{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,7]],"date-time":"2026-02-07T10:52:47Z","timestamp":1770461567914,"version":"3.49.0"},"reference-count":47,"publisher":"Oxford University Press (OUP)","issue":"12","license":[{"start":{"date-parts":[[2021,9,15]],"date-time":"2021-09-15T00:00:00Z","timestamp":1631664000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"Beijing Baidu Netcom Science Technology"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61872113"],"award-info":[{"award-number":["61872113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61876052"],"award-info":[{"award-number":["61876052"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62006061"],"award-info":[{"award-number":["62006061"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Special Foundation for Technology Research Program of Guangdong Province","award":["2015B010131010"],"award-info":[{"award-number":["2015B010131010"]}]},{"name":"Strategic Emerging Industry Development Special Funds of Shenzhen","award":["JCYJ20180306172232154"],"award-info":[{"award-number":["JCYJ20180306172232154"]}]},{"name":"CCF-Baidu Open Fund","award":["CCF-BAIDUOF2020004"],"award-info":[{"award-number":["CCF-BAIDUOF2020004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,11,25]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Objective<\/jats:title><jats:p>There have been various methods to deal with the erroneous training data in distantly supervised relation extraction (RE), however, their performance is still far from satisfaction. We aimed to deal with the insufficient modeling problem on instance-label correlations for predicting biomedical relations using deep learning and reinforcement learning.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and Methods<\/jats:title><jats:p>In this study, a new computational model called piecewise attentive convolutional neural network and reinforcement learning (PACNN+RL) was proposed to perform RE on distantly supervised data generated from Unified Medical Language System with MEDLINE abstracts and benchmark datasets. In PACNN+RL, PACNN was introduced to encode semantic information of biomedical text, and the RL method with memory backtracking mechanism was leveraged to alleviate the erroneous data issue. Extensive experiments were conducted on 4 biomedical RE tasks.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The proposed PACNN+RL model achieved competitive performance on 8 biomedical corpora, outperforming most baseline systems. Specifically, PACNN+RL outperformed all baseline methods with the F1-score of 0.5592 on the may-prevent dataset, 0.6666 on the may-treat dataset, and 0.3838 on the DDI corpus, 2011. For the protein-protein interaction RE task, we obtained new state-of-the-art performance on 4 out of 5 benchmark datasets.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The performance on many distantly supervised biomedical RE tasks was substantially improved, primarily owing to the denoising effect of the proposed model. It is anticipated that PACNN+RL will become a useful tool for large-scale RE and other downstream tasks to facilitate biomedical knowledge acquisition. We also made the demonstration program and source code publicly available at http:\/\/112.74.48.115:9000\/.<\/jats:p><\/jats:sec>","DOI":"10.1093\/jamia\/ocab176","type":"journal-article","created":{"date-parts":[[2021,8,6]],"date-time":"2021-08-06T11:18:53Z","timestamp":1628248733000},"page":"2571-2581","source":"Crossref","is-referenced-by-count":11,"title":["Distantly supervised biomedical relation extraction using piecewise attentive convolutional neural network and reinforcement learning"],"prefix":"10.1093","volume":"28","author":[{"given":"Tiantian","family":"Zhu","sequence":"first","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"},{"name":"Department of Network Intelligence, Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Xiang","sequence":"additional","affiliation":[{"name":"Department of Network Intelligence, Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7490-684X","authenticated-orcid":false,"given":"Baotian","family":"Hu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8473-7293","authenticated-orcid":false,"given":"Qingcai","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, China"},{"name":"Department of Network Intelligence, Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weihua","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Knowledge Graph, Baidu International Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2021,9,15]]},"reference":[{"issue":"3","key":"2021120106305899400_ocab176-B1","doi-asserted-by":"crossref","first-page":"bbaa057","DOI":"10.1093\/bib\/bbaa057","article-title":"Recent advances in biomedical literature mining","volume":"22","author":"Zhao","year":"2021","journal-title":"Brief Bioinform"},{"key":"2021120106305899400_ocab176-B2","doi-asserted-by":"crossref","first-page":"bas041","DOI":"10.1093\/database\/bas041","article-title":"Accelerating literature curation with text-mining tools: a case study of using PubTator to curate genes in PubMed abstracts","volume":"2012","author":"Wei","year":"2012","journal-title":"Database (Oxford)"},{"issue":"3","key":"2021120106305899400_ocab176-B3","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1093\/bib\/6.3.239","article-title":"Text mining and ontologies in biomedicine: making sense of raw text","volume":"6","author":"Spasic","year":"2005","journal-title":"Brief Bioinform"},{"key":"2021120106305899400_ocab176-B4","article-title":"Advances of biomedical text mining for semantic search","volume":"5","author":"Ananiadou","year":"2011","journal-title":"Web Sci Med Domain"},{"key":"2021120106305899400_ocab176-B5","doi-asserted-by":"crossref","first-page":"W518","DOI":"10.1093\/nar\/gkt441","article-title":"PubTator: a web-based text mining tool for assisting biocuration","volume":"41 (Web Server issue","author":"Wei","year":"2013","journal-title":"Nucleic Acids Res"},{"issue":"2","key":"2021120106305899400_ocab176-B6","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1093\/bioinformatics\/17.2.155","article-title":"Automated extraction of information on protein-protein interactions from the biological literature","volume":"17","author":"Ono","year":"2001","journal-title":"Bioinformatics"},{"key":"2021120106305899400_ocab176-B7","first-page":"659","author":"Ciaramita","year":"2005"},{"key":"2021120106305899400_ocab176-B8","doi-asserted-by":"crossref","first-page":"S2","DOI":"10.1186\/1471-2105-9-S11-S2","article-title":"All-paths graph kernel for protein-protein interaction extraction with evaluation of cross-corpus learning","volume":"9 (Suppl 11","author":"Airola","year":"2008","journal-title":"BMC Bioinformatics"},{"issue":"23","key":"2021120106305899400_ocab176-B9","doi-asserted-by":"crossref","first-page":"3365","DOI":"10.1093\/bioinformatics\/btu557","article-title":"A novel feature-based approach to extract drug-drug interactions from biomedical text","volume":"30","author":"Bui","year":"2014","journal-title":"Bioinformatics"},{"key":"2021120106305899400_ocab176-B10","first-page":"77","author":"Craven","year":"1999"},{"key":"2021120106305899400_ocab176-B11","first-page":"1003","author":"Mintz","year":"2009"},{"key":"2021120106305899400_ocab176-B12","first-page":"25","author":"Thomas","year":"2011"},{"key":"2021120106305899400_ocab176-B13","first-page":"184","author":"Li","year":"2017"},{"key":"2021120106305899400_ocab176-B14","first-page":"35","author":"Bobi\u0107","year":"2012"},{"key":"2021120106305899400_ocab176-B15","first-page":"148","author":"Riedel","year":"2010"},{"key":"2021120106305899400_ocab176-B16","first-page":"541","author":"Hoffmann","year":"2011"},{"key":"2021120106305899400_ocab176-B17","first-page":"455","author":"Surdeanu","year":"2012"},{"key":"2021120106305899400_ocab176-B18","first-page":"1753","author":"Zeng","year":"2015"},{"key":"2021120106305899400_ocab176-B19","first-page":"2124","author":"Lin","year":"2016"},{"key":"2021120106305899400_ocab176-B20","first-page":"3060","author":"Ji","year":"2017"},{"key":"2021120106305899400_ocab176-B21","first-page":"5779","author":"Feng","year":"2018"},{"key":"2021120106305899400_ocab176-B22","first-page":"2137","author":"Qin","year":"2018"},{"key":"2021120106305899400_ocab176-B23","first-page":"97","author":"Roller","year":"2015"},{"key":"2021120106305899400_ocab176-B24","first-page":"1","author":"Segura-Bedmar","year":"2011"},{"issue":"2","key":"2021120106305899400_ocab176-B25","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.artmed.2004.07.016","article-title":"Comparative experiments on learning information extractors for proteins and their interactions","volume":"33","author":"Bunescu","year":"2005","journal-title":"Artif Intell Med"},{"key":"2021120106305899400_ocab176-B26","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1186\/1471-2105-8-50","article-title":"BioInfer: a corpus for information extraction in the biomedical domain","volume":"8","author":"Pyysalo","year":"2007","journal-title":"BMC Bioinformatics"},{"issue":"3","key":"2021120106305899400_ocab176-B27","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1093\/bioinformatics\/btl616","article-title":"RelEx\u2013relation extraction using dependency parse trees","volume":"23","author":"Fundel","year":"2007","journal-title":"Bioinformatics"},{"key":"2021120106305899400_ocab176-B28","first-page":"326","author":"Ding","year":"2002"},{"key":"2021120106305899400_ocab176-B29","first-page":"1","author":"N\u00e9dellec","year":"2005"},{"key":"2021120106305899400_ocab176-B30","doi-asserted-by":"crossref","first-page":"D267","DOI":"10.1093\/nar\/gkh061","article-title":"The Unified Medical Language System (UMLS): integrating biomedical terminology","volume":"32 (Database issue","author":"Bodenreider","year":"2004","journal-title":"Nucleic Acids Res"},{"key":"2021120106305899400_ocab176-B31","author":"Thomas","year":"2012"},{"key":"2021120106305899400_ocab176-B32","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/j.jbi.2015.03.002","article-title":"Extracting drug-drug interactions from literature using a rich feature-based linear kernel approach","volume":"55","author":"Kim","year":"2015","journal-title":"J Biomed Inform"},{"key":"2021120106305899400_ocab176-B33","doi-asserted-by":"crossref","first-page":"1850404","DOI":"10.1155\/2016\/1850404","article-title":"Multichannel convolutional neural network for biological relation extraction","volume":"2016","author":"Quan","year":"2016","journal-title":"Biomed Res Int"},{"key":"2021120106305899400_ocab176-B34","first-page":"39","author":"Moen","year":"2013"},{"key":"2021120106305899400_ocab176-B35","first-page":"2335","author":"Zeng","year":"2014"},{"issue":"3\u20134","key":"2021120106305899400_ocab176-B36","doi-asserted-by":"crossref","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Mach Learn"},{"key":"2021120106305899400_ocab176-B37","first-page":"1057","author":"Sutton","year":"1999"},{"issue":"3","key":"2021120106305899400_ocab176-B38","doi-asserted-by":"crossref","first-page":"11","DOI":"10.5121\/ijdkp.2016.6302","article-title":"Two level self-supervised relation extraction from MEDLINE using UMLS","volume":"6","author":"Banuqitah","year":"2016","journal-title":"Int J Data Mining Knowl Manag Process"},{"issue":"7","key":"2021120106305899400_ocab176-B39","doi-asserted-by":"crossref","first-page":"e1000837","DOI":"10.1371\/journal.pcbi.1000837","article-title":"A comprehensive benchmark of kernel methods to extract protein-protein interactions from literature","volume":"6","author":"Tikk","year":"2010","journal-title":"PLoS Comput Biol"},{"key":"2021120106305899400_ocab176-B40","first-page":"2810","author":"Ye","year":"2019"},{"issue":"4","key":"2021120106305899400_ocab176-B41","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"issue":"5","key":"2021120106305899400_ocab176-B42","doi-asserted-by":"crossref","first-page":"879","DOI":"10.1016\/j.jbi.2012.04.004","article-title":"The EU-ADR corpus: annotated drugs, diseases, targets, and their relationships","volume":"45","author":"van Mulligen","year":"2012","journal-title":"J Biomed Inform"},{"issue":"23","key":"2021120106305899400_ocab176-B43","doi-asserted-by":"crossref","first-page":"3158","DOI":"10.1093\/bioinformatics\/bts591","article-title":"SemMedDB: a PubMed-scale repository of biomedical semantic predications","volume":"28","author":"Kilicoglu","year":"2012","journal-title":"Bioinformatics"},{"issue":"6","key":"2021120106305899400_ocab176-B44","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1016\/j.jbi.2003.11.003","article-title":"The interaction of domain knowledge and linguistic structure in natural language processing: interpreting hypernymic propositions in biomedical text","volume":"36","author":"Rindflesch","year":"2003","journal-title":"J Biomed Inform"},{"key":"2021120106305899400_ocab176-B45","article-title":"Biomedical and clinical English model packages for the Stanza Python NLP library","author":"Zhang","year":"2021","journal-title":"JAMIA"},{"key":"2021120106305899400_ocab176-B46","first-page":"319","author":"Neumann","year":"2019"},{"issue":"05","key":"2021120106305899400_ocab176-B47","doi-asserted-by":"crossref","first-page":"9757","DOI":"10.1609\/aaai.v34i05.6526","article-title":"LATTE: Latent type modeling for biomedical entity linking","volume":"34","author":"Zhu","year":"2020","journal-title":"AAAI"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/28\/12\/2571\/41325337\/ocab176.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/28\/12\/2571\/41325337\/ocab176.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T00:46:07Z","timestamp":1699317967000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/28\/12\/2571\/6370661"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,15]]},"references-count":47,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,9,15]]},"published-print":{"date-parts":[[2021,11,25]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocab176","relation":{},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,12,1]]},"published":{"date-parts":[[2021,9,15]]}}}