{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T14:03:38Z","timestamp":1789394618505,"version":"build-2803163510"},"reference-count":51,"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\/na","name":"Gansu Province","doi-asserted-by":"publisher","award":["2026CYZC-013"],"award-info":[{"award-number":["2026CYZC-013"]}],"id":[{"id":"10.13039\/na","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>Drug\u2013drug interactions (DDIs) can alter therapeutic efficacy or cause severe adverse reactions, posing major risks in polypharmacy. Accurate DDI prediction is therefore important for medication safety and early stage drug screening. Although molecular graph learning has been widely used for DDI prediction, many methods still rely on atom-centered propagation and global graph aggregation, which may obscure interaction-relevant local structural patterns. To address this limitation, we propose SSE-DDI, a molecular structure-driven framework centered on selective substructure encoding for relation-specific DDI prediction. SSE introduces a bond-level substructure-selective encoder in molecular line graphs, where chemical bonds serve as fundamental representation units and DDI-relevant local patterns are emphasized before drug-level representation learning. The encoder performs selective information routing between adjacent bond states and condenses interaction-relevant substructures into compact molecular representations. These representations are further refined by an edge-fusion graph transformer. To complement local structural modeling, SSE-DDI refines SMILES-derived Morgan-fingerprint similarity profiles to suppress noisy global structural signals without external biomedical annotations. Experiments on DrugBank and Twosides under transductive and inductive settings show that SSE-DDI outperforms representative baselines across multiple metrics. Ablation and visualization analyses verify the effectiveness of selective encoding and highlight DDI-relevant molecular substructures. The source code is available at https:\/\/github.com\/qichi77\/SSE-DDI.<\/jats:p>","DOI":"10.1021\/acs.jcim.6c01505","type":"journal-article","created":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T23:43:22Z","timestamp":1788219802000},"page":"10674-10691","source":"Crossref","is-referenced-by-count":0,"title":["SSE-DDI: Selective\nSubstructure Encoding with Bond-Centered\nMolecular Representations for Drug\u2013Drug Interaction Prediction"],"prefix":"10.1021","volume":"66","author":[{"given":"Shiwei","family":"Gao","sequence":"first","affiliation":[{"name":"College of Artificial Intelligence and Computing (Software School), Northwest Normal University , , ,","place":["Lanzhou, Gansu, China, 730070"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0821-5487","authenticated-orcid":true,"given":"Tianqi","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence and Computing (Software School), Northwest Normal University , , ,","place":["Lanzhou, Gansu, China, 730070"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowan","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence and Computing (Software School), Northwest Normal University , , ,","place":["Lanzhou, Gansu, China, 730070"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiping","family":"Hu","sequence":"additional","affiliation":[{"name":"Third People\u2019s Hospital of Gansu Province , ,","place":["Lanzhou, China, 730000"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"316","published-online":{"date-parts":[[2026,8,25]]},"reference":[{"key":"2026091409072248000_cit1","volume-title":"Medication Safety in Polypharmacy","author":"World Health Organization.","year":"2019"},{"issue":"2","key":"2026091409072248000_cit2","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1007\/s40264-015-0378-5","article-title":"Appropriate polypharmacy and medicine\nsafety: when many is not too many","volume":"39","author":"Cadogan","year":"2016","journal-title":"Drug Saf."},{"issue":"1","key":"2026091409072248000_cit3","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1517\/14740338.2012.631910","article-title":"Epidemiology\nand characteristics\nof adverse drug reactions caused by drug\u2013drug interactions","volume":"11","author":"Magro","year":"2012","journal-title":"Expert Opin. Drug Saf."},{"issue":"4","key":"2026091409072248000_cit4","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1586\/17512433.2014.910111","article-title":"Understanding and preventing drug\u2013drug\nand drug\u2013gene\ninteractions","volume":"7","author":"Tannenbaum","year":"2014","journal-title":"Expert Rev. Clin. Pharmacol."},{"issue":"5","key":"2026091409072248000_cit5","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1016\/j.jbi.2013.07.011","article-title":"The DDI corpus: an\nannotated corpus with pharmacological substances and drug\u2013drug\ninteractions","volume":"46","author":"Herrero-Zazo","year":"2013","journal-title":"J. Biomed. Inf."},{"key":"2026091409072248000_cit6","unstructured":"Boyce, R.; Gardner, G.; Harkema, H.\n          Using\nnatural\nlanguage processing to extract drug\u2013drug interaction information\nfrom package inserts. In  Proceedings of the\n2012 Workshop on Biomedical Natural Language Processing; University of Pittsburgh, 2012; pp 206\u2013213."},{"issue":"18","key":"2026091409072248000_cit7","doi-asserted-by":"publisher","first-page":"i547","DOI":"10.1093\/bioinformatics\/btq382","article-title":"Discovering\ndrug\u2013drug interactions: a text-mining and reasoning approach\nbased on properties of drug metabolism","volume":"26","author":"Tari","year":"2010","journal-title":"Bioinformatics"},{"key":"2026091409072248000_cit8","first-page":"410","article-title":"Discovery and\nexplanation of drug\u2013drug interactions via text mining","volume-title":"Pacific Symposium on Biocomputing","author":"Percha","year":"2012"},{"issue":"e2","key":"2026091409072248000_cit9","doi-asserted-by":"publisher","first-page":"e278","DOI":"10.1136\/amiajnl-2013-002512","article-title":"Machine learning-based\nprediction of drug\u2013drug interactions\nby integrating drug phenotypic, therapeutic, chemical, and genomic\nproperties","volume":"21","author":"Cheng","year":"2014","journal-title":"J. Am. Med. Inform. Assoc."},{"key":"2026091409072248000_cit10","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s12859-016-1415-9","article-title":"Predicting potential drug\u2013drug\ninteractions by integrating\nchemical, biological, phenotypic and network data","volume":"18","author":"Zhang","year":"2017","journal-title":"BMC Bioinf."},{"issue":"6","key":"2026091409072248000_cit11","doi-asserted-by":"publisher","first-page":"1066","DOI":"10.1136\/amiajnl-2012-000935","article-title":"Drug\u2013drug interaction\nthrough molecular structure\nsimilarity analysis","volume":"19","author":"Vilar","year":"2012","journal-title":"J. Am. Med. Inform. Assoc."},{"issue":"3","key":"2026091409072248000_cit12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0058321","article-title":"Detection of drug\u2013drug\ninteractions by modeling interaction profile fingerprints","volume":"8","author":"Vilar","year":"2013","journal-title":"PLoS One"},{"issue":"18","key":"2026091409072248000_cit13","doi-asserted-by":"publisher","first-page":"E4304","DOI":"10.1073\/pnas.1803294115","article-title":"Deep learning improves\nprediction\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":"2026091409072248000_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"},{"key":"2026091409072248000_cit15","doi-asserted-by":"publisher","first-page":"104772","DOI":"10.1016\/j.jbi.2025.104772","article-title":"A multi-source\ndrug combination and omnidirectional\nfeature fusion approach for predicting drug\u2013drug interaction\nevents","volume":"162","author":"Gao","year":"2025","journal-title":"J. Biomed. Inf."},{"issue":"3","key":"2026091409072248000_cit16","doi-asserted-by":"publisher","first-page":"2276","DOI":"10.1109\/JBHI.2025.3600045","article-title":"Multi-view\nContrastive Learning for Drug-Drug Interaction Event Prediction","volume":"30","author":"Li","year":"2026","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"1","key":"2026091409072248000_cit17","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1109\/JBHI.2025.3585290","article-title":"LLM-DDI: Leveraging Large Language Models for Drug-Drug Interaction\nPrediction on Biomedical Knowledge Graph","volume":"30","author":"Li","year":"2026","journal-title":"IEEE\nJ. Biomed. Health Inform."},{"issue":"3","key":"2026091409072248000_cit18","doi-asserted-by":"publisher","first-page":"1771","DOI":"10.1109\/JBHI.2024.3419015","article-title":"Knowledge Graph Neural Network with\nSpatial-Aware Capsule for Drug-Drug Interaction Prediction","volume":"29","author":"Su","year":"2025","journal-title":"IEEE J. Biomed. Health Inform."},{"issue":"1","key":"2026091409072248000_cit19","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1609\/aaai.v38i1.27777","article-title":"Dual-Channel\nLearning\nFramework for Drug-Drug Interaction Prediction via Relation-Aware\nHeterogeneous Graph Transformer","volume":"38","author":"Su","year":"2024","journal-title":"Proc. AAAI\nConf. Artif. Intell."},{"key":"2026091409072248000_cit20","volume-title":"Basic Concepts in\nMedicinal Chemistry","author":"Harrold","year":"2013"},{"key":"2026091409072248000_cit21","article-title":"Semi-supervised\nclassification with graph convolutional networks","volume-title":"International Conference on Learning Representations","author":"Kipf","year":"2017"},{"key":"2026091409072248000_cit22","unstructured":"Velic\u030ckovic\u0301, P.; Cucurull, G.; Casanova, A.; Romero, A.; Lio\u0300, P.; Bengio, Y.\n          Graph\nattention networks. In  International Conference\non Learning Representations, OpenReview.net: 2018."},{"key":"2026091409072248000_cit23","unstructured":"Gilmer, J.; Schoenholz, S. S.; Riley, P. F.; Vinyals, O.; Dahl, G. E.\n          Neural message\npassing for quantum chemistry. In  Proceedings\nof the 34th International Conference on Machine Learning; PMLR, 2017; pp 1263\u20131272."},{"issue":"8","key":"2026091409072248000_cit24","doi-asserted-by":"publisher","first-page":"3370","DOI":"10.1021\/acs.jcim.9b00237","article-title":"Analyzing learned molecular\nrepresentations for property prediction","volume":"59","author":"Yang","year":"2019","journal-title":"J.\nChem. Inf. Model."},{"issue":"1","key":"2026091409072248000_cit25","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1021\/acs.jcim.3c01250","article-title":"Chemprop:\na machine\nlearning package for chemical property prediction","volume":"64","author":"Heid","year":"2024","journal-title":"J. Chem. Inf. Model."},{"key":"2026091409072248000_cit26","doi-asserted-by":"publisher","first-page":"412","DOI":"10.1186\/s12859-021-04325-y","article-title":"AttentionDDI:\nSiamese attention-based deep learning method for drug\u2013drug\ninteraction predictions","volume":"22","author":"Schwarz","year":"2021","journal-title":"BMC Bioinf."},{"key":"2026091409072248000_cit27","doi-asserted-by":"crossref","first-page":"15567","DOI":"10.1038\/s41598-022-19999-4","article-title":"Prediction of drug\u2013drug\ninteraction\nevents using graph neural networks","volume":"12","author":"Al-Rabeah","year":"2022","journal-title":"Sci. Rep."},{"issue":"24","key":"2026091409072248000_cit28","doi-asserted-by":"publisher","first-page":"5406","DOI":"10.1093\/bioinformatics\/btac682","article-title":"LaGAT: link-aware\ngraph attention\nnetwork for drug\u2013drug interaction prediction","volume":"38","author":"Hong","year":"2022","journal-title":"Bioinformatics"},{"issue":"6","key":"2026091409072248000_cit29","doi-asserted-by":"publisher","first-page":"bbab133","DOI":"10.1093\/bib\/bbab133","article-title":"SSI-DDI:\nsubstructure\u2013substructure interactions\nfor drug\u2013drug interaction prediction","volume":"22","author":"Nyamabo","year":"2021","journal-title":"Briefings Bioinf."},{"issue":"1","key":"2026091409072248000_cit30","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1010812","article-title":"A dual graph neural\nnetwork for drug\u2013drug interactions prediction\nbased on molecular structure and interactions","volume":"19","author":"Ma","year":"2023","journal-title":"PLoS Comput. Biol."},{"issue":"1","key":"2026091409072248000_cit31","doi-asserted-by":"publisher","first-page":"bbab441","DOI":"10.1093\/bib\/bbab441","article-title":"Drug\u2013drug\ninteraction prediction\nwith learnable size-adaptive molecular substructures","volume":"23","author":"Nyamabo","year":"2022","journal-title":"Briefings Bioinf."},{"key":"2026091409072248000_cit32","doi-asserted-by":"publisher","first-page":"1369403","DOI":"10.3389\/fphar.2024.1369403","article-title":"MASMDDI: multi-layer\nadaptive soft-mask graph neural network for drug\u2013drug interaction\nprediction","volume":"15","author":"Lin","year":"2024","journal-title":"Front. Pharmacol."},{"key":"2026091409072248000_cit33","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.ymeth.2024.05.010","article-title":"MGDDI: a multi-scale graph neural networks\nfor drug\u2013drug\ninteraction prediction","volume":"228","author":"Geng","year":"2024","journal-title":"Methods."},{"key":"2026091409072248000_cit34","doi-asserted-by":"publisher","first-page":"108355","DOI":"10.1016\/j.compbiolchem.2025.108355","article-title":"MSMDL-DDI: Multi-Layer Soft Mask Dual-View Learning\nfor Drug\u2013Drug Interactions","volume":"115","author":"Lu","year":"2025","journal-title":"Comput. Biol.\nChem."},{"issue":"2","key":"2026091409072248000_cit35","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1089\/cmb.2024.0476","article-title":"BiRNN-DDI:\nA Drug-Drug Interaction\nEvent Type Prediction Model Based on Bidirectional Recurrent Neural\nNetwork and Graph2Seq Representation","volume":"32","author":"Wang","year":"2025","journal-title":"J. Comput.\nBiol."},{"issue":"8","key":"2026091409072248000_cit36","doi-asserted-by":"publisher","first-page":"6081","DOI":"10.1109\/JBHI.2025.3550019","article-title":"MMDDI-SSE: A Novel Multi-Modal Feature\nFusion Model With Static Subgraph\nEmbedding for Drug-Drug Interaction Event Prediction","volume":"29","author":"Wang","year":"2025","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"2026091409072248000_cit37","doi-asserted-by":"crossref","unstructured":"Wang, G.; Wang, H.; Chen, H.; et al.; MMDDI-GDSS:\nMulti-Modal\nFeature Fusion Drug-Drug Interaction Event Prediction Model. In  Proceedings of the 2025 IEEE International Conference\non Bioinformatics and Biomedicine; IEEE, 2025; pp 353\u2013358.10.1109\/BIBM66473.2025.11356316.","DOI":"10.1109\/BIBM66473.2025.11356316"},{"issue":"5","key":"2026091409072248000_cit38","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1021\/ci100050t","article-title":"Extended-connectivity\nfingerprints","volume":"50","author":"Rogers","year":"2010","journal-title":"J. Chem.\nInf. Model."},{"key":"2026091409072248000_cit39","doi-asserted-by":"crossref","unstructured":"Hussain, M. S.; Zaki, M. J.; Subramanian, D.\n          Global self-attention\nas a replacement for graph convolution. In  Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery\nand Data Mining; ACM, 2022; 10.1145\/3534678.3539296.","DOI":"10.1145\/3534678.3539296"},{"key":"2026091409072248000_cit40","unstructured":"Vaswani, A.; Shazeer, N.; Parmar, N.; et al.; Attention is all you need.\nIn  Advances in\nNeural Information Processing Systems; NPIS, 2017; pp 5998\u20136008."},{"key":"2026091409072248000_cit41","unstructured":"Ioffe, S.; Szegedy, C.\n          Batch\nnormalization:\naccelerating deep network training by reducing internal covariate\nshift.  Proceedings of the 32nd International\nConference on Machine Learning; PMLR, 2015, 37, 448\u2013456."},{"key":"2026091409072248000_cit42","doi-asserted-by":"crossref","unstructured":"He, K.; Zhang, X.; Ren, S.; Sun, J.\n          Deep residual learning for image recognition. In  Proceedings of the IEEE Conference on Computer Vision\nand Pattern Recognition; IEEE, 2016; pp 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"issue":"3434","key":"2026091409072248000_cit43","doi-asserted-by":"publisher","first-page":"1115","DOI":"10.1126\/science.132.3434.1115","article-title":"A computer program\nfor classifying plants","volume":"132","author":"Rogers","year":"1960","journal-title":"Science"},{"issue":"D1","key":"2026091409072248000_cit44","doi-asserted-by":"publisher","first-page":"D1265","DOI":"10.1093\/nar\/gkad976","article-title":"DrugBank 6.0: the DrugBank\nKnowledgebase for 2024","volume":"52","author":"Knox","year":"2024","journal-title":"Nucleic Acids Res."},{"issue":"125","key":"2026091409072248000_cit45","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":"2026091409072248000_cit46","doi-asserted-by":"crossref","unstructured":"Wang, Z.; Zhang, J.; Feng, J.; Chen, Z.\n          Knowledge graph embedding by\ntranslating on hyperplanes.  Proc. AAAI Conf.\nArtif. Intell.; PKP, 2014; Vol. 28, p 8870.10.1609\/aaai.v28i1.8870.","DOI":"10.1609\/aaai.v28i1.8870"},{"key":"2026091409072248000_cit47","doi-asserted-by":"crossref","unstructured":"Xu, N.; Wang, P.; Chen, L.; Tao, J.; Zhao, J.\n          MR-GNN: Multi-resolution and dual graph neural network\nfor predicting structured entity interactions. In  Proceedings of the Twenty-Eighth International Joint Conference on\nArtificial Intelligence, International Joint\nConferences on Artificial Intelligence Organization (IJCAI): 2019; pp 3968\u20133974.10.24963\/ijcai.2019\/551.","DOI":"10.24963\/ijcai.2019\/551"},{"issue":"9","key":"2026091409072248000_cit48","doi-asserted-by":"publisher","first-page":"3004","DOI":"10.3390\/molecules27093004","article-title":"Prediction of drug-drug interaction\nusing an attention-based\ngraph neural network on drug molecular graphs","volume":"27","author":"Feng","year":"2022","journal-title":"Molecules"},{"key":"2026091409072248000_cit49","doi-asserted-by":"publisher","first-page":"8693","DOI":"10.1039\/D2SC02023H","article-title":"Learning size-adaptive\nmolecular substructures for explainable drug-drug interaction prediction\nby substructure-aware graph neural network","volume":"13","author":"Yang","year":"2022","journal-title":"Chem. Sci."},{"key":"2026091409072248000_cit50","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1186\/s12859-024-05654-4","article-title":"SSF-DDI: a\ndeep learning method utilizing drug sequence and substructure features\nfor drug-drug interaction prediction","volume":"25","author":"Zhu","year":"2024","journal-title":"BMC Bioinf."},{"key":"2026091409072248000_cit51","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."}],"container-title":["Journal of Chemical Information\nand Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.acs.org\/doi\/pdf\/10.1021\/acs.jcim.6c01505","content-type":"application\/pdf","content-version":"vor","intended-application":"unspecified"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/10674\/67407138\/acs.jcim.6c01505.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article-pdf\/66\/17\/10674\/67407138\/acs.jcim.6c01505.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T13:09:55Z","timestamp":1789391395000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.acs.org\/jcisd8\/article\/66\/17\/10674\/5328973\/SSE-DDI-Selective-Substructure-Encoding-with-Bond"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,25]]},"references-count":51,"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.6c01505","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]]}}}