{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T06:26:39Z","timestamp":1785392799276,"version":"3.55.0"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"11","funder":[{"name":"NIH Intramural Research Program, National Library of Medicine"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,11,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Information retrieval (IR) is essential in biomedical knowledge acquisition and clinical decision support. While recent progress has shown that language model encoders perform better semantic retrieval, training such models requires abundant query\u2013article annotations that are difficult to obtain in biomedicine. As a result, most biomedical IR systems only conduct lexical matching. In response, we introduce MedCPT, a first-of-its-kind Contrastively Pre-trained Transformer model for zero-shot semantic IR in biomedicine.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>To train MedCPT, we collected an unprecedented scale of 255 million user click logs from PubMed. With such data, we use contrastive learning to train a pair of closely integrated retriever and re-ranker. Experimental results show that MedCPT sets new state-of-the-art performance on six biomedical IR tasks, outperforming various baselines including much larger models, such as GPT-3-sized cpt-text-XL. In addition, MedCPT also generates better biomedical article and sentence representations for semantic evaluations. As such, MedCPT can be readily applied to various real-world biomedical IR tasks.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The MedCPT code and model are available at https:\/\/github.com\/ncbi\/MedCPT.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad651","type":"journal-article","created":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T17:26:13Z","timestamp":1699291573000},"source":"Crossref","is-referenced-by-count":143,"title":["MedCPT: Contrastive Pre-trained Transformers with large-scale PubMed search logs for zero-shot biomedical information retrieval"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1268-7239","authenticated-orcid":false,"given":"Qiao","family":"Jin","sequence":"first","affiliation":[{"name":"National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Won","family":"Kim","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6036-1516","authenticated-orcid":false,"given":"Qingyu","family":"Chen","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donald C","family":"Comeau","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lana","family":"Yeganova","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"W John","family":"Wilbur","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9998-916X","authenticated-orcid":false,"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[{"name":"National Center for Biotechnology Information (NCBI), National Library of Medicine (NLM), National Institutes of Health (NIH) , Bethesda, MD, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,11,1]]},"reference":[{"key":"2023110617255717400_btad651-B1","doi-asserted-by":"crossref","first-page":"W594","DOI":"10.1093\/nar\/gkz289","article-title":"LitSense: making sense of biomedical literature at sentence level","volume":"47","author":"Allot","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023110617255717400_btad651-B2","doi-asserted-by":"crossref","first-page":"baz085","DOI":"10.1093\/database\/baz085","article-title":"Large expert-curated database for benchmarking document similarity detection in biomedical literature search","volume":"2019","author":"Brown","year":"2019","journal-title":"Database"},{"key":"2023110617255717400_btad651-B3","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2023110617255717400_btad651-B4","first-page":"1","author":"Chen","year":"2019"},{"key":"2023110617255717400_btad651-B5","first-page":"2270","author":"Cohan","year":"2020"},{"key":"2023110617255717400_btad651-B6","first-page":"1533","author":"Dai","year":"2020"},{"key":"2023110617255717400_btad651-B7","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1197\/jamia.M1608","article-title":"Answering physicians' clinical questions: obstacles and potential solutions","volume":"12","author":"Ely","year":"2005","journal-title":"J Am Med Inform Assoc"},{"key":"2023110617255717400_btad651-B8","doi-asserted-by":"crossref","first-page":"e2005343","DOI":"10.1371\/journal.pbio.2005343","article-title":"Best match: new relevance search for PubMed","volume":"16","author":"Fiorini","year":"2018","journal-title":"PLoS Biol"},{"key":"2023110617255717400_btad651-B9","first-page":"280","author":"Gao","year":"2021"},{"key":"2023110617255717400_btad651-B10","doi-asserted-by":"crossref","first-page":"103141","DOI":"10.1016\/j.jbi.2019.103141","article-title":"A survey on literature based discovery approaches in biomedical domain","volume":"93","author":"Gopalakrishnan","year":"2019","journal-title":"J Biomed Inform"},{"key":"2023110617255717400_btad651-B11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3458754","article-title":"Domain-specific language model pretraining for biomedical natural language processing","volume":"3","author":"Gu","year":"2021","journal-title":"ACM Trans Comput Healthc"},{"key":"2023110617255717400_btad651-B12","doi-asserted-by":"crossref","first-page":"bas020","DOI":"10.1093\/database\/bas020","article-title":"Text mining for the biocuration workflow","volume":"2012","author":"Hirschman","year":"2012","journal-title":"Database (Oxford)"},{"key":"2023110617255717400_btad651-B13","first-page":"113","author":"Hofst\u00e4tter","year":"2021"},{"key":"2023110617255717400_btad651-B14","author":"Izacard","year":"2021"},{"key":"2023110617255717400_btad651-B15","doi-asserted-by":"crossref","first-page":"1302","DOI":"10.1681\/ASN.0000000000000166","article-title":"Retrieve, summarize, and verify: how will ChatGPT affect information seeking from the medical literature?","volume":"34","author":"Jin","year":"2023","journal-title":"J Am Soc Nephrol"},{"key":"2023110617255717400_btad651-B16","doi-asserted-by":"crossref","first-page":"160035","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, a freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci Data"},{"key":"2023110617255717400_btad651-B17","first-page":"6769","author":"Karpukhin","year":"2020"},{"key":"2023110617255717400_btad651-B18","first-page":"39","author":"Khattab","year":"2020"},{"key":"2023110617255717400_btad651-B19","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-02181-7","volume-title":"Pretrained Transformers for Text Ranking: BERT and Beyond","author":"Lin","year":"2022"},{"key":"2023110617255717400_btad651-B20","doi-asserted-by":"crossref","first-page":"423","DOI":"10.1186\/1471-2105-8-423","article-title":"PubMed related articles: a probabilistic topic-based model for content similarity","volume":"8","author":"Lin","year":"2007","journal-title":"BMC Bioinformatics"},{"key":"2023110617255717400_btad651-B21","author":"Ma","year":"2020"},{"key":"2023110617255717400_btad651-B22","author":"Neelakantan","year":"2022"},{"key":"2023110617255717400_btad651-B23","author":"Ni","year":"2021"},{"key":"2023110617255717400_btad651-B24","author":"Nogueira","year":"2019"},{"key":"2023110617255717400_btad651-B25","author":"Nogueira","year":"2019"},{"key":"2023110617255717400_btad651-B26","author":"Ostendorff","year":"2022"},{"key":"2023110617255717400_btad651-B27","author":"Simpson","year":"2014"},{"key":"2023110617255717400_btad651-B28","author":"Roberts","year":"2017"},{"key":"2023110617255717400_btad651-B29","author":"Shin","year":"2023"},{"key":"2023110617255717400_btad651-B30","doi-asserted-by":"crossref","first-page":"i49","DOI":"10.1093\/bioinformatics\/btx238","article-title":"BIOSSES: a semantic sentence similarity estimation system for the biomedical domain","volume":"33","author":"Sogancioglu","year":"2017","journal-title":"Bioinformatics"},{"key":"2023110617255717400_btad651-B31","author":"Thakur","year":"2021"},{"key":"2023110617255717400_btad651-B32","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1186\/s12859-015-0564-6","article-title":"An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition","volume":"16","author":"Tsatsaronis","year":"2015","journal-title":"BMC Bioinformatics"},{"key":"2023110617255717400_btad651-B33","author":"Vaswani","year":"2017"},{"key":"2023110617255717400_btad651-B34","first-page":"1","volume-title":"ACM SIGIR Forum","author":"Voorhees","year":"2021"},{"key":"2023110617255717400_btad651-B35","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1007\/s10579-018-9431-1","article-title":"MedSTS: a resource for clinical semantic textual similarity","volume":"54","author":"Wang","year":"2020","journal-title":"Lang Resour Eval"},{"key":"2023110617255717400_btad651-B36","author":"Xiong","year":"2020"},{"key":"2023110617255717400_btad651-B37","doi-asserted-by":"crossref","first-page":"bay052","DOI":"10.1093\/database\/bay052","article-title":"A Field Sensor: computing the composition and intent of PubMed queries","volume":"2018","author":"Yeganova","year":"2018","journal-title":"Database (Oxford)"},{"key":"2023110617255717400_btad651-B38","doi-asserted-by":"crossref","first-page":"981","DOI":"10.1007\/s11390-015-1576-4","article-title":"Multi-factor duplicate question detection in stack overflow","volume":"30","author":"Zhang","year":"2015","journal-title":"J Comput Sci Technol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/11\/btad651\/52799559\/btad651.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/11\/btad651\/52799559\/btad651.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,6]],"date-time":"2023-11-06T17:26:25Z","timestamp":1699291585000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad651\/7335842"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,11,1]]},"references-count":38,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,11,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad651","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,11,1]]},"published":{"date-parts":[[2023,11,1]]},"article-number":"btad651"}}