{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T09:19:03Z","timestamp":1775726343979,"version":"3.50.1"},"reference-count":40,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2017,12,20]],"date-time":"2017-12-20T00:00:00Z","timestamp":1513728000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100005825","name":"National Institute of Food and Agriculture","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005825","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003526","name":"Department of Agriculture","doi-asserted-by":"publisher","award":["2015-70016-23029"],"award-info":[{"award-number":["2015-70016-23029"]}],"id":[{"id":"10.13039\/501100003526","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ACI 1245880, ACI 1229576, CCF-1128805, CNS-1624782"],"award-info":[{"award-number":["ACI 1245880, ACI 1229576, CCF-1128805, CNS-1624782"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01GM110240"],"award-info":[{"award-number":["R01GM110240"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,5,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Best performing named entity recognition (NER) methods for biomedical literature are based on hand-crafted features or task-specific rules, which are costly to produce and difficult to generalize to other corpora. End-to-end neural networks achieve state-of-the-art performance without hand-crafted features and task-specific knowledge in non-biomedical NER tasks. However, in the biomedical domain, using the same architecture does not yield competitive performance compared with conventional machine learning models.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We propose a novel end-to-end deep learning approach for biomedical NER tasks that leverages the local contexts based on n-gram character and word embeddings via Convolutional Neural Network (CNN). We call this approach GRAM-CNN. To automatically label a word, this method uses the local information around a word. Therefore, the GRAM-CNN method does not require any specific knowledge or feature engineering and can be theoretically applied to a wide range of existing NER problems. The GRAM-CNN approach was evaluated on three well-known biomedical datasets containing different BioNER entities. It obtained an F1-score of 87.26% on the Biocreative II dataset, 87.26% on the NCBI dataset and 72.57% on the JNLPBA dataset. Those results put GRAM-CNN in the lead of the biological NER methods. To the best of our knowledge, we are the first to apply CNN based structures to BioNER problems.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The GRAM-CNN source code, datasets and pre-trained model are available online at: https:\/\/github.com\/valdersoul\/GRAM-CNN.<\/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\/btx815","type":"journal-article","created":{"date-parts":[[2017,12,19]],"date-time":"2017-12-19T20:17:12Z","timestamp":1513714632000},"page":"1547-1554","source":"Crossref","is-referenced-by-count":127,"title":["GRAM-CNN: a deep learning approach with local context for named entity recognition in biomedical text"],"prefix":"10.1093","volume":"34","author":[{"given":"Qile","family":"Zhu","sequence":"first","affiliation":[{"name":"National Science Foundation Center for Big Learning, University of Florida, Gainesville, FL, USA"},{"name":"Department of Computer & Information Science & Engineering, University of Florida, Gainesville, FL, USA"}]},{"given":"Xiaolin","family":"Li","sequence":"additional","affiliation":[{"name":"National Science Foundation Center for Big Learning, University of Florida, Gainesville, FL, USA"},{"name":"Department of Electrical and Computer Engineering, University of Florida, Gainesville, FL, USA"}]},{"given":"Ana","family":"Conesa","sequence":"additional","affiliation":[{"name":"Department of Microbiology and Cell Science, Institute for Food and Agricultural Sciences, University of Florida, Gainesville, FL, USA"},{"name":"Genomics of Gene Expression Laboratory, Centro de Investigaci\u00f3n Pr\u00edncipe Felipe, Valencia, Spain"}]},{"given":"C\u00e9cile","family":"Pereira","sequence":"additional","affiliation":[{"name":"Department of Microbiology and Cell Science, Institute for Food and Agricultural Sciences, University of Florida, Gainesville, FL, USA"}]}],"member":"286","published-online":{"date-parts":[[2017,12,20]]},"reference":[{"key":"2023012713021209400_btx815-B1","author":"Abadi","year":"2015"},{"key":"2023012713021209400_btx815-B2","author":"Ananiadou","year":"1994"},{"key":"2023012713021209400_btx815-B3","author":"Ando","year":"2007"},{"key":"2023012713021209400_btx815-B4","volume-title":"Natural Language Processing with Python","author":"Bird","year":"2009"},{"key":"2023012713021209400_btx815-B5","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1186\/1471-2105-14-54","article-title":"Gimli: open source and high-performance biomedical name recognition","volume":"14","author":"Campos","year":"2013","journal-title":"BMC Bioinformatics"},{"key":"2023012713021209400_btx815-B6","author":"Chiu","year":"2016"},{"key":"2023012713021209400_btx815-B7","author":"Collier","year":"2000"},{"key":"2023012713021209400_btx815-B8","first-page":"2493","article-title":"Natural language processing (almost) from scratch","volume":"12","author":"Collobert","year":"2011","journal-title":"J. Mach. Learn. Res"},{"key":"2023012713021209400_btx815-B9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jbi.2013.12.006","article-title":"Ncbi disease corpus: a resource for disease name recognition and concept normalization","volume":"47","author":"Do\u011fan","year":"2014","journal-title":"J. Biomed. Inf"},{"key":"2023012713021209400_btx815-B10","author":"Finkel","year":"2004"},{"key":"2023012713021209400_btx815-B11","author":"Glorot","year":"2010"},{"key":"2023012713021209400_btx815-B12","author":"He","year":"2015"},{"key":"2023012713021209400_btx815-B13","author":"He","year":"2016"},{"key":"2023012713021209400_btx815-B14","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","article-title":"Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups","volume":"29","author":"Hinton","year":"2012","journal-title":"IEEE Signal Process. Mag"},{"key":"2023012713021209400_btx815-B15","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/S1532-0464(03)00014-5","article-title":"Rutabaga by any other name: extracting biological names","volume":"35","author":"Hirschman","year":"2002","journal-title":"J. Biomed. Inf"},{"key":"2023012713021209400_btx815-B16","doi-asserted-by":"crossref","first-page":"i286","DOI":"10.1093\/bioinformatics\/btn183","article-title":"Integrating high dimensional bi-directional parsing models for gene mention tagging","volume":"24","author":"Hsu","year":"2008","journal-title":"Bioinformatics"},{"key":"2023012713021209400_btx815-B17","author":"Kim","year":"2004"},{"key":"2023012713021209400_btx815-B18","author":"Kim","year":"2015"},{"key":"2023012713021209400_btx815-B19","author":"Kingma","year":"2014"},{"key":"2023012713021209400_btx815-B20","author":"Lafferty","year":"2001"},{"key":"2023012713021209400_btx815-B21","author":"Lample","year":"2016"},{"key":"2023012713021209400_btx815-B22","doi-asserted-by":"crossref","first-page":"2839","DOI":"10.1093\/bioinformatics\/btw343","article-title":"Taggerone: joint named entity recognition and normalization with semi-markov models","volume":"32","author":"Leaman","year":"2016","journal-title":"Bioinformatics"},{"key":"2023012713021209400_btx815-B23","author":"Leaman","year":"2008"},{"key":"2023012713021209400_btx815-B24","doi-asserted-by":"crossref","first-page":"2909","DOI":"10.1093\/bioinformatics\/btt474","article-title":"Dnorm: disease name normalization with pairwise learning to rank","volume":"29","author":"Leaman","year":"2013","journal-title":"Bioinformatics"},{"key":"2023012713021209400_btx815-B25","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"2023012713021209400_btx815-B26","author":"Li","year":"2016"},{"key":"2023012713021209400_btx815-B27","first-page":"10","author":"Limsopatham","year":"2016"},{"key":"2023012713021209400_btx815-B28","author":"Ma","year":"2016"},{"key":"2023012713021209400_btx815-B29","first-page":"313","article-title":"Building a large annotated corpus of english: the penn treebank","volume":"19","author":"Marcus","year":"1993","journal-title":"Computat. Linguist"},{"key":"2023012713021209400_btx815-B30","author":"Sang","year":"1999"},{"key":"2023012713021209400_btx815-B31","doi-asserted-by":"crossref","first-page":"3191","DOI":"10.1093\/bioinformatics\/bti475","article-title":"ABNER: An open source tool for automatically tagging genes, proteins, and other entity names in text","volume":"21","author":"Settles","year":"2005","journal-title":"Bioinformatics"},{"key":"2023012713021209400_btx815-B32","doi-asserted-by":"crossref","first-page":"S2","DOI":"10.1186\/gb-2008-9-s2-s2","article-title":"Overview of biocreative ii gene mention recognition","volume":"9","author":"Smith","year":"2008","journal-title":"Genome Biol"},{"key":"2023012713021209400_btx815-B33","author":"Song","year":"2004"},{"key":"2023012713021209400_btx815-B34","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res"},{"key":"2023012713021209400_btx815-B35","author":"Szegedy","year":"2015"},{"key":"2023012713021209400_btx815-B36","author":"Tjong Kim Sang","year":"2003"},{"key":"2023012713021209400_btx815-B37","doi-asserted-by":"crossref","first-page":"S11","DOI":"10.1186\/1471-2105-7-S5-S11","article-title":"Nerbio: using selected word conjunctions, term normalization, and global patterns to improve biomedical named entity recognition","volume":"7","author":"Tsai","year":"2006","journal-title":"BMC Bioinformatics"},{"key":"2023012713021209400_btx815-B38","first-page":"382","volume-title":"Panhellenic Conference on Informatics","author":"Tsuruoka","year":"2005"},{"key":"2023012713021209400_btx815-B39","author":"Zeiler","year":"2012"},{"key":"2023012713021209400_btx815-B40","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.1093\/bioinformatics\/bth060","article-title":"Recognizing names in biomedical texts: a machine learning approach","volume":"20","author":"Zhou","year":"2004","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/9\/1547\/48914863\/bioinformatics_34_9_1547.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/34\/9\/1547\/48914863\/bioinformatics_34_9_1547.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,27]],"date-time":"2023-01-27T13:53:51Z","timestamp":1674827631000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/34\/9\/1547\/4764002"}},"subtitle":[],"editor":[{"given":"Janet","family":"Kelso","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2017,12,20]]},"references-count":40,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2018,5,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btx815","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,5,1]]},"published":{"date-parts":[[2017,12,20]]}}}