{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T18:44:58Z","timestamp":1791830698629,"version":"4.3.4"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1013619","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T00:00:00Z","timestamp":1791763200000}}],"reference-count":45,"publisher":"Public Library of Science (PLoS)","issue":"10","license":[{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000268","name":"Biotechnology and Biological Sciences Research Council","doi-asserted-by":"publisher","award":["BB\/K004131\/1"],"award-info":[{"award-number":["BB\/K004131\/1"]}],"id":[{"id":"10.13039\/501100000268","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000268","name":"Biotechnology and Biological Sciences Research Council","doi-asserted-by":"publisher","award":["BB\/F00964X\/1"],"award-info":[{"award-number":["BB\/F00964X\/1"]}],"id":[{"id":"10.13039\/501100000268","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000268","name":"Biotechnology and Biological Sciences Research Council","doi-asserted-by":"publisher","award":["BB\/ M025047\/1"],"award-info":[{"award-number":["BB\/ M025047\/1"]}],"id":[{"id":"10.13039\/501100000268","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000265","name":"Medical Research Council","doi-asserted-by":"publisher","award":["MR\/ T001070\/1"],"award-info":[{"award-number":["MR\/ T001070\/1"]}],"id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013704","name":"Consejo Nacional de Ciencia y Tecnolog\u00eda, Paraguay","doi-asserted-by":"publisher","award":["PINV01-719"],"award-info":[{"award-number":["PINV01-719"]}],"id":[{"id":"10.13039\/501100013704","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013704","name":"Consejo Nacional de Ciencia y Tecnolog\u00eda, Paraguay","doi-asserted-by":"publisher","award":["PINV01-108"],"award-info":[{"award-number":["PINV01-108"]}],"id":[{"id":"10.13039\/501100013704","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013704","name":"Consejo Nacional de Ciencia y Tecnolog\u00eda, Paraguay","doi-asserted-by":"publisher","award":["PINV01-108"],"award-info":[{"award-number":["PINV01-108"]}],"id":[{"id":"10.13039\/501100013704","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013704","name":"Consejo Nacional de Ciencia y Tecnolog\u00eda, Paraguay","doi-asserted-by":"publisher","award":["PINV01-719"],"award-info":[{"award-number":["PINV01-719"]}],"id":[{"id":"10.13039\/501100013704","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1660648"],"award-info":[{"award-number":["1660648"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundac\u00e3o de Amparo a Pesquisa do Estado do Rio de Janeiro","award":["E-26\/ 201.079\/2021 (260380)"],"award-info":[{"award-number":["E-26\/ 201.079\/2021 (260380)"]}]},{"name":"Fundac\u00e3o de Amparo a Pesquisa do Estado do Rio de Janeiro","award":["E-26\/204.352\/2024"],"award-info":[{"award-number":["E-26\/204.352\/2024"]}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["311181\/2022-8"],"award-info":[{"award-number":["311181\/2022-8"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016883","name":"Funda\u00e7\u00e3o Getulio Vargas","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016883","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100016883","name":"Funda\u00e7\u00e3o Getulio Vargas","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100016883","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Fundac\u00e3o de Amparo a Pesquisa do Estado do Rio de Janeiro","award":["E-26\/210.037\/2026 (319256)"],"award-info":[{"award-number":["E-26\/210.037\/2026 (319256)"]}]},{"DOI":"10.13039\/501100003593","name":"Conselho Nacional de Desenvolvimento Cient\u00edfico e Tecnol\u00f3gico","doi-asserted-by":"publisher","award":["313268\/2026-6"],"award-info":[{"award-number":["313268\/2026-6"]}],"id":[{"id":"10.13039\/501100003593","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>Side effects caused by drug combinations pose a major challenge in healthcare. Knowledge of these side effects is limited because often they are not detected in clinical trials, which typically involve a restricted number of participants and tested drug combinations. We introduce DCSE (Drug Combinations Side Effects), a novel machine learning method for predicting polypharmacy side effects. DCSE learns latent signatures for drugs, drug pairs, and side effects to predict the probability that a side effect occurs in a given drug combination. We first evaluate its performance in the commonly adopted experimental settings in the literature. However, these rely on balanced testing datasets and sampled negative examples, which do not capture the highly imbalanced and structured set of unknown side effects encountered in practice. Therefore, a key contribution of this paper is the introduction of more realistic experimental settings under prospective evaluations. Here, we attempt to predict side effects reported between 2009 and 2014 after training only on data available prior to that period. These evaluations include warm-start scenarios, in which some side effects are already known for a drug pair, and cold-start scenarios, in which the model predicts side effects for previously uncharacterized drug pairs. Our results indicate that DCSE consistently outperforms state-of-the-art methods, demonstrating its robustness and efficacy in real-world applications.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1013619","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T17:54:17Z","timestamp":1791222857000},"page":"e1013619","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust prediction of drug combination side effects in realistic settings"],"prefix":"10.1371","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8577-351X","authenticated-orcid":true,"given":"Ruben","family":"Jimenez","sequence":"first","affiliation":[{"name":"Escola de Matem\u00e1tica Aplicada, Funda\u00e7\u00e3o Get\u00falio Vargas","place":["Rio de Janeiro, Brazil"]},{"name":"Royal Holloway University of London","place":["Egham, United Kingdom"],"department":["Department of Computer Science, Centre for Systems and Synthetic Biology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8059-1346","authenticated-orcid":true,"given":"Alberto","family":"Paccanaro","sequence":"additional","affiliation":[{"name":"Escola de Matem\u00e1tica Aplicada, Funda\u00e7\u00e3o Get\u00falio Vargas","place":["Rio de Janeiro, Brazil"]},{"name":"Royal Holloway University of London","place":["Egham, United Kingdom"],"department":["Department of Computer Science, Centre for Systems and Synthetic Biology"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,10,5]]},"reference":[{"issue":"5","key":"pcbi.1013619.ref001","doi-asserted-by":"crossref","first-page":"463","DOI":"10.1038\/nbt.3834","article-title":"Synergistic drug combinations for cancer identified in a CRISPR screen for pairwise genetic interactions","volume":"35","author":"K Han","year":"2017","journal-title":"Nat Biotechnol"},{"issue":"12","key":"pcbi.1013619.ref002","doi-asserted-by":"crossref","first-page":"1213","DOI":"10.1038\/nbt.3052","article-title":"A community computational challenge to predict the activity of pairs of compounds","volume":"32","author":"M Bansal","year":"2014","journal-title":"Nat Biotechnol"},{"key":"pcbi.1013619.ref003","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkab880","article-title":"DDInter: An online drug-drug interaction database towards improving clinical decision-making and patient safety","volume":"50","author":"G Xiong","year":"2022","journal-title":"Nucleic Acids Res"},{"issue":"4","key":"pcbi.1013619.ref004","doi-asserted-by":"crossref","first-page":"473","DOI":"10.1001\/jamainternmed.2015.8581","article-title":"Changes in prescription and over-the-counter medication and dietary supplement use among older adults in the United States, 2005 vs 2011","volume":"176","author":"DM Qato","year":"2016","journal-title":"JAMA Intern Med"},{"issue":"13","key":"pcbi.1013619.ref005","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/bty294","article-title":"Modeling polypharmacy side effects with graph convolutional networks","volume":"34","author":"M Zitnik","year":"2018","journal-title":"Bioinformatics"},{"key":"pcbi.1013619.ref006","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.neucom.2016.03.080","article-title":"Predicting drug\u2013target interaction using positive-unlabeled learning","volume":"206","author":"W Lan","year":"2016","journal-title":"Neurocomputing"},{"key":"pcbi.1013619.ref007","doi-asserted-by":"crossref","first-page":"102778","DOI":"10.1016\/j.artmed.2024.102778","article-title":"SSLDTI: A novel method for drug-target interaction prediction based on self-supervised learning","volume":"149","author":"Z Liu","year":"2024","journal-title":"Artif Intell Med"},{"issue":"6","key":"pcbi.1013619.ref008","doi-asserted-by":"crossref","first-page":"4486","DOI":"10.1109\/JBHI.2025.3530794","article-title":"The large language models on biomedical data analysis: A survey","volume":"29","author":"W Lan","year":"2025","journal-title":"IEEE J Biomed Health Inform"},{"issue":"125","key":"pcbi.1013619.ref009","doi-asserted-by":"crossref","DOI":"10.1126\/scitranslmed.3003377","article-title":"Data-driven prediction of drug effects and interactions","volume":"4","author":"NP Tatonetti","year":"2012","journal-title":"Sci Transl Med"},{"key":"pcbi.1013619.ref010","doi-asserted-by":"crossref","DOI":"10.1093\/nar\/gkq1126","article-title":"DrugBank 3.0: A comprehensive resource for \u201comics\u201d research on drugs","volume":"39","author":"C Knox","year":"2011","journal-title":"Nucleic Acids Res"},{"issue":"6","key":"pcbi.1013619.ref011","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1136\/amiajnl-2012-000935","article-title":"Drug-drug interaction through molecular structure similarity analysis","volume":"19","author":"S Vilar","year":"2012","journal-title":"J Am Med Inform Assoc"},{"key":"pcbi.1013619.ref012","doi-asserted-by":"crossref","first-page":"12339","DOI":"10.1038\/srep12339","article-title":"Label propagation prediction of drug-drug interactions based on clinical side effects","volume":"5","author":"P Zhang","year":"2015","journal-title":"Sci Rep"},{"key":"pcbi.1013619.ref013","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1186\/s12859-017-1818-2","article-title":"Predicting combinative drug pairs towards realistic screening via integrating heterogeneous features","volume":"18","author":"J-Y Shi","year":"2017","journal-title":"BMC Bioinform"},{"issue":"5","key":"pcbi.1013619.ref014","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0196865","article-title":"Predicting potential drug-drug interactions on topological and semantic similarity features using statistical learning","volume":"13","author":"A Kastrin","year":"2018","journal-title":"PLoS One"},{"key":"pcbi.1013619.ref015","first-page":"449","article-title":"Predicting polypharmacy side-effects using knowledge graph embeddings","volume":"2020","author":"V Nov\u00e1\u010dek","year":"2020","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"issue":"1","key":"pcbi.1013619.ref016","doi-asserted-by":"crossref","first-page":"15590","DOI":"10.1038\/s41598-022-19999-4","article-title":"Prediction of drug-drug interaction events using graph neural networks based feature extraction","volume":"12","author":"MH Al-Rabeah","year":"2022","journal-title":"Sci Rep"},{"key":"pcbi.1013619.ref017","doi-asserted-by":"crossref","first-page":"701","DOI":"10.1145\/2623330.2623732","article-title":"DeepWalk: online learning of social representations.","volume-title":"Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. KDD \u201914","author":"B Perozzi","year":"2014"},{"key":"pcbi.1013619.ref018","doi-asserted-by":"crossref","unstructured":"Chen T, Guestrin C. Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016. pp. 785\u201394.","DOI":"10.1145\/2939672.2939785"},{"issue":"18","key":"pcbi.1013619.ref019","article-title":"Deep learning improves prediction of drug-drug and drug-food interactions","volume":"115","author":"JY Ryu","year":"2018","journal-title":"Proc Natl Acad Sci U S A"},{"issue":"1","key":"pcbi.1013619.ref020","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab441","article-title":"Drug-drug interaction prediction with learnable size-adaptive molecular substructures","volume":"23","author":"AK Nyamabo","year":"2022","journal-title":"Brief Bioinform"},{"issue":"6","key":"pcbi.1013619.ref021","doi-asserted-by":"crossref","DOI":"10.1093\/bib\/bbab133","article-title":"SSI-DDI: Substructure-substructure interactions for drug-drug interaction prediction","volume":"22","author":"AK Nyamabo","year":"2021","journal-title":"Brief Bioinform"},{"issue":"1","key":"pcbi.1013619.ref022","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1038\/s43856-024-00486-y","article-title":"Accurate and interpretable drug-drug interaction prediction enabled by knowledge subgraph learning","volume":"4","author":"Y Wang","year":"2024","journal-title":"Commun Med (Lond)"},{"issue":"1","key":"pcbi.1013619.ref023","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1186\/s12859-024-05654-4","article-title":"SSF-DDI: A deep learning method utilizing drug sequence and substructure features for drug-drug interaction prediction","volume":"25","author":"J Zhu","year":"2024","journal-title":"BMC Bioinformatics"},{"key":"pcbi.1013619.ref024","doi-asserted-by":"crossref","first-page":"104981","DOI":"10.1016\/j.jbi.2026.104981","article-title":"FG-DDI: Functional group-aware graph neural networks for drug-drug interaction prediction","volume":"174","author":"F Zhou","year":"2026","journal-title":"J Biomed Inform"},{"issue":"3","key":"pcbi.1013619.ref025","doi-asserted-by":"crossref","first-page":"2276","DOI":"10.1109\/JBHI.2025.3600045","article-title":"Multi-view contrastive learning for drug-drug interaction event prediction","volume":"30","author":"D Li","year":"2026","journal-title":"IEEE J Biomed Health Inform"},{"issue":"1","key":"pcbi.1013619.ref026","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1109\/JBHI.2025.3585290","article-title":"LLM-DDI: Leveraging large language models for drug-drug interaction prediction on biomedical knowledge graph","volume":"30","author":"D Li","year":"2026","journal-title":"IEEE J Biomed Health Inform"},{"issue":"3","key":"pcbi.1013619.ref027","doi-asserted-by":"crossref","first-page":"1771","DOI":"10.1109\/JBHI.2024.3419015","article-title":"Knowledge graph neural network with spatial-aware capsule for drug-drug interaction prediction","volume":"29","author":"X Su","year":"2025","journal-title":"IEEE J Biomed Health Inform"},{"issue":"1","key":"pcbi.1013619.ref028","first-page":"249","article-title":"Dual-channel learning framework for drug-drug interaction prediction via relation-aware heterogeneous graph transformer","volume":"38","author":"X Su","year":"2024","journal-title":"Proc AAAI Conf Artif Intell"},{"issue":"11","key":"pcbi.1013619.ref029","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btaf569","article-title":"Benchmarking drug-drug interaction prediction methods: A perspective of distribution changes","volume":"41","author":"Z Shen","year":"2025","journal-title":"Bioinformatics"},{"issue":"1","key":"pcbi.1013619.ref030","doi-asserted-by":"crossref","first-page":"4575","DOI":"10.1038\/s41467-020-18305-y","article-title":"Predicting the frequencies of drug side effects","volume":"11","author":"D Galeano","year":"2020","journal-title":"Nat Commun"},{"key":"pcbi.1013619.ref031","unstructured":"International Organizations of Medical Sciences C, et al. Benefit-risk balance for marketed drugs: evaluating safety signals: report of CIOMS Working Group IV. (No Title). 1998."},{"issue":"5","key":"pcbi.1013619.ref032","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1007\/s10928-016-9490-0","article-title":"Assessment of non-linear combination effect terms for drug-drug interactions","volume":"43","author":"G Koch","year":"2016","journal-title":"J Pharmacokinet Pharmacodyn"},{"issue":"7","key":"pcbi.1013619.ref033","doi-asserted-by":"crossref","first-page":"100108","DOI":"10.1016\/j.patter.2020.100108","article-title":"Using machine learning to identify adverse drug effects posing increased risk to women","volume":"1","author":"P Chandak","year":"2020","journal-title":"Patterns (N Y)"},{"key":"pcbi.1013619.ref034","first-page":"3111","article-title":"Distributed Representations of Words and Phrases and their Compositionality.","volume-title":"Advances in Neural Information Processing Systems 26","author":"T Mikolov","year":"2013"},{"issue":"1","key":"pcbi.1013619.ref035","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v28i1.8870","article-title":"Knowledge graph embedding by translating on hyperplanes","volume":"28","author":"Z Wang","year":"2014","journal-title":"AAAI"},{"issue":"114","key":"pcbi.1013619.ref036","doi-asserted-by":"crossref","DOI":"10.1126\/scitranslmed.3002774","article-title":"Predicting adverse drug events using pharmacological network models","volume":"3","author":"A Cami","year":"2011","journal-title":"Sci Transl Med"},{"issue":"12","key":"pcbi.1013619.ref037","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0083016","article-title":"Gathering and exploring scientific knowledge in pharmacovigilance","volume":"8","author":"P Lopes","year":"2013","journal-title":"PLoS One"},{"issue":"2","key":"pcbi.1013619.ref038","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1111\/bph.13895","article-title":"Drug repurposing screens and synergistic drug-combinations for infectious diseases","volume":"175","author":"W Zheng","year":"2018","journal-title":"Br J Pharmacol"},{"issue":"3","key":"pcbi.1013619.ref039","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"T Saito","year":"2015","journal-title":"PLoS One"},{"issue":"5","key":"pcbi.1013619.ref040","doi-asserted-by":"crossref","first-page":"566","DOI":"10.1001\/jamaneurol.2017.5144","article-title":"Association of coprescription of triptan antimigraine drugs and selective serotonin reuptake inhibitor or selective norepinephrine reuptake inhibitor antidepressants with serotonin syndrome","volume":"75","author":"Y Orlova","year":"2018","journal-title":"JAMA Neurol"},{"key":"pcbi.1013619.ref041","unstructured":"Drugs com. Fluoxetine and Naratriptan Interactions. 2026. https:\/\/www.drugs.com\/drug-interactions\/fluoxetine-with-naratriptan-1115-0-1692-0.html"},{"key":"pcbi.1013619.ref042","unstructured":"Mayo Clinic Staff. Serotonin syndrome - Symptoms and causes. 2024. https:\/\/www.mayoclinic.org\/diseases-conditions\/serotonin-syndrome\/symptoms-causes\/syc-20354758"},{"issue":"12","key":"pcbi.1013619.ref043","doi-asserted-by":"crossref","first-page":"1335","DOI":"10.1007\/s40264-023-01353-w","article-title":"Supporting pharmacovigilance signal validation and prioritization with analyses of routinely collected health data: lessons learned from an EHDEN network study","volume":"46","author":"O Gauffin","year":"2023","journal-title":"Drug Saf"},{"issue":"1","key":"pcbi.1013619.ref044","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1016\/j.celrep.2012.12.008","article-title":"Deciphering signatures of mutational processes operative in human cancer","volume":"3","author":"LB Alexandrov","year":"2013","journal-title":"Cell Rep"},{"issue":"7463","key":"pcbi.1013619.ref045","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1038\/nature12477","article-title":"Signatures of mutational processes in human cancer","volume":"500","author":"LB Alexandrov","year":"2013","journal-title":"Nature"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1013619","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T00:00:00Z","timestamp":1791763200000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T17:47:06Z","timestamp":1791827226000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1013619"}},"subtitle":[],"editor":[{"given":"Boyang","family":"Ji","sequence":"first","affiliation":[{"name":"BioInnovation Institute","place":["DENMARK"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,10,5]]},"references-count":45,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,10,5]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1013619","relation":{},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,5]]}}}