{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T15:10:07Z","timestamp":1785856207973,"version":"3.56.0"},"reference-count":56,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2021,9,24]],"date-time":"2021-09-24T00:00:00Z","timestamp":1632441600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"name":"National Research and Development Program of China","award":["2019YFC0118802"],"award-info":[{"award-number":["2019YFC0118802"]}]},{"name":"Key R & D Program of Zhejiang Province","award":["2020C03010"],"award-info":[{"award-number":["2020C03010"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672453"],"award-info":[{"award-number":["61672453"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang University Education Foundation","award":["K18-511120-004"],"award-info":[{"award-number":["K18-511120-004"]}]},{"name":"Zhejiang University Education Foundation","award":["K17-511120-017"],"award-info":[{"award-number":["K17-511120-017"]}]},{"name":"Zhejiang University Education Foundation","award":["K17-518051-02"],"award-info":[{"award-number":["K17-518051-02"]}]},{"name":"Zhejiang public welfare technology research project","award":["LGF20F020013"],"award-info":[{"award-number":["LGF20F020013"]}]},{"name":"Medical and Health Research Project of Zhejiang Province of China","award":["2019KY667"],"award-info":[{"award-number":["2019KY667"]}]},{"name":"Wenzhou Bureau of Science and Technology of China","award":["Y2020082"],"award-info":[{"award-number":["Y2020082"]}]},{"name":"Key Laboratory of Medical Neurobiology of Zhejiang Province"},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-1617735"],"award-info":[{"award-number":["CCF-1617735"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,1,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Drug response prediction (DRP) plays an important role in precision medicine (e.g. for cancer analysis and treatment). Recent advances in deep learning algorithms make it possible to predict drug responses accurately based on genetic profiles. However, existing methods ignore the potential relationships among genes. In addition, similarity among cell lines\/drugs was rarely considered explicitly.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We propose a novel DRP framework, called TGSA, to make better use of prior domain knowledge. TGSA consists of Twin Graph neural networks for Drug Response Prediction (TGDRP) and a Similarity Augmentation (SA) module to fuse fine-grained and coarse-grained information. Specifically, TGDRP abstracts cell lines as graphs based on STRING protein\u2013protein association networks and uses Graph Neural Networks (GNNs) for representation learning. SA views DRP as an edge regression problem on a heterogeneous graph and utilizes GNNs to smooth the representations of similar cell lines\/drugs. Besides, we introduce an auxiliary pre-training strategy to remedy the identified limitations of scarce data and poor out-of-distribution generalization. Extensive experiments on the GDSC2 dataset demonstrate that our TGSA consistently outperforms all the state-of-the-art baselines under various experimental settings. We further evaluate the effectiveness and contributions of each component of TGSA via ablation experiments. The promising performance of TGSA shows enormous potential for clinical applications in precision medicine.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The source code is available at https:\/\/github.com\/violet-sto\/TGSA.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btab650","type":"journal-article","created":{"date-parts":[[2021,9,17]],"date-time":"2021-09-17T19:14:19Z","timestamp":1631906059000},"page":"461-468","source":"Crossref","is-referenced-by-count":65,"title":["TGSA: protein\u2013protein association-based twin graph neural networks for drug response prediction with similarity augmentation"],"prefix":"10.1093","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8020-9979","authenticated-orcid":false,"given":"Yiheng","family":"Zhu","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University , Hangzhou 310000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4314-8692","authenticated-orcid":false,"given":"Zhenqiu","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Polytechnic Institute, Zhejiang University , Hangzhou 310000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbo","family":"Chen","sequence":"additional","affiliation":[{"name":"Polytechnic Institute, Zhejiang University , Hangzhou 310000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiwei","family":"Feng","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University , Hangzhou 310000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6565-2884","authenticated-orcid":false,"given":"Danny Z","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Notre Dame , Notre Dame, IN 46556, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Cao","sequence":"additional","affiliation":[{"name":"College of Pharmaceutical Sciences, Zhejiang University , Hangzhou 310000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Ophthalmology of the Second Affiliated Hospital School of Medicine, and School of Public Health, Zhejiang University , Hangzhou 310000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2021,9,24]]},"reference":[{"key":"2023020201173938400_btab650-B1","doi-asserted-by":"crossref","first-page":"i455","DOI":"10.1093\/bioinformatics\/btw433","article-title":"Drug response prediction by inferring pathway\u2013response associations with kernelized Bayesian matrix factorization","volume":"32","author":"Ammad-Ud Din","year":"2016","journal-title":"Bioinformatics"},{"key":"2023020201173938400_btab650-B2","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1093\/bib\/bbz171","article-title":"Deep learning for drug response prediction in cancer","volume":"22","author":"Baptista","year":"2021","journal-title":"Brief. Bioinf"},{"key":"2023020201173938400_btab650-B3","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":"2023020201173938400_btab650-B4","first-page":"874","author":"Bianchi","year":"2020"},{"key":"2023020201173938400_btab650-B5","doi-asserted-by":"crossref","first-page":"8857","DOI":"10.1038\/s41598-018-27214-6","article-title":"Cancer drug response profile scan (CDRscan): a deep learning model that predicts drug effectiveness from cancer genomic signature","volume":"8","author":"Chang","year":"2018","journal-title":"Sci. Rep"},{"key":"2023020201173938400_btab650-B6","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1186\/s12920-019-0569-5","article-title":"Predicting drug response of tumors from integrated genomic profiles by deep neural networks","volume":"12","author":"Chiu","year":"2019","journal-title":"BMC Med. Genomics"},{"key":"2023020201173938400_btab650-B7","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1186\/s13321-019-0364-5","article-title":"KekuleScope: prediction of cancer cell line sensitivity and compound potency using convolutional neural networks trained on compound images","volume":"11","author":"Cort\u00e9s-Ciriano","year":"2019","journal-title":"J. Cheminf"},{"key":"2023020201173938400_btab650-B8","doi-asserted-by":"crossref","first-page":"1944","DOI":"10.1109\/TPAMI.2007.1115","article-title":"Weighted graph cuts without eigenvectors a multilevel approach","volume":"29","author":"Dhillon","year":"2007","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"2023020201173938400_btab650-B9","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1158\/1541-7786.MCR-17-0378","article-title":"Precision oncology beyond targeted therapy: combining omics data with machine learning matches the majority of cancer cells to effective therapeutics","volume":"16","author":"Ding","year":"2018","journal-title":"Mol. Cancer Res"},{"key":"2023020201173938400_btab650-B10","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1186\/s12885-015-1492-6","article-title":"Anticancer drug sensitivity prediction in cell lines from baseline gene expression through recursive feature selection","volume":"15","author":"Dong","year":"2015","journal-title":"BMC Cancer"},{"key":"2023020201173938400_btab650-B11","first-page":"17","article-title":"On the evolution of random graphs","volume":"5","author":"Erdos","year":"1960","journal-title":"Publ. Math. Inst. Hung. Acad. Sci"},{"key":"2023020201173938400_btab650-B12","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/nrg2499","article-title":"The evolution of hierarchical gene regulatory networks","volume":"10","author":"Erwin","year":"2009","journal-title":"Nat. Rev. Genet"},{"key":"2023020201173938400_btab650-B13","author":"Fey","year":"2019"},{"key":"2023020201173938400_btab650-B14","doi-asserted-by":"crossref","first-page":"747","DOI":"10.1038\/nrc4015","article-title":"Precision medicine for cancer with next-generation functional diagnostics","volume":"15","author":"Friedman","year":"2015","journal-title":"Nat. Rev. Cancer"},{"key":"2023020201173938400_btab650-B15","doi-asserted-by":"crossref","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","article-title":"ChEMBL: a large-scale bioactivity database for drug discovery","volume":"40","author":"Gaulton","year":"2012","journal-title":"Nucleic Acids Res"},{"key":"2023020201173938400_btab650-B16","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"Gilmer","year":"2017"},{"key":"2023020201173938400_btab650-B17","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1016\/j.omtn.2019.05.017","article-title":"Anticancer drug response prediction in cell lines using weighted graph regularized matrix factorization","volume":"17","author":"Guan","year":"2019","journal-title":"Mol. Therapy Nucleic Acids"},{"key":"2023020201173938400_btab650-B18","first-page":"1024","author":"Hamilton","year":"2017"},{"key":"2023020201173938400_btab650-B19","author":"He","year":"2019"},{"key":"2023020201173938400_btab650-B20","doi-asserted-by":"crossref","first-page":"S49","DOI":"10.1038\/537S49a","article-title":"Precision medicine","volume":"537","author":"Hodson","year":"2016","journal-title":"Nature"},{"key":"2023020201173938400_btab650-B21","author":"Hu","year":"2020"},{"key":"2023020201173938400_btab650-B22","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1016\/j.cell.2016.06.017","article-title":"A landscape of pharmacogenomic interactions in cancer","volume":"166","author":"Iorio","year":"2016","journal-title":"Cell"},{"key":"2023020201173938400_btab650-B23","first-page":"4171","author":"Kenton","year":"2019"},{"key":"2023020201173938400_btab650-B24","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc. IEEE"},{"key":"2023020201173938400_btab650-B25","doi-asserted-by":"crossref","first-page":"408","DOI":"10.1186\/s12859-019-2910-6","article-title":"Improving prediction of phenotypic drug response on cancer cell lines using deep convolutional network","volume":"20","author":"Liu","year":"2019","journal-title":"BMC Bioinformatics"},{"key":"2023020201173938400_btab650-B26","doi-asserted-by":"crossref","first-page":"i911","DOI":"10.1093\/bioinformatics\/btaa822","article-title":"DeepCDR: a hybrid graph convolutional network for predicting cancer drug response","volume":"36","author":"Liu","year":"2020","journal-title":"Bioinformatics"},{"key":"2023020201173938400_btab650-B27","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1016\/j.bbrc.2018.05.039","article-title":"PAFAH1B2 is a HIF1a target gene and promotes metastasis in pancreatic cancer","volume":"501","author":"Ma","year":"2018","journal-title":"Biochem. Biophys. Res. Commun"},{"key":"2023020201173938400_btab650-B28","doi-asserted-by":"crossref","first-page":"80","DOI":"10.3389\/fenvs.2015.00080","article-title":"DeepTox: toxicity prediction using deep learning","volume":"3","author":"Mayr","year":"2016","journal-title":"Front. Environ. Sci"},{"key":"2023020201173938400_btab650-B29","doi-asserted-by":"crossref","first-page":"3276","DOI":"10.1182\/blood-2008-08-173369","article-title":"The NAD biosynthesis inhibitor APO866 has potent antitumor activity against hematologic malignancies","volume":"113","author":"Nahimana","year":"2009","journal-title":"Blood"},{"key":"2023020201173938400_btab650-B30","article-title":"Graph convolutional networks for drug response prediction","author":"Nguyen","year":"2021","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinf"},{"key":"2023020201173938400_btab650-B31","first-page":"8024","author":"Paszke","year":"2019"},{"key":"2023020201173938400_btab650-B32","doi-asserted-by":"crossref","first-page":"19","DOI":"10.4161\/auto.6.1.10323","article-title":"Bortezomib blocks the catabolic process of autophagy via a cathepsin-dependent mechanism, affects endoplasmic reticulum stress, and induces caspase-dependent cell death in antiestrogen\u2013sensitive and resistant ER+ breast cancer cells","volume":"6","author":"Periyasamy-Thandavan","year":"2010","journal-title":"Autophagy"},{"key":"2023020201173938400_btab650-B33","doi-asserted-by":"crossref","first-page":"789","DOI":"10.1038\/nrc1977","article-title":"Topoisomerase i inhibitors: camptothecins and beyond","volume":"6","author":"Pommier","year":"2006","journal-title":"Nat. Rev. Cancer"},{"key":"2023020201173938400_btab650-B34","doi-asserted-by":"crossref","first-page":"2563","DOI":"10.1158\/1535-7163.MCT-16-0141","article-title":"Azd5153: a novel bivalent bet bromodomain inhibitor highly active against hematologic malignancies","volume":"15","author":"Rhyasen","year":"2016","journal-title":"Mol. Cancer Therap"},{"key":"2023020201173938400_btab650-B35","doi-asserted-by":"crossref","first-page":"2609","DOI":"10.1056\/NEJMoa030288","article-title":"A phase 2 study of bortezomib in relapsed, refractory myeloma","volume":"348","author":"Richardson","year":"2003","journal-title":"N. Engl. J. Med"},{"key":"2023020201173938400_btab650-B36","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":"2023020201173938400_btab650-B37","first-page":"618","article-title":"Grad-cam: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"2023020201173938400_btab650-B38","doi-asserted-by":"crossref","first-page":"i501","DOI":"10.1093\/bioinformatics\/btz318","article-title":"MOLI: multi-omics late integration with deep neural networks for drug response prediction","volume":"35","author":"Sharifi-Noghabi","year":"2019","journal-title":"Bioinformatics"},{"key":"2023020201173938400_btab650-B39","first-page":"3131","article-title":"Bortezomib inhibits tumor adaptation to hypoxia by stimulating the FIH-mediated repression of hypoxia-inducible factor-1. Blood","volume":"111","author":"Shin","year":"2008","journal-title":"J. Am. Soc. Hematol"},{"key":"2023020201173938400_btab650-B40","doi-asserted-by":"crossref","first-page":"2324","DOI":"10.1021\/acs.jcim.5b00559","article-title":"ZINC 15\u2013ligand discovery for everyone","volume":"55","author":"Sterling","year":"2015","journal-title":"J. Chem. Inf. Model"},{"key":"2023020201173938400_btab650-B41","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1093\/bib\/bbz042","article-title":"Graph convolutional networks for computational drug development and discovery","volume":"21","author":"Sun","year":"2020","journal-title":"Brief. Bioinf"},{"key":"2023020201173938400_btab650-B42","doi-asserted-by":"crossref","first-page":"3907","DOI":"10.1093\/bioinformatics\/bty452","article-title":"Predicting cancer drug response using a recommender system","volume":"34","author":"Suphavilai","year":"2018","journal-title":"Bioinformatics"},{"key":"2023020201173938400_btab650-B43","doi-asserted-by":"crossref","first-page":"D607","DOI":"10.1093\/nar\/gky1131","article-title":"STRING v11: protein\u2013protein association networks with increased coverage, supporting functional discovery in genome-wide experimental datasets","volume":"47","author":"Szklarczyk","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023020201173938400_btab650-B44","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1007\/s40262-018-0679-9","article-title":"Clinical pharmacokinetics and pharmacodynamics of bortezomib","volume":"58","author":"Tan","year":"2019","journal-title":"Clin. Pharmacokinet"},{"key":"2023020201173938400_btab650-B45","doi-asserted-by":"crossref","first-page":"D941","DOI":"10.1093\/nar\/gky1015","article-title":"COSMIC: the catalogue of somatic mutations in cancer","volume":"47","author":"Tate","year":"2019","journal-title":"Nucleic Acids Res"},{"key":"2023020201173938400_btab650-B46","doi-asserted-by":"crossref","first-page":"422","DOI":"10.1038\/s41563-018-0241-z","article-title":"Avoiding common pitfalls in machine learning omic data science","volume":"18","author":"Teschendorff","year":"2019","journal-title":"Nat. Mater"},{"key":"2023020201173938400_btab650-B47","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":"2023020201173938400_btab650-B48","author":"Velickovic","year":"2018"},{"key":"2023020201173938400_btab650-B49","author":"Velickovic","year":"2019"},{"key":"2023020201173938400_btab650-B50","doi-asserted-by":"crossref","first-page":"513","DOI":"10.1186\/s12885-017-3500-5","article-title":"Improved anticancer drug response prediction in cell lines using matrix factorization with similarity regularization","volume":"17","author":"Wang","year":"2017","journal-title":"BMC Cancer"},{"key":"2023020201173938400_btab650-B51","first-page":"6861","author":"Wu","year":"2019"},{"key":"2023020201173938400_btab650-B52","first-page":"5453","author":"Xu","year":"2018"},{"key":"2023020201173938400_btab650-B53","author":"Xu","year":"2019"},{"key":"2023020201173938400_btab650-B54","doi-asserted-by":"crossref","first-page":"D955","DOI":"10.1093\/nar\/gks1111","article-title":"Genomics of drug sensitivity in cancer (GDSC): a resource for therapeutic biomarker discovery in cancer cells","volume":"41","author":"Yang","year":"2013","journal-title":"Nucleic Acids Res"},{"key":"2023020201173938400_btab650-B55","author":"Ying","year":"2018"},{"key":"2023020201173938400_btab650-B56","doi-asserted-by":"crossref","first-page":"e1004498","DOI":"10.1371\/journal.pcbi.1004498","article-title":"Predicting anticancer drug responses using a dual-layer integrated cell line-drug network model","volume":"11","author":"Zhang","year":"2015","journal-title":"PLoS Comput. Biol"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btab650\/40533130\/btab650.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/2\/461\/49006459\/btab650.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/38\/2\/461\/49006459\/btab650.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T03:37:57Z","timestamp":1675309077000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/38\/2\/461\/6374919"}},"subtitle":[],"editor":[{"given":"Pier Luigi","family":"Martelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,9,24]]},"references-count":56,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2022,1,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btab650","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,1,15]]},"published":{"date-parts":[[2021,9,24]]}}}