{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T17:53:41Z","timestamp":1780336421445,"version":"3.54.1"},"reference-count":64,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2023,9,22]],"date-time":"2023-09-22T00:00:00Z","timestamp":1695340800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"Ministry of Science and Technology of China","award":["G2021029011L"],"award-info":[{"award-number":["G2021029011L"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,22]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The simultaneous use of two or more drugs due to multi-disease comorbidity continues to increase, which may cause adverse reactions between drugs that seriously threaten public health. Therefore, the prediction of drug\u2013drug interaction (DDI) has become a hot topic not only in clinics but also in bioinformatics. In this study, we propose a novel pre-trained heterogeneous graph neural network (HGNN) model named HetDDI, which aggregates the structural information in drug molecule graphs and rich semantic information in biomedical knowledge graph to predict DDIs. In HetDDI, we first initialize the parameters of the model with different pre-training methods. Then we apply the pre-trained HGNN to learn the feature representation of drugs from multi-source heterogeneous information, which can more effectively utilize drugs\u2019 internal structure and abundant external biomedical knowledge, thus leading to better DDI prediction. We evaluate our model on three DDI prediction tasks (binary-class, multi-class and multi-label) with three datasets and further assess its performance on three scenarios (S1, S2 and S3). The results show that the accuracy of HetDDI can achieve 98.82% in the binary-class task, 98.13% in the multi-class task and 96.66% in the multi-label one on S1, which outperforms the state-of-the-art methods by at least 2%. On S2 and S3, our method also achieves exciting performance. Furthermore, the case studies confirm that our model performs well in predicting unknown DDIs. Source codes are available at https:\/\/github.com\/LinsLab\/HetDDI.<\/jats:p>","DOI":"10.1093\/bib\/bbad385","type":"journal-article","created":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T23:27:56Z","timestamp":1698708476000},"source":"Crossref","is-referenced-by-count":40,"title":["HetDDI: a pre-trained heterogeneous graph neural network model for drug\u2013drug interaction prediction"],"prefix":"10.1093","volume":"24","author":[{"given":"Zhe","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science, University of South China , Hengyang, 421001 Hunan , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyi","family":"Tu","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of South China , Hengyang, 421001 Hunan , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuping","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Pharmacy, University of South China , Hengyang 421001 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbin","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Mathematics and Physics, University of South China , Hengyang 421001 , China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,10,30]]},"reference":[{"issue":"7139","key":"2023103020153375900_ref1","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1038\/446975a","article-title":"When good drugs go bad","volume":"446","author":"Giacomini","year":"2007","journal-title":"Nature"},{"issue":"4","key":"2023103020153375900_ref2","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1002\/jcph.1557","article-title":"A review of cannabis and interactions with anticoagulant and antiplatelet agents","volume":"60","author":"Greger","year":"2020","journal-title":"J Clin Pharmacol"},{"issue":"21","key":"2023103020153375900_ref3","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.1016\/S1359-6446(05)03632-9","article-title":"Keynote review: in vitro safety pharmacology profiling: an essential tool for successful drug development","volume":"10","author":"Whitebread","year":"2005","journal-title":"Drug Discov Today"},{"issue":"11","key":"2023103020153375900_ref4","doi-asserted-by":"crossref","first-page":"1318","DOI":"10.1038\/nm.3954","article-title":"High-throughput screening using patient-derived tumor xenografts to predict clinical trial drug response","volume":"21","author":"Gao","year":"2015","journal-title":"Nat Med"},{"issue":"6","key":"2023103020153375900_ref5","doi-asserted-by":"crossref","first-page":"2099","DOI":"10.1093\/bib\/bbz125","article-title":"A novel molecular representation with bigru neural networks for learning atom","volume":"21","author":"Lin","year":"2020","journal-title":"Brief Bioinform"},{"issue":"18","key":"2023103020153375900_ref6","doi-asserted-by":"crossref","first-page":"E4304","DOI":"10.1073\/pnas.1803294115","article-title":"Deep learning improves prediction of drug\u2013drug and drug\u2013food interactions","volume":"115","author":"Ryu","year":"2018","journal-title":"Proc Natl Acad Sci"},{"issue":"1","key":"2023103020153375900_ref7","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-019-3013-0","article-title":"Novel deep learning model for more accurate prediction of drug\u2013drug interaction effects","volume":"20","author":"Lee","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"2023103020153375900_ref8","first-page":"2739","article-title":"Kgnn: knowledge graph neural network for drug\u2013drug interaction prediction","volume":"380","author":"Lin","year":"2020","journal-title":"IJCAI"},{"issue":"1","key":"2023103020153375900_ref9","doi-asserted-by":"crossref","first-page":"bbab451","DOI":"10.1093\/bib\/bbab451","article-title":"Egfi: drug\u2013drug interaction extraction and generation with fusion of enriched entity and sentence information","volume":"23","author":"Huang","year":"2022","journal-title":"Brief Bioinform"},{"issue":"4","key":"2023103020153375900_ref10","article-title":"Stnn-ddi: a substructure-aware tensor neural network to predict drug\u2013drug interactions","volume":"23","author":"Hui","year":"2022","journal-title":"Brief Bioinform"},{"issue":"22","key":"2023103020153375900_ref11","doi-asserted-by":"crossref","first-page":"3444","DOI":"10.1093\/bioinformatics\/btw486","article-title":"Drug drug interaction extraction from biomedical literature using syntax convolutional neural network","volume":"32","author":"Zhao","year":"2016","journal-title":"Bioinformatics"},{"issue":"5","key":"2023103020153375900_ref12","doi-asserted-by":"crossref","first-page":"863","DOI":"10.1093\/bib\/bbx010","article-title":"Detection of drug\u2013drug interactions through data mining studies using clinical sources, scientific literature and social media","volume":"19","author":"Vilar","year":"2018","journal-title":"Brief Bioinform"},{"issue":"1","key":"2023103020153375900_ref13","doi-asserted-by":"crossref","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"},{"issue":"12","key":"2023103020153375900_ref14","doi-asserted-by":"crossref","first-page":"1739","DOI":"10.1093\/bioinformatics\/btaa907","article-title":"Using drug descriptions and molecular structures for drug\u2013drug interaction extraction from literature","volume":"37","author":"Asada","year":"2021","journal-title":"Bioinformatics"},{"issue":"6","key":"2023103020153375900_ref15","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":"2023103020153375900_ref16","doi-asserted-by":"crossref","first-page":"3966","DOI":"10.3389\/fphar.2021.814858","article-title":"A review of approaches for predicting drug\u2013drug interactions based on machine learning","volume":"12","author":"Han","year":"2022","journal-title":"Front Pharmacol"},{"issue":"6","key":"2023103020153375900_ref17","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1136\/amiajnl-2012-000935","article-title":"Drug\u2014drug interaction through molecular structure similarity analysis","volume":"19","author":"Vilar","year":"2012","journal-title":"J Am Med Inform Assoc"},{"issue":"12","key":"2023103020153375900_ref18","doi-asserted-by":"crossref","first-page":"2007","DOI":"10.1093\/bioinformatics\/btv080","article-title":"Large-scale exploration and analysis of drug combinations","volume":"31","author":"Li","year":"2015","journal-title":"Bioinformatics"},{"issue":"15","key":"2023103020153375900_ref19","first-page":"1","article-title":"Ddigip: predicting drug\u2013drug interactions based on gaussian interaction profile kernels","volume":"20","author":"Yan","year":"2019","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"2023103020153375900_ref20","doi-asserted-by":"crossref","first-page":"13645","DOI":"10.1038\/s41598-019-50121-3","article-title":"Drug\u2013drug interaction predicting by neural network using integrated similarity","volume":"9","author":"Rohani","year":"2019","journal-title":"Sci Rep"},{"key":"2023103020153375900_ref21","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.jbi.2017.04.021","article-title":"Computational prediction of drug-drug interactions based on drugs functional similarities","volume":"70","author":"Ferdousi","year":"2017","journal-title":"J Biomed Inform"},{"issue":"1","key":"2023103020153375900_ref22","doi-asserted-by":"crossref","first-page":"168","DOI":"10.1109\/TCBB.2020.2988018","article-title":"Predicting drug-drug interactions based on integrated similarity and semi-supervised learning","volume":"19","author":"Yan","year":"2020","journal-title":"IEEE\/ACM Trans Comput Biol Bioinform"},{"issue":"1","key":"2023103020153375900_ref23","doi-asserted-by":"crossref","first-page":"592","DOI":"10.1038\/msb.2012.26","article-title":"Indi: a computational framework for inferring drug interactions and their associated recommendations","volume":"8","author":"Gottlieb","year":"2012","journal-title":"Mol Syst Biol"},{"issue":"e2","key":"2023103020153375900_ref24","doi-asserted-by":"crossref","first-page":"e278","DOI":"10.1136\/amiajnl-2013-002512","article-title":"Machine learning-based prediction of drug\u2013drug interactions by integrating drug phenotypic, therapeutic, chemical, and genomic properties","volume":"21","author":"Cheng","year":"2014","journal-title":"J Am Med Inform Assoc"},{"issue":"5","key":"2023103020153375900_ref25","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0196865","article-title":"Predicting potential drug-drug interactions on topological and semantic similarity features using statistical learning","volume":"13","author":"Kastrin","year":"2018","journal-title":"PloS One"},{"key":"2023103020153375900_ref26","first-page":"702","article-title":"Caster: predicting drug interactions with chemical substructure representation","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Huang","year":"2020"},{"key":"2023103020153375900_ref27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-016-1415-9","article-title":"Predicting potential drug-drug interactions by integrating chemical, biological, phenotypic and network data","volume":"18","author":"Zhang","year":"2017","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"2023103020153375900_ref28","first-page":"1","article-title":"Predicting drug\u2013drug interactions through drug structural similarities and interaction networks incorporating pharmacokinetics and pharmacodynamics knowledge","volume":"9","author":"Takeda","year":"2017","journal-title":"J Chem"},{"issue":"1","key":"2023103020153375900_ref29","doi-asserted-by":"crossref","first-page":"12339","DOI":"10.1038\/srep12339","article-title":"Label propagation prediction of drug-drug interactions based on clinical side effects","volume":"5","author":"Zhang","year":"2015","journal-title":"Sci Rep"},{"issue":"15","key":"2023103020153375900_ref30","doi-asserted-by":"crossref","first-page":"4316","DOI":"10.1093\/bioinformatics\/btaa501","article-title":"A multimodal deep learning framework for predicting drug\u2013drug interaction events","volume":"36","author":"Deng","year":"2020","journal-title":"Bioinformatics"},{"issue":"1","key":"2023103020153375900_ref31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2022\/3681749","article-title":"Mddi-scl: predicting multi-type drug-drug interactions via supervised contrastive learning","volume":"14","author":"Lin","year":"2022","journal-title":"J Chem"},{"issue":"1","key":"2023103020153375900_ref32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-020-77766-9","article-title":"Skipgnn: predicting molecular interactions with skip-graph networks","volume":"10","author":"Huang","year":"2020","journal-title":"Sci Rep"},{"issue":"8","key":"2023103020153375900_ref33","doi-asserted-by":"crossref","first-page":"2315","DOI":"10.1093\/bioinformatics\/btac094","article-title":"Effective knowledge graph embeddings based on multidirectional semantics relations for polypharmacy side effects prediction","volume":"38","author":"Yao","year":"2022","journal-title":"Bioinformatics"},{"key":"2023103020153375900_ref34","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac602","article-title":"A social theory-enhanced graph representation learning framework for multitask prediction of drug\u2013drug interactions","volume":"24","author":"Feng","year":"2023","journal-title":"Brief Bioinform"},{"issue":"1","key":"2023103020153375900_ref35","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac597","article-title":"Dsn-ddi: an accurate and generalized framework for drug\u2013drug interaction prediction by dual-view representation learning","volume":"24","author":"Li","year":"2023","journal-title":"Brief Bioinform"},{"key":"2023103020153375900_ref36","article-title":"Semi-supervised classification with graph convolutional networks.","author":"Kipf","year":"2016"},{"key":"2023103020153375900_ref37","first-page":"7370","article-title":"Graph convolutional networks for text classification","volume-title":": Proceedings of the AAAI Conference on Artificial Intelligence","author":"Yao","year":"2019"},{"key":"2023103020153375900_ref38","article-title":"Graph attention networks","volume":"1050","author":"Velickovic","journal-title":"Stat"},{"key":"2023103020153375900_ref39","doi-asserted-by":"crossref","first-page":"950","DOI":"10.1145\/3292500.3330989","article-title":"Kgat: knowledge graph attention network for recommendation","volume-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","author":"Wang","year":"2019"},{"issue":"3","key":"2023103020153375900_ref40","doi-asserted-by":"crossref","first-page":"bbac134","DOI":"10.1093\/bib\/bbac134","article-title":"3dgt-ddi: 3D graph and text based neural network for drug\u2013drug interaction prediction","volume":"23","author":"He","year":"2022","journal-title":"Brief Bioinform"},{"key":"2023103020153375900_ref41","first-page":"1","article-title":"Introduction: what is a knowledge graph?","volume":"02","author":"Fensel","year":"2020","journal-title":"Knowl Graphs: Methodol Tools Select Cases"},{"issue":"3","key":"2023103020153375900_ref42","doi-asserted-by":"crossref","first-page":"1490","DOI":"10.3390\/molecules28031490","article-title":"A knowledge-graph-based multimodal deep learning framework for identifying drug\u2013drug interactions","volume":"28","author":"Zhang","year":"2023","journal-title":"Molecules"},{"issue":"18","key":"2023103020153375900_ref43","doi-asserted-by":"crossref","first-page":"2988","DOI":"10.1093\/bioinformatics\/btab207","article-title":"Sumgnn: multi-typed drug interaction prediction via efficient knowledge graph summarization","volume":"37","author":"Yue","year":"2021","journal-title":"Bioinformatics"},{"key":"2023103020153375900_ref44","article-title":"Attention-based knowledge graph representation learning for predicting drug-drug interactions","volume":"23","author":"Xiaorui","journal-title":"Brief Bioinform"},{"key":"2023103020153375900_ref45","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1145\/3307339.3342161","article-title":"Drug-drug interaction prediction based on knowledge graph embeddings and convolutional-LSTM network","volume-title":"Proceedings of the 10th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","author":"Karim","year":"2019"},{"issue":"2","key":"2023103020153375900_ref46","doi-asserted-by":"crossref","first-page":"319","DOI":"10.3390\/life12020319","article-title":"Smilegnn: drug\u2013drug interaction prediction based on the smiles and graph neural network","volume":"12","author":"Han","year":"2022","journal-title":"Life"},{"issue":"17","key":"2023103020153375900_ref47","doi-asserted-by":"crossref","first-page":"2651","DOI":"10.1093\/bioinformatics\/btab169","article-title":"Muffin: multi-scale feature fusion for drug\u2013drug interaction prediction","volume":"37","author":"Chen","year":"2021","journal-title":"Bioinformatics"},{"issue":"5","key":"2023103020153375900_ref48","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac363","article-title":"A biomedical knowledge graph-based method for drug\u2013drug interactions prediction through combining local and global features with deep neural networks","volume":"23","author":"Ren","year":"2022","journal-title":"Brief Bioinform"},{"key":"2023103020153375900_ref49","article-title":"Predicting drug\u2013drug interactions by graph convolutional network with multi-kernel","volume":"23","author":"Wang","journal-title":"Brief Bioinform"},{"issue":"1","key":"2023103020153375900_ref50","doi-asserted-by":"crossref","first-page":"bbab545","DOI":"10.1093\/bib\/bbab545","article-title":"Amde: a novel attention-mechanism-based multidimensional feature encoder for drug\u2013drug interaction prediction","volume":"23","author":"Pang","year":"2022","journal-title":"Brief Bioinform"},{"issue":"1","key":"2023103020153375900_ref51","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-020-03724-x","article-title":"Dpddi: a deep predictor for drug-drug interactions","volume":"21","author":"Feng","year":"2020","journal-title":"BMC Bioinformatics"},{"key":"2023103020153375900_ref52","article-title":"Enhancing drug-drug interaction prediction using deep attention neural networks","volume":"23","author":"Liu"},{"key":"2023103020153375900_ref53","article-title":"Strategies for pre-training graph neural networks.","author":"Hu","year":"2019"},{"key":"2023103020153375900_ref54","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11604","article-title":"Deeper insights into graph convolutional networks for semi-supervised learning","volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence","author":"Li","year":"2018"},{"key":"2023103020153375900_ref55","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"International Conference on Machine Learning","author":"Keyulu","year":"2018"},{"key":"2023103020153375900_ref56","article-title":"Deepergcn: all you need to train deeper gcns.","author":"Li","year":"2020"},{"key":"2023103020153375900_ref57","article-title":"Realformer: transformer likes residual attention.","author":"He","year":"2020"},{"issue":"D1","key":"2023103020153375900_ref58","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":"2023103020153375900_ref59","article-title":"Data-driven prediction of drug effects and interactions","volume":"4","author":"Tatonetti","journal-title":"Sci Transl Med"},{"key":"2023103020153375900_ref60","article-title":"Drkg-drug repurposing knowledge graph for Covid-19.","author":"Ioannidis","year":"2020"},{"issue":"5","key":"2023103020153375900_ref61","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac296","article-title":"Molormer: a lightweight self-attention-based method focused on spatial structure of molecular graph for drug\u2013drug interactions prediction","volume":"23","author":"Zhang","year":"2022","journal-title":"Brief Bioinform"},{"issue":"1","key":"2023103020153375900_ref62","doi-asserted-by":"crossref","first-page":"bbab421","DOI":"10.1093\/bib\/bbab421","article-title":"Mdf-sa-ddi: predicting drug\u2013drug interaction events based on multi-source drug fusion, multi-source feature fusion and transformer self-attention mechanism","volume":"23","author":"Lin","year":"2022","journal-title":"Brief Bioinform"},{"key":"2023103020153375900_ref63","doi-asserted-by":"crossref","first-page":"469","DOI":"10.2165\/00003088-200645050-00003","article-title":"Clinical pharmacokinetics of ranolazine","volume":"45","author":"Jerling","year":"2006","journal-title":"Clin Pharmacokinet"},{"key":"2023103020153375900_ref64","first-page":"S10","article-title":"Advances in the management of stable angina","volume":"12","author":"Trujillo","year":"2006","journal-title":"J Manag Care Pharm"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/24\/6\/bbad385\/52689975\/bbad385.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/24\/6\/bbad385\/52689975\/bbad385.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,30]],"date-time":"2023-10-30T23:29:10Z","timestamp":1698708550000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbad385\/7333670"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,22]]},"references-count":64,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,9,22]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbad385","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,11,1]]},"published":{"date-parts":[[2023,9,22]]},"article-number":"bbad385"}}