{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T13:02:09Z","timestamp":1767963729941,"version":"3.49.0"},"reference-count":26,"publisher":"Oxford University Press (OUP)","issue":"24","license":[{"start":{"date-parts":[[2018,3,14]],"date-time":"2018-03-14T00:00:00Z","timestamp":1520985600000},"content-version":"vor","delay-in-days":243,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000867","name":"Commonwealth Scholarship Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000867","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>To understand the molecular mechanisms involved in cancer development, significant efforts are being invested in cancer research. This has resulted in millions of scientific articles. An efficient and thorough review of the existing literature is crucially important to drive new research. This time-demanding task can be supported by emerging computational approaches based on text mining which offer a great opportunity to organize and retrieve the desired information efficiently from sizable databases. One way to organize existing knowledge on cancer is to utilize the widely accepted framework of the Hallmarks of Cancer. These hallmarks refer to the alterations in cell behaviour that characterize the cancer cell.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We created an extensive Hallmarks of Cancer taxonomy and developed automatic text mining methodology and a tool (CHAT) capable of retrieving and organizing millions of cancer-related references from PubMed into the taxonomy. The efficiency and accuracy of the tool was evaluated intrinsically as well as extrinsically by case studies. The correlations identified by the tool show that it offers a great potential to organize and correctly classify cancer-related literature. Furthermore, the tool can be useful, for example, in identifying hallmarks associated with extrinsic factors, biomarkers and therapeutics targets.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>CHAT can be accessed at: http:\/\/chat.lionproject.net. The corpus of hallmark-annotated PubMed abstracts and the software are available at: http:\/\/chat.lionproject.net\/about<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btx454","type":"journal-article","created":{"date-parts":[[2017,7,13]],"date-time":"2017-07-13T10:28:31Z","timestamp":1499941711000},"page":"3973-3981","source":"Crossref","is-referenced-by-count":88,"title":["Cancer Hallmarks Analytics Tool (CHAT): a text mining approach to organize and evaluate scientific literature on cancer"],"prefix":"10.1093","volume":"33","author":[{"given":"Simon","family":"Baker","sequence":"first","affiliation":[{"name":"Computer Laboratory, University of Cambridge, Cambridge, UK"},{"name":"Language Technology Lab, Department of Theoretical and Applied Linguistics, University of Cambridge, Cambridge, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Imran","family":"Ali","sequence":"additional","affiliation":[{"name":"Institute of Environmental Medicine, Karolinska Institutet, Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ilona","family":"Silins","sequence":"additional","affiliation":[{"name":"Institute of Environmental Medicine, Karolinska Institutet, Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sampo","family":"Pyysalo","sequence":"additional","affiliation":[{"name":"Language Technology Lab, Department of Theoretical and Applied Linguistics, University of Cambridge, Cambridge, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yufan","family":"Guo","sequence":"additional","affiliation":[{"name":"Language Technology Lab, Department of Theoretical and Applied Linguistics, University of Cambridge, Cambridge, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johan","family":"H\u00f6gberg","sequence":"additional","affiliation":[{"name":"Institute of Environmental Medicine, Karolinska Institutet, Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ulla","family":"Stenius","sequence":"additional","affiliation":[{"name":"Institute of Environmental Medicine, Karolinska Institutet, Stockholm, Sweden"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Korhonen","sequence":"additional","affiliation":[{"name":"Language Technology Lab, Department of Theoretical and Applied Linguistics, University of Cambridge, Cambridge, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2017,7,14]]},"reference":[{"key":"2023020207504533700_btx454-B1","first-page":"2333","author":"Baker","year":"2016"},{"key":"2023020207504533700_btx454-B2","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1093\/bioinformatics\/btv585","article-title":"Automatic semantic classification of scientific literature according to the hallmarks of cancer","volume":"32","author":"Baker","year":"2016","journal-title":"Bioinformatics"},{"key":"2023020207504533700_btx454-B3","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1038\/nrc.2016.4","article-title":"Aspirin and colorectal cancer: the promise of precision chemoprevention","volume":"16","author":"Drew","year":"2016","journal-title":"Nat. Rev. Cancer"},{"key":"2023020207504533700_btx454-B4","volume-title":"Statistical Methods for Rates and Proportions","author":"Fleiss","year":"2013"},{"key":"2023020207504533700_btx454-B5","author":"Guo","year":"2012"},{"key":"2023020207504533700_btx454-B6","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/S0092-8674(00)81683-9","article-title":"The hallmarks of cancer","volume":"100","author":"Hanahan","year":"2000","journal-title":"Cell"},{"key":"2023020207504533700_btx454-B7","doi-asserted-by":"crossref","first-page":"646","DOI":"10.1016\/j.cell.2011.02.013","article-title":"Hallmarks of cancer: the next generation","volume":"144","author":"Hanahan","year":"2011","journal-title":"Cell"},{"key":"2023020207504533700_btx454-B8","author":"IARC","year":"2014"},{"key":"2023020207504533700_btx454-B9","doi-asserted-by":"crossref","first-page":"43763.","DOI":"10.1038\/srep43763","article-title":"Identification of stable housekeeping genes in response to ionizing radiation in cancer research","volume":"7","author":"Iyer","year":"2017","journal-title":"Sci. Rep"},{"key":"2023020207504533700_btx454-B10","first-page":"61","author":"Kulick","year":"2004"},{"key":"2023020207504533700_btx454-B11","doi-asserted-by":"crossref","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data","author":"Landis","year":"1977","journal-title":"Biometrics"},{"key":"2023020207504533700_btx454-B151","author":"McDonald","year":"2009","journal-title":"Handbook of biological statistics"},{"key":"2023020207504533700_btx454-B12","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1038\/nrc2622","article-title":"Metastasis: from dissemination to organ-specific colonization","volume":"9","author":"Nguyen","year":"2009","journal-title":"Nat. Rev. Cancer"},{"key":"2023020207504533700_btx454-B13","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.gene.2005.10.018","article-title":"Epidermal growth factor receptor (EGFR) signaling in cancer","volume":"366","author":"Normanno","year":"2006","journal-title":"Gene"},{"key":"2023020207504533700_btx454-B14","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res"},{"key":"2023020207504533700_btx454-B15","doi-asserted-by":"crossref","first-page":"605","DOI":"10.1016\/j.ijmedinf.2014.06.009","article-title":"Text mining of cancer-related information: review of current status and future directions","volume":"83","author":"Spasic","year":"2014","journal-title":"Int. J. Med. Inform"},{"key":"2023020207504533700_btx454-B16","doi-asserted-by":"crossref","first-page":"319.","DOI":"10.1186\/1471-2105-9-319","article-title":"\u2032A comprehensive comparison of random forests and support vector machines for microarray-based cancer classification\u2032","volume":"9","author":"Statnikov","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"2023020207504533700_btx454-B17","author":"Sun","year":"2009"},{"key":"2023020207504533700_btx454-B18","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1126\/science.1260825","article-title":"Variation in cancer risk among tissues can be explained by the number of stem cell divisions","volume":"347","author":"Tomasetti","year":"2015","journal-title":"Science"},{"key":"2023020207504533700_btx454-B19","first-page":"467","author":"Tsuruoka","year":"2005"},{"key":"2023020207504533700_btx454-B20","first-page":"382","author":"Tsuruoka","year":"2005"},{"key":"2023020207504533700_btx454-B21","doi-asserted-by":"crossref","first-page":"91.","DOI":"10.1186\/1471-2105-7-91","article-title":"Bias in error estimation when using cross-validation for model selection","volume":"7","author":"Varma","year":"2006","journal-title":"BMC Bioinformatics"},{"key":"2023020207504533700_btx454-B22","doi-asserted-by":"crossref","first-page":"307","DOI":"10.1038\/nrd1691","article-title":"Cellular processing of platinum anticancer drugs","volume":"4","author":"Wang","year":"2005","journal-title":"Nat. Rev. Drug Discov"},{"key":"2023020207504533700_btx454-B23","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1038\/nature16166","article-title":"Substantial contribution of extrinsic risk factors to cancer development","volume":"529","author":"Wu","year":"2016","journal-title":"Nature"},{"key":"2023020207504533700_btx454-B24","doi-asserted-by":"crossref","first-page":"660","DOI":"10.1634\/theoncologist.2014-0465","article-title":"Targeting angiogenesis in cancer therapy: moving beyond vascular endothelial growth factor","volume":"20","author":"Zhao","year":"2015","journal-title":"Oncologist"},{"key":"2023020207504533700_btx454-B25","doi-asserted-by":"crossref","first-page":"200","DOI":"10.1016\/j.jbi.2012.10.007","article-title":"Biomedical text mining and its applications in cancer research","volume":"46","author":"Zhu","year":"2013","journal-title":"J. Biomed. Inform"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/24\/3973\/49041943\/bioinformatics_33_24_3973.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/24\/3973\/49041943\/bioinformatics_33_24_3973.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T07:52:02Z","timestamp":1675324322000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/33\/24\/3973\/3965324"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2017,7,14]]},"references-count":26,"journal-issue":{"issue":"24","published-print":{"date-parts":[[2017,12,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btx454","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017,12,15]]},"published":{"date-parts":[[2017,7,14]]}}}