{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T02:02:08Z","timestamp":1777168928149,"version":"3.51.4"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2017,3,7]],"date-time":"2017-03-07T00:00:00Z","timestamp":1488844800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"EU Horizon 2020 project ExCAPE","award":["671555"],"award-info":[{"award-number":["671555"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1186\/s13321-017-0203-5","type":"journal-article","created":{"date-parts":[[2017,3,7]],"date-time":"2017-03-07T09:49:30Z","timestamp":1488880170000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":144,"title":["ExCAPE-DB: an integrated large scale dataset facilitating Big Data analysis in chemogenomics"],"prefix":"10.1186","volume":"9","author":[{"given":"Jiangming","family":"Sun","sequence":"first","affiliation":[]},{"given":"Nina","family":"Jeliazkova","sequence":"additional","affiliation":[]},{"given":"Vladimir","family":"Chupakhin","sequence":"additional","affiliation":[]},{"given":"Jose-Felipe","family":"Golib-Dzib","sequence":"additional","affiliation":[]},{"given":"Ola","family":"Engkvist","sequence":"additional","affiliation":[]},{"given":"Lars","family":"Carlsson","sequence":"additional","affiliation":[]},{"given":"J\u00f6rg","family":"Wegner","sequence":"additional","affiliation":[]},{"given":"Hugo","family":"Ceulemans","sequence":"additional","affiliation":[]},{"given":"Ivan","family":"Georgiev","sequence":"additional","affiliation":[]},{"given":"Vedrin","family":"Jeliazkov","sequence":"additional","affiliation":[]},{"given":"Nikolay","family":"Kochev","sequence":"additional","affiliation":[]},{"given":"Thomas J.","family":"Ashby","sequence":"additional","affiliation":[]},{"given":"Hongming","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,3,7]]},"reference":[{"key":"203_CR1","doi-asserted-by":"publisher","first-page":"1260419","DOI":"10.1126\/science.1260419","volume":"347","author":"M Uhlen","year":"2015","unstructured":"Uhlen M, Fagerberg L, Hallstrom BM, Lindskog C, Oksvold P, Mardinoglu A et al (2015) Proteomics. Tissue-based map of the human proteome. Science 347:1260419","journal-title":"Science"},{"key":"203_CR2","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1038\/ng.2764","volume":"45","author":"JN Weinstein","year":"2013","unstructured":"Cancer Genome Atlas Research Network, Weinstein JN, Collisson EA, Mills GB, Shaw KR, Ozenberger BA et al (2013) The cancer genome atlas pan-cancer analysis project. Nat Genet 45:1113\u20131120","journal-title":"Nat Genet"},{"key":"203_CR3","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1016\/j.drudis.2011.10.005","volume":"16","author":"S Muresan","year":"2011","unstructured":"Muresan S, Petrov P, Southan C, Kjellberg MJ, Kogej T, Tyrchan C et al (2011) Making every SAR point count: the development of chemistry connect for the large-scale integration of structure and bioactivity data. Drug Discov Today 16:1019\u20131030","journal-title":"Drug Discov Today"},{"key":"203_CR4","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1038\/nrg1317","volume":"5","author":"M Bredel","year":"2004","unstructured":"Bredel M, Jacoby E (2004) Chemogenomics: an emerging strategy for rapid target and drug discovery. Nat Rev Genet 5:262\u2013275","journal-title":"Nat Rev Genet"},{"key":"203_CR5","doi-asserted-by":"publisher","first-page":"D1075","DOI":"10.1093\/nar\/gkt978","volume":"42","author":"Y Wang","year":"2014","unstructured":"Wang Y, Suzek T, Zhang J, Wang J, He S, Cheng T et al (2014) PubChem BioAssay: 2014 update. Nucleic Acids Res 42:D1075\u2013D1082","journal-title":"Nucleic Acids Res"},{"key":"203_CR6","doi-asserted-by":"publisher","first-page":"D1045","DOI":"10.1093\/nar\/gkv1072","volume":"44","author":"MK Gilson","year":"2016","unstructured":"Gilson MK, Liu T, Baitaluk M, Nicola G, Hwang L, Chong J (2016) BindingDB in 2015: a public database for medicinal chemistry, computational chemistry and systems pharmacology. Nucleic Acids Res 44:D1045\u2013D1053","journal-title":"Nucleic Acids Res"},{"key":"203_CR7","doi-asserted-by":"publisher","first-page":"D1083","DOI":"10.1093\/nar\/gkt1031","volume":"42","author":"AP Bento","year":"2014","unstructured":"Bento AP, Gaulton A, Hersey A, Bellis LJ, Chambers J, Davies M et al (2014) The ChEMBL bioactivity database: an update. Nucleic Acids Res 42:D1083\u2013D1090","journal-title":"Nucleic Acids Res"},{"key":"203_CR8","doi-asserted-by":"publisher","first-page":"D1202","DOI":"10.1093\/nar\/gkv951","volume":"44","author":"S Kim","year":"2016","unstructured":"Kim S, Thiessen PA, Bolton EE, Chen J, Fu G, Gindulyte A et al (2016) PubChem substance and compound databases. Nucleic Acids Res 44:D1202\u2013D1213","journal-title":"Nucleic Acids Res"},{"key":"203_CR9","doi-asserted-by":"crossref","unstructured":"Olah M, Rad R, Ostopovici L, Bora A, Hadaruga N, Hadaruga D et al (2007) WOMBAT and WOMBAT-PK: bioactivity databases for lead and drug discovery. In: Schreiber SL, Kapoor TM, Wess G (eds) Chemical biology: from small molecules to systems biology and drug design. Wiley-VCH, pp 760\u2013786","DOI":"10.1002\/9783527619375.ch13b"},{"key":"203_CR10","doi-asserted-by":"publisher","first-page":"bat044","DOI":"10.1093\/database\/bat044","volume":"2013","author":"SL Mathias","year":"2013","unstructured":"Mathias SL, Hines-Kay J, Yang JJ, Zahoransky-Kohalmi G, Bologa CG, Ursu O et al (2013) The CARLSBAD database: a confederated database of chemical bioactivities. Database 2013:bat044","journal-title":"Database"},{"key":"203_CR11","first-page":"60","volume-title":"SCiFinder: information at the desktop for scientists. Online","author":"J Williams","year":"1995","unstructured":"Williams J (1995) SCiFinder: information at the desktop for scientists. Online. ETATS-UNIS, Wilton, CT, pp 60\u201366"},{"key":"203_CR12","unstructured":"GOSTAR database release 2016. http:\/\/www.gostardb.com\/ . Accessed 1 Oct 2016"},{"key":"203_CR13","unstructured":"Reaxys database. http:\/\/www.reaxys.com . Accessed 1 Oct 2016"},{"key":"203_CR14","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1186\/s13321-015-0110-6","volume":"7","author":"A Lusci","year":"2015","unstructured":"Lusci A, Browning M, Fooshee D, Swamidass J, Baldi P (2015) Accurate and efficient target prediction using a potency-sensitive influence-relevance voter. J Cheminform 7:63","journal-title":"J Cheminform"},{"key":"203_CR15","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/s13321-015-0098-y","volume":"7","author":"LH Mervin","year":"2015","unstructured":"Mervin LH, Afzal AM, Drakakis G, Lewis R, Engkvist O, Bender A (2015) Target prediction utilising negative bioactivity data covering large chemical space. J Cheminform 7:51","journal-title":"J Cheminform"},{"key":"203_CR16","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1021\/acs.jcim.5b00498","volume":"56","author":"KY Helal","year":"2016","unstructured":"Helal KY, Maciejewski M, Gregori-Puigjane E, Glick M, Wassermann AM (2016) Public domain HTS fingerprints: design and evaluation of compound bioactivity profiles from PubChem\u2019s bioassay repository. J Chem Inf Model 56:390\u2013398","journal-title":"J Chem Inf Model"},{"key":"203_CR17","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1038\/nchembio.1881","volume":"11","author":"D Fourches","year":"2015","unstructured":"Fourches D, Muratov E, Tropsha A (2015) Curation of chemogenomics data. Nat Chem Biol 11:535","journal-title":"Nat Chem Biol"},{"key":"203_CR18","unstructured":"ExCAPE project website. http:\/\/www.excape-h2020.eu . Accessed 1 Oct 2016"},{"key":"203_CR19","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/1758-2946-3-18","volume":"3","author":"N Jeliazkova","year":"2011","unstructured":"Jeliazkova N, Jeliazkov V (2011) AMBIT RESTful web services: an implementation of the OpenTox application programming interface. J Cheminform 3:18","journal-title":"J Cheminform"},{"key":"203_CR20","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1002\/minf.201200133","volume":"32","author":"NT Kochev","year":"2013","unstructured":"Kochev NT, Paskaleva VH, Jeliazkova N (2013) Ambit-Tautomer: an open source tool for tautomer generation. Mol Inform 32:481\u2013504","journal-title":"Mol Inform"},{"key":"203_CR21","doi-asserted-by":"crossref","first-page":"707","DOI":"10.1002\/minf.201100028","volume":"30","author":"N Jeliazkova","year":"2011","unstructured":"Jeliazkova N, Kochev N (2011) AMBIT-SMARTS: efficient searching of chemical structures and fragments. Mol Inform 30:707\u2013720","journal-title":"Mol Inform"},{"key":"203_CR22","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1021\/ci025584y","volume":"43","author":"C Steinbeck","year":"2003","unstructured":"Steinbeck C, Han Y, Kuhn S, Horlacher O, Luttmann E, Willighagen E (2003) The chemistry development kit (CDK): an open-source java library for chemo- and bio-informatics. J Chem Inf Comput Sci 43:493\u2013500","journal-title":"J Chem Inf Comput Sci"},{"key":"203_CR23","doi-asserted-by":"publisher","first-page":"2111","DOI":"10.2174\/138161206777585274","volume":"12","author":"C Steinbeck","year":"2006","unstructured":"Steinbeck C, Hoppe C, Kuhn S, Floris M, Guha R, Willighagen EL (2006) Recent developments of the chemistry development kit (CDK)\u2014an open-source java library for chemo- and bio-informatics. Curr Pharm Des 12:2111\u20132120","journal-title":"Curr Pharm Des"},{"key":"203_CR24","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1186\/s13321-015-0068-4","volume":"7","author":"SR Heller","year":"2015","unstructured":"Heller SR, Mcnaught A, Pletnev I, Stein S, Tchekhovskoi D (2015) InChI, the IUPAC international chemical identifier. J Cheminform 7:23","journal-title":"J Cheminform"},{"key":"203_CR25","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","volume":"28","author":"D Weininger","year":"1988","unstructured":"Weininger D (1988) SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules. J Chem Inf Comput Sci 28:31\u201336","journal-title":"J Chem Inf Comput Sci"},{"key":"203_CR26","unstructured":"SMIRKS web site. http:\/\/www.daylight.com\/dayhtml\/doc\/theory\/theory.smirks.html . Accessed 1 Oct 2016"},{"key":"203_CR27","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/S0169-409X(00)00129-0","volume":"46","author":"CA Lipinski","year":"2001","unstructured":"Lipinski CA, Lombardo F, Dominy BW, Feeney PJ (2001) Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings. Adv Drug Deliv Rev 46:3\u201326","journal-title":"Adv Drug Deliv Rev"},{"key":"203_CR28","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/1758-2946-3-3","volume":"3","author":"G Hinselmann","year":"2011","unstructured":"Hinselmann G, Rosenbaum L, Jahn A, Fechner N, Zell A (2011) jCompoundMapper: an open source java library and command-line tool for chemical fingerprints. J Cheminform 3:3","journal-title":"J Cheminform"},{"key":"203_CR29","doi-asserted-by":"publisher","first-page":"887","DOI":"10.1021\/ci300584r","volume":"53","author":"P Carbonell","year":"2013","unstructured":"Carbonell P, Carlsson L, Faulon J-L (2013) Stereo signature molecular descriptor. J Chem Inf Model 53:887\u2013897","journal-title":"J Chem Inf Model"},{"key":"203_CR30","doi-asserted-by":"publisher","first-page":"D54","DOI":"10.1093\/nar\/gki031","volume":"33","author":"D Maglott","year":"2005","unstructured":"Maglott D, Ostell J, Pruitt KD, Tatusova T (2005) Entrez gene: gene-centered information at NCBI. Nucleic Acids Res 33:D54\u2013D58","journal-title":"Nucleic Acids Res"},{"key":"203_CR31","doi-asserted-by":"publisher","first-page":"D1079","DOI":"10.1093\/nar\/gku1071","volume":"43","author":"KA Gray","year":"2015","unstructured":"Gray KA, Yates B, Seal RL, Wright MW, Bruford EA (2015) Genenames.org: the HGNC resources in 2015. Nucleic Acids Res 43:D1079\u2013D1085","journal-title":"Nucleic Acids Res"},{"key":"203_CR32","doi-asserted-by":"publisher","first-page":"D743","DOI":"10.1093\/nar\/gku1026","volume":"43","author":"M Shimoyama","year":"2015","unstructured":"Shimoyama M, De Pons J, Hayman GT, Laulederkind SJ, Liu W, Nigam R et al (2015) The rat genome database 2015: genomic, phenotypic and environmental variations and disease. Nucleic Acids Res 43:D743\u2013D750","journal-title":"Nucleic Acids Res"},{"key":"203_CR33","doi-asserted-by":"publisher","first-page":"D726","DOI":"10.1093\/nar\/gku967","volume":"43","author":"JT Eppig","year":"2015","unstructured":"Eppig JT, Blake JA, Bult CJ, Kadin JA, Richardson JE, Mouse Genome Database Group (2015) The mouse genome database (MGD): facilitating mouse as a model for human biology and disease. Nucleic Acids Res 43:D726\u2013D736","journal-title":"Nucleic Acids Res"},{"key":"203_CR34","unstructured":"NCBI Gene. https:\/\/www.ncbi.nlm.nih.gov\/gene . Accessed 12 Jan 2016"},{"key":"203_CR35","unstructured":"Apache Solr. https:\/\/lucene.apache.org\/solr . Accessed 1 Oct 2016"},{"key":"203_CR36","unstructured":"Flush program. https:\/\/github.com\/OpenEye-Contrib\/Flush . Accessed 1 Oct 2016"},{"key":"203_CR37","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1007\/s10822-009-9264-5","volume":"23","author":"N Blomberg","year":"2009","unstructured":"Blomberg N, Cosgrove DA, Kenny PW, Kolmodin K (2009) Design of compound libraries for fragment screening. J Comput Aided Mol Des 23:513\u2013525","journal-title":"J Comput Aided Mol Des"},{"key":"203_CR38","unstructured":"ClogP version 4.3. http:\/\/www.biobyte.com\/ . Accessed 1 Apr 2016"},{"key":"203_CR39","doi-asserted-by":"publisher","first-page":"6752","DOI":"10.1021\/jm901241e","volume":"52","author":"F Lovering","year":"2009","unstructured":"Lovering F, Bikker J, Humblet C (2009) Escape from flatland: increasing saturation as an approach to improving clinical success. J Med Chem 52:6752\u20136756","journal-title":"J Med Chem"},{"key":"203_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1961189.1961199","volume":"2","author":"C-C Chang","year":"2011","unstructured":"Chang C-C, Lin C-J (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2:1\u201327","journal-title":"ACM Trans Intell Syst Technol"},{"key":"203_CR41","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1177\/001316446002000104","volume":"20","author":"J Cohen","year":"1960","unstructured":"Cohen J (1960) A coefficient of agreement for nominal scales. Educ Psychol Meas 20:37\u201346","journal-title":"Educ Psychol Meas"}],"updated-by":[{"DOI":"10.1186\/s13321-017-0222-2","type":"erratum","label":"Erratum","source":"publisher","updated":{"date-parts":[[2017,6,14]],"date-time":"2017-06-14T00:00:00Z","timestamp":1497398400000}}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-017-0203-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13321-017-0203-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-017-0203-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,3]],"date-time":"2020-10-03T13:03:31Z","timestamp":1601730211000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-017-0203-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3,7]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["203"],"URL":"https:\/\/doi.org\/10.1186\/s13321-017-0203-5","relation":{"erratum":[{"id-type":"doi","id":"10.1186\/s13321-017-0222-2","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,3,7]]},"assertion":[{"value":"5 December 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2017","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 March 2017","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"17"}}