{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:22:44Z","timestamp":1789039364364,"version":"build-2803163510"},"reference-count":57,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2013,4,25]],"date-time":"2013-04-25T00:00:00Z","timestamp":1366848000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"DOI":"10.1371\/journal.pcbi.1003044","type":"journal-article","created":{"date-parts":[[2013,4,25]],"date-time":"2013-04-25T20:52:11Z","timestamp":1366923131000},"page":"e1003044","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":17,"title":["Chapter 16: Text Mining for Translational Bioinformatics"],"prefix":"10.1371","volume":"9","author":[{"given":"K. Bretonnel","family":"Cohen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lawrence E.","family":"Hunter","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2013,4,25]]},"reference":[{"key":"ref1","doi-asserted-by":"crossref","first-page":"1146","DOI":"10.1164\/rccm.200408-1104OC","article-title":"Clinical and pathologic features of familial interstitial pneumonia","volume":"172","author":"MP Steele","year":"2005","journal-title":"Am J Respir Crit Care Med"},{"key":"ref2","doi-asserted-by":"crossref","first-page":"e5134","DOI":"10.1371\/journal.pone.0005134","article-title":"Molecular phenotypes distinguish patients with relatively stable from progressive idiopathic pulmonary fibrosis (ipf)","volume":"4","author":"K Boon","year":"2009","journal-title":"PLoS ONE"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1016\/j.jbi.2004.03.002","article-title":"Fever detection from free-text clinical records for biosurveillance","volume":"37","author":"W Chapman","year":"2004","journal-title":"J Biomed Inform"},{"key":"ref4","article-title":"Can chief complaints detect febrile syndromic patients?","volume":"3","author":"W Chapman","year":"2007","journal-title":"Journal of Advances in Disease Surveillance"},{"key":"ref5","unstructured":"Elhadad N (2006) User-sensitive text summarization: application to the medical domain [Ph.D. thesis]. New York: Columbia University."},{"key":"ref6","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1136\/jamia.2010.003947","article-title":"Extracting medication information from clinical text","volume":"17","author":"O Uzuner","year":"2010","journal-title":"J Am Med Inform Assoc"},{"key":"ref7","doi-asserted-by":"crossref","unstructured":"Hunter LE (2009) The processes of life: an introduction to molecular biology. Cambridge (MA): MIT Press.","DOI":"10.7551\/mitpress\/9780262013055.001.0001"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1186\/1471-2105-10-326","article-title":"Text mining and manual curation of chemical-gene-disease networks for the Comparative Toxicogenomics Database (CTD)","volume":"10","author":"TC Wiegers","year":"2009","journal-title":"BMC Bioinformatics"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1038\/clpt.2010.310","article-title":"Pharmacogenomics: \u201cnoninferiority\u201d is sufficient for initial implementation","volume":"89","author":"RB Altman","year":"2011","journal-title":"Clin Pharmacol Ther"},{"key":"ref10","article-title":"Speech and language processing: an introduction to natural language processing, computational linguistics, and speech recognition","author":"D Jurafsky","year":"2008","journal-title":"Pearson Prentice Hall"},{"key":"ref11","unstructured":"Manning C, Schuetze H (1999) Foundations of statistical natural language processing. Cambridge (MA): MIT Press."},{"key":"ref12","article-title":"Natural language processing for online applications: text retrieval, extraction, and categorization. 2nd edition","author":"P Jackson","year":"2002","journal-title":"John Benjamins Publishing Company"},{"key":"ref13","unstructured":"Cohen KB, Fox L, Ogren PV, Hunter L (2005) Empirical data on corpus design and usage in biomedical natural language processing. In: AMIA 2005 symposium proceedings. pp. 156\u2013160."},{"key":"ref14","unstructured":"Cohen KB, Roeder C, Jr WAB, Hunter L, Verspoor K (2010) Test suite design for biomedical ontology concept recognition systems. In: Proceedings of the Language Resources and Evaluation Conference."},{"key":"ref15","unstructured":"Cohen KB, Tanabe L, Kinoshita S, Hunter L (2004) A resource for constructing customized test suites for molecular biology entity identification systems. In: HLT-NAACL 2004 Workshop: BioLINK 2004, Linking Biological Literature, Ontologies and Databases. Association for Computational Linguistics, pp. 1\u20138."},{"key":"ref16","article-title":"The BioCreative II \u2013 critical assessment for information extraction in biology challenge","volume":"9","author":"M Krallinger","year":"2008","journal-title":"Genome Biol"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1186\/1471-2105-11-492","article-title":"The structural and content aspects of abstracts versus bodies of full text journal articles are different","volume":"11","author":"KB Cohen","year":"2010","journal-title":"BMC Bioinformatics"},{"key":"ref18","doi-asserted-by":"crossref","unstructured":"Lin J, Karakos D, Demner-Fushman D, Khudanpur S (2006) Generative content models for struc-tural analysis of medical abstracts. In: Proceedings of the HLT-NAACL BioNLP Workshop on Linking Natural Language and Biology. New York, New York: Association for Computational Linguistics. pp. 65\u201372.","DOI":"10.3115\/1654415.1654427"},{"key":"ref19","unstructured":"Demner-Fushman D, Abhyankar S, Jimeno-Yepes A, Loane R, Rance B, <etal>et al<\/etal>.. (2011) A knowledge-based approach to medical records retrieval. In: Proceedings of TREC 2011."},{"key":"ref20","unstructured":"Fukuda K, Tamura A, Tsunoda T, Takagi T (1998) Toward information extraction: identifying protein names from biological papers. In: Pac Symp Biocomput. pp. 707\u2013718."},{"key":"ref21","doi-asserted-by":"crossref","first-page":"130","DOI":"10.1108\/eb046814","article-title":"An algorithm for suffix stripping","volume":"14","author":"MF Porter","year":"1980","journal-title":"Program"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1186\/2041-1480-3-3","article-title":"BioLemmatizer: a lemmatization tool for morphological processing of biomedical text","volume":"3","author":"H Liu","year":"2012","journal-title":"J Biomed Semantics"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"2320","DOI":"10.1093\/bioinformatics\/bth227","article-title":"Medpost: A part-of-speech tagger for biomedical text","volume":"20","author":"L Smith","year":"2004","journal-title":"Bioinformatics"},{"key":"ref24","doi-asserted-by":"crossref","unstructured":"Tsuruoka Y, Tateishi Y, Kim JD, Ohta T, Mcnaught J, <etal>et al<\/etal>.. (2005) Developing a robust part-of-speech tagger for biomedical text. In: Proceedings of the 10th Panhellenic Conference on Informatics. pp. 382\u2013392.","DOI":"10.1007\/11573036_36"},{"key":"ref25","doi-asserted-by":"crossref","unstructured":"Caporaso JG, Baumgartner WA Jr, Cohen KB, Johnson HL, Paquette J, <etal>et al<\/etal>.. (2005) Concept recognition and the TREC Genomics tasks. In: The Fourteenth Text REtrieval Conference (TREC 2005) Proceedings.","DOI":"10.6028\/NIST.SP.500-266.genomics-ucolorado.cohen"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1055\/s-0038-1634945","article-title":"The Unified Medical Language System","volume":"32","author":"D Lindberg","year":"1993","journal-title":"Methods Inf Med"},{"key":"ref27","unstructured":"Aronson A (2001) Effective mapping of biomedical text to the UMLS Metathesaurus: The MetaMap program. In: Proc AMIA 2001. pp. 17\u201321."},{"key":"ref28","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1136\/jamia.2009.002733","article-title":"An overview of MetaMap: historical perspective and recent advances","volume":"17","author":"AR Aronson","year":"2010","journal-title":"J Am Med Inform Assoc"},{"key":"ref29","doi-asserted-by":"crossref","first-page":"S14","DOI":"10.1186\/1471-2105-6-S1-S14","article-title":"ProMiner: rule-based protein and gene entity recognition","volume":"6 Suppl 1","author":"D Hanisch","year":"2005","journal-title":"BMC Bioinformatics"},{"key":"ref30","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1109\/TCBB.2010.48","article-title":"Exploring species-based strategies for gene normalization","volume":"7","author":"K Verspoor","year":"2010","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"key":"ref31","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1186\/1471-2105-9-78","article-title":"OpenDMAP: An open-source, ontology-driven concept analysis engine, with applications to capturing knowledge regarding pro-tein transport, protein interactions and cell-specific gene expression","volume":"9","author":"L Hunter","year":"2008","journal-title":"BMC Bioinformatics"},{"key":"ref32","doi-asserted-by":"crossref","unstructured":"Kilicoglu H, Bergler S (2009) Syntactic dependency based heuristics for biological event extraction. In: Proceedings of the BioNLP 2009 Workshop Companion Volume for Shared Task. Boulder, Colorado: Association for Computational Linguistics. pp. 119\u2013127.","DOI":"10.3115\/1572340.1572361"},{"key":"ref33","doi-asserted-by":"crossref","unstructured":"Kim JD, Ohta T, Pyysalo S, Kano Y, Tsujii J (2009) Overview of BioNLP&apos;09 shared task on event extraction. In: BioNLP 2009 Companion Volume: Shared Task on Entity Extraction. pp. 1\u20139.","DOI":"10.3115\/1572340.1572342"},{"key":"ref34","doi-asserted-by":"crossref","unstructured":"Lin J, Demner-Fushman D (2005) Automatically evaluating answers to definition questions. In: Proceedings of the 2005 Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT\/EMNLP 2005). pp. 931\u2013938.","DOI":"10.3115\/1220575.1220692"},{"key":"ref35","unstructured":"Yu H, Wei Y (2006) The semantics of a definiendum constrains both the lexical semantics and the lexicosyntactic patterns in the definiens. In: HTL-NAACL BioNLP Workshop: Linking Natural Language Processing and Biology: Towards Deeper Biological Literature Analysis. ACL, pp. 1\u20138."},{"key":"ref36","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1016\/j.jbi.2007.03.002","article-title":"Development, implementation, and a cognitive evaluation of a definitional question answering system for physicians","volume":"40","author":"H Yu","year":"2007","journal-title":"J Biomed Inform"},{"key":"ref37","unstructured":"Zweigenbaum P (2003) Question answering in biomedicine. In: Proceedings of the workshop on natural language processing for question answering. pp. 1\u20134."},{"key":"ref38","unstructured":"Lu Z, Cohen BK, Hunter L (2006) Finding GeneRIFs via Gene Ontology annotations. In: PSB 2006. pp. 52\u201363."},{"key":"ref39","unstructured":"Lu Z, Cohen KB, Hunter L (2007) GeneRIF quality assurance as summary revision. In: Pacific Symposium on Biocomputing."},{"key":"ref40","doi-asserted-by":"crossref","first-page":"S9","DOI":"10.1186\/gb-2008-9-s2-s9","article-title":"Concept recognition for extracting protein interaction relations from biomedical text","volume":"9 Suppl 2","author":"WA Baumgartner Jr","year":"2008","journal-title":"Genome Biol"},{"key":"ref41","doi-asserted-by":"crossref","unstructured":"Jin F, Huang M, Lu Z, Zhu X (2009) Towards automatic generation of gene summary. In: Proceedings of the BioNLP 2009 Workshop. Boulder, Colorado: Association for Computational Linguistics. pp. 97\u2013105.","DOI":"10.3115\/1572364.1572377"},{"key":"ref42","doi-asserted-by":"crossref","unstructured":"Pestian JP, Brew C, Matykiewicz P, Hovermale D, Johnson N, <etal>et al<\/etal>.. (2007) A shared task involving multi-label classification of clinical free text. In: Proceedings of BioNLP 2007. Association for Computational Linguistics.","DOI":"10.3115\/1572392.1572411"},{"key":"ref43","article-title":"TREC genomics special issue overview","author":"W Hersh","year":"2008","journal-title":"Information Retrieval"},{"key":"ref44","article-title":"Testing computer software. 2nd edition","author":"C Kaner","year":"1999","journal-title":"John Wiley and Sons"},{"key":"ref45","doi-asserted-by":"crossref","unstructured":"Cohen KB, Baumgartner Jr WA, Hunter L (2008) Software testing and the naturally occurring data assumption in natural language processing. In: Software Engineering, Testing, and Qual-ity Assurance for Natural Language Processing. Columbus, Ohio: Association for Computational Linguistics. pp. 23\u201330.","DOI":"10.3115\/1622110.1622116"},{"key":"ref46","unstructured":"Johnson HL, Cohen KB, Hunter L (2007) A fault model for ontology mapping, alignment, and linking systems. In: Pacific Symposium on Biocomputing. World Scientific Publishing Company. pp. 233\u2013244."},{"key":"ref47","unstructured":"Hearst M, Divoli A, Jerry Y, Wooldridge M (2007) Exploring the effcacy of caption search for bioscience journal search interfaces. In: Biological, translational, and clinical language processing. Prague, Czech Republic: Association for Computational Linguistics. pp. 73\u201380."},{"key":"ref48","first-page":"568","article-title":"Evidence for showing gene\/protein name suggestions in bioscience literature search interfaces","volume":"2008","author":"A Divoli","year":"2008","journal-title":"Pac Symp Biocomput"},{"key":"ref49","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1136\/amiajnl-2011-000203","article-title":"2010 i2b2\/VA challenge on concepts, assertions, and relations in clinical text","volume":"18","author":"O Uzuner","year":"2011","journal-title":"J Am Med Inform Assoc"},{"key":"ref50","article-title":"Biomedical natural language processing","author":"KB Cohen","journal-title":"John Benjamins Publishing Company"},{"key":"ref51","unstructured":"Cohen KB (2010) Biomedical text mining. In: Indurkhya N, Damerau FJ, editors. Handbook of natural language processing. 2nd edition."},{"key":"ref52","article-title":"Natural language processing for online applications: text retrieval, extraction, and categorization","author":"P Jackson","year":"2002","journal-title":"John Benjamins Publishing Company"},{"key":"ref53","unstructured":"Nobata C, Collier N, Tsujii J (1999) Automatic term identification and classification in biology texts. In: Proceedings of the fifth Natural Language Processing Pacific Rim Symposium (NLPRS). pp. 369\u2013374."},{"key":"ref54","first-page":"60","article-title":"Automatic extraction of biological information from scientific text: protein-protein interactions","volume":"1999","author":"C Blaschke","year":"1999","journal-title":"Proc Int Conf Intell Syst Mol Biol"},{"key":"ref55","first-page":"77","article-title":"Constructing biological knowledge bases by extracting information from text sources","volume":"1999","author":"M Craven","year":"1999","journal-title":"Proc Int Conf Intell Syst Mol Biol"},{"key":"ref56","doi-asserted-by":"crossref","first-page":"S74","DOI":"10.1093\/bioinformatics\/17.suppl_1.S74","article-title":"GENIES: a natural-language processing system for the extraction of molecular pathways from journal articles","volume":"17","author":"C Friedman","year":"2001","journal-title":"Bioinformatics"},{"key":"ref57","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.jbi.2003.10.001","article-title":"Geneways: a system for extracting, analyzing, visualizing, and integrating molecular pathway data","volume":"37","author":"A Rzhetsky","year":"2004","journal-title":"J Biomed Inform"}],"container-title":["PLoS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/dx.plos.org\/10.1371\/journal.pcbi.1003044","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T06:34:48Z","timestamp":1745994888000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1003044"}},"subtitle":[],"editor":[{"given":"Fran","family":"Lewitter","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]},{"given":"Maricel","family":"Kann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2013,4,25]]},"references-count":57,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2013,4,25]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1003044","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2013,4,25]]}}}