{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T21:51:07Z","timestamp":1778622667229,"version":"3.51.4"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFF1201200"],"award-info":[{"award-number":["2021YFF1201200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFF1200900"],"award-info":[{"award-number":["2021YFF1200900"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Drug combination therapy shows significant advantages over monotherapy in cancer treatment. Since the combinational space is difficult to be traversed experimentally, identifying novel synergistic drug combinations based on computational methods has become a powerful tool for pre-screening. Among them, methods based on deep learning have far outperformed other methods. However, most deep learning-based methods are unstable and will give inconsistent predictions even by simply changing the input order of drugs. In addition, the insufficient experimental data of drug combination screening limits the generalization ability of existing models. These problems prevent the deep learning-based models from being in service.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>In this article, we propose CGMS to address the above problems. CGMS models a drug combination and a cell line as a heterogeneous complete graph, and generates the whole-graph embedding to characterize their interaction by leveraging the heterogeneous graph attention network. Based on the whole-graph embedding, CGMS can make a stable, order-independent prediction. To enhance the generalization ability of CGMS, we apply the multi-task learning technique to train the model on drug synergy prediction task and drug sensitivity prediction task simultaneously. We compare CGMS\u2019s generalization ability with six state-of-the-art methods on a public dataset, and CGMS significantly outperforms other methods in the leave-drug combination-out scenario, as well as in the leave-cell line-out and leave-drug-out scenarios. We further present the benefit of eliminating the order dependency and the discrimination power of whole-graph embeddings, interpret the rationality of the attention mechanism, and verify the contribution of multi-task learning.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The code of CGMS is available via https:\/\/github.com\/TOJSSE-iData\/CGMS.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad351","type":"journal-article","created":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T15:41:24Z","timestamp":1685634084000},"source":"Crossref","is-referenced-by-count":29,"title":["A complete graph-based approach with multi-task learning for predicting synergistic drug combinations"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1880-7921","authenticated-orcid":false,"given":"Xiaowen","family":"Wang","sequence":"first","affiliation":[{"name":"School of Software Engineering, Tongji University , Shanghai 201804, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5795-5279","authenticated-orcid":false,"given":"Hongming","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Tongji University , Shanghai 201804, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danyi","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Tongji University , Shanghai 201804, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongsheng","family":"Yu","sequence":"additional","affiliation":[{"name":"Drug Discovery and Development Department, Tasly Biopharmaceuticals Co., Ltd , Shanghai 201203, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Liu","sequence":"additional","affiliation":[{"name":"Translational Medical Center for Stem Cell Therapy and Institute for Regenerative Medicine, Shanghai East Hospital, Bioinformatics Department, School of Life Sciences and Technology, Tongji University , Shanghai 200092, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9352-1694","authenticated-orcid":false,"given":"Qin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Tongji University , Shanghai 201804, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2023,6,1]]},"reference":[{"key":"2023061104230538600_btad351-B1","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/978-3-319-57454-7_7","volume-title":"Advances in Knowledge Discovery and Data Mining","author":"Atarashi","year":"2017"},{"key":"2023061104230538600_btad351-B2","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1038\/nature11003","article-title":"The cancer cell line encyclopedia enables predictive modelling of anticancer drug sensitivity","volume":"483","author":"Barretina","year":"2012","journal-title":"Nature"},{"key":"2023061104230538600_btad351-B3","doi-asserted-by":"crossref","first-page":"1336","DOI":"10.1109\/JBHI.2018.2852274","article-title":"Ensemble prediction of synergistic drug combinations incorporating biological, chemical, pharmacological, and network knowledge","volume":"23","author":"Ding","year":"2019","journal-title":"IEEE J Biomed Health Inform"},{"key":"2023061104230538600_btad351-B4","doi-asserted-by":"crossref","first-page":"100492","DOI":"10.1016\/j.xcrm.2021.100492","article-title":"A community challenge for a pancancer drug mechanism of action inference from perturbational profile data","volume":"3","author":"Douglass","year":"2022","journal-title":"Cell Rep Med"},{"key":"2023061104230538600_btad351-B5","doi-asserted-by":"crossref","first-page":"285","DOI":"10.1007\/s00280-022-04467-7","article-title":"Anti-cancer drug combinations approved by US FDA from 2011 to 2021: main design features of clinical trials and role of pharmacokinetics","volume":"90","author":"Fudio","year":"2022","journal-title":"Cancer Chemother Pharmacol"},{"key":"2023061104230538600_btad351-B6","doi-asserted-by":"crossref","first-page":"669","DOI":"10.3390\/cancers13040669","article-title":"Drug combination in cancer treatment-from cocktails to conjugated combinations","volume":"13","author":"Gilad","year":"2021","journal-title":"Cancers"},{"key":"2023061104230538600_btad351-B7","doi-asserted-by":"crossref","first-page":"3564","DOI":"10.1158\/0008-5472.CAN-17-0489","article-title":"The National Cancer Institute ALMANAC: A Comprehensive Screening Resource for the Detection of Anticancer Drug Pairs with Enhanced Therapeutic Activity","volume":"77","author":"Holbeck","year":"2017","journal-title":"Cancer Res"},{"key":"2023061104230538600_btad351-B8","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.csbj.2020.02.006","article-title":"Deep graph embedding for prioritizing synergistic anticancer drug combinations","volume":"18","author":"Jiang","year":"2020","journal-title":"Comput Struct Biotechnol J"},{"key":"2023061104230538600_btad351-B9","first-page":"148","author":"Jin","year":"2021"},{"key":"2023061104230538600_btad351-B10","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1093\/jamia\/ocaa212","article-title":"Anticancer drug synergy prediction in understudied tissues using transfer learning","volume":"28","author":"Kim","year":"2021","journal-title":"J Am Med Inform Assoc"},{"key":"2023061104230538600_btad351-B11","author":"Landrum"},{"key":"2023061104230538600_btad351-B12","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"},{"key":"2023061104230538600_btad351-B13","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab562","article-title":"An enhanced cascade-based deep forest model for drug combination prediction","volume":"23","author":"Lin","year":"2022","journal-title":"Brief Bioinformatics"},{"key":"2023061104230538600_btad351-B14","doi-asserted-by":"crossref","first-page":"e1008653","DOI":"10.1371\/journal.pcbi.1008653","article-title":"Transynergy: mechanism-driven interpretable deep neural network for the synergistic prediction and pathway deconvolution of drug combinations","volume":"17","author":"Liu","year":"2021","journal-title":"PLoS Comput Biol"},{"key":"2023061104230538600_btad351-B15","first-page":"285","article-title":"The problem of synergism and antagonism of combined drugs","volume":"3","author":"Loewe","year":"1953","journal-title":"Arzneimittelforschung"},{"key":"2023061104230538600_btad351-B16","doi-asserted-by":"crossref","first-page":"188","DOI":"10.1038\/nrd3368","article-title":"Impact of high-throughput screening in biomedical research","volume":"10","author":"Macarron","year":"2011","journal-title":"Nat Rev Drug Discov"},{"key":"2023061104230538600_btad351-B17","doi-asserted-by":"crossref","first-page":"38022","DOI":"10.18632\/oncotarget.16723","article-title":"Combination therapy in combating cancer","volume":"8","author":"Mokhtari","year":"2017","journal-title":"Oncotarget"},{"key":"2023061104230538600_btad351-B18","doi-asserted-by":"crossref","first-page":"1155","DOI":"10.1158\/1535-7163.MCT-15-0843","article-title":"An unbiased oncology compound screen to identify novel combination strategies","volume":"15","author":"O\u2019Neil","year":"2016","journal-title":"Mol Cancer Ther"},{"key":"2023061104230538600_btad351-B19","doi-asserted-by":"crossref","first-page":"1538","DOI":"10.1093\/bioinformatics\/btx806","article-title":"DeepSynergy: predicting anti-cancer drug synergy with deep learning","volume":"34","author":"Preuer","year":"2018","journal-title":"Bioinformatics"},{"key":"2023061104230538600_btad351-B20","doi-asserted-by":"crossref","first-page":"509","DOI":"10.3389\/fchem.2019.00509","article-title":"Predicting synergism of cancer drug combinations using NCI-ALMANAC data","volume":"7","author":"Sidorov","year":"2019","journal-title":"Front Chem"},{"key":"2023061104230538600_btad351-B21","doi-asserted-by":"crossref","first-page":"4483","DOI":"10.1093\/bioinformatics\/btaa287","article-title":"DTF: deep tensor factorization for predicting anticancer drug synergy","volume":"36","author":"Sun","year":"2020","journal-title":"Bioinformatics"},{"key":"2023061104230538600_btad351-B22","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"2023061104230538600_btad351-B23","doi-asserted-by":"crossref","first-page":"D923","DOI":"10.1093\/nar\/gky872","article-title":"Cell model passports\u2014a hub for clinical, genetic and functional datasets of preclinical cancer models","volume":"47","author":"van der Meer","year":"2018","journal-title":"Nucleic Acids Res"},{"key":"2023061104230538600_btad351-B24","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inform Process Syst"},{"key":"2023061104230538600_btad351-B25","article-title":"DeepDDS: deep graph neural network with attention mechanism to predict synergistic drug combinations","volume":"23","author":"Wang","year":"2022","journal-title":"Brief Bioinformatics"},{"key":"2023061104230538600_btad351-B26","first-page":"2022","author":"Wang","year":"2019"},{"key":"2023061104230538600_btad351-B27","article-title":"PRODeepSyn: predicting anticancer synergistic drug combinations by embedding cell lines with protein\u2013protein interaction network","volume":"23","author":"Wang","year":"2022","journal-title":"Brief Bioinformatics"},{"key":"2023061104230538600_btad351-B28","doi-asserted-by":"crossref","first-page":"2336","DOI":"10.1093\/jamia\/ocab162","article-title":"GraphSynergy: a network-inspired deep learning model for anticancer drug combination prediction","volume":"28","author":"Yang","year":"2021","journal-title":"J Am Med Inform Assoc"},{"key":"2023061104230538600_btad351-B29","doi-asserted-by":"crossref","first-page":"W43","DOI":"10.1093\/nar\/gkz337","article-title":"DrugComb: an integrative cancer drug combination data portal","volume":"47","author":"Zagidullin","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023061104230538600_btad351-B30","first-page":"223","volume-title":"Synergistic Drug Combination Prediction by Integrating Multiomics Data in Deep Learning Models","author":"Zhang","year":"2021"},{"key":"2023061104230538600_btad351-B31","doi-asserted-by":"crossref","first-page":"5586","DOI":"10.1109\/TKDE.2021.3070203","article-title":"A survey on multi-task learning","volume":"34","author":"Zhang","year":"2021","journal-title":"IEEE Trans Knowledge Data Eng"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad351\/50502982\/btad351.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/6\/btad351\/50570498\/btad351.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/6\/btad351\/50570498\/btad351.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,11]],"date-time":"2023-06-11T04:23:32Z","timestamp":1686457412000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad351\/7188101"}},"subtitle":[],"editor":[{"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":31,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad351","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,6,1]]},"published":{"date-parts":[[2023,6,1]]},"article-number":"btad351"}}