yang G.S., Feldmann H., Stroher U., Freeman D., Siddiqui A., Petric M., Chan S.Y., Brunham R.C., Flick R., Griffith O.L., Khattra J., Astell C.R., Holt R.A., Upton C., Normand S., Robertson A.G., Gray M., Mayo M., Schein J.E., Grolla A., Asano J.K., Petrescu A.S., Smailus D.E., Stott J.M., Bernard K., Montgomery S.B., Plummer F., Andonov A., Artsob H., Barber S.A., Bastien N., Booth T.F., Bowness D., Butterfield Y.S.N., Coughlin S.M., Czub M., Drebot M., Fernando L., Garbutt M., Girn N., Jones S.J.M., Kabani A., Krajden M., Leach S.R., Meyers A., Pandoh P.K., Roper R.L., Skowronski D.M., Tipples G.A., Tyler S., Vogrig R., Watson B.",
                "protein_xref_pubmed",
                "12730501",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "Comparative full-length genome sequence analysis of 14 SARS coronavirus isolates and common mutations associated with putative origins of infection.",
                "Lancet",
                "2003",
                "Zhang T., Ren E.C., Lim L., Stanton L.W., Ruan Y., Liu E.T., Ng M.L., Vega V.B., Chiu K.P., Ng P., Wei C.L., Chan K.P., Chia J.-M., Leo S.Y., Ling A.E., Long P.M., Ng L.F.P., Oon L.E.L., Se Thoe S.Y., Thoreau H.",
                "protein_xref_pubmed",
                "12781537",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "Coronavirus genomic-sequence variations and the epidemiology of the severe acute respiratory syndrome.",
                "N. Engl. J. Med.",
                "2003",
                "Tsui S.K.W., Chim S.S.C., Lo Y.M.D.",
                "protein_xref_pubmed",
                "12853594",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "The complete genome sequence of severe acute respiratory syndrome coronavirus strain HKU-39849 (HK-39).",
                "Exp. Biol. Med.",
                "2003",
                "Li J., Zheng B., Wang C.Y., Guan Y., Chen J.D., Zeng F.Y., Wang P.Y., Chan C.W., Chan K.H., Chan M.N., Chow K.Y.C., Hon C.C.C., Hui R.K.H., Leung F.C., Li V.Y.Y., Peiris J.S.M., Poon L.L.M., Yuen K.Y.",
                "protein_xref_pubmed",
                "12876307",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "Mechanisms and enzymes involved in SARS coronavirus genome expression.",
                "J. Gen. Virol.",
                "2003",
                "Bayer S., Thiel V., Ziebuhr J., Gorbalenya A.E., Snijder E.J., Doerr H.W., Hertzig T., Ivanov K.A., Putics A., Rabenau H., Schelle B., Weissbrich B.",
                "protein_xref_pubmed",
                "12917450",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "Isolation and characterization of viruses related to the SARS coronavirus from animals in southern China.",
                "Science",
                "2003",
                "Guan Y., Guan Y.J., Lim W., Zheng B.J., Chan K.W., Liu X.L., Zhang L.J., Butt K.M., Cheung C.L., He Y.Q., Li P.H., Luo S.W., Peiris J.S.M., Poon L.L.M., Shortridge K.F., Wong K.L., Yuen K.Y., Zhuang Z.X.",
                "protein_xref_pubmed",
                "12958366",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "Severe acute respiratory syndrome-associated coronavirus genotype and its characterization.",
                "Chin. Med. J.",
                "2003",
                "Chen S., Hu S., Li L., Li M., Lu Y., Wang S., Wang X., Wang Z., Yu Y., Zhang M., Zhang Y., Zhu H., Lu Q., Mei L., Yan J., Cheng S., Wu N., Bao Q., Yao J., Yao P., Weng J., Bo X., Wo J.",
                "protein_xref_pubmed",
                "14527350",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "Structure of the N-terminal RNA-binding domain of the SARS CoV nucleocapsid protein.",
                "Biochemistry",
                "2004",
                "Huang Q., Yu L., Liu Z., Xu N., Fesik S.W., Mack J., Olejniczak E.T., Petros A.M., Gunasekera A., Hajduk P.",
                "protein_xref_pubmed",
                "15147189",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "Characterization of protein-protein interactions between the nucleocapsid protein and membrane protein of the SARS coronavirus.",
                "Virus Res.",
                "2004",
                "Cao J., Li X., Li Y., Plummer F.A., Baker L., He R., Ballantine M., Feldmann H., Cutts T., Andonov A., Bastien N., Booth T.F., Dobie F., Leeson A., Strocher U., Theriault S., Tyler S.",
                "protein_xref_pubmed",
                "15351485",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "The nucleocapsid protein of SARS coronavirus has a high binding affinity to the human cellular heterogeneous nuclear ribonucleoprotein A1.",
                "FEBS Lett.",
                "2005",
                "Chen J., Jiang H., Chen Q., Luo H., Chen K., Shen X.",
                "protein_xref_pubmed",
                "15862300",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "Crystal structure of the severe acute respiratory syndrome (SARS) coronavirus nucleocapsid protein dimerization domain reveals evolutionary linkage between corona- and arteriviridae.",
                "J. Biol. Chem.",
                "2006",
                "Chen J., Zhang J., Oldham M.L., Yu I.M.",
                "protein_xref_pubmed",
                "16627473",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "The intracellular sites of early replication and budding of SARS-coronavirus.",
                "Virology",
                "2007",
                "Garcia-Sastre A., Reichelt M., Weber F., Martinez-Sobrido L., Kochs G., Stertz S., Kuri T., Spiegel M.",
                "protein_xref_pubmed",
                "17210170",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "Ribonucleocapsid formation of severe acute respiratory syndrome coronavirus through molecular action of the N-terminal domain of N protein.",
                "J. Virol.",
                "2007",
                "Stevens R.C., Kuhn P., Subramanian V., Buchmeier M.J., Joseph J.S., Neuman B.W., Saikatendu K.S.",
                "protein_xref_pubmed",
                "17229691",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "Structure of the SARS coronavirus nucleocapsid protein RNA-binding dimerization domain suggests a mechanism for helical packaging of viral RNA.",
                "J. Mol. Biol.",
                "2007",
                "Huang T.H., Chen C.Y., Hsiao C.D., Sue S.C., Chang C.K., Chang Y.W., Bai H.I., Riang L.",
                "protein_xref_pubmed",
                "17379242",
                "protein_xref_uniprotkb",
                "P59595"
            ],
            [
                "P59595-1",
                "Solution structure of the c-terminal dimerization domain of SARS coronavirus nucleocapsid protein solved by the SAIL-NMR method.",
                "J. Mol. Biol.",
                "2008",
                "Takeda M., Ikeya T., Huang T.H., Guentert P., Kainosho M., Hsu Y.L., Chang Y.H., Chang C.K.",
                "protein_xref_pubmed",
                "18561946",
                "protein_xref_uniprotkb",
                "P59595"
            ]
        ]
    },
    "readme": "Name\n   - SARS-CoV1 Protein Citations (UniProtKB)\n\nVersion\n   - 1.7.10\n\nCreated on\n  - 2020-04-03T11:46:41.584409\n\nModified on\n   - 2020-04-09T18:40:17.006737\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-1) Protein Citations dataset contains publication information for sarscov1 [taxid:694009] 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-human-sars-coronavirus.nt\n      URI: https://data.glygen.org/ln2wwwdata/source/uniprot-proteome-human-sars-coronavirus.nt\n      Name: sarscov1_protein_masterlist.csv\n      URI: https://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_masterlist.csv\n   Output Subdomain\n      Name: sarscov1_protein_citations_uniprotkb.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_citations_uniprotkb.csv\n      Name: sarscov1_protein_citations_uniprotkb.stat.csv\n      URI: http://data.glygen.org/ln2wwwdata/reviewed/sarscov1_protein_citations_uniprotkb.stat.csv\n\nFields\n      Name: \"uniprotkb_canonical_ac\"\n     Description: \"\"\n      Unique Values: \"15\"\n      Name: \"xref_id\"\n     Description: \"ID of the X-ref\"\n      Unique Values: \"108\"\n      Name: \"title\"\n     Description: \"Title of the published article in the journal\"\n      Unique Values: \"108\"\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: \"15\"\n      Name: \"journal_name\"\n     Description: \"The name of the journal in which the article is published\"\n      Unique Values: \"34\"\n      Name: \"authors\"\n     Description: \"NA\"\n      Unique Values: \"108\"\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: \"12\"\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/sarscov1_protein_citations_uniprotkb.csv"
}
