{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T11:25:18Z","timestamp":1787570718253,"version":"build-2736575974"},"reference-count":33,"publisher":"Oxford University Press (OUP)","issue":"Supplement_2","license":[{"start":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T00:00:00Z","timestamp":1787529600000},"content-version":"vor","delay-in-days":23,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Diet plays a critical role in human health, with growing evidence linking dietary habits to disease outcomes. However, extracting structured dietary knowledge from biomedical literature remains challenging due to the lack of dedicated relation extraction datasets. To address this gap, we introduce RECoDe, a novel relation extraction (RE) dataset designed specifically for diet, disease, and related biomedical entities. RECoDe captures a diverse set of relation types, including a broad spectrum of positive association patterns and explicit negative examples, with over 5000 human-annotated instances validated by up to five independent annotators. Furthermore, we benchmark various natural language processing (NLP) RE models, including BERT-based architectures and enhanced prompting techniques with locally deployed large language models (LLMs) to improve classification performance on underrepresented relation types. The best performing model was gpt-oss-20B, a locally-deployed open-weight LLM, achieving an F1-score of 61% (macro) for multi-class classification and 89% for binary classification using a hierarchical prompting strategy with a separate reflection step built in. To demonstrate the practical utility of RECoDe, we introduce the Contextual Co-occurrence Summarisation (CoCoS) framework, which aggregates sentence-level relation extractions into document-level summaries and further integrates evidence across multiple documents. CoCoS produces effect estimates consistent with established dietary knowledge, demonstrating its validity as a general framework for systematic evidence synthesis.<\/jats:p>\n                  <jats:p>Availability: The code, models, and dataset are publicly available at https:\/\/github.com\/omicsNLP\/RECoDe.<\/jats:p>","DOI":"10.1093\/bioinformatics\/btag439","type":"journal-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T11:36:51Z","timestamp":1782214611000},"source":"Crossref","is-referenced-by-count":0,"title":["Relation extraction for diet, non-communicable disease and biomarker associations (RECoDe): a CoDiet study"],"prefix":"10.1093","volume":"42","author":[{"given":"Donghee","family":"Choi","sequence":"first","affiliation":[{"name":"Section of Bioinformatics, Division of Systems Medicine, Department of Metabolism, Digestion and Reproduction, Imperial College London , London, W12 0NN,","place":["United Kingdom"]},{"name":"School of Computer Science and Engineering, Pusan National University , Busan, 46241,","place":["South Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yajie","family":"Gu","sequence":"additional","affiliation":[{"name":"Centre for Health Informatics, School of Medicine, University of Nottingham , Nottingham, NG7 2RD,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai Qi","family":"Zong","sequence":"additional","affiliation":[{"name":"Section of Bioinformatics, Division of Systems Medicine, Department of Metabolism, Digestion and Reproduction, Imperial College London , London, W12 0NN,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antoine D","family":"Lain","sequence":"additional","affiliation":[{"name":"Section of Bioinformatics, Division of Systems Medicine, Department of Metabolism, Digestion and Reproduction, Imperial College London , London, W12 0NN,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitrios","family":"Zaikis","sequence":"additional","affiliation":[{"name":"School of Informatics, Aristotle University of Thessaloniki , Thessaloniki, 57001,","place":["Greece"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Rowlands","sequence":"additional","affiliation":[{"name":"Centre for Health Informatics, School of Medicine, University of Nottingham , Nottingham, NG7 2RD,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marek","family":"Rei","sequence":"additional","affiliation":[{"name":"Department of Computing, Imperial College London , London, SW7 2AZ,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"name":"The CoDiet Consortium","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donghee","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yajie","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai Qi","family":"Zong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Antoine D","family":"Lain","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dimitrios","family":"Zaikis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Rowlands","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marek","family":"Rei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim","family":"Beck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joram M","family":"Posma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tim","family":"Beck","sequence":"additional","affiliation":[{"name":"Centre for Health Informatics, School of Medicine, University of Nottingham , Nottingham, NG7 2RD,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4971-9003","authenticated-orcid":false,"given":"Joram M","family":"Posma","sequence":"additional","affiliation":[{"name":"Section of Bioinformatics, Division of Systems Medicine, Department of Metabolism, Digestion and Reproduction, Imperial College London , London, W12 0NN,","place":["United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"2026082407022445100_btag439-B1","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":"2026082407022445100_btag439-B2","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1177\/001316446002000104","article-title":"A coefficient of agreement for nominal scales","volume":"20","author":"Cohen","year":"1960","journal-title":"Educ Psychol Meas"},{"key":"2026082407022445100_btag439-B3","doi-asserted-by":"crossref","first-page":"107718","DOI":"10.1016\/j.appet.2024.107718","article-title":"The role of nutrient sensing dysregulation in anorexia of ageing: the little we know and the much we don\u2019t","volume":"203","author":"Dagbasi","year":"2024","journal-title":"Appetite"},{"key":"2026082407022445100_btag439-B4","first-page":"4171","author":"Devlin","year":"2019"},{"key":"2026082407022445100_btag439-B5","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1093\/bioinformatics\/btq667","article-title":"Toward an automatic method for extracting cancer-and other disease-related point mutations from the biomedical literature","volume":"27","author":"Doughty","year":"2011","journal-title":"Bioinformatics"},{"key":"2026082407022445100_btag439-B6","doi-asserted-by":"publisher","author":"Geleta","year":"2021","DOI":"10.1101\/2021.10.28.466262"},{"key":"2026082407022445100_btag439-B7","doi-asserted-by":"crossref","first-page":"885","DOI":"10.1016\/j.jbi.2012.04.008","article-title":"Development of a benchmark corpus to support the automatic extraction of drug-related adverse effects from medical case reports","volume":"45","author":"Gurulingappa","year":"2012","journal-title":"J Biomed Inform"},{"key":"2026082407022445100_btag439-B8","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1093\/jamia\/ocz166","article-title":"2018 n2c2 shared task on adverse drug events and medication extraction in electronic health records","volume":"27","author":"Henry","year":"2020","journal-title":"J Am Med Inform Assoc"},{"key":"2026082407022445100_btag439-B9","doi-asserted-by":"crossref","first-page":"914","DOI":"10.1016\/j.jbi.2013.07.011","article-title":"The DDI corpus: an annotated corpus with pharmacological substances and drug\u2013drug interactions","volume":"46","author":"Herrero-Zazo","year":"2013","journal-title":"J Biomed Inform"},{"key":"2026082407022445100_btag439-B10","doi-asserted-by":"crossref","first-page":"998","DOI":"10.1093\/jamia\/ocaf054","article-title":"DiMB-RE: mining the scientific literature for diet-microbiome associations","volume":"32","author":"Hong","year":"2025","journal-title":"J Am Med Inform Assoc"},{"key":"2026082407022445100_btag439-B11","doi-asserted-by":"crossref","first-page":"616","DOI":"10.1002\/jrsm.1715","article-title":"Can large language models replace humans in systematic reviews? Evaluating GPT-4\u2019s efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languages","volume":"15","author":"Khraisha","year":"2024","journal-title":"Res Synth Methods"},{"key":"2026082407022445100_btag439-B12","doi-asserted-by":"publisher","first-page":"1218","DOI":"10.3390\/nu5041218","article-title":"Dyslipidemia in obesity: mechanisms and potential targets","volume":"5","author":"Klop","year":"2013","journal-title":"Nutrients"},{"key":"2026082407022445100_btag439-B13","doi-asserted-by":"crossref","first-page":"104487","DOI":"10.1016\/j.jbi.2023.104487","article-title":"BioREx: improving biomedical relation extraction by leveraging heterogeneous datasets","volume":"146","author":"Lai","year":"2023","journal-title":"J Biomed Inform"},{"key":"2026082407022445100_btag439-B14","doi-asserted-by":"publisher","author":"Lain","year":"2025","DOI":"10.1101\/2025.09.04.673740"},{"key":"2026082407022445100_btag439-B15","first-page":"D784","article-title":"ChimerDB 3.0: an enhanced database for fusion genes from cancer transcriptome and literature data mining","volume":"45","author":"Lee","year":"2017","journal-title":"Nucleic Acids Res"},{"key":"2026082407022445100_btag439-B16","doi-asserted-by":"crossref","first-page":"2297","DOI":"10.3945\/jn.108.097154","article-title":"Application of systematic review methodology to the field of nutrition","volume":"138","author":"Lichtenstein","year":"2008","journal-title":"J Nutr"},{"key":"2026082407022445100_btag439-B17","doi-asserted-by":"crossref","first-page":"e0190926","DOI":"10.1371\/journal.pone.0190926","article-title":"Drug drug interaction extraction from the literature using a recursive neural network","volume":"13","author":"Lim","year":"2018","journal-title":"PLoS One"},{"key":"2026082407022445100_btag439-B18","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1111\/nbu.12722","article-title":"Dietary fats and cardiometabolic health\u2013from public health to personalised nutrition: \u2018one for all\u2019 and \u2018all for one\u2019","volume":"50","author":"Lovegrove","year":"2025","journal-title":"Nutr Bull"},{"key":"2026082407022445100_btag439-B19","doi-asserted-by":"crossref","first-page":"bbac282","DOI":"10.1093\/bib\/bbac282","article-title":"BioRED: a rich biomedical relation extraction dataset","volume":"23","author":"Luo","year":"2022","journal-title":"Brief Bioinform"},{"key":"2026082407022445100_btag439-B20","doi-asserted-by":"publisher","first-page":"1474","DOI":"10.3390\/nu12051474","article-title":"The firmicutes\/bacteroidetes ratio: a relevant marker of gut dysbiosis in obese patients?","volume":"12","author":"Magne","year":"2020","journal-title":"Nutrients"},{"key":"2026082407022445100_btag439-B21","first-page":"11","author":"Miranda","year":"2021"},{"key":"2026082407022445100_btag439-B22","first-page":"77","article-title":"Can generalist foundation models outcompete special-purpose tuning? Case study in medicine","volume":"84","author":"Nori","year":"2023","journal-title":"Medicine (Baltimore)"},{"key":"2026082407022445100_btag439-B23","doi-asserted-by":"crossref","first-page":"122","DOI":"10.1016\/j.tjnut.2024.11.004","article-title":"A metabolome wide association study of fruit and vegetable consumption and associations with cardiovascular disease risk factors: the international study of macro-\/micronutrients and blood pressure (INTERMAP) study","volume":"155","author":"Oude Griep","year":"2025","journal-title":"J Nutr"},{"key":"2026082407022445100_btag439-B24","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":"Trans Assoc Comput Linguist"},{"key":"2026082407022445100_btag439-B25","doi-asserted-by":"crossref","first-page":"102844","DOI":"10.1016\/j.eclinm.2024.102844","article-title":"Increase in colonic propionate as a method of preventing weight gain over 12 months in adults aged 20\u201340 years (iPREVENT): a multi-Centre, double-blind, randomised, parallel-group trial","volume":"76","author":"Pugh","year":"2024","journal-title":"EClinicalMedicine"},{"key":"2026082407022445100_btag439-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"},{"key":"2026082407022445100_btag439-B27","doi-asserted-by":"publisher","author":"Renze","year":"2024","DOI":"10.1109\/FLLM63129.2024.10852426"},{"key":"2026082407022445100_btag439-B28","author":"Ridnik","year":"2024"},{"key":"2026082407022445100_btag439-B29","doi-asserted-by":"crossref","first-page":"lqab062","DOI":"10.1093\/nargab\/lqab062","article-title":"RENET2: high-performance full-text gene\u2013disease relation extraction with iterative training data expansion","volume":"3","author":"Su","year":"2021","journal-title":"NAR Genom Bioinform"},{"key":"2026082407022445100_btag439-B30","author":"Tamoyan"},{"key":"2026082407022445100_btag439-B31","doi-asserted-by":"crossref","first-page":"205","DOI":"10.1038\/s41597-020-0543-2","article-title":"Building a pubmed knowledge graph","volume":"7","author":"Xu","year":"2020","journal-title":"Sci Data"},{"key":"2026082407022445100_btag439-B32","first-page":"619","author":"Yoon","year":"2022"},{"key":"2026082407022445100_btag439-B33","doi-asserted-by":"publisher","first-page":"2038","DOI":"10.1038\/s41591-022-01973-2","article-title":"The burden of proof studies: assessing the evidence of risk","volume":"28","author":"Zheng","year":"2022","journal-title":"Nat Med"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/Supplement_2\/btag439\/70726278\/btag439.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/Supplement_2\/btag439\/70726278\/btag439.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T11:02:31Z","timestamp":1787569351000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag439\/8767276"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,1]]},"references-count":33,"journal-issue":{"issue":"Supplement_2","published-print":{"date-parts":[[2026,8,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag439","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,8]]},"published":{"date-parts":[[2026,8,1]]},"article-number":"btag439"}}