{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:50:00Z","timestamp":1785336600522,"version":"3.55.0"},"reference-count":36,"publisher":"Oxford University Press (OUP)","issue":"11","license":[{"start":{"date-parts":[[2021,9,2]],"date-time":"2021-09-02T00:00:00Z","timestamp":1630540800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["71972164"],"award-info":[{"award-number":["71972164"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Health and Medical Research Fund of the Food and Health Bureau of Hong Kong","award":["16171991"],"award-info":[{"award-number":["16171991"]}]},{"name":"Innovation and Technology Fund of Innovation and Technology Commission of Hong Kong","award":["MHP\/081\/19"],"award-info":[{"award-number":["MHP\/081\/19"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Science and Technology of China","award":["2019YFE0198600"],"award-info":[{"award-number":["2019YFE0198600"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,10,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To develop an end-to-end deep learning framework based on a protein\u2013protein interaction (PPI) network to make synergistic anticancer drug combination predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>We propose a deep learning framework named Graph Convolutional Network for Drug Synergy (GraphSynergy). GraphSynergy adapts a spatial-based Graph Convolutional Network component to encode the high-order topological relationships in the PPI network of protein modules targeted by a pair of drugs, as well as the protein modules associated with a specific cancer cell line. The pharmacological effects of drug combinations are explicitly evaluated by their therapy and toxicity scores. An attention component is also introduced in GraphSynergy, which aims to capture the pivotal proteins that play a part in both PPI network and biomolecular interactions between drug combinations and cancer cell lines.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>GraphSynergy outperforms the classic and state-of-the-art models in predicting synergistic drug combinations on the 2 latest drug combination datasets. Specifically, GraphSynergy achieves accuracy values of 0.7553 (11.94% improvement compared to DeepSynergy, the latest published drug combination prediction algorithm) and 0.7557 (10.95% improvement compared to DeepSynergy) on DrugCombDB and Oncology-Screen datasets, respectively. Furthermore, the proteins allocated with high contribution weights during the training of GraphSynergy are proved to play a role in view of molecular functions and biological processes, such as transcription and transcription regulation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The introduction of topological relations between drug combination and cell line within the PPI network can significantly improve the capability of synergistic drug combination identification.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocab162","type":"journal-article","created":{"date-parts":[[2021,7,15]],"date-time":"2021-07-15T15:11:03Z","timestamp":1626361863000},"page":"2336-2345","source":"Crossref","is-referenced-by-count":113,"title":["GraphSynergy: a network-inspired deep learning model for anticancer drug combination prediction"],"prefix":"10.1093","volume":"28","author":[{"given":"Jiannan","family":"Yang","sequence":"first","affiliation":[{"name":"School of Data Science, City University of Hong Kong, Hong Kong, S.A.R. of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongzhi","family":"Xu","sequence":"additional","affiliation":[{"name":"Hong Kong Jockey Club Centre for Suicide Research and Prevention, The University of Hong Kong, Hong Kong, S.A.R. of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William Ka Kei","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Anaesthesia and Intensive Care, Chinese University of Hong Kong, Hong Kong, S.A.R. of China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Chu","sequence":"additional","affiliation":[{"name":"Department of Thoracic Oncology, Tongji Hospital, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6819-0686","authenticated-orcid":false,"given":"Qingpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Data Science, City University of Hong Kong, Hong Kong, S.A.R. of China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2021,9,2]]},"reference":[{"issue":"205","key":"2021101218242586200_ocab162-B1","doi-asserted-by":"crossref","first-page":"205rv1","DOI":"10.1126\/scitranslmed.3006667","article-title":"High-throughput methods for combinatorial drug discovery","volume":"5","author":"Sun","year":"2013","journal-title":"Sci Transl Med"},{"key":"2021101218242586200_ocab162-B2","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1016\/j.csbj.2015.09.001","article-title":"Searching for drug synergy in complex dose\u2013response landscapes using an interaction potency model","volume":"13","author":"Yadav","year":"2015","journal-title":"Comput Struct Biotechnol J"},{"issue":"12","key":"2021101218242586200_ocab162-B3","doi-asserted-by":"crossref","first-page":"1001","DOI":"10.1038\/nrd2424","article-title":"The design of drugs for HIV and HCV","volume":"6","author":"De Clercq","year":"2007","journal-title":"Nat Rev Drug Discov"},{"issue":"2","key":"2021101218242586200_ocab162-B4","doi-asserted-by":"crossref","first-page":"199","DOI":"10.1007\/s00432-013-1528-8","article-title":"Treatment outcomes of transcatheter arterial chemoembolization combined with local ablative therapy versus monotherapy in hepatocellular carcinoma: a meta-analysis","volume":"140","author":"Gu","year":"2014","journal-title":"J Cancer Res Clin Oncol"},{"issue":"6","key":"2021101218242586200_ocab162-B5","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1056\/NEJMoa0808268","article-title":"Chemotherapy, bevacizumab, and cetuximab in metastatic colorectal cancer","volume":"360","author":"Tol","year":"2009","journal-title":"N Engl J Med"},{"key":"2021101218242586200_ocab162-B6","doi-asserted-by":"crossref","first-page":"351","DOI":"10.1007\/978-1-4939-7493-1_17","volume-title":"Cancer Systems Biology","author":"He","year":"2018"},{"issue":"6","key":"2021101218242586200_ocab162-B7","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1016\/j.cels.2015.12.003","article-title":"Prediction of synergism from chemical-genetic interactions by machine learning","volume":"1","author":"Wildenhain","year":"2015","journal-title":"Cell Syst"},{"key":"2021101218242586200_ocab162-B8","doi-asserted-by":"crossref","first-page":"1000","DOI":"10.3389\/fgene.2020.01000","article-title":"A machine learning method for drug combination prediction","volume":"11","author":"Li","year":"2020","journal-title":"Front Genet"},{"issue":"12","key":"2021101218242586200_ocab162-B9","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":"9","key":"2021101218242586200_ocab162-B10","doi-asserted-by":"crossref","first-page":"1538","DOI":"10.1093\/bioinformatics\/btx806","article-title":"DeepSynergy: predicting anticancer drug synergy with Deep Learning","volume":"34","author":"Preuer","year":"2018","journal-title":"Bioinformatics"},{"key":"2021101218242586200_ocab162-B11","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1007\/978-1-0716-0849-4_12","volume-title":"Translational Bioinformatics for Therapeutic Development","author":"Zhang","year":"2021"},{"issue":"42","key":"2021101218242586200_ocab162-B12","first-page":"4729","article-title":"Promising targets in anticancer drug development: Recent updates","volume":"24","author":"Kumar","year":"2017","journal-title":"Curr Med Chem"},{"issue":"1","key":"2021101218242586200_ocab162-B13","doi-asserted-by":"crossref","first-page":"10331","DOI":"10.1038\/ncomms10331","article-title":"Network-based in silico drug efficacy screening","volume":"7","author":"Guney","year":"2016","journal-title":"Nat Commun"},{"issue":"1","key":"2021101218242586200_ocab162-B14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-019-09692-y","article-title":"Network-based prediction of drug combinations","volume":"10","author":"Cheng","year":"2019","journal-title":"Nat Commun"},{"issue":"18","key":"2021101218242586200_ocab162-B15","doi-asserted-by":"crossref","first-page":"5446","DOI":"10.1158\/0008-5472.CAN-18-0740","article-title":"Network propagation predicts drug synergy in cancers","volume":"78","author":"Li","year":"2018","journal-title":"Cancer Res"},{"issue":"2","key":"2021101218242586200_ocab162-B16","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/s12253-016-0089-y","article-title":"Low expression LncRNA TUBA4B is a poor predictor of prognosis and regulates cell proliferation in non-small cell lung cancer","volume":"23","author":"Chen","year":"2017","journal-title":"Pathol Oncol Res"},{"key":"2021101218242586200_ocab162-B17","author":"Kipf","year":"2016"},{"key":"2021101218242586200_ocab162-B18","author":"Bahdanau","year":"2014"},{"issue":"12","key":"2021101218242586200_ocab162-B19","doi-asserted-by":"crossref","first-page":"e1002819","DOI":"10.1371\/journal.pcbi.1002819","article-title":"Protein interactions and disease","volume":"8","author":"Gonzalez","year":"2012","journal-title":"PLoS Comput Biol"},{"key":"2021101218242586200_ocab162-B20","year":"2020"},{"issue":"1","key":"2021101218242586200_ocab162-B21","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-020-15424-4","article-title":"Prostate-specific antigen dynamics predict individual responses to intermittent androgen deprivation","volume":"11","author":"Brady-Nicholls","year":"2020","journal-title":"Nat Commun"},{"issue":"7391","key":"2021101218242586200_ocab162-B22","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"},{"issue":"D1","key":"2021101218242586200_ocab162-B23","first-page":"D871","article-title":"DrugCombDB: a comprehensive database of drug combinations toward the discovery of combinatorial therapy","volume":"48","author":"Liu","year":"2020","journal-title":"Nucleic Acids Res"},{"issue":"6","key":"2021101218242586200_ocab162-B24","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'Neil","year":"2016","journal-title":"Mol Cancer Ther"},{"key":"2021101218242586200_ocab162-B25","year":"2015"},{"key":"2021101218242586200_ocab162-B26","year":"2014"},{"key":"2021101218242586200_ocab162-B27","year":"2016"},{"issue":"6208","key":"2021101218242586200_ocab162-B28","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1126\/science.1261509","article-title":"Unanchored ubiquitin in virus uncoating","volume":"346","author":"Rajsbaum","year":"2014","journal-title":"Science"},{"issue":"12","key":"2021101218242586200_ocab162-B29","doi-asserted-by":"crossref","first-page":"4554","DOI":"10.1172\/JCI92914","article-title":"Recurrent ubiquitin B silencing in gynecological cancers establishes dependence on ubiquitin C","volume":"127","author":"Kedves","year":"2017","journal-title":"J Clin Invest"},{"issue":"6833","key":"2021101218242586200_ocab162-B30","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1038\/35075138","article-title":"Lethality and centrality in protein networks","volume":"411","author":"Jeong","year":"2001","journal-title":"Nature"},{"issue":"1","key":"2021101218242586200_ocab162-B31","doi-asserted-by":"crossref","first-page":"e3","DOI":"10.1097\/JTO.0b013e3182762d20","article-title":"High-dose pemetrexed in combination with high-dose crizotinib for the treatment of refractory CNS metastases in ALK-rearranged non\u2013small-cell lung cancer","volume":"8","author":"Gandhi","year":"2013","journal-title":"J Thorac Oncol"},{"issue":"27","key":"2021101218242586200_ocab162-B32","doi-asserted-by":"crossref","first-page":"3258","DOI":"10.1200\/JCO.2016.66.9218","article-title":"Randomized phase II trial of gefitinib with and without pemetrexed as first-line therapy in patients with advanced nonsquamous non\u2013small-cell lung cancer with activating epidermal growth factor receptor mutations","volume":"34","author":"Cheng","year":"2016","journal-title":"J Clin Oncol"},{"issue":"6","key":"2021101218242586200_ocab162-B33","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1002\/kjm2.12194","article-title":"Overexpression of tripartite motif containing 26 inhibits non-small cell lung cancer cell growth by suppressing PI3K\/AKT signaling","volume":"36","author":"Tao","year":"2020","journal-title":"Kaohsiung J Med Sci"},{"issue":"3\u20134","key":"2021101218242586200_ocab162-B34","doi-asserted-by":"crossref","first-page":"553","DOI":"10.1007\/s10555-007-9080-0","article-title":"The role of the hypoxia-inducible BH3-only proteins BNIP3 and BNIP3L in cancer","volume":"26","author":"Mellor","year":"2007","journal-title":"Cancer Metastasis Rev"},{"key":"2021101218242586200_ocab162-B35","doi-asserted-by":"crossref","first-page":"2491","DOI":"10.2147\/OTT.S231257","article-title":"MET oncogene in non-small cell lung cancer: mechanism of MET dysregulation and agents targeting the HGF\/c-Met axis","volume":"13","author":"Liang","year":"2020","journal-title":"Onco Targets Ther"},{"issue":"15","key":"2021101218242586200_ocab162-B36","doi-asserted-by":"crossref","first-page":"4418","DOI":"10.1158\/0008-5472.CAN-16-0069","article-title":"IKBKE is a substrate of EGFR and a therapeutic target in non\u2013small cell lung cancer with activating mutations of EGFR","volume":"76","author":"Challa","year":"2016","journal-title":"Cancer Res"}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/28\/11\/2336\/40576607\/ocab162.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/jamia\/article-pdf\/28\/11\/2336\/40576607\/ocab162.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,4]],"date-time":"2023-01-04T08:32:10Z","timestamp":1672821130000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/28\/11\/2336\/6362567"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,2]]},"references-count":36,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2021,9,2]]},"published-print":{"date-parts":[[2021,10,12]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocab162","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-315189\/v1","asserted-by":"object"}]},"ISSN":["1527-974X"],"issn-type":[{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,11,1]]},"published":{"date-parts":[[2021,9,2]]}}}