{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T14:19:28Z","timestamp":1789395568731,"version":"build-2803163510"},"reference-count":42,"publisher":"American Chemical Society (ACS)","issue":"17","license":[{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-045"}],"funder":[{"DOI":"10.13039\/501100012151","name":"Sanming Project of Medicine in Shenzen Municipality","doi-asserted-by":"publisher","award":["SZSM202411021"],"award-info":[{"award-number":["SZSM202411021"]}],"id":[{"id":"10.13039\/501100012151","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82270400"],"award-info":[{"award-number":["82270400"]}],"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":["82570457"],"award-info":[{"award-number":["82570457"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2023A1515010731"],"award-info":[{"award-number":["2023A1515010731"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"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>With the increasing use of multiple medications in clinical practice, accurate and interpretable prediction of organ-level adverse drug reactions (ADRs) induced by drug combinations is essential for drug safety assessment and precision medicine. Existing knowledge graph (KG)-based methods primarily model biomedical associations but leave direct structure-level interactions within drug pairs undercharacterized, while molecular representation methods often rely on whole-molecule or latent substructure encodings, offering limited chemically meaningful evidence for ADR risks. This study proposes MolADR, a multiscale complementary learning framework that integrates GNN-based KG learning with dual-granularity molecular cross-attention modeling to combine macro-level biomedical associations with microlevel molecular interaction cues. Under an emerging-drug setting, MolADR achieves PR-AUC scores of 81.17 \u00b1 3.97, 84.04 \u00b1 4.67, and 74.37 \u00b1 9.90 on three data sets, consistently outperforming state-of-the-art baselines, with further analyses supporting its robustness and suggesting its ability to highlight chemically plausible atoms and functional groups for organ-level ADR prediction.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01536","type":"journal-article","created":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T03:58:22Z","timestamp":1788235102000},"page":"10720-10736","source":"Crossref","is-referenced-by-count":0,"title":["MolADR: Multi-Scale\nComplementary Learning of Dual-Granularity\nMolecules and Knowledge Graphs for ADR Prediction in Drug Combinations"],"prefix":"10.1021","volume":"66","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5740-2832","authenticated-orcid":true,"given":"Yifan","family":"Qi","sequence":"first","affiliation":[{"name":"The University of Hong Kong-Shenzhen Hospital , , ,","place":["Shenzhen, Guangdong, China, 518053"]},{"name":"Nankai University , , ,","place":["Tianjin, China, 300350"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingwen","family":"Ren","sequence":"additional","affiliation":[{"name":"The University of Hong Kong , Pokfulam, , ,","place":["Hong Kong, Hong Kong SAR, China, 999077"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxu","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong , Pokfulam, , ,","place":["Hong Kong, Hong Kong SAR, China, 999077"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guihua","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Hong Kong , Pokfulam, , ,","place":["Hong Kong, Hong Kong SAR, China, 999077"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ami","family":"Matsumoto","sequence":"additional","affiliation":[{"name":"The University of Hong Kong , Pokfulam, , ,","place":["Hong Kong, Hong Kong SAR, China, 999077"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shitian","family":"Guo","sequence":"additional","affiliation":[{"name":"The University of Hong Kong-Shenzhen Hospital , , ,","place":["Shenzhen, Guangdong, China, 518053"]},{"name":"The University of Hong Kong , Pokfulam, , ,","place":["Hong Kong, Hong Kong SAR, China, 999077"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ran","family":"Guo","sequence":"additional","affiliation":[{"name":"The University of Hong Kong , Pokfulam, , ,","place":["Hong Kong, Hong Kong SAR, China, 999077"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haochen","family":"Xuan","sequence":"additional","affiliation":[{"name":"The University of Hong Kong-Shenzhen Hospital , , ,","place":["Shenzhen, Guangdong, China, 518053"]},{"name":"The University of Hong Kong , Pokfulam, , ,","place":["Hong Kong, Hong Kong SAR, China, 999077"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingnan","family":"Zhang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong-Shenzhen Hospital , , ,","place":["Shenzhen, Guangdong, China, 518053"]},{"name":"The University of Hong Kong , Pokfulam, , ,","place":["Hong Kong, Hong Kong SAR, China, 999077"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenli","family":"Gu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong-Shenzhen Hospital , , ,","place":["Shenzhen, Guangdong, China, 518053"]},{"name":"The University of Hong Kong , Pokfulam, , ,","place":["Hong Kong, Hong Kong SAR, China, 999077"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayi","family":"Huang","sequence":"additional","affiliation":[{"name":"The University of Hong Kong , Pokfulam, , ,","place":["Hong Kong, Hong Kong SAR, China, 999077"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai Hang","family":"Yiu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong-Shenzhen Hospital , , ,","place":["Shenzhen, Guangdong, China, 518053"]},{"name":"The University of Hong Kong , Pokfulam, , ,","place":["Hong Kong, Hong Kong SAR, China, 999077"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,25]]},"reference":[{"issue":"1","key":"2026091409080539900_cit1","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1038\/s41572-022-00376-4","article-title":"Multimorbidity","volume":"8","author":"Skou","year":"2022","journal-title":"Nat. Rev. Dis.\nPrimers"},{"issue":"4","key":"2026091409080539900_cit2","doi-asserted-by":"publisher","DOI":"10.1016\/S2666-7568(24)00007-2","article-title":"Prevalence of multimorbidity\nand polypharmacy among adults and older adults: a systematic review","volume":"5","author":"Nicholson","year":"2024","journal-title":"Lancet Healthy Longevity"},{"issue":"5","key":"2026091409080539900_cit3","doi-asserted-by":"publisher","DOI":"10.1016\/S2666-7568(23)00036-3","article-title":"Polypharmacy\nstewardship: a novel\napproach to tackle a major public health crisis","volume":"4","author":"Daunt","year":"2023","journal-title":"Lancet Healthy Longevity"},{"key":"2026091409080539900_cit4","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-074892","article-title":"Deprescribing\nin older adults with\npolypharmacy","volume":"385","author":"Hung","year":"2024","journal-title":"BMJ"},{"issue":"7","key":"2026091409080539900_cit5","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1001\/jama.2023.8872","article-title":"Polypharmacy\nand Deprescribing","volume":"330","author":"Vordenberg","year":"2023","journal-title":"JAMA"},{"issue":"7","key":"2026091409080539900_cit6","doi-asserted-by":"publisher","first-page":"2158","DOI":"10.1021\/acs.jcim.3c00582","article-title":"Application\nof Artificial Intelligence in Drug\u2013Drug Interactions Prediction:\nA Review","volume":"64","author":"Zhang","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409080539900_cit7","doi-asserted-by":"publisher","first-page":"103981","DOI":"10.1016\/j.inffus.2025.103981","article-title":"A Multimodal\nInformation Fusion Framework for Accurate and Robust Prediction of\nDrug-Drug Interactions","volume":"128","author":"Zhu","year":"2026","journal-title":"Inf. Fusion"},{"issue":"3","key":"2026091409080539900_cit8","doi-asserted-by":"publisher","first-page":"109148","DOI":"10.1016\/j.isci.2024.109148","article-title":"Drug-drug\ninteractions prediction based on deep learning and knowledge\ngraph: A review","volume":"27","author":"Luo","year":"2024","journal-title":"iScience"},{"issue":"6","key":"2026091409080539900_cit9","doi-asserted-by":"publisher","first-page":"bbac404","DOI":"10.1093\/bib\/bbac404","article-title":"A review of biomedical\ndatasets relating to drug discovery: a knowledge graph perspective","volume":"23","author":"Bonner","year":"2022","journal-title":"Briefings Bioinf."},{"issue":"6","key":"2026091409080539900_cit10","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1038\/s41573-019-0024-5","article-title":"Applications of machine learning in drug discovery and development","volume":"18","author":"Vamathevan","year":"2019","journal-title":"Nat. Rev. Drug Discovery"},{"issue":"2","key":"2026091409080539900_cit11","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1038\/s41573-023-00832-0","article-title":"Integrating QSAR modelling and deep\nlearning in drug\ndiscovery: the emergence of deep QSAR","volume":"23","author":"Tropsha","year":"2024","journal-title":"Nat.\nRev. Drug Discovery"},{"issue":"7","key":"2026091409080539900_cit12","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1038\/s43588-025-00816-7","article-title":"Predicting adverse\ndrug reactions\nfor combination pharmacotherapy with cross-scale associative learning\nvia attention modules","volume":"5","author":"Li","year":"2025","journal-title":"Nat. Comput. Sci."},{"issue":"18","key":"2026091409080539900_cit13","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1803294115","article-title":"Deep learning improves prediction\nof drug\u2013drug and drug\u2013food interactions","volume":"115","author":"Ryu","year":"2018","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"issue":"15","key":"2026091409080539900_cit14","doi-asserted-by":"publisher","first-page":"4316","DOI":"10.1093\/bioinformatics\/btaa501","article-title":"A multimodal\ndeep learning framework for predicting drug\u2013drug interaction\nevents","volume":"36","author":"Deng","year":"2020","journal-title":"Bioinformatics"},{"issue":"12","key":"2026091409080539900_cit15","doi-asserted-by":"publisher","first-page":"7623","DOI":"10.1109\/JBHI.2024.3453956","article-title":"Geometric Molecular\nGraph Representation Learning Model for Drug-Drug Interactions Prediction","volume":"28","author":"Jiang","year":"2024","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"2026091409080539900_cit16","doi-asserted-by":"publisher","first-page":"3997","DOI":"10.1038\/s41467-025-59431-9","article-title":"Predicting rare drug-drug\ninteraction events with dual-granular\nstructure-adaptive and pair variational representation","volume":"16","author":"Ren","year":"2025","journal-title":"Nat. Commun."},{"issue":"1","key":"2026091409080539900_cit17","doi-asserted-by":"publisher","first-page":"bbab421","DOI":"10.1093\/bib\/bbab421","article-title":"MDF-SA-DDI: predicting\ndrug\u2013drug interaction\nevents based on multi-source drug fusion, multi-source feature fusion\nand transformer self-attention mechanism","volume":"23","author":"Lin","year":"2022","journal-title":"Briefings\nBioinf."},{"issue":"9","key":"2026091409080539900_cit18","doi-asserted-by":"publisher","first-page":"4442","DOI":"10.1021\/acs.jcim.5c00075","article-title":"SF-Rx: A Multioutput Deep Neural\nNetwork-Based Framework Predicting Drug\u2013Drug Interaction under\nRealistic Conditions for Safe Prescription","volume":"65","author":"Kim","year":"2025","journal-title":"J. Chem. Inf. Model."},{"issue":"6","key":"2026091409080539900_cit19","doi-asserted-by":"publisher","first-page":"bbab133","DOI":"10.1093\/bib\/bbab133","article-title":"SSI\u2013DDI:\nSubstructure\u2013Substructure Interactions\nfor Drug\u2013Drug Interaction Prediction","volume":"22","author":"Nyamabo","year":"2021","journal-title":"Briefings Bioinf."},{"issue":"1","key":"2026091409080539900_cit20","doi-asserted-by":"publisher","first-page":"bbab441","DOI":"10.1093\/bib\/bbab441","article-title":"Drug\u2013drug interaction prediction\nwith learnable size-adaptive molecular substructures","volume":"23","author":"Nyamabo","year":"2022","journal-title":"Briefings Bioinf."},{"issue":"1","key":"2026091409080539900_cit21","doi-asserted-by":"publisher","first-page":"bbac597","DOI":"10.1093\/bib\/bbac597","article-title":"DSN-DDI:\nan accurate and generalized framework for drug\u2013drug interaction\nprediction by dual-view representation learning","volume":"24","author":"Li","year":"2023","journal-title":"Briefings Bioinf."},{"key":"2026091409080539900_cit22","first-page":"2739","article-title":"KGNN: Knowledge graph neural network\nfor drug-drug\ninteraction prediction","volume-title":"Proceedings of the\nTwenty-Ninth International Joint Conference on Artificial Intelligence\nIJCAI-20","author":"Lin","year":"2020"},{"issue":"18","key":"2026091409080539900_cit23","doi-asserted-by":"publisher","first-page":"2988","DOI":"10.1093\/bioinformatics\/btab207","article-title":"SumGNN: multi-typed\ndrug interaction prediction via efficient knowledge\ngraph summarization","volume":"37","author":"Yu","year":"2021","journal-title":"Bioinformatics"},{"issue":"5","key":"2026091409080539900_cit24","doi-asserted-by":"publisher","first-page":"bbad285","DOI":"10.1093\/bib\/bbad285","article-title":"A model-agnostic framework\nto enhance knowledge graph-based drug\ncombination prediction with drug\u2013drug interaction data and\nsupervised contrastive learning","volume":"24","author":"Gu","year":"2023","journal-title":"Briefings Bioinf."},{"key":"2026091409080539900_cit25","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1038\/s43856-024-00486-y","article-title":"Accurate and interpretable\ndrug-drug\ninteraction prediction enabled by knowledge subgraph learning","volume":"4","author":"Wang","year":"2024","journal-title":"Commun. Med."},{"issue":"12","key":"2026091409080539900_cit26","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1038\/s43588-023-00558-4","article-title":"Emerging drug interaction\nprediction enabled by a flow-based graph\nneural network with biomedical network","volume":"3","author":"Zhang","year":"2023","journal-title":"Nat.\nComput. Sci."},{"issue":"6","key":"2026091409080539900_cit27","doi-asserted-by":"publisher","first-page":"bbad385","DOI":"10.1093\/bib\/bbad385","article-title":"HetDDI: a pre-trained\nheterogeneous\ngraph neural network model for drug\u2013drug interaction prediction","volume":"24","author":"Li","year":"2023","journal-title":"Briefings Bioinf."},{"key":"2026091409080539900_cit28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/JBHI.2025.3610870","article-title":"KGMAEDDI: Knowledge\nGraph and Molecular-Graph Masked Autoencoder for Drug-Drug Interaction\nPrediction","author":"Li","year":"2025","journal-title":"IEEE J. Biomed. Health Inf."},{"issue":"125","key":"2026091409080539900_cit29","doi-asserted-by":"publisher","first-page":"125ra31","DOI":"10.1126\/scitranslmed.3003377","article-title":"Data-Driven Prediction\nof Drug Effects and Interactions","volume":"4","author":"Tatonetti","year":"2012","journal-title":"Sci. Transl.\nMed."},{"key":"2026091409080539900_cit30","volume-title":"Guidelines for ATC Classification and DDD Assignment 2026","author":"WHO Collaborating Centre for Drug Statistics Methodology.","year":"2025"},{"issue":"1","key":"2026091409080539900_cit31","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1038\/s41597-023-01960-3","article-title":"Building a knowledge\ngraph to enable\nprecision medicine","volume":"10","author":"Chandak","year":"2023","journal-title":"Sci. Data"},{"key":"2026091409080539900_cit32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.6980","article-title":"Adam: A method\nfor stochastic\noptimization","author":"Kingma","year":"2014","journal-title":"arXiv"},{"key":"2026091409080539900_cit33","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1007\/s10115-025-02636-7","article-title":"GIL-DDI: multi-view\ngraph invariant learning for unknown drug\u2013drug interaction\nprediction","volume":"68","author":"Li","year":"2026","journal-title":"Knowl. Inf. Syst."},{"key":"2026091409080539900_cit34","doi-asserted-by":"publisher","first-page":"114981","DOI":"10.1016\/j.knosys.2025.114981","article-title":"DDINet: A Multi-Task\nNeural Network for Accurate Drug\u2013Drug Interaction Prediction\nand Effect Analysis","volume":"333","author":"Ali","year":"2026","journal-title":"Knowl.-Based Syst."},{"key":"2026091409080539900_cit35","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1007\/978-981-95-3830-0_11","volume-title":"Database Systems for\nAdvanced Applications:\n30th International Conference, DASFAA 2025, Proceedings, Part II","author":"Zhao","year":"2026"},{"issue":"17","key":"2026091409080539900_cit36","doi-asserted-by":"publisher","first-page":"5029","DOI":"10.1021\/jm060379l","article-title":"Medicinal Chemistry\nof hERG Optimizations: Highlights and Hang-Ups","volume":"49","author":"Jamieson","year":"2006","journal-title":"J. Med. Chem."},{"key":"2026091409080539900_cit37","doi-asserted-by":"publisher","first-page":"112290","DOI":"10.1016\/j.ejmech.2020.112290","article-title":"hERG Toxicity Assessment:\nUseful Guidelines for Drug\nDesign","volume":"195","author":"Garrido","year":"2020","journal-title":"Eur. J. Med. Chem."},{"issue":"3","key":"2026091409080539900_cit38","doi-asserted-by":"publisher","DOI":"10.1111\/jpi.12672","article-title":"Melatonin receptor\nligands: A pharmaco-chemical perspective","volume":"69","author":"Boutin","year":"2020","journal-title":"J.\nPineal Res."},{"issue":"3","key":"2026091409080539900_cit39","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1038\/sj.bjp.0705283","article-title":"The antipsychotic\ndrug chlorpromazine\ninhibits HERG potassium channels","volume":"139","author":"Thomas","year":"2003","journal-title":"Br. J. Pharmacol."},{"issue":"23","key":"2026091409080539900_cit40","doi-asserted-by":"publisher","first-page":"6917","DOI":"10.1021\/jm060500o","article-title":"Common\npharmacophores for uncharged human ether-a-go-go-related gene (hERG)\nblockers","volume":"49","author":"Aronov","year":"2006","journal-title":"J. Med. Chem."},{"issue":"46","key":"2026091409080539900_cit41","doi-asserted-by":"publisher","first-page":"45763","DOI":"10.1074\/jbc.M305481200","article-title":"A Novel Mechanism\nof Cyclooxygenase-2 Inhibition Involving\nInteractions with Ser-530 and Tyr-385","volume":"278","author":"Rowlinson","year":"2003","journal-title":"J. Biol.\nChem."},{"issue":"4","key":"2026091409080539900_cit42","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/s12154-014-0121-1","article-title":"Resistance to Antifungals That Target CYP51","volume":"7","author":"Parker","year":"2014","journal-title":"J. Chem. Biol."}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01536","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/10720\/67409949\/acs.jcim.6c01536.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/10720\/67409949\/acs.jcim.6c01536.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T13:30:20Z","timestamp":1789392620000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/17\/10720\/5329135\/MolADR-Multi-Scale-Complementary-Learning-of-Dual"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,25]]},"references-count":42,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2026,8,25]]},"published-print":{"date-parts":[[2026,9,14]]}},"URL":"https:\/\/doi.org\/10.1021\/acs.jcim.6c01536","relation":{},"ISSN":["1549-9596","1549-960X"],"issn-type":[{"value":"1549-9596","type":"print"},{"value":"1549-960X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,25]]}}}