{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:12:15Z","timestamp":1773655935835,"version":"3.50.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"S1","license":[{"start":{"date-parts":[[2015,1,19]],"date-time":"2015-01-19T00:00:00Z","timestamp":1421625600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1186\/1758-2946-7-s1-s6","type":"journal-article","created":{"date-parts":[[2015,6,18]],"date-time":"2015-06-18T11:38:16Z","timestamp":1434627496000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Optimising chemical named entity recognition with pre-processing analytics, knowledge-rich features and heuristics"],"prefix":"10.1186","volume":"7","author":[{"given":"Riza","family":"Batista-Navarro","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rafal","family":"Rak","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sophia","family":"Ananiadou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,1,19]]},"reference":[{"issue":"4","key":"625_CR1","doi-asserted-by":"publisher","first-page":"58201","DOI":"10.1371\/journal.pone.0058201","volume":"8","author":"AP Davis","year":"2013","unstructured":"Davis AP, Wiegers TC, Johnson RJ, Lay JM, Lennon-Hopkins K, Saraceni-Richards C, Sciaky D, Murphy CG, Mattingly CJ: Text mining effectively scores and ranks the literature for improving chemical-gene-disease curation at the comparative toxicogenomics database. PLoS ONE. 2013, 8 (4): 58201-10.1371\/journal.pone.0058201.","journal-title":"PLoS ONE"},{"key":"625_CR2","first-page":"123","volume-title":"Chemical Information Mining","author":"C Kol\u00e1\u0159ik","year":"2009","unstructured":"Kol\u00e1\u0159ik C, Hofmann-Apitius M: Linking Chemical and Biological Information with Natural Language Processing. Chemical Information Mining. Edited by: Banville DL. 2009, Chap 7: 123-150."},{"issue":"S-5","key":"625_CR3","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/1471-2105-11-S5-P9","volume":"11","author":"I Segura-Bedmar","year":"2010","unstructured":"Segura-Bedmar I, Mart\u00ednez P, de Pablo-S\u00e1nchez C: Extracting drug-drug interactions from biomedical texts. BMC Bioinformatics. 2010, 11 (S-5): 9-","journal-title":"BMC Bioinformatics"},{"issue":"3","key":"625_CR4","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1002\/wsbm.147","volume":"3","author":"SN Deftereos","year":"2011","unstructured":"Deftereos SN, Andronis C, Friedla EJ, Persidis A, Persidis A: Drug repurposing and adverse event prediction using high-throughput literature analysis. Wiley interdisciplinary reviews. Systems biology and medicine. 2011, 3 (3): 323-34.","journal-title":"Systems biology and medicine"},{"key":"625_CR5","volume-title":"Briefings in Bioinformatics","author":"C Li","year":"2013","unstructured":"Li C, Liakata M, Rebholz-Schuhmann D: Biological network extraction from scientific literature: state of the art and challenges. Briefings in Bioinformatics. 2013"},{"issue":"1","key":"625_CR6","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1016\/S1359-6446(05)03682-2","volume":"11","author":"DL Banville","year":"2006","unstructured":"Banville DL: Mining chemical structural information from the drug literature. Drug Discovery Today. 2006, 11 (1): 35-42.","journal-title":"Drug Discovery Today"},{"issue":"6-7","key":"625_CR7","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1002\/minf.201100005","volume":"30","author":"M Vazquez","year":"2011","unstructured":"Vazquez M, Krallinger M, Leitner F, Valencia A: Text mining for drugs and chemical compounds: Methods, tools and applications. Molecular Informatics. 2011, 30 (6-7): 506-519. 10.1002\/minf.201100005.","journal-title":"Molecular Informatics"},{"key":"625_CR8","first-page":"16194","volume-title":"RSC Adv","author":"H Gurulingappa","year":"2013","unstructured":"Gurulingappa H, Mudi A, Toldo L, Hofmann-Apitius M, Bhate J: Challenges in mining the literature for chemical information. RSC Adv. 2013, 16194-16211."},{"key":"625_CR9","doi-asserted-by":"publisher","first-page":"9","DOI":"10.5402\/2012\/619427","volume":"2012","author":"T Grego","year":"2012","unstructured":"Grego T, Pesquita C, Bastos HP, Couto FM: Chemical Entity Recognition and Resolution to ChEBI. ISRN Bioinformatics. 2012, 2012: 9-","journal-title":"ISRN Bioinformatics"},{"key":"625_CR10","doi-asserted-by":"publisher","first-page":"57","DOI":"10.3115\/1572392.1572403","volume-title":"Proceedings of the Workshop on BioNLP 2007: Biological, Translational, and Clinical Language Processing. BioNLP '07","author":"P Corbett","year":"2007","unstructured":"Corbett P, Batchelor C, Teufel S: Annotation of chemical named entities. Proceedings of the Workshop on BioNLP 2007: Biological, Translational, and Clinical Language Processing. BioNLP '07. 2007, Association for Computational Linguistics, Stroudsburg, PA, USA, 57-64."},{"key":"625_CR11","unstructured":"Chemistry Using Text Annotations. Accessed: October 2013, [ http:\/\/nactem.ac.uk\/cheta ]"},{"issue":"1","key":"625_CR12","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1142\/S0219720010004562","volume":"8","author":"D Rebholz-Schuhmann","year":"2010","unstructured":"Rebholz-Schuhmann D, Yepes J, Jose A, Van Mulligen EM, Kang N, Kors J, Milward D, Corbett P, Buyko E, Beisswanger E, Hahn U: CALBC silver standard corpus. Journal of Bioinformatics and Computational Biology. 2010, 8 (1): 163-79. 10.1142\/S0219720010004562.","journal-title":"Journal of Bioinformatics and Computational Biology"},{"key":"625_CR13","first-page":"51","volume-title":"Proceedings of the Workshop on Building and Evaluating Resources for Biomedical Text Mining. LREC","author":"C Kol\u00e1\u0159ik","year":"2008","unstructured":"Kol\u00e1\u0159ik C, Klinger R, Friedrich CM, Hofmann-Apitius M, Fluck J: Chemical names: Terminological resources and corpora annotation. Proceedings of the Workshop on Building and Evaluating Resources for Biomedical Text Mining. LREC. 2008, 51-58."},{"key":"625_CR14","unstructured":"Fraunhofer SCAI Corpora for Chemical Entity Recognition. Accessed: October 2013, [ http:\/\/www.scai.fraunhofer.de\/chem-corpora.html ]"},{"issue":"Suppl 11","key":"625_CR15","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1186\/1471-2105-9-S11-S4","volume":"9","author":"P Corbett","year":"2008","unstructured":"Corbett P, Copestake A: Cascaded classifiers for confidence-based chemical named entity recognition. BMC Bioinformatics. 2008, 9 (Suppl 11): 4-10.1186\/1471-2105-9-S11-S4.","journal-title":"BMC Bioinformatics"},{"issue":"12","key":"625_CR16","doi-asserted-by":"publisher","first-page":"1633","DOI":"10.1093\/bioinformatics\/bts183","volume":"28","author":"T Rockt\u00e4schel","year":"2012","unstructured":"Rockt\u00e4schel T, Weidlich M, Leser U: ChemSpot: a hybrid system for chemical named entity recognition. Bioinformatics. 2012, 28 (12): 1633-1640. 10.1093\/bioinformatics\/bts183.","journal-title":"Bioinformatics"},{"issue":"22","key":"625_CR17","doi-asserted-by":"publisher","first-page":"2983","DOI":"10.1093\/bioinformatics\/btp535","volume":"25","author":"KM Hettne","year":"2009","unstructured":"Hettne KM, Stierum RH, Schuemie MJ, Hendriksen PJM, Schijvenaars BJA, van Mulligen EM, Kleinjans J, Kors JA: A dictionary to identify small molecules and drugs in free text. Bioinformatics. 2009, 25 (22): 2983-2991. 10.1093\/bioinformatics\/btp535.","journal-title":"Bioinformatics"},{"key":"625_CR18","first-page":"282","volume-title":"Proceedings of the Eighteenth International Conference on Machine Learning. ICML '01","author":"JD Lafferty","year":"2001","unstructured":"Lafferty JD, McCallum A, Pereira FCN: Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. Proceedings of the Eighteenth International Conference on Machine Learning. ICML '01. 2001, Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 282-289."},{"issue":"Suppl 1","key":"625_CR19","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1186\/1758-2946-7-S1-S1","volume":"7","author":"M Krallinger","year":"2015","unstructured":"Krallinger M, Leitner F, Rabal O, Vazquez M, Oyarzabal J, Valencia A: CHEMDNER: The drugs and chemical names extraction challenge. J Cheminform. 2015, 7 (Suppl 1): S1-","journal-title":"J Cheminform"},{"issue":"Suppl 1","key":"625_CR20","doi-asserted-by":"publisher","first-page":"S2","DOI":"10.1186\/1758-2946-7-S1-S2","volume":"7","author":"M Krallinger","year":"2015","unstructured":"Krallinger M, Rabal O, Leitner F, Vazquez M, Salgado D, Lu Z, Leaman R, Lu Y, Ji D, Lowe DM, Sayle RA, Batista-Navarro RT, Rak R, Huber T, Rocktaschel T, Matos S, Campos D, Tang B, Xu H, Munkhdalai T, Ryu KH, Ramanan SV, Nathan S, Zitnik S, Bajec M, Weber L, Irmer M, Akhondi SA, Kors JA, Xu S, An X, Sikdar UK, Ekbal A, Yoshioka M, Dieb TM, Choi M, Verspoor K, Khabsa M, Giles CL, Liu H, Ravikumar KE, Lamurias A, Couto FM, Dai H, Tsai RT, Ata C, Can T, Usie A, Alves R, Segura-Bedmar I, Martinez P, Oryzabal J, Valencia A: The CHEMDNER corpus of chemicals and drugs and its annotation principles. J Cheminform. 2015, 7 (Suppl 1): S2-","journal-title":"J Cheminform"},{"key":"625_CR21","first-page":"064","volume":"2014","author":"R Rak","year":"2014","unstructured":"Rak R, Batista-Navarro RT, Carter J, Rowley A, Ananiadou S: Processing biological literature with customizable web services supporting interoperable formats. Database. 2014, 2014: 064-","journal-title":"Database"},{"key":"625_CR22","first-page":"55","volume":"2","author":"RTB Batista-Navarro","year":"2013","unstructured":"Batista-Navarro RTB, Rak R, Ananiadou S: Chemistry-specific features and heuristics for developing a CRF-based chemical named entity recogniser. Proceedings of the Fourth BioCreative Challenge Evaluation Workshop. 2013, 2: 55-59.","journal-title":"Proceedings of the Fourth BioCreative Challenge Evaluation Workshop"},{"issue":"1","key":"625_CR23","doi-asserted-by":"publisher","first-page":"94","DOI":"10.1007\/s11306-010-0251-6","volume":"7","author":"C Nobata","year":"2011","unstructured":"Nobata C, Dobson PD, Iqbal SA, Mendes P, Tsujii J, Kell DB, Ananiadou S: Mining metabolites: extracting the yeast metabolome from the literature. Metabolomics. 2011, 7 (1): 94-101. 10.1007\/s11306-010-0251-6.","journal-title":"Metabolomics"},{"key":"625_CR24","unstructured":"OSCAR4. Accessed: October 2013, [ https:\/\/bitbucket.org\/wwmm\/oscar4\/wiki\/Home ]"},{"key":"625_CR25","unstructured":"ChemSpot. Accessed: October 2013, [ https:\/\/github.com\/rockt\/ChemSpot ]"},{"key":"625_CR26","volume-title":"Nucleic Acids Research","author":"J Hastings","year":"2012","unstructured":"Hastings J, de Matos P, Dekker A, Ennis M, Harsha B, Kale N, Muthukrishnan V, Owen G, Turner S, Williams M, Steinbeck C: The ChEBI reference database and ontology for biologically relevant chemistry: enhancements for 2013. Nucleic Acids Research. 2012"},{"issue":"suppl 1","key":"625_CR27","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1093\/nar\/gkn810","volume":"37","author":"DS Wishart","year":"2009","unstructured":"Wishart DS, Knox C, Guo AC, Eisner R, Young N, Gautam B, Hau DD, Psychogios N, Dong E, Bouatra S, Mandal R, Sinelnikov I, Xia J, Jia L, Cruz JA, Lim E, Sobsey CA, Shrivastava S, Huang P, Liu P, Fang L, Peng J, Fradette R, Cheng D, Tzur D, Clements M, Lewis A, De Souza A, Zuniga A, Dawe M, Xiong Y, Clive D, Nazyrova A, Shaykhutdinov R, Li L, Vogel HJ, Forsythe I: HMDB: a knowledgebase for the human metabolome. Nucleic Acids Research. 2009, 37 (suppl 1): 603-610.","journal-title":"Nucleic Acids Research"},{"key":"625_CR28","unstructured":"NaCTeM Metabolite and Enzyme Corpus. Accessed: October 2013, [ http:\/\/www.nactem.ac.uk\/metabolite-corpus ]"},{"key":"625_CR29","first-page":"942","volume-title":"Proceedings of the 10th International Work-Conference on Artificial Neural Networks: Part II: Distributed Computing, Artificial Intelligence, Bioinformatics, Soft Computing, and Ambient Assisted Living. IWANN '09","author":"T Grego","year":"2009","unstructured":"Grego T, P\u0119zik P, Couto FM, Rebholz-Schuhmann D: Identification of chemical entities in patent documents. Proceedings of the 10th International Work-Conference on Artificial Neural Networks: Part II: Distributed Computing, Artificial Intelligence, Bioinformatics, Soft Computing, and Ambient Assisted Living. IWANN '09. 2009, Springer, Berlin, Heidelberg, 942-949."},{"key":"625_CR30","unstructured":"Patents Gold Standard Annotations. Accessed: October 2013, [ http:\/\/chebi.cvs.sourceforge.net\/viewvc\/chebi\/chapati\/patentsGoldStandard ]"},{"issue":"5","key":"625_CR31","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1016\/j.jbi.2013.07.011","volume":"46","author":"M Herrero-Zazo","year":"2013","unstructured":"Herrero-Zazo M, Segura-Bedmar I, Mart\u00ednez P, Declerck T: The ddi corpus: An annotated corpus with pharmacological substances and drug-drug interactions. Journal of Biomedical Informatics. 2013, 46 (5): 914-920. 10.1016\/j.jbi.2013.07.011.","journal-title":"Journal of Biomedical Informatics"},{"key":"625_CR32","unstructured":"Corpora for Drug-Drug Interaction Extraction. Accessed: October 2013, [ http:\/\/labda.inf.uc3m.es\/doku.php?id=en:labda_ddicorpus ]"},{"issue":"1","key":"625_CR33","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1186\/1471-2105-14-35","volume":"14","author":"H-Y Wu","year":"2013","unstructured":"Wu H-Y, Karnik S, Subhadarshini A, Wang Z, Philips S, Han X, Chiang C, Liu L, Boustani M, Rocha L, Quinney S, Flockhart D, Li L: An integrated pharmacokinetics ontology and corpus for text mining. BMC Bioinformatics. 2013, 14 (1): 35-10.1186\/1471-2105-14-35.","journal-title":"BMC Bioinformatics"},{"key":"625_CR34","unstructured":"Pharmacokinetics Corpus. Accessed: October 2013, [ http:\/\/rweb.compbio.iupui.edu\/corpus ]"},{"key":"625_CR35","first-page":"010","volume-title":"Database : The Journal of Biological Databases and Curation","author":"R Rak","year":"2012","unstructured":"Rak R, Rowley A, Black W, Ananiadou S: Argo: an integrative, interactive, text mining-based workbench supporting curation. Database : The Journal of Biological Databases and Curation. 2012, 010-"},{"issue":"5","key":"625_CR36","doi-asserted-by":"publisher","first-page":"20181","DOI":"10.1371\/journal.pone.0020181","volume":"6","author":"B Kolluru","year":"2011","unstructured":"Kolluru B, Hawizy L, Murray-Rust P, Tsujii J, Ananiadou S: Using workflows to explore and optimise named entity recognition for chemistry. PLoS ONE. 2011, 6 (5): 20181-10.1371\/journal.pone.0020181.","journal-title":"PLoS ONE"},{"key":"625_CR37","unstructured":"Alias-I: LingPipe 4.1.0. Accessed: July 2013, [ http:\/\/alias-i.com\/lingpipe ]"},{"key":"625_CR38","unstructured":"Cafetiere English Sentence Detector. Accessed: October 2013, [ http:\/\/metashare.metanet4u.eu\/repository\/browse\/u-compare-cafetiere-english-sentence-detector\/aff1ddc0bc8911e1a404080027e73ea259aeca28412944ea97f7b2580a41caec\/# ]"},{"key":"625_CR39","first-page":"382","volume":"3746","author":"Y Tsuruoka","year":"2005","unstructured":"Tsuruoka Y, Tateisi Y, Kim J-D, Ohta T, McNaught J, Ananiadou S, Tsujii J: Developing a Robust Part-of-Speech Tagger for Biomedical Text. In: Advances in Informatics - 10th Panhellenic Conference on Informatics. LNCS, Springer, Volos, Greece. 2005, 3746: 382-392.","journal-title":"LNCS, Springer, Volos, Greece"},{"issue":"1","key":"625_CR40","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1186\/1758-2946-3-41","volume":"3","author":"DM Jessop","year":"2011","unstructured":"Jessop DM, Adams SE, Willighagen EL, Hawizy L, Murray-Rust P: OSCAR4: a flexible architecture for chemical text-mining. Journal of Cheminformatics. 2011, 3 (1): 41-10.1186\/1758-2946-3-41.","journal-title":"Journal of Cheminformatics"},{"key":"625_CR41","unstructured":"Okazaki N: CRFsuite: a fast implementation of Conditional Random Fields (CRFs). Accessed: July 2013, [ http:\/\/www.chokkan.org\/software\/crfsuite ]"},{"key":"625_CR42","doi-asserted-by":"crossref","unstructured":"Knox C, Law V, Jewison T, Liu P, Ly S, Frolkis A, Pon A, Banco K, Mak C, Neveu V, Djoumbou Y, Eisner R, Guo AC, Wishart DS: DrugBank 3.0: a comprehensive resource for 'omics' research on drugs. Nucleic acids research. 2011, 1035-41. 39 Database","DOI":"10.1093\/nar\/gkq1126"},{"key":"625_CR43","volume-title":"Nucleic Acids Research","author":"AP Davis","year":"2012","unstructured":"Davis AP, Murphy CG, Johnson R, Lay JM, Lennon-Hopkins K, Saraceni-Richards C, Sciaky D, King BL, Rosenstein MC, Wiegers TC, Mattingly CJ: The Comparative Toxicogenomics Database: update 2013. Nucleic Acids Research. 2012"},{"key":"625_CR44","volume-title":"Annual Reports in Computational Chemistry","author":"EE Bolton","year":"2008","unstructured":"Bolton EE, Wang Y, Thiessen PA, Bryant SH: PubChem: Integrated Platform of Small Molecules and Biological Activities. Annual Reports in Computational Chemistry. 2008, 4:"},{"key":"625_CR45","volume-title":"Registry file basic name segment dictionary. Technical report","author":"American Chemical Society","year":"1993","unstructured":"American Chemical Society: Registry file basic name segment dictionary. Technical report. 1993"},{"key":"625_CR46","first-page":"451","volume-title":"Pacific Symposium on Biocomputing","author":"AS Schwartz","year":"2003","unstructured":"Schwartz AS, Hearst MA: A simple algorithm for identifying abbreviation definitions in biomedical text. Pacific Symposium on Biocomputing. 2003, 451-462."},{"key":"625_CR47","first-page":"341","volume-title":"Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013)","author":"I Segura-Bedmar","year":"2013","unstructured":"Segura-Bedmar I, Mart\u00ednez P, Herrero Zazo M: SemEval-2013 Task 9: Extraction of Drug-Drug Interactions from Biomedical Texts (DDIExtraction 2013). Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013). 2013, Association for Computational Linguistics, Atlanta, Georgia, USA, 341-350."},{"key":"625_CR48","unstructured":"Cho H-C, Okazaki N, Miwa M, Tsujii J: NERsuite: a named entity recognition toolkit. Accessed: July 2013, [ https:\/\/github.com\/nlplab\/nersuite ]"},{"key":"625_CR49","unstructured":"Leitner F: BioCreative II.5 Evaluation Library. Accessed: August 2013, [ http:\/\/www.biocreative.org\/resources\/biocreative-ii5\/evaluation-library ]"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1758-2946-7-S1-S6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1758-2946-7-S1-S6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1758-2946-7-S1-S6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,14]],"date-time":"2022-05-14T00:16:35Z","timestamp":1652487395000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/1758-2946-7-S1-S6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,1,19]]},"references-count":49,"journal-issue":{"issue":"S1","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["625"],"URL":"https:\/\/doi.org\/10.1186\/1758-2946-7-s1-s6","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,1,19]]},"assertion":[{"value":"19 January 2015","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"S6"}}