{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,24]],"date-time":"2026-08-24T11:25:19Z","timestamp":1787570719088,"version":"build-2736575974"},"reference-count":31,"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:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Polypharmacy is increasingly common in clinical practice, and the sheer number of possible drug combinations makes manual interaction screening impractical. Early computational approaches relied on chemical similarity metrics and rule-based systems, while subsequent machine learning and deep learning methods improved predictive power but continued to treat drugs as isolated entities, missing the broader biological context that governs interaction behaviour. Graph Neural Network (GNN) based methods address this by modeling drugs alongside proteins, diseases, and side effects in a shared relational graph, but tend to fall short on sparsely represented long-tail interaction classes due to the severe class imbalance that characterizes real-world biomedical interaction data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We construct a large-scale heterogeneous biomedical knowledge graph\u201426\u2009408 nodes across five entity types and 1\u2009679\u2009387 edges across six relation types\u2014and benchmark MLP, GCN, HGT, and RGCN for 105- class DDI prediction. RGCN achieves the strongest overall performance (Macro F1: 0.694, Recall: 0.720), with relation-specific weight matrices proving the critical factor in heterogeneous DDI modelling. Among class imbalance strategies tested, Tail-Aware Focal Loss outperforms standard cross-entropy by 3.1% on Macro F1 and 7.4% on Recall, striking a better balance between class performance than either weighted cross-entropy or weighted random sampling.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag413","type":"journal-article","created":{"date-parts":[[2026,6,23]],"date-time":"2026-06-23T11:38:20Z","timestamp":1782214700000},"source":"Crossref","is-referenced-by-count":0,"title":["Tail\u2014aware heterogeneous graph neural networks for multi\u2014class drug\u2014drug interaction prediction"],"prefix":"10.1093","volume":"42","author":[{"given":"Varshini","family":"Venkatesh","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Sri Sivasubramaniya Nadar College of Engineering, OMR , Chennai, Tamil Nadu 603110,","place":["India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Varsha","family":"G","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Sri Sivasubramaniya Nadar College of Engineering, OMR , Chennai, Tamil Nadu 603110,","place":["India"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhannya","family":"S M","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Sri Sivasubramaniya Nadar College of Engineering, OMR , Chennai, Tamil Nadu 603110,","place":["India"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,8,21]]},"reference":[{"key":"2026082407021995400_btag413-B1","author":"Cao","year":"2019"},{"key":"2026082407021995400_btag413-B2","doi-asserted-by":"crossref","first-page":"4406","DOI":"10.1093\/bioinformatics\/btaa524","article-title":"TransformerCPI: improving compound\u2014protein interaction prediction by sequence\u2014based deep learning with self - attention mechanism and label reversal experiments","volume":"36","author":"Chen","year":"2020","journal-title":"Bioinformatics"},{"key":"2026082407021995400_btag413-B3","first-page":"9268","author":"Cui","year":"2019"},{"key":"2026082407021995400_btag413-B4","doi-asserted-by":"crossref","first-page":"bbab514","DOI":"10.1093\/bib\/bbab514","article-title":"META\u2014DDIE: predicting drug\u2014drug interaction events with few - shot learning","volume":"23","author":"Deng","year":"2022","journal-title":"Brief Bioinform"},{"key":"2026082407021995400_btag413-B5","doi-asserted-by":"crossref","first-page":"7112","DOI":"10.1109\/TPAMI.2021.3095381","article-title":"ProtTrans: toward understanding the language of life through self - supervised learning","volume":"44","author":"Elnaggar","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"2026082407021995400_btag413-B6","author":"Fey","year":"2019"},{"key":"2026082407021995400_btag413-B7","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"2026082407021995400_btag413-B8","author":"Hooker","year":"2019"},{"key":"2026082407021995400_btag413-B9","first-page":"2704","author":"Hu","year":"2020"},{"key":"2026082407021995400_btag413-B10","doi-asserted-by":"crossref","first-page":"D1516","DOI":"10.1093\/nar\/gkae1059","article-title":"PubChem 2025 update","volume":"53","author":"Kim","year":"2025","journal-title":"Nucleic Acids Res"},{"key":"2026082407021995400_btag413-B11","doi-asserted-by":"crossref","first-page":"D1075","DOI":"10.1093\/nar\/gkv1075","article-title":"The SIDER database of drugs and side effects","volume":"44","author":"Kuhn","year":"2016","journal-title":"Nucleic Acids Res"},{"key":"2026082407021995400_btag413-B12","author":"Lin","year":"2017"},{"key":"2026082407021995400_btag413-B13","first-page":"2739","author":"Lin","year":"2020"},{"key":"2026082407021995400_btag413-B14","first-page":"1109","author":"Liu","year":"2021"},{"key":"2026082407021995400_btag413-B15","doi-asserted-by":"crossref","first-page":"e2000013","DOI":"10.1002\/minf.202000013","article-title":"CompoundDB4j: integrated drug resource of heterogeneous chemical databases","volume":"39","author":"Murali","year":"2020","journal-title":"Mol Inform"},{"key":"2026082407021995400_btag413-B16","doi-asserted-by":"crossref","first-page":"i821","DOI":"10.1093\/bioinformatics\/bty593","article-title":"DeepDTA: deep drug\u2014target binding affinity prediction","volume":"34","author":"\u00d6zt\u00fcrk","year":"2018","journal-title":"Bioinformatics"},{"key":"2026082407021995400_btag413-B17","doi-asserted-by":"crossref","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended - connectivity fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J Chem Inf Model"},{"key":"2026082407021995400_btag413-B18","author":"Schlichtkrull","year":"2018"},{"key":"2026082407021995400_btag413-B19","doi-asserted-by":"crossref","first-page":"D638","DOI":"10.1093\/nar\/gkac1000","article-title":"The STRING database in 2023: protein-protein association networks and functional enrichment analyses for any sequenced genome of interest","volume":"51","author":"Szklarczyk","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2026082407021995400_btag413-B21","article-title":"Drug repurposing knowledge graph (DRKG): a knowledge graph and a set of tools for drug repurposing","author":"Team DRKG","year":"2020","journal-title":"Dataset and Code Repository"},{"key":"2026082407021995400_btag413-B22","doi-asserted-by":"publisher","first-page":"D523","DOI":"10.1093\/nar\/gkac1052","article-title":"UniProt: the universal protein knowledgebase in 2023","volume":"51","author":"The UniProt Consortium","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2026082407021995400_btag413-B23","author":"Thomas","year":"2017"},{"key":"2026082407021995400_btag413-B24","doi-asserted-by":"crossref","first-page":"2147","DOI":"10.1038\/nprot.2014.151","article-title":"Similarity\u2014based modeling in large\u2014scale prediction of drug - drug interactions","volume":"9","author":"Vilar","year":"2014","journal-title":"Nat Protoc"},{"key":"2026082407021995400_btag413-B25","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J Chem Inf Comput Sci"},{"key":"2026082407021995400_btag413-B26","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 Research"},{"key":"2026082407021995400_btag413-B27","author":"World Health Organization","year":"2025"},{"key":"2026082407021995400_btag413-B28","first-page":"E4304","article-title":"Deep learning improves prediction of drug\u2014drug and drug\u2014food interactions","volume":"115","author":"Yong Ryu","year":"2018","journal-title":"Proc Natl Acad Sci"},{"key":"2026082407021995400_btag413-B29","doi-asserted-by":"publisher","author":"Yu","DOI":"10.1093\/bioinformatics\/btab207"},{"key":"2026082407021995400_btag413-B30","doi-asserted-by":"crossref","first-page":"D1180","DOI":"10.1093\/nar\/gkad1004","article-title":"ChEMBL database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods","volume":"52","author":"Zdrazil","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026082407021995400_btag413-B31","doi-asserted-by":"crossref","first-page":"i457","DOI":"10.1093\/bioinformatics\/bty294","article-title":"Modeling polypharmacy side effects with graph convolutional networks","volume":"34","author":"Zitnik","year":"2018","journal-title":"Bioinformatics"},{"key":"2026082407021995400_btag413-B32","author":"Zitnik","year":"2018"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/Supplement_2\/btag413\/70726026\/btag413.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/Supplement_2\/btag413\/70726026\/btag413.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\/btag413\/8767272"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,1]]},"references-count":31,"journal-issue":{"issue":"Supplement_2","published-print":{"date-parts":[[2026,8,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag413","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":"btag413"}}