{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T10:12:16Z","timestamp":1773655936010,"version":"3.50.1"},"reference-count":28,"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-s7","type":"journal-article","created":{"date-parts":[[2015,6,18]],"date-time":"2015-06-18T09:14:04Z","timestamp":1434618844000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["A document processing pipeline for annotating chemical entities in scientific documents"],"prefix":"10.1186","volume":"7","author":[{"given":"David","family":"Campos","sequence":"first","affiliation":[]},{"given":"S\u00e9rgio","family":"Matos","sequence":"additional","affiliation":[]},{"given":"Jos\u00e9 L","family":"Oliveira","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2015,1,19]]},"reference":[{"key":"626_CR1","first-page":"839","volume-title":"Current Methodologies for Biomedical Named Entity Recognition","author":"D Campos","year":"2013","unstructured":"Campos D, Matos S, Oliveira JL: Current Methodologies for Biomedical Named Entity Recognition. 2013, John Wiley & Sons, Inc., Hoboken, New Jersey, 839-868."},{"issue":"Suppl 2","key":"626_CR2","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/gb-2008-9-s2-s2","volume":"9","author":"L Smith","year":"2008","unstructured":"Smith L, Tanabe LK, Ando RJn, Kuo C-J, Chung I-F, Hsu C-N, Lin Y-S, Klinger R, Friedrich CM, Ganchev K, Torii M, Liu H, Haddow B, Struble CA, Povinelli RJ, Vlachos A, Baumgartner Wa, Hunter L, Carpenter B, Tsai RT-H, Dai H-J, Liu F, Chen Y, Sun C, Katrenko S, Adriaans P, Blaschke C, Torres R, Neves M, Nakov P, Divoli A, Man\u00e3-l\u00f3pez M, Mata J, Wilbur WJ: Overview of BioCreative II gene mention recognition. Genome Biology. 2008, 9 (Suppl 2): 2-10.1186\/gb-2008-9-s2-s2.","journal-title":"Genome Biology"},{"issue":"Suppl 8","key":"626_CR3","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/1471-2105-12-S8-S2","volume":"12","author":"Z Lu","year":"2011","unstructured":"Lu Z, Kao H-Y, Wei C-H, Huang M, Liu J, Kuo C-J, Hsu C-N, Tsai RT-H, Dai H-J, Okazaki N, Cho H-C, Gerner M, Solt I, Agarwal S, Liu F, Vishnyakova D, Ruch P, Romacker M, Rinaldi F, Bhattacharya S, Srinivasan P, Liu H, Torii M, Matos S, Campos D, Verspoor K, Livingston KM, Wilbur WJ: The gene normalization task in BioCreative III. BMC bioinformatics. 2011, 12 (Suppl 8): 2-10.1186\/1471-2105-12-S8-S2.","journal-title":"BMC bioinformatics"},{"key":"626_CR4","first-page":"175","volume-title":"Theory and Applications for Advanced Text Mining, InTech, Rijeka, Croatia","author":"D Campos","year":"2012","unstructured":"Campos D, Matos S, Oliveira JL: Biomedical Named Entity Recognition: A Survey of Machine-Learning Tools. Theory and Applications for Advanced Text Mining, InTech, Rijeka, Croatia. Edited by: Sakurai S. 2012, 175-195."},{"key":"626_CR5","first-page":"27","volume-title":"Proceedings of the Workshop on Detecting Structure in Scholarly Discourse. ACL '12, Association for Computational Linguistics, Stroudsburg, PA, USA","author":"T Ohta","year":"2012","unstructured":"Ohta T, Pyysalo S, Tsujii J, Ananiadou S: Open-domain anatomical entity mention detection. Proceedings of the Workshop on Detecting Structure in Scholarly Discourse. ACL '12, Association for Computational Linguistics, Stroudsburg, PA, USA. 2012, 27-36."},{"key":"626_CR6","volume-title":"Proceedings of BioNLP'12. Association for Computational Linguistics, Stroudsburg, PA, USA","author":"RI Do\u01e7an","year":"2012","unstructured":"Do\u01e7an RI, Lu Z: An improved corpus of disease mentions in PubMed citations. Proceedings of BioNLP'12. Association for Computational Linguistics, Stroudsburg, PA, USA. 2012"},{"key":"626_CR7","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1186\/1471-2105-13-161","volume":"13","author":"M Bada","year":"2012","unstructured":"Bada M, Eckert M, Evans D, Garcia K, Shipley K, Sitnikov D, Baumgartner Wa, Cohen KB, Verspoor K, Blake JA, Hunter LE: Concept annotation in the CRAFT corpus. BMC bioinformatics. 2012, 13: 161-10.1186\/1471-2105-13-161.","journal-title":"BMC bioinformatics"},{"key":"626_CR8","doi-asserted-by":"crossref","unstructured":"Campos D, Matos S, Oliveira JL: A modular framework for biomedical concept recognition. BMC bioinformatics. 2013, 14 (281):","DOI":"10.1186\/1471-2105-14-281"},{"issue":"6-7","key":"626_CR9","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: 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"},{"issue":"22","key":"626_CR10","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, Mulligen EMv, Kleinjans J, Kors Ja: A dictionary to identify small molecules and drugs in free text. Bioinformatics (Oxford, England). 2009, 25 (22): 2983-2991. 10.1093\/bioinformatics\/btp535.","journal-title":"Bioinformatics (Oxford, England)"},{"key":"626_CR11","first-page":"51","volume-title":"Workshop on Building and Evaluating Resources for Biomedical Text Mining (Language Resources and Evaluation Conference)","author":"C Kol\u00e1rik","year":"2008","unstructured":"Kol\u00e1rik C, Klinger R, Friedrich CM, Hofmann-Apitius M, Fluck J: Chemical names: terminological resources and corpora annotation. Workshop on Building and Evaluating Resources for Biomedical Text Mining (Language Resources and Evaluation Conference). 2008, 51-58."},{"key":"626_CR12","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. Association for Computational Linguistics, Stroudsburg, PA, USA","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. Association for Computational Linguistics, Stroudsburg, PA, USA. 2007, 57-64."},{"key":"626_CR13","doi-asserted-by":"crossref","unstructured":"Corbett P, Copestake AA: Cascaded classifiers for confidence-based chemical named entity recognition. BMC Bioinformatics. 2008, 9 (S-11):","DOI":"10.1186\/1471-2105-9-S11-S4"},{"issue":"13","key":"626_CR14","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1093\/bioinformatics\/btn181","volume":"24","author":"R Klinger","year":"2008","unstructured":"Klinger R, Kol\u00e1rik C, Fluck J, Hofmann-Apitius M, Friedrich CM: Detection of IUPAC and IUPAC-like chemical names. Bioinformatics (Oxford, England). 2008, 24 (13): 268-76. 10.1093\/bioinformatics\/btn181.","journal-title":"Bioinformatics (Oxford, England)"},{"key":"626_CR15","first-page":"2","volume":"2","author":"M Krallinger","year":"2013","unstructured":"Krallinger M, Leitner F, Rabal O, Vazquez M, Oyarzabal J, Valencia A: Overview of the chemical compound and drug name recognition (chemdner) task. BioCreative Challenge Evaluation Workshop. 2013, 2: 2-","journal-title":"BioCreative Challenge Evaluation Workshop"},{"issue":"15","key":"626_CR16","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1093\/bioinformatics\/btt317","volume":"29","author":"T Nunes","year":"2013","unstructured":"Nunes T, Campos D, Matos S, Oliveira JL: BeCAS: biomedical concept recognition services and visualization. Bioinformatics (Oxford, England). 2013, 29 (15): 1915-1916. 10.1093\/bioinformatics\/btt317.","journal-title":"Bioinformatics (Oxford, England)"},{"key":"626_CR17","volume-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"J Lafferty","year":"2001","unstructured":"Lafferty J, McCallum A, Pereira F: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. 2001"},{"key":"626_CR18","unstructured":"McCallum AK: MALLET: A Machine Learning for Language Toolkit. [\n                    http:\/\/mallet.cs.umass.edu\n                    \n                  ]"},{"issue":"1","key":"626_CR19","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1186\/1471-2105-14-54","volume":"14","author":"D Campos","year":"2013","unstructured":"Campos D, Matos S, Oliveira JL: Gimli: open source and high-performance biomedical name recognition. BMC bioinformatics. 2013, 14 (1): 54-10.1186\/1471-2105-14-54.","journal-title":"BMC bioinformatics"},{"key":"626_CR20","unstructured":"Alias-i I: LingPipe. [\n                    http:\/\/alias-i.com\/lingpipe\/index.html\n                    \n                  ]"},{"key":"626_CR21","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1186\/1471-2105-13-207","volume":"13","author":"K Verspoor","year":"2012","unstructured":"Verspoor K, Cohen KB, Lanfranchi A, Warner C, Johnson HL, Roeder C, Choi JD, Funk C, Malenkiy Y, Eckert M, Xue N, Baumgartner Wa, Bada M, Palmer M, Hunter LE: A corpus of full-text journal articles is a robust evaluation tool for revealing differences in performance of biomedical natural language processing tools. BMC bioinformatics. 2012, 13: 207-10.1186\/1471-2105-13-207.","journal-title":"BMC bioinformatics"},{"key":"626_CR22","first-page":"1044","volume-title":"Eleventh Conference on Computational Natural Language Learning, Prague, Czech Republic. Association for Computational Linguistics","author":"K Sagae","year":"2007","unstructured":"Sagae K: Dependency parsing and domain adaptation with LR models and parser ensembles. Eleventh Conference on Computational Natural Language Learning, Prague, Czech Republic. Association for Computational Linguistics. 2007, 1044-1050."},{"issue":"suppl 1","key":"626_CR23","first-page":"344","volume":"36","author":"K Degtyarenko","year":"2008","unstructured":"Degtyarenko K, De Matos P, Ennis M, Hastings J, Zbinden M, McNaught A, Alc\u00e1ntara R, Darsow M, Guedj M, Ashburner M: ChEBI: a database and ontology for chemical entities of biological interest. Nucleic acids research. 2008, 36 (suppl 1): 344-350.","journal-title":"Nucleic acids research"},{"key":"626_CR24","doi-asserted-by":"crossref","unstructured":"Davis AP, Murphy CG, Saraceni-Richards CA, Rosenstein MC, Wiegers TC, Mattingly CJ: Comparative Toxicogenomics Database: a knowledgebase and discovery tool for chemical-gene-disease networks. Nucleic acids research. 2009, 786-92. 37 Database","DOI":"10.1093\/nar\/gkn580"},{"issue":"suppl 2","key":"626_CR25","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1093\/nar\/gkp456","volume":"37","author":"Y Wang","year":"2009","unstructured":"Wang Y, Xiao J, Suzek TO, Zhang J, Wang J, Bryant SH: Pubchem: a public information system for analyzing bioactivities of small molecules. Nucleic acids research. 2009, 37 (suppl 2): 623-633.","journal-title":"Nucleic acids research"},{"key":"626_CR26","doi-asserted-by":"crossref","unstructured":"Wishart DS, Knox C, Guo AC, Shrivastava S, Hassanali M, Stothard P, Chang Z, Woolsey J: DrugBank: a comprehensive resource for in silico drug discovery and exploration. Nucleic acids research. 2006, 668-72. 34 Database","DOI":"10.1093\/nar\/gkj067"},{"issue":"9","key":"626_CR27","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1093\/bioinformatics\/bts125","volume":"28","author":"D Campos","year":"2012","unstructured":"Campos D, Matos S, Lewin I, Oliveira JL, Rebholz-Schuhmann D: Harmonization of gene\/protein annotations: towards a gold standard MEDLINE. Bioinformatics (Oxford, England). 2012, 28 (9): 1253-1261. 10.1093\/bioinformatics\/bts125.","journal-title":"Bioinformatics (Oxford, England)"},{"key":"626_CR28","first-page":"451","volume-title":"Pacific Symposium on Biocomputing, Hawaii, HI, USA","author":"AS Schwartz","year":"2003","unstructured":"Schwartz AS, Hearst MA: A simple algorithm for identifying abbreviation definitions in biomedical text. Pacific Symposium on Biocomputing, Hawaii, HI, USA. 2003, Computer Science Division, University of California, Berkeley, Berkeley, CA 94720, USA, 451-462."}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/1758-2946-7-S1-S7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/1758-2946-7-S1-S7\/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-S7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,6,24]],"date-time":"2019-06-24T14:10:44Z","timestamp":1561385444000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/1758-2946-7-S1-S7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,1,19]]},"references-count":28,"journal-issue":{"issue":"S1","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["626"],"URL":"https:\/\/doi.org\/10.1186\/1758-2946-7-s1-s7","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":"S7"}}