{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T19:05:20Z","timestamp":1773515120752,"version":"3.50.1"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"22","license":[{"start":{"date-parts":[[2022,10,7]],"date-time":"2022-10-07T00:00:00Z","timestamp":1665100800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,11,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>The interaction between drugs and targets (DTI) in human body plays a crucial role in biomedical science and applications. As millions of papers come out every year in the biomedical domain, automatically discovering DTI knowledge from biomedical literature, which are usually triplets about drugs, targets and their interaction, becomes an urgent demand in the industry. Existing methods of discovering biological knowledge are mainly extractive approaches that often require detailed annotations (e.g. all mentions of biological entities, relations between every two entity mentions, etc.). However, it is difficult and costly to obtain sufficient annotations due to the requirement of expert knowledge from biomedical domains.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>To overcome these difficulties, we explore an end-to-end solution for this task by using generative approaches. We regard the DTI triplets as a sequence and use a Transformer-based model to directly generate them without using the detailed annotations of entities and relations. Further, we propose a semi-supervised method, which leverages the aforementioned end-to-end model to filter unlabeled literature and label them. Experimental results show that our method significantly outperforms extractive baselines on DTI discovery. We also create a dataset, KD-DTI, to advance this task and release it to the community.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Our code and data are available at https:\/\/github.com\/bert-nmt\/BERT-DTI.<\/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\/btac648","type":"journal-article","created":{"date-parts":[[2022,10,7]],"date-time":"2022-10-07T14:25:38Z","timestamp":1665152738000},"page":"5100-5107","source":"Crossref","is-referenced-by-count":11,"title":["Discovering drug\u2013target interaction knowledge from biomedical literature"],"prefix":"10.1093","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8660-1891","authenticated-orcid":false,"given":"Yutai","family":"Hou","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology , Harbin 150001, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9823-9033","authenticated-orcid":false,"given":"Yingce","family":"Xia","sequence":"additional","affiliation":[{"name":"Microsoft Research , Beijing 100080, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3530-590X","authenticated-orcid":false,"given":"Lijun","family":"Wu","sequence":"additional","affiliation":[{"name":"Microsoft Research , Beijing 100080, China"}]},{"given":"Shufang","family":"Xie","sequence":"additional","affiliation":[{"name":"Microsoft Research , Beijing 100080, China"}]},{"given":"Yang","family":"Fan","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China , Hefei 230027, China"}]},{"given":"Jinhua","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China , Hefei 230027, China"}]},{"given":"Tao","family":"Qin","sequence":"additional","affiliation":[{"name":"Microsoft Research , Beijing 100080, China"}]},{"given":"Tie-Yan","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research , Beijing 100080, China"}]}],"member":"286","published-online":{"date-parts":[[2022,10,7]]},"reference":[{"key":"2022112014190996900_btac648-B1","author":"Alt","year":"2019"},{"key":"2022112014190996900_btac648-B2","doi-asserted-by":"crossref","first-page":"baz095","DOI":"10.1093\/database\/baz095","article-title":"Extraction of chemical\u2013protein interactions from the literature using neural networks and narrow instance representation","volume":"2019","author":"Antunes","year":"2019","journal-title":"Database"},{"key":"2022112014190996900_btac648-B3","author":"Christopoulou","year":"2019"},{"key":"2022112014190996900_btac648-B4","author":"Devlin","year":"2019"},{"key":"2022112014190996900_btac648-B5","first-page":"13042","author":"Dong","year":"2019"},{"key":"2022112014190996900_btac648-B6","doi-asserted-by":"crossref","first-page":"e0220925","DOI":"10.1371\/journal.pone.0220925","article-title":"Automated recognition of functional compound-protein relationships in literature","volume":"15","author":"D\u00f6ring","year":"2020","journal-title":"PLoS One"},{"key":"2022112014190996900_btac648-B7","author":"Gardent","year":"2017"},{"key":"2022112014190996900_btac648-B8","first-page":"1","author":"Gu","year":"2020"},{"key":"2022112014190996900_btac648-B900","author":"Haller","year":"1985"},{"key":"2022112014190996900_btac648-B9","author":"Hinton","year":"2015"},{"key":"2022112014190996900_btac648-B10","doi-asserted-by":"crossref","first-page":"347","DOI":"10.1038\/s42256-020-0189-y","article-title":"A novel machine learning framework for automated biomedical relation extraction from large-scale literature repositories","volume":"2","author":"Hong","year":"2020","journal-title":"Nat. Mach. Intell"},{"key":"2022112014190996900_btac648-B11","author":"Kingma","year":"2015"},{"key":"2022112014190996900_btac648-B12","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1038\/nj7612-457a","article-title":"Scientific literature: information overload","volume":"535","author":"Landhuis","year":"2016","journal-title":"Nature"},{"key":"2022112014190996900_btac648-B13","doi-asserted-by":"crossref","first-page":"baw068","DOI":"10.1093\/database\/baw068","article-title":"BioCreative V CDR task corpus: a resource for chemical disease relation extraction","volume":"2016","author":"Li","year":"2016","journal-title":"Database"},{"key":"2022112014190996900_btac648-B14","first-page":"402","author":"Li","year":"2014"},{"key":"2022112014190996900_btac648-B15","doi-asserted-by":"crossref","first-page":"bay060","DOI":"10.1093\/database\/bay060","article-title":"Chemical\u2013gene relation extraction using recursive neural network","volume":"2018","author":"Lim","year":"2018","journal-title":"Database"},{"key":"2022112014190996900_btac648-B16","doi-asserted-by":"crossref","DOI":"10.1007\/b107408","volume-title":"Data Mining and Knowledge Discovery Handbook","author":"Maimon","year":"2005"},{"key":"2022112014190996900_btac648-B17","first-page":"1003","author":"Mintz","year":"2009"},{"key":"2022112014190996900_btac648-B18","author":"Miwa","year":"2016"},{"key":"2022112014190996900_btac648-B19","author":"Nan","year":"2020"},{"key":"2022112014190996900_btac648-B20","first-page":"319","author":"Neumann","year":"2019"},{"key":"2022112014190996900_btac648-B21","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1162\/tacl_a_00049","article-title":"Cross-sentence N-ary relation extraction with graph LSTMs","volume":"5","author":"Peng","year":"2017","journal-title":"TACL"},{"key":"2022112014190996900_btac648-B22","author":"Phan","year":"2021"},{"key":"2022112014190996900_btac648-B23","author":"Quirk","year":"2017"},{"key":"2022112014190996900_btac648-B24","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"2022112014190996900_btac648-B25","first-page":"148","author":"Riedel","year":"2010"},{"key":"2022112014190996900_btac648-B26","doi-asserted-by":"crossref","first-page":"103159","DOI":"10.1016\/j.jbi.2019.103159","article-title":"A comprehensive review of feature based methods for drug target interaction prediction","volume":"93","author":"Sachdev","year":"2019","journal-title":"J. Biomed. Inform"},{"key":"2022112014190996900_btac648-B27","author":"Sennrich","year":"2015"},{"key":"2022112014190996900_btac648-B28","first-page":"5998","author":"Vaswani","year":"2017"},{"key":"2022112014190996900_btac648-B29","author":"Verga","year":"2018"},{"key":"2022112014190996900_btac648-B30","first-page":"D1031","article-title":"Therapeutic target database 2020: enriched resource for facilitating research and early development of targeted therapeutics","volume":"48","author":"Wang","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2022112014190996900_btac648-B31","first-page":"1476","author":"Wei","year":"2020"},{"key":"2022112014190996900_btac648-B32","doi-asserted-by":"crossref","first-page":"D1074","DOI":"10.1093\/nar\/gkx1037","article-title":"DrugBank 5.0: a major update to the DrugBank database for 2018","volume":"46","author":"Wishart","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2022112014190996900_btac648-B33","first-page":"272","author":"Wu","year":"2019"},{"key":"2022112014190996900_btac648-B34","doi-asserted-by":"crossref","first-page":"1134","DOI":"10.3389\/fphar.2018.01134","article-title":"Network-based methods for prediction of drug-target interactions","volume":"9","author":"Wu","year":"2018","journal-title":"Front. Pharmacol"},{"key":"2022112014190996900_btac648-B35","doi-asserted-by":"crossref","first-page":"i232","DOI":"10.1093\/bioinformatics\/btn162","article-title":"Prediction of drug\u2013target interaction networks from the integration of chemical and genomic spaces","volume":"24","author":"Yamanishi","year":"2008","journal-title":"Bioinformatics"},{"key":"2022112014190996900_btac648-B36","author":"Yao","year":"2019"},{"key":"2022112014190996900_btac648-B37","author":"Ye","year":"2021"},{"key":"2022112014190996900_btac648-B38","author":"Zeng","year":"2014"},{"key":"2022112014190996900_btac648-B39","author":"Zeng","year":"2020"},{"key":"2022112014190996900_btac648-B40","author":"Zhang","year":"2019"},{"key":"2022112014190996900_btac648-B41","author":"Zhong","year":"2020"},{"key":"2022112014190996900_btac648-B42","author":"Zhu","year":"2020"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac648\/46571897\/btac648.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/22\/5100\/47153759\/btac648.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/22\/5100\/47153759\/btac648.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,20]],"date-time":"2022-11-20T14:19:34Z","timestamp":1668953974000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/22\/5100\/6751771"}},"subtitle":[],"editor":[{"given":"Sydnee","family":"Pollo","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2022,10,7]]},"references-count":43,"journal-issue":{"issue":"22","published-online":{"date-parts":[[2022,10,7]]},"published-print":{"date-parts":[[2022,11,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac648","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,11,15]]},"published":{"date-parts":[[2022,10,7]]}}}