{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T14:19:23Z","timestamp":1789395563580,"version":"build-2803163510"},"reference-count":48,"publisher":"American Chemical Society (ACS)","issue":"17","license":[{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"name":"Science and Technology Plan Project of Liaoning Province","award":["2025-MSLH-351"],"award-info":[{"award-number":["2025-MSLH-351"]}]},{"name":"Fundamental Research Funds for the Liaoning Universities","award":["LJ212410146026"],"award-info":[{"award-number":["LJ212410146026"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,9,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Drug combination therapy plays an increasingly important role in the clinical treatment of complex diseases, such as cancer, as rational drug combinations can enhance therapeutic efficacy and reduce toxic side effects. However, existing methods still exhibit limitations in the granularity of drug molecular representation, drug interaction modeling, and cell line context awareness, which restrict further improvements in predictive performance. To address these issues, we propose FragSyn, a deep graph learning framework for predicting synergistic drug combinations based on molecular fragmentations. FragSyn first decomposes drug molecules into chemically meaningful fragments according to breaks of retrosynthetically interesting chemical substructure rules and learns fragment-level molecular representations through a graph isomorphism network with edge features. It then captures nonlinear relationships between drug pairs from multiple perspectives while introducing a gating modulation mechanism conditioned on cell line features, enabling drug representations to adapt dynamically to the cell line context. Finally, multisource features are fused to perform binary classification of synergy versus antagonism. FragSyn achieves AUC, AUPR, and ACC of 0.944, 0.942, and 0.872, respectively, outperforming eight baseline models, and demonstrates optimal generalization performance in both leave-one-out cross-validation and external validation. Ablation studies and interpretability analyses further validate the rationality of FragSyn and its ability to identify key fragments. These results indicate that FragSyn, through the synergistic design of fragment-level representation and cellular context awareness, provides an effective and interpretable new approach to synergistic drug combination prediction.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01930","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T16:02:35Z","timestamp":1786982555000},"page":"10819-10834","source":"Crossref","is-referenced-by-count":0,"title":["Molecular Fragment-Based\nGraph Isomorphism Networks\nfor Interpretable Prediction of Synergistic Drug Combinations"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5269-4311","authenticated-orcid":true,"given":"Lifeng","family":"Shao","sequence":"first","affiliation":[{"name":"University of Science and Technology Liaoning , , ,","place":["Anshan, China, 114051"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqiang","family":"Sun","sequence":"additional","affiliation":[{"name":"Linyi University , , ,","place":["Linyi, China, 276000"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongzhan","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Science and Technology Liaoning , , ,","place":["Anshan, China, 114051"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9713-1864","authenticated-orcid":true,"given":"Qi","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Science and Technology Liaoning , , ,","place":["Anshan, China, 114051"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,17]]},"reference":[{"key":"2026091409081118400_cit1","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1038\/s41573-022-00615-z","article-title":"Rational Combinations of Targeted\nCancer Therapies: Background, Advances and Challenges","volume":"22","author":"Jin","year":"2023","journal-title":"Nat. Rev. Drug Discovery"},{"key":"2026091409081118400_cit2","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-023-02852-4","article-title":"Combination\nTherapies for Cancer:\nChallenges and Opportunities","volume":"21","author":"Zhou","year":"2023","journal-title":"BMC Med."},{"key":"2026091409081118400_cit3","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.3006667","article-title":"High-Throughput\nMethods for Combinatorial\nDrug Discovery","volume":"5","author":"Sun","year":"2013","journal-title":"Sci. Transl. Med."},{"key":"2026091409081118400_cit4","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1093\/bib\/bbw104","article-title":"Predictive\nApproaches for Drug Combination Discovery in Cancer","volume":"19","author":"Madani Tonekaboni","year":"2018","journal-title":"Briefings Bioinf."},{"key":"2026091409081118400_cit5","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-Connectivity Fingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem.\nInf. Model."},{"key":"2026091409081118400_cit6","doi-asserted-by":"publisher","first-page":"3091","DOI":"10.1021\/acs.jcim.6c00033","article-title":"Dual-Modal Fusion Based\non Peptide Sequence and Molecular Graph with Bidirectional Cross-Attention\nfor Precise Peptide Toxicity Prediction","volume":"66","author":"Li","year":"2026","journal-title":"J.\nChem. Inf. Model."},{"key":"2026091409081118400_cit7","doi-asserted-by":"publisher","first-page":"7922","DOI":"10.1109\/JBHI.2025.3561887","article-title":"Enhancing Drug Synergy\nCombination: Integrating\nGraph Transformers and BiLSTM for Accurate Drug Synergy Prediction","volume":"29","author":"Sun","year":"2025","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"2026091409081118400_cit8","doi-asserted-by":"publisher","first-page":"3585","DOI":"10.1145\/3447548.3467186","volume-title":"MoCL:\nData-Driven Molecular\nFingerprint via Knowledge-Aware Contrastive Learning from Molecular\nGraph","author":"Sun","year":"2021"},{"key":"2026091409081118400_cit9","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","article-title":"Molecular\nContrastive Learning of Representations via Graph Neural Networks","volume":"4","author":"Wang","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"2026091409081118400_cit10","unstructured":"Wang, H.; Li, W.; Jin, X.; et al. In  Chemical-Reaction-Aware\nMolecule\nRepresentation Learning, Proceedings of the 10th International\nConference on Learning Representations; ICLR, 2022."},{"key":"2026091409081118400_cit11","doi-asserted-by":"publisher","first-page":"6547","DOI":"10.1021\/acs.jcim.5c00430","article-title":"Advancing Drug Discovery with Enhanced Chemical\nUnderstanding via Asymmetric Contrastive Multimodal Learning","volume":"65","author":"Wang","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409081118400_cit12","doi-asserted-by":"publisher","DOI":"10.1038\/s42004-025-01586-z","article-title":"Multimodal\nFusion with Relational\nLearning for Molecular Property Prediction","volume":"8","author":"Zhou","year":"2025","journal-title":"Commun. Chem."},{"key":"2026091409081118400_cit13","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202412987","article-title":"A Multi-Task Self-Supervised\nStrategy for Predicting Molecular Properties and FGFR1 Inhibitors","volume":"12","author":"Yang","year":"2025","journal-title":"Adv. Sci."},{"key":"2026091409081118400_cit14","doi-asserted-by":"publisher","first-page":"12799","DOI":"10.1021\/acs.jcim.5c02280","article-title":"Multimodal Feature Fusion\nfor Bone Toxicity Prediction and Local Platform","volume":"65","author":"Pan","year":"2025","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409081118400_cit15","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1021\/acs.jcim.5c02664","article-title":"HetGAT-LMI: Interpretable\nHeterogeneous Graph Attention Method for Predicting lncRNA\u2013miRNA\nInteractions","volume":"66","author":"Liu","year":"2026","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409081118400_cit16","doi-asserted-by":"publisher","DOI":"10.34133\/research.0869","article-title":"E-SegNet: E-Shaped Structure\nNetworks for Accurate 2D and 3D Medical Image Segmentation","volume":"8","author":"Wu","year":"2025","journal-title":"Research"},{"key":"2026091409081118400_cit17","doi-asserted-by":"publisher","first-page":"1766","DOI":"10.1021\/acs.jmedchem.5c03551","article-title":"Multimodal Multi-Granularity Fusion\nModel with Mamba Architecture for Ames Mutagenicity Prediction","volume":"69","author":"Han","year":"2026","journal-title":"J. Med. Chem."},{"key":"2026091409081118400_cit18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijbiomac.2026.152448","article-title":"DVCH-LMI: A Dual-View\nContrastive Framework for lncRNA-miRNA Interaction Prediction under\nClass Imbalance","volume":"366","author":"Liu","year":"2026","journal-title":"Int. J. Biol. Macromol."},{"key":"2026091409081118400_cit19","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab390","article-title":"DeepDDS: Deep Graph Neural Network with Attention\nMechanism to Predict Synergistic Drug Combinations","volume":"23","author":"Wang","year":"2022","journal-title":"Briefings Bioinf."},{"key":"2026091409081118400_cit20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ymeth.2023.06.006","article-title":"MPFFPSDC: A Multi-Pooling Feature Fusion Model\nfor Predicting Synergistic Drug Combinations","volume":"217","author":"Bao","year":"2023","journal-title":"Methods"},{"key":"2026091409081118400_cit21","doi-asserted-by":"publisher","DOI":"10.1186\/s12915-025-02302-y","article-title":"Accurate Prediction\nof Synergistic Drug Combination Using a Multi-Source Information Fusion\nFramework","volume":"23","author":"Jin","year":"2025","journal-title":"BMC Biol."},{"key":"2026091409081118400_cit22","doi-asserted-by":"publisher","first-page":"1503","DOI":"10.1002\/cmdc.200800178","article-title":"On the Art of Compiling\nand Using \u201cDrug-Like\u201d Chemical Fragment Spaces","volume":"3","author":"Degen","year":"2008","journal-title":"ChemMedChem"},{"key":"2026091409081118400_cit23","doi-asserted-by":"publisher","first-page":"1155","DOI":"10.1158\/1535-7163.MCT-15-0843","article-title":"An Unbiased Oncology\nCompound Screen to Identify Novel Combination Strategies","volume":"15","author":"O\u2019Neil","year":"2016","journal-title":"Mol. Cancer Ther."},{"key":"2026091409081118400_cit24","doi-asserted-by":"publisher","first-page":"D1516","DOI":"10.1093\/nar\/gkae1059","article-title":"PubChem 2025 Update","volume":"53","author":"Kim","year":"2025","journal-title":"Nucleic Acids Res."},{"key":"2026091409081118400_cit25","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1038\/nature11003","article-title":"The Cancer Cell Line\nEncyclopedia Enables Predictive Modelling of Anticancer Drug Sensitivity","volume":"483","author":"Barretina","year":"2012","journal-title":"Nature"},{"key":"2026091409081118400_cit26","doi-asserted-by":"publisher","first-page":"D966","DOI":"10.1093\/nar\/gkae1078","article-title":"GENCODE 2025: Reference\nGene Annotation for Human and Mouse","volume":"53","author":"Mudge","year":"2025","journal-title":"Nucleic\nAcids Res."},{"key":"2026091409081118400_cit27","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab587","article-title":"PRODeepSyn: Predicting Anticancer Synergistic\nDrug Combinations by Embedding Cell Lines with Protein\u2013Protein\nInteraction Network","volume":"23","author":"Wang","year":"2022","journal-title":"Briefings Bioinf."},{"key":"2026091409081118400_cit28","doi-asserted-by":"publisher","first-page":"D711","DOI":"10.1093\/nar\/gky964","article-title":"ArrayExpress Update\n\u2013 from Bulk to Single-Cell Expression Data","volume":"47","author":"Athar","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"2026091409081118400_cit29","doi-asserted-by":"publisher","first-page":"D941","DOI":"10.1093\/nar\/gky1015","article-title":"COSMIC: The Catalogue\nOf Somatic Mutations In Cancer","volume":"47","author":"Tate","year":"2019","journal-title":"Nucleic Acids\nRes."},{"key":"2026091409081118400_cit30","doi-asserted-by":"publisher","first-page":"D607","DOI":"10.1093\/nar\/gky1131","article-title":"STRING V11: Protein\u2013Protein\nAssociation Networks with Increased Coverage, Supporting Functional\nDiscovery in Genome-Wide Experimental Datasets","volume":"47","author":"Szklarczyk","year":"2019","journal-title":"Nucleic Acids Res."},{"key":"2026091409081118400_cit31","doi-asserted-by":"publisher","first-page":"2854","DOI":"10.1021\/acs.jcim.3c00709","article-title":"AttenSyn: An Attention-Based Deep\nGraph Neural Network for Anticancer Synergistic Drug Combination Prediction","volume":"64","author":"Wang","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409081118400_cit32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1010951","article-title":"MGAE-DC: Predicting the Synergistic\nEffects of Drug Combinations\nthrough Multi-Channel Graph Autoencoders","volume":"19","author":"Zhang","year":"2023","journal-title":"PLoS\nComput. Biol."},{"key":"2026091409081118400_cit33","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-024-05765-y","article-title":"MFSynDCP:\nMulti-Source\nFeature Collaborative Interactive Learning for Drug Combination Synergy\nPrediction","volume":"25","author":"Dong","year":"2024","journal-title":"BMC Bioinf."},{"key":"2026091409081118400_cit34","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-09799-2","article-title":"Community Assessment\nto Advance Computational Prediction of Cancer Drug Combinations in\na Pharmacogenomic Screen","volume":"10","author":"Menden","year":"2019","journal-title":"Nat. Commun."},{"key":"2026091409081118400_cit35","doi-asserted-by":"publisher","DOI":"10.1038\/s41419-020-03001-y","article-title":"A20 Promotes Melanoma\nProgression via the Activation of Akt Pathway","volume":"11","author":"Ma","year":"2020","journal-title":"Cell Death Dis."},{"key":"2026091409081118400_cit36","doi-asserted-by":"publisher","first-page":"4200","DOI":"10.1158\/1078-0432.CCR-10-2537","article-title":"WEE1 Kinase\nTargeting Combined with DNA-Damaging Cancer Therapy Catalyzes Mitotic\nCatastrophe","volume":"17","author":"De Witt Hamer","year":"2011","journal-title":"Clin. Cancer Res."},{"key":"2026091409081118400_cit37","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejmech.2020.112524","article-title":"Structure-Activity Relationships of Wee1 Inhibitors:\nA Review","volume":"203","author":"Du","year":"2020","journal-title":"Eur. J. Med. Chem."},{"key":"2026091409081118400_cit38","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0109705","article-title":"Computational Insights\ninto the Inhibitory Mechanism of Human AKT1 by an Orally Active Inhibitor,\nMK-2206","volume":"9","author":"Rehan","year":"2014","journal-title":"PLoS One"},{"key":"2026091409081118400_cit39","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-024-00496-y","article-title":"Integrative Modeling\nUncovers P21-Driven Drug Resistance and Prioritizes Therapies for\nPIK3CA-Mutant Breast Cancer","volume":"8","author":"Yip","year":"2024","journal-title":"npj Precis. Oncol."},{"key":"2026091409081118400_cit40","doi-asserted-by":"publisher","first-page":"6084","DOI":"10.1158\/0008-5472.CAN-07-6854","article-title":"An Integrative Genomic\nand Proteomic Analysis of PIK3CA, PTEN, and AKT Mutations in Breast\nCancer","volume":"68","author":"Stemke-Hale","year":"2008","journal-title":"Cancer Res."},{"key":"2026091409081118400_cit41","doi-asserted-by":"publisher","first-page":"1059","DOI":"10.1158\/1535-7163.MCT-10-0792","article-title":"Ridaforolimus (AP23573;\nMK-8669), a Potent mTOR Inhibitor, Has Broad Antitumor Activity and\nCan Be Optimally Administered Using Intermittent Dosing Regimens","volume":"10","author":"Rivera","year":"2011","journal-title":"Mol. Cancer Ther."},{"key":"2026091409081118400_cit42","doi-asserted-by":"publisher","DOI":"10.3390\/cells12040659","article-title":"Doxorubicin\u2500An\nAgent with Multiple Mechanisms of Anticancer Activity","volume":"12","author":"Kciuk","year":"2023","journal-title":"Cells"},{"key":"2026091409081118400_cit43","doi-asserted-by":"publisher","first-page":"1576","DOI":"10.1021\/jm001103v","article-title":"Synthesis and NMR-Driven\nConformational Analysis of Taxol Analogues Conformationally Constrained\non the C13 Side Chain","volume":"44","author":"Barboni","year":"2001","journal-title":"J. Med. Chem."},{"key":"2026091409081118400_cit44","doi-asserted-by":"publisher","DOI":"10.3390\/ph15040468","article-title":"Synthesis\nand Antiproliferative Activity of Novel Imipridone\u2013Ferrocene\nHybrids with Triazole and Alkyne Linkers","volume":"15","author":"Czuczi","year":"2022","journal-title":"Pharmaceuticals"},{"key":"2026091409081118400_cit45","doi-asserted-by":"publisher","first-page":"3131","DOI":"10.7150\/jca.18457","article-title":"Breast Cancer Cell\nLine Classification and Its Relevance with Breast Tumor Subtyping","volume":"8","author":"Dai","year":"2017","journal-title":"J. Cancer"},{"key":"2026091409081118400_cit46","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1038\/bjc.2016.238","article-title":"Combined PI3K and CDK2\nInhibition Induces Cell Death and Enhances in Vivo Antitumour Activity\nin Colorectal Cancer","volume":"115","author":"Beale","year":"2016","journal-title":"Br. J. Cancer"},{"key":"2026091409081118400_cit47","doi-asserted-by":"publisher","DOI":"10.3390\/ijms26052197","article-title":"Dinaciclib Interrupts\nCell Cycle and Induces Apoptosis in Oral Squamous Cell Carcinoma:\nMechanistic Insights and Therapeutic Potential","volume":"26","author":"Oner","year":"2025","journal-title":"Int. J. Mol. Sci."},{"key":"2026091409081118400_cit48","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/S0163-7258(02)00182-1","article-title":"Structure-Based Design\nof Cyclin-Dependent Kinase Inhibitors","volume":"93","author":"Davies","year":"2002","journal-title":"Pharm.\nTher."}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01930","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/10819\/66648683\/acs.jcim.6c01930.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/10819\/66648683\/acs.jcim.6c01930.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T13:30:23Z","timestamp":1789392623000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/17\/10819\/5262073\/Molecular-Fragment-Based-Graph-Isomorphism"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,17]]},"references-count":48,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,8,17]]},"published-print":{"date-parts":[[2026,9,14]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01930","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,17]]}}}