{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T23:15:49Z","timestamp":1778886949510,"version":"3.51.4"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1013567","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T00:00:00Z","timestamp":1761177600000}}],"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T00:00:00Z","timestamp":1760486400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The University Synergy Innovation Program of Anhui Province","award":["GXXT-2022-035"],"award-info":[{"award-number":["GXXT-2022-035"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302007"],"award-info":[{"award-number":["62302007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322301, 62172002"],"award-info":[{"award-number":["62322301, 62172002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100017128","name":"Science Fund for Distinguished Young Scholars of Anhui Province","doi-asserted-by":"publisher","award":["2008085QF294"],"award-info":[{"award-number":["2008085QF294"]}],"id":[{"id":"10.13039\/100017128","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The University Outstanding Youth Research Project of Anhui Province","award":["2022AH020010"],"award-info":[{"award-number":["2022AH020010"]}]},{"name":"The University Synergy Innovation Program of Anhui Province","award":["GXXT-2021-039"],"award-info":[{"award-number":["GXXT-2021-039"]}]},{"name":"The Project of Key Laboratory of Intelligent Computing & Signal Processing (Anhui University), Ministry of Education","award":["2020A005"],"award-info":[{"award-number":["2020A005"]}]},{"name":"State Key Laboratory of Pathogenesis, Prevention and Treatment of High Incidence Diseases in Central Asia \u2013 Anhui University Work station Joint Fund Project","award":["SKL-HIDCA-2024- AH3"],"award-info":[{"award-number":["SKL-HIDCA-2024- AH3"]}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Cancer drug combination therapies offer a promising strategy to overcome resistance and improve treatment efficacy, but identifying synergistic drug pairs is challenging due to complex biological interactions and tumor heterogeneity. Current machine learning algorithms for drug synergy prediction primarily rely on large-scale, multimodal datasets, yet suffer from critical limitations including poor interpretability, difficulty distinguishing causative biological relationships from correlations, and inadequate modeling of cancer-specific molecular interactions. To address these challenges, we propose CASynergy (Causal Attention and Cross-attention Synergy), a novel deep learning model for predicting cancer drug synergy that addresses limitations of prior approaches in accuracy and interpretability. CASynergy introduces a causal attention mechanism to distinguish true causal genomic features from spurious correlations, cell line-specific gene network construction to capture the unique molecular context of each cancer cell line, and a cross-attention module to integrate drug molecular features with cell line gene expression profiles. These improvements allow CASynergy to clearly identify significant drug-gene interactions and provides interpretable insights into why a combination is predicted to be synergistic. Experiments on two benchmark datasets (DrugCombDB and Oncology-Screen) suggests that CASynergy outperformed five state-of-the-art models. CASynergy offers a better and more reliable way to predict effective drug combinations. It works well across different cancer types and is easier to understand, which is important for personalized cancer treatment and finding new drugs.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1013567","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T17:41:53Z","timestamp":1760550113000},"page":"e1013567","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["CASynergy: A causal attention model for interpretable prediction of cancer drug synergy"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1137-5487","authenticated-orcid":true,"given":"Haitao","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Long","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiwei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junjie","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunhou","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3855-7133","authenticated-orcid":true,"given":"Yansen","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,10,15]]},"reference":[{"issue":"8","key":"pcbi.1013567.ref001","first-page":"2168","article-title":"Cell cycle-mediated drug resistance: an emerging concept in cancer therapy","volume":"7","author":"MA Shah","year":"2001","journal-title":"Clin Cancer Res"},{"issue":"1","key":"pcbi.1013567.ref002","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1124\/pr.112.007336","article-title":"Computational methods in drug discovery","volume":"66","author":"G Sliwoski","year":"2013","journal-title":"Pharmacol Rev"},{"issue":"3","key":"pcbi.1013567.ref003","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-Vector Networks","volume":"20","author":"C Cortes","year":"1995","journal-title":"Machine Learning"},{"key":"pcbi.1013567.ref004","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Machine learning"},{"key":"pcbi.1013567.ref005","first-page":"161","author":"R Caruana","year":"2006"},{"key":"pcbi.1013567.ref006","first-page":"14","author":"MA Thafar","year":"2020"},{"issue":"6","key":"pcbi.1013567.ref007","article-title":"Machine learning approaches for drug combination therapies","volume":"22","author":"B G\u00fcven\u00e7 Paltun","year":"2021","journal-title":"Brief Bioinform"},{"issue":"9","key":"pcbi.1013567.ref008","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":"K Preuer","year":"2018","journal-title":"Bioinformatics"},{"issue":"3","key":"pcbi.1013567.ref009","doi-asserted-by":"crossref","DOI":"10.1002\/ctd2.317","article-title":"Deep learning for predicting synergistic drug combinations: State\u2010of\u2010the\u2010arts and future directions","volume":"4","author":"Y Wang","year":"2024","journal-title":"Clinical and Translational Dis"},{"key":"pcbi.1013567.ref010","article-title":"Semi-supervised classification with graph convolutional networks","author":"TN Kipf","year":"2016","journal-title":"arXiv preprint"},{"issue":"9","key":"pcbi.1013567.ref011","first-page":"29","article-title":"Knowledge graphs: New directions for knowledge representation on the semantic web (dagstuhl seminar 18371)","volume":"8","author":"PA Bonatti","year":"2019","journal-title":"Dagstuhl reports"},{"issue":"11","key":"pcbi.1013567.ref012","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":"J Yang","year":"2021","journal-title":"J Am Med Inform Assoc"},{"issue":"3","key":"pcbi.1013567.ref013","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbad167","article-title":"KGANSynergy: knowledge graph attention network for drug synergy prediction","volume":"24","author":"G Zhang","year":"2023","journal-title":"Brief Bioinform"},{"issue":"20","key":"pcbi.1013567.ref014","doi-asserted-by":"crossref","first-page":"4782","DOI":"10.1093\/bioinformatics\/btac579","article-title":"Multi-way relation-enhanced hypergraph representation learning for anti-cancer drug synergy prediction","volume":"38","author":"X Liu","year":"2022","journal-title":"Bioinformatics"},{"issue":"6","key":"pcbi.1013567.ref015","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbac403","article-title":"Predicting cell line-specific synergistic drug combinations through a relational graph convolutional network with attention mechanism","volume":"23","author":"P Zhang","year":"2022","journal-title":"Brief Bioinform"},{"key":"pcbi.1013567.ref016","first-page":"1696","author":"Y Sui","year":"2022"},{"issue":"1","key":"pcbi.1013567.ref017","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab390","article-title":"DeepDDS: deep graph neural network with attention mechanism to predict synergistic drug combinations","volume":"23","author":"J Wang","year":"2022","journal-title":"Brief Bioinform"},{"issue":"8","key":"pcbi.1013567.ref018","doi-asserted-by":"crossref","first-page":"556","DOI":"10.3390\/metabo11080556","article-title":"Targeting Metabolic Reprogramming to Improve Breast Cancer Treatment: An In Vitro Evaluation of Selected Metabolic Inhibitors Using a Metabolomic Approach","volume":"11","author":"A Draguet","year":"2021","journal-title":"Metabolites"},{"issue":"3","key":"pcbi.1013567.ref019","article-title":"Gene Set Knowledge Discovery with Enrichr","volume":"1","author":"Z Xie","year":"2021","journal-title":"Curr Protoc"},{"issue":"1","key":"pcbi.1013567.ref020","doi-asserted-by":"crossref","first-page":"319","DOI":"10.1007\/s11033-022-08034-4","article-title":"Combined treatment with ruxolitinib and MK-2206 inhibits the JAK2\/STAT5 and PI3K\/AKT pathways via apoptosis in MDA-MB-231 breast cancer cell line","volume":"50","author":"E Guvenir Celik","year":"2023","journal-title":"Mol Biol Rep"},{"issue":"1","key":"pcbi.1013567.ref021","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1186\/s13046-019-1214-z","article-title":"The roles of glucose metabolic reprogramming in chemo- and radio-resistance","volume":"38","author":"J Lin","year":"2019","journal-title":"J Exp Clin Cancer Res"},{"issue":"4","key":"pcbi.1013567.ref022","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.7150\/thno.81847","article-title":"Role of p53 in breast cancer progression: An insight into p53 targeted therapy","volume":"13","author":"C Marvalim","year":"2023","journal-title":"Theranostics"},{"issue":"9","key":"pcbi.1013567.ref023","doi-asserted-by":"crossref","first-page":"536","DOI":"10.3390\/md17090536","article-title":"Synergistic Cytotoxicity of Renieramycin M and Doxorubicin in MCF-7 Breast Cancer Cells","volume":"17","author":"JO Tun","year":"2019","journal-title":"Mar Drugs"},{"issue":"8","key":"pcbi.1013567.ref024","doi-asserted-by":"crossref","first-page":"4668","DOI":"10.21037\/jtd-21-150","article-title":"Does denosumab offer survival benefits? -Our experience with denosumab in metastatic non-small cell lung cancer patients treated with immune-checkpoint inhibitors","volume":"13","author":"Y Cao","year":"2021","journal-title":"J Thorac Dis"},{"key":"pcbi.1013567.ref025","doi-asserted-by":"crossref","first-page":"908436","DOI":"10.3389\/fimmu.2022.908436","article-title":"Efficacy and safety of concomitant immunotherapy and denosumab in patients with advanced non-small cell lung cancer carrying bone metastases: A retrospective chart review","volume":"13","author":"H-S Li","year":"2022","journal-title":"Front Immunol"},{"issue":"5","key":"pcbi.1013567.ref026","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2117754119","article-title":"Senescence induction dictates response to chemo- and immunotherapy in preclinical models of ovarian cancer","volume":"119","author":"SV Paffenholz","year":"2022","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"10","key":"pcbi.1013567.ref027","doi-asserted-by":"crossref","first-page":"2504","DOI":"10.1002\/1878-0261.12761","article-title":"Clearance of therapy-induced senescent tumor cells by the senolytic ABT-263 via interference with BCL-XL -BAX interaction","volume":"14","author":"T Saleh","year":"2020","journal-title":"Mol Oncol"},{"issue":"2","key":"pcbi.1013567.ref028","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1016\/j.surg.2005.06.016","article-title":"Suberoylanilide hydroxamic acid combined with gemcitabine enhances apoptosis in non-small cell lung cancer","volume":"138","author":"BK Rundall","year":"2005","journal-title":"Surgery"},{"issue":"12","key":"pcbi.1013567.ref029","doi-asserted-by":"crossref","first-page":"789","DOI":"10.3390\/biom9120789","article-title":"Paclitaxel\u2019s Mechanistic and Clinical Effects on Breast Cancer","volume":"9","author":"TM Abu Samaan","year":"2019","journal-title":"Biomolecules"},{"key":"pcbi.1013567.ref030","doi-asserted-by":"crossref","first-page":"105200","DOI":"10.1016\/j.tiv.2021.105200","article-title":"Lapatinib enhances paclitaxel toxicity in MCF-7, T47D, and MDA-MB-321 breast cancer cells","volume":"75","author":"A Zajdel","year":"2021","journal-title":"Toxicol In Vitro"},{"issue":"14","key":"pcbi.1013567.ref031","doi-asserted-by":"crossref","first-page":"3795","DOI":"10.1158\/1078-0432.CCR-10-0503","article-title":"Safety, efficacy, pharmacokinetics, and pharmacodynamics of the combination of sorafenib and tanespimycin","volume":"16","author":"UN Vaishampayan","year":"2010","journal-title":"Clin Cancer Res"},{"issue":"2","key":"pcbi.1013567.ref032","doi-asserted-by":"crossref","first-page":"342","DOI":"10.1158\/1535-7163.MCT-08-0534","article-title":"Vorinostat and bortezomib exert synergistic antiproliferative and proapoptotic effects in colon cancer cell models","volume":"8","author":"TM Pitts","year":"2009","journal-title":"Mol Cancer Ther"},{"key":"pcbi.1013567.ref033","article-title":"DrugCombDB: a comprehensive database of drug combinations toward the discovery of combinatorial therapy","volume":"48","author":"H Liu","year":"2020","journal-title":"Nucleic Acids Res"},{"issue":"6","key":"pcbi.1013567.ref034","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":"J O\u2019Neil","year":"2016","journal-title":"Mol Cancer Ther"},{"issue":"1","key":"pcbi.1013567.ref035","doi-asserted-by":"crossref","first-page":"1197","DOI":"10.1038\/s41467-019-09186-x","article-title":"Network-based prediction of drug combinations","volume":"10","author":"F Cheng","year":"2019","journal-title":"Nat Commun"},{"issue":"7391","key":"pcbi.1013567.ref036","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":"J Barretina","year":"2012","journal-title":"Nature"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1013567","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T00:00:00Z","timestamp":1761177600000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013567","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,23]],"date-time":"2025-10-23T17:48:35Z","timestamp":1761241715000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013567"}},"subtitle":[],"editor":[{"given":"Lun","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":36,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2025,10,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1013567","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,15]]}}}