{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T17:50:06Z","timestamp":1776275406976,"version":"3.50.1"},"reference-count":58,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2016,10,7]],"date-time":"2016-10-07T00:00:00Z","timestamp":1475798400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"published-print":{"date-parts":[[2016,12]]},"DOI":"10.1186\/s13321-016-0165-z","type":"journal-article","created":{"date-parts":[[2016,10,7]],"date-time":"2016-10-07T04:33:59Z","timestamp":1475814839000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":52,"title":["Improving chemical disease relation extraction with rich features and weakly labeled data"],"prefix":"10.1186","volume":"8","author":[{"given":"Yifan","family":"Peng","sequence":"first","affiliation":[]},{"given":"Chih-Hsuan","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,10,7]]},"reference":[{"key":"165_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-9-S11-S2","volume":"9","author":"A Airola","year":"2008","unstructured":"Airola A et al (2008) All-paths graph kernel for protein-protein interaction extraction with evaluation of cross-corpus learning. BMC Bioinfo 9:1\u201312","journal-title":"BMC Bioinfo"},{"key":"165_CR2","doi-asserted-by":"crossref","unstructured":"Airola A et al (2008b) A graph kernel for protein\u2013protein interaction extraction. In: Proceedings of the workshop on current trends in biomedical natural language processing, Stroudsburg, pp 1\u20139","DOI":"10.3115\/1572306.1572308"},{"key":"165_CR3","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.jbi.2015.11.004","volume":"58","author":"N Alvaro","year":"2015","unstructured":"Alvaro N et al (2015) Crowdsourcing Twitter annotations to identify first-hand experiences of prescription drug use. J Biomed Inform 58:280\u2013287","journal-title":"J Biomed Inform"},{"key":"165_CR4","doi-asserted-by":"publisher","first-page":"i41","DOI":"10.1093\/bioinformatics\/btm229","volume":"23","author":"WA Baumgartner Jr","year":"2007","unstructured":"Baumgartner WA Jr et al (2007) Manual curation is not sufficient for annotation of genomic databases. Bioinformatics 23:i41\u201348","journal-title":"Bioinformatics"},{"key":"165_CR5","doi-asserted-by":"publisher","first-page":"S4","DOI":"10.1186\/1471-2105-13-S11-S4","volume":"13","author":"J Bj\u00f6rne","year":"2012","unstructured":"Bj\u00f6rne J, Ginter F, Salakoski T (2012) University of Turku in the BioNLP\u201911 Shared Task. BMC Bioinf 13:S4","journal-title":"BMC Bioinf"},{"key":"165_CR6","unstructured":"Bockhorst J, Craven M (2002) Exploiting relations among concepts to acquire weakly labeled training data. In: Proceedings of the 19th international conference on machine learning, pp 43\u201350"},{"key":"165_CR7","unstructured":"Bravo \u00c0 et al (2015) Combining machine learning, crowdsourcing and expert knowledge to detect chemical-induced diseases in text. In: The fifth BioCreative challenge evaluation workshop, pp 266\u2013273"},{"key":"165_CR8","doi-asserted-by":"crossref","unstructured":"Charniak E, Johnson M (2005) Coarse-to-fine n-best parsing and MaxEnt discriminative reranking. In: Proceedings of the 43rd annual meeting on association for computational linguistics, pp 173\u2013180","DOI":"10.3115\/1219840.1219862"},{"key":"165_CR9","doi-asserted-by":"publisher","first-page":"D914","DOI":"10.1093\/nar\/gku935","volume":"43","author":"AP Davis","year":"2015","unstructured":"Davis AP et al (2015) The comparative toxicogenomics database\u2019s 10th year anniversary: update 2015. Nucleic Acids Res 43:D914\u2013920","journal-title":"Nucleic Acids Res"},{"key":"165_CR10","doi-asserted-by":"publisher","first-page":"bat080","DOI":"10.1093\/database\/bat080","volume":"2013","author":"AP Davis","year":"2013","unstructured":"Davis AP et al (2013) A CTD-Pfizer collaboration: manual curation of 88,000 scientific articles text mined for drug-disease and drug-phenotype interactions. Database (Oxford) 2013:bat080","journal-title":"Database (Oxford)"},{"key":"165_CR11","doi-asserted-by":"crossref","unstructured":"De Marneffe M-C, Manning CD (2008) The Stanford typed dependencies representation. Coling 2008: proceedings of the workshop on cross-framework and cross-domain parser evaluation, pp 1\u20138","DOI":"10.3115\/1608858.1608859"},{"key":"165_CR12","unstructured":"De Marneffe M-C, Manning CD (2015) Stanford typed dependencies manual. Stanford University"},{"key":"165_CR13","doi-asserted-by":"publisher","first-page":"286","DOI":"10.1067\/mcp.2001.115132","volume":"69","author":"JA Dimasi","year":"2001","unstructured":"Dimasi JA (2001) New drug development in the United States from 1963 to 1999. Clin Pharmacol Ther 69:286\u2013296","journal-title":"Clin Pharmacol Ther"},{"key":"165_CR14","unstructured":"Ellendor TR et al (2015) Ontogene term and relation recognition for CDR. In: The fifth BioCreative challenge evaluation workshop, pp 305\u2013310"},{"key":"165_CR15","unstructured":"Erkan G, \u00d6zg\u00fcr A, Radev DR (2007) Semi-supervised classification for extracting protein interaction sentences using dependency parsing. In: Proceedings of EMNLP-CoNLL, Prague, pp 228\u2013237"},{"key":"165_CR16","unstructured":"Fukuda K-I et al (1998) Toward information extraction: identifying protein names from biological papers. In: Pacific symposium on biocomputing, pp 707\u2013718"},{"key":"165_CR17","doi-asserted-by":"publisher","first-page":"bat041","DOI":"10.1093\/database\/bat041","volume":"2013","author":"J Gobeill","year":"2013","unstructured":"Gobeill J et al (2013) Managing the data deluge: data-driven GO category assignment improves while complexity of functional annotation increases. Database (Oxford) 2013:bat041","journal-title":"Database (Oxford)"},{"key":"165_CR18","unstructured":"Good BM et al (2015) Microtask crowdsourcing for disease mention annotation in PubMed abstracts. In: Pacific symposium on biocomputing, 282\u2013293"},{"key":"165_CR19","unstructured":"Gu J, Qian L, Zhou G (2015) Chemical-induced disease relation extraction with lexical features. In: The fifth BioCreative challenge evaluation workshop, pp 220\u2013225"},{"key":"165_CR20","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1016\/j.jbi.2012.04.008","volume":"45","author":"H Gurulingappa","year":"2012","unstructured":"Gurulingappa H et al (2012) Development of a benchmark corpus to support the automatic extraction of drug-related adverse effects from medical case reports. J Biomed Info 45:885\u2013892","journal-title":"J Biomed Info"},{"key":"165_CR21","unstructured":"Jiang Z et al (2015) A CRD-WEL system for chemical-disease relations extraction. In: The fifth BioCreative challenge evaluation workshop, pp 317\u2013326"},{"key":"165_CR22","unstructured":"Kilicoglu H, Rogers WJ (2015) A hybrid system for extracting chemical-disease relationships from scientific literature. In: The fifth BioCreative challenge evaluation workshop, pp 260\u2013265"},{"key":"165_CR23","unstructured":"Kim J-D, Yue W, Yamamoto Y (2013) The Genia Event Extraction Shared Task, 2013 Edition\u2014overview. In: Proceedings of the workshop on BioNLP shared task 2013, Sofia, pp 20\u201327"},{"key":"165_CR24","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1093\/bioinformatics\/btm544","volume":"24","author":"S Kim","year":"2008","unstructured":"Kim S, Yoon J, Yang J (2008) Kernel approaches for genic interaction extraction. Bioinformatics 24:118\u2013126","journal-title":"Bioinformatics"},{"issue":"Suppl 8","key":"165_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-12-S8-S3","volume":"12","author":"M Krallinger","year":"2011","unstructured":"Krallinger M et al (2011) The Protein-Protein Interaction tasks of BioCreative III: classification\/ranking of articles and linking bio-ontology concepts to full text. BMC Bioinfo 12(Suppl 8):1\u201331","journal-title":"BMC Bioinfo"},{"key":"165_CR26","doi-asserted-by":"publisher","first-page":"2909","DOI":"10.1093\/bioinformatics\/btt474","volume":"29","author":"R Leaman","year":"2013","unstructured":"Leaman R, Do\u011fan RI, Lu Z (2013) DNorm: disease name normalization with pairwise learning to rank. Bioinformatics 29:2909\u20132917","journal-title":"Bioinformatics"},{"key":"165_CR27","doi-asserted-by":"publisher","first-page":"S3","DOI":"10.1186\/1758-2946-7-S1-S3","volume":"7","author":"R Leaman","year":"2015","unstructured":"Leaman R, Wei C-H, Lu Z (2015) tmChem: a high performance approach for chemical named entity recognition and normalization. J Cheminfo 7:S3","journal-title":"J Cheminfo"},{"key":"165_CR28","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1186\/1471-2105-14-323","volume":"14","author":"HJ Lee","year":"2013","unstructured":"Lee HJ et al (2013) CoMAGC: a corpus with multi-faceted annotations of gene-cancer relations. BMC Bioinfo 14:323","journal-title":"BMC Bioinfo"},{"key":"165_CR29","unstructured":"Li D et al (2015) Resolution of chemical disease relations with diverse features and rules. In: The fifth BioCreative challenge evaluation workshop, pp 280\u2013285"},{"key":"165_CR30","doi-asserted-by":"publisher","first-page":"e1004391","DOI":"10.1371\/journal.pcbi.1004391","volume":"11","author":"G Li","year":"2015","unstructured":"Li G et al (2015) miRTex: a text mining system for miRNA-gene relation extraction. PLoS Comput Biol 11:e1004391","journal-title":"PLoS Comput Biol"},{"key":"165_CR31","unstructured":"Li J et al (2015) Annotating chemicals, diseases and their interactions in biomedical literature. In: Proceedings of the fifth BioCreative challenge evaluation workshop, Sevilla, pp 173\u2013182"},{"key":"165_CR32","unstructured":"Li TS et al (2015) Extracting structured chemical-induced disease relations from free text via crowdsourcing. In: Proceedings of the fifth BioCreative challenge evaluation workshop, Sevilla, pp 292\u2013298"},{"key":"165_CR33","unstructured":"Lowe DM, O\u2019Boyle NM, nd Sayle RA (2015) LeadMine: disease identification and concept mapping using Wikipedia. In: The fifth BioCreative challenge evaluation workshop, pp 240\u2013246"},{"key":"165_CR34","first-page":"bas043","volume":"2012","author":"Z Lu","year":"2012","unstructured":"Lu Z, Hirschman L (2012) Biocuration workflows and text mining: overview of the BioCreative 2012 workshop track II. Database (Oxford) 2012:bas043","journal-title":"Database (Oxford)"},{"key":"165_CR35","doi-asserted-by":"crossref","unstructured":"Manning CD et al (2014) Stanford CoreNLP natural language processing toolkit. In: Proceedings of the 52nd annual meeting of the association for computational linguistics: system demonstrations, pp 55\u201360","DOI":"10.3115\/v1\/P14-5010"},{"key":"165_CR36","volume-title":"Any domain parsing: Automatic domain adaptation for natural language parsing","author":"D McClosky","year":"2009","unstructured":"McClosky D (2009) Any domain parsing: Automatic domain adaptation for natural language parsing. Department of Computer Science, Brown University"},{"key":"165_CR37","doi-asserted-by":"crossref","unstructured":"Mintz M et al (2009) Distant supervision for relation extraction without labeled data. In: Proceedings of the 47th annual meeting of the ACL and the 4th IJCNLP of the AFNLP, pp 1003\u20131011","DOI":"10.3115\/1690219.1690287"},{"key":"165_CR38","doi-asserted-by":"crossref","unstructured":"Miwa M et al (2009) A rich feature vector for protein-protein interaction extraction from multiple corpora. In: Proceedings of the 2009 conference on empirical methods in natural language processing, pp 121\u2013130","DOI":"10.3115\/1699510.1699527"},{"issue":"suppl","key":"165_CR39","first-page":"1319","volume":"21","author":"M Narayanaswamy","year":"2005","unstructured":"Narayanaswamy M, Ravikumar K, Vijay-Shanker K (2005) Beyond the clause: extraction of phosphorylation information from Medline abstracts. Bioinformatics 21(suppl):1319\u20131327","journal-title":"Bioinformatics"},{"key":"165_CR40","doi-asserted-by":"crossref","first-page":"671","DOI":"10.1093\/jamia\/ocu041","volume":"22","author":"A Nikfarjam","year":"2015","unstructured":"Nikfarjam A et al (2015) Pharmacovigilance from social media: mining adverse drug reaction mentions using sequence labeling with word embedding cluster features. J Am Med Inform Assoc 22:671\u2013681","journal-title":"J Am Med Inform Assoc"},{"key":"165_CR41","doi-asserted-by":"crossref","unstructured":"Peng Y et al (2015) An extended dependency graph for relation extraction in biomedical texts. In: Proceedings of the 2015 workshop on biomedical natural language processing (BioNLP 2015), Beijing, pp 21\u201330","DOI":"10.18653\/v1\/W15-3803"},{"key":"165_CR42","unstructured":"Pons E et al (2015) RELigator: Chemical-disease relation extraction using prior knowledge and textual information. In: The fifth BioCreative challenge evaluation workshop, pp 247\u2013253"},{"key":"165_CR43","first-page":"120","volume":"20","author":"H Poon","year":"2015","unstructured":"Poon H, Toutanova K, Quirk C (2015) Distant supervision for cancer pathway extraction from text. Pacific Symp Biocomput 20:120\u2013131","journal-title":"Pacific Symp Biocomput"},{"key":"165_CR44","doi-asserted-by":"publisher","first-page":"S6","DOI":"10.1186\/1471-2105-9-S3-S6","volume":"9","author":"S Pyysalo","year":"2008","unstructured":"Pyysalo S et al (2008) Comparative analysis of five protein-protein interaction corpora. BMC Bioinfo 9:S6","journal-title":"BMC Bioinfo"},{"key":"165_CR45","doi-asserted-by":"publisher","first-page":"bau070","DOI":"10.1093\/database\/bau070","volume":"2014","author":"R Rak","year":"2014","unstructured":"Rak R et al (2014) Text-mining-assisted biocuration workflows in Argo. Database (Oxford) 2014:bau070","journal-title":"Database (Oxford)"},{"issue":"Suppl 3","key":"165_CR46","doi-asserted-by":"crossref","first-page":"S2","DOI":"10.1186\/2041-1480-3-S3-S2","volume":"3","author":"K Ravikumar","year":"2012","unstructured":"Ravikumar K et al (2012) Literature mining of protein-residue associations with graph rules learned through distant supervision. J Biomed Semantics 3(Suppl 3):S2","journal-title":"J Biomed Semantics"},{"key":"165_CR47","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1016\/j.drudis.2013.10.024","volume":"19","author":"D Rebholz-Schuhmann","year":"2014","unstructured":"Rebholz-Schuhmann D et al (2014) A case study: semantic integration of gene-disease associations for type 2 diabetes mellitus from literature and biomedical data resources. Drug Discovery Today 19:882\u2013889","journal-title":"Drug Discovery Today"},{"key":"165_CR48","doi-asserted-by":"crossref","unstructured":"Roller R, Stevenson M (2015) Making the most of limited training data using distant supervision. In: 2015 workshop on biomedical natural language processing (BioNLP 2015), Beijing, pp 12\u201320","DOI":"10.18653\/v1\/W15-3802"},{"key":"165_CR49","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4057.001.0001","volume-title":"Kernel methods in computational biology. Computational molecular biology","author":"B Sch\u00f6lkopf","year":"2004","unstructured":"Sch\u00f6lkopf B, Tsuda K, Vert J-P (2004) Kernel methods in computational biology. Computational molecular biology. MIT Press, Cambridge"},{"key":"165_CR50","doi-asserted-by":"publisher","first-page":"e1000837","DOI":"10.1371\/journal.pcbi.1000837","volume":"6","author":"D Tikk","year":"2010","unstructured":"Tikk D et al (2010) A comprehensive benchmark of kernel methods to extract protein\u2013protein interactions from literature. PLoS Comput Biol 6:e1000837","journal-title":"PLoS Comput Biol"},{"key":"165_CR51","unstructured":"Van Landeghem S et al (2008) Extracting protein-protein interactions from text using rich feature vectors and feature selection. In: Proceedings of the third international symposium on semantic mining in biomedicine (SMBM), pp 77\u201384"},{"key":"165_CR52","first-page":"baw032","volume":"2016","author":"C-H Wei","year":"2016","unstructured":"Wei C-H et al (2016) Assessing the state of the art in biomedical relation extraction: overview of the BioCreative V chemical-disease relation (CDR) task. Database (Oxford) 2016:baw032","journal-title":"Database (Oxford)"},{"key":"165_CR53","unstructured":"Wei C-H et al (2015) Overview of the BioCreative V chemical disease relation (CDR) task. In: Fifth BioCreative challenge evaluation workshop, Sevilla, pp 154\u2013166"},{"key":"165_CR54","doi-asserted-by":"publisher","first-page":"W518","DOI":"10.1093\/nar\/gkt441","volume":"41","author":"CH Wei","year":"2013","unstructured":"Wei CH, Kao HY, Lu Z (2013) PubTator: a web-based text mining tool for assisting biocuration. Nucleic Acids Res 41:W518\u2013522","journal-title":"Nucleic Acids Res"},{"key":"165_CR55","unstructured":"Xu J et al (2015) UTH-CCB@BioCreative V CDR task: identifying chemical-induced disease relations in biomedical text. In: The fifth BioCreative challenge evaluation workshop, pp 254\u2013259"},{"key":"165_CR56","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/j.jbi.2014.05.013","volume":"51","author":"R Xua","year":"2014","unstructured":"Xua R, Wang Q (2014) Automatic construction of a large-scale and accurate drug-side-effect association knowledge base from biomedical literature. J Biomed Info 51:191\u2013199","journal-title":"J Biomed Info"},{"key":"165_CR57","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.jbi.2015.07.013","volume":"57","author":"W Zheng","year":"2015","unstructured":"Zheng W, Blake C (2015) Using distant supervised learning to identify protein subcellular localizations from full-text scientific articles. J Biomed Inform 57:134\u2013144","journal-title":"J Biomed Inform"},{"key":"165_CR58","doi-asserted-by":"publisher","first-page":"bau087","DOI":"10.1093\/database\/bau087","volume":"2016","author":"D Zhu","year":"2014","unstructured":"Zhu D et al (2014) Integrating information retrieval with distant supervision for gene ontology annotation. Database (Oxford) 2016:bau087","journal-title":"Database (Oxford)"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-016-0165-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s13321-016-0165-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-016-0165-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,9]],"date-time":"2022-07-09T21:58:12Z","timestamp":1657403892000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-016-0165-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10,7]]},"references-count":58,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2016,12]]}},"alternative-id":["165"],"URL":"https:\/\/doi.org\/10.1186\/s13321-016-0165-z","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,10,7]]},"assertion":[{"value":"22 March 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 September 2016","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 October 2016","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"53"}}