{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T05:06:50Z","timestamp":1779340010817,"version":"3.51.4"},"reference-count":31,"publisher":"MDPI AG","issue":"10","license":[{"start":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T00:00:00Z","timestamp":1778198400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science, Research and Innovation Fund (NSRF) and King Mongkut's University of Technology North Bangkok","award":["KMUTNB-FF-68-B-21"],"award-info":[{"award-number":["KMUTNB-FF-68-B-21"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJMS"],"abstract":"<jats:p>Adverse drug reactions (ADRs) remain a major clinical challenge and a leading cause of morbidity and mortality worldwide. Among them, severe cutaneous adverse drug reactions (SCARs), including Stevens\u2013Johnson syndrome (SJS) and toxic epidermal necrolysis (TEN), represent life-threatening immune-mediated hypersensitivity responses strongly associated with specific human leukocyte antigen (HLA) alleles. Despite well-established pharmacogenetic associations, current diagnostic strategies remain largely retrospective and lack predictive capability for novel drug\u2013HLA risk pairs. Here, we present an integrative network-informed machine learning framework for predicting HLA-associated SCAR risk by combining pharmacogenomic features, drug chemical structure, and topological descriptors derived from drug\u2013drug and drug\u2013symptom interaction networks. An Extreme Gradient Boosting (XGBoost) classifier trained on integrated HLA allele and drug features, labeled using curated HLA\u2013SCAR associations, achieved an accuracy of 0.860 \u00b1 0.005, an F1-score of 0.689 \u00b1 0.010, with an area under the receiver operating characteristic curve (AUROC) of 0.922 \u00b1 0.003 and an area under the precision\u2013recall curve (AUPRC) of 0.768 \u00b1 0.007. Notably, several predicted positive associations absent from the training data corresponded to biologically plausible and literature-supported cases, including carbamazepine\u2014HLA-B*15:11, supporting the model\u2019s ability to generalize beyond known associations. Molecular docking provides structural evidence for the predicted associations, highlighting allele-specific binding patterns underlying these results. Overall, our results demonstrate that network-informed machine learning provides a proactive and integrative approach to SCAR risk prediction and may support early risk stratification and personalized drug safety assessment in precision medicine.<\/jats:p>","DOI":"10.3390\/ijms27104187","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T19:10:52Z","timestamp":1778267452000},"page":"4187","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Integrating Pharmacogenomics and Network Topology for Machine Learning Prediction of HLA-Associated Severe Cutaneous Adverse Drug Reactions"],"prefix":"10.3390","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3182-6838","authenticated-orcid":false,"given":"Tanaporn","family":"Ponduan","sequence":"first","affiliation":[{"name":"Department of Mathematics and Computer Science, Faculty of Science, Chulalongkorn University, Bangkok 10330, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arisara","family":"Kunsombut","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Faculty of Science, Chulalongkorn University, Bangkok 10330, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6007-1301","authenticated-orcid":false,"given":"Thummarat","family":"Paklao","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Faculty of Science, Chulalongkorn University, Bangkok 10330, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3439-6619","authenticated-orcid":false,"given":"Apichat","family":"Suratanee","sequence":"additional","affiliation":[{"name":"Department of Mathematics, Faculty of Applied Science, King Mongkut\u2019s University of Technology North Bangkok, Bangkok 10800, Thailand"},{"name":"Intelligent and Nonlinear Dynamic Innovations Research Center, Science and Technology Research Institute, King Mongkut\u2019s University of Technology North Bangkok, Bangkok 10800, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3833-0537","authenticated-orcid":false,"given":"Natapol","family":"Pornputtapong","sequence":"additional","affiliation":[{"name":"Department of Biochemistry and Microbiology, Faculty of Pharmaceutical Sciences, Chulalongkorn University, Bangkok 10330, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0416-8316","authenticated-orcid":false,"given":"Kitiporn","family":"Plaimas","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Faculty of Science, Chulalongkorn University, Bangkok 10330, Thailand"},{"name":"Centre of Excellence in Mathematics, Ministry of Higher Education, Science, Research, and Innovation, National University of Sciences, Bangkok 10400, Thailand"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,8]]},"reference":[{"key":"ref_1","unstructured":"Kommu, S., Carter, C., and Whitfield, P. (2024). Adverse Drug Reactions, StatPearls Publishing."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"673","DOI":"10.1038\/s41397-021-00246-4","article-title":"Side effect prediction based on drug-induced gene expression profiles and random forest with iterative feature selection","volume":"21","author":"Cakir","year":"2021","journal-title":"Pharmacogenomics J."},{"key":"ref_3","unstructured":"Marwa, K., Goldin, J., and Kondamudi, N.P. (2025). Type IV Hypersensitivity Reaction, StatPearls Publishing."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Chu, M.T., Chang, W.C., Pao, S.C., and Hung, S.I. (2023). Delayed Drug Hypersensitivity Reactions: Molecular Recognition, Genetic Susceptibility, and Immune Mediators. Biomedicines, 11.","DOI":"10.3390\/biomedicines11010177"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"481","DOI":"10.7861\/clinmedicine.16-5-481","article-title":"Adverse drug reactions","volume":"16","author":"Coleman","year":"2016","journal-title":"Clin. Med."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Peng, H., Zhang, X., Zhao, Z., Yin, J., and Li, J. (2018). Predicting adverse drug reactions of combined medication from heterogeneous pharmacologic databases. BMC Bioinform., 19.","DOI":"10.1186\/s12859-018-2520-8"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"100011","DOI":"10.1016\/j.aichem.2023.100011","article-title":"Application of artificial intelligence and machine learning in early detection of adverse drug reactions (ADRs) and drug-induced toxicity","volume":"1","author":"Yang","year":"2023","journal-title":"Artif. Intell. Chem."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Shareef, O., Kwan, J.T., Lau, S., Tahboub, M.A., and Saeed, H.N. (2022). An alternative model for assessing mortality risk in Stevens Johnson syndrome\/toxic epidermal necrolysis using a random forests classifier: A pilot study. Front. Med., 9.","DOI":"10.3389\/fmed.2022.935408"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Hu, Q., Chen, Y., Zou, D., He, Z., and Xu, T. (2024). Predicting adverse drug event using machine learning based on electronic health records: A systematic review and meta-analysis. Front. Pharmacol., 15.","DOI":"10.3389\/fphar.2024.1497397"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Sagulkoo, P., Suratanee, A., and Plaimas, K. (2022). Immune-Related Protein Interaction Network in Severe COVID-19 Patients toward the Identification of Key Proteins and Drug Repurposing. Biomolecules, 12.","DOI":"10.3390\/biom12050690"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"11779322211013350","DOI":"10.1177\/11779322211013350","article-title":"Prediction of Human-Plasmodium vivax Protein Associations From Heterogeneous Network Structures Based on Machine-Learning Approach","volume":"15","author":"Suratanee","year":"2021","journal-title":"Bioinform. Biol. Insights"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Suratanee, A., and Plaimas, K. (2020). Heterogeneous Network Model to Identify Potential Associations Between Plasmodium vivax and Human Proteins. Int. J. Mol. Sci., 21.","DOI":"10.3390\/ijms21041310"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1002\/psp4.13076","article-title":"Machine learning-based integration of network features and chemical structure of compounds for SARS-CoV-2 drug effect analysis","volume":"13","author":"Spath","year":"2024","journal-title":"CPT Pharmacomet. Syst. Pharmacol."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"229","DOI":"10.7164\/antibiotics.36.229","article-title":"Synthesis and biological activity of 7 beta-(2-amino-2-carboxy)-ethylthioacetamido-7 alpha-methoxycephalosporin derivatives","volume":"36","author":"Iwamatsu","year":"1983","journal-title":"J. Antibiot."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Zhou, F., and Uddin, S. (2023). Interpretable Drug-to-Drug Network Features for Predicting Adverse Drug Reactions. Healthcare, 11.","DOI":"10.3390\/healthcare11040610"},{"key":"ref_16","unstructured":"(2024, April 07). Allele Frequency Net Database (AFND) 2020. Available online: https:\/\/www.allelefrequencies.net\/."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"184","DOI":"10.1111\/ijd.15792","article-title":"HLA-B*15:11 status and carbamazepine-induced severe cutaneous adverse drug reactions in HLA-B*15:02 negative Chinese","volume":"61","author":"Wong","year":"2022","journal-title":"Int. J. Dermatol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"49","DOI":"10.2217\/pgs-2021-0126","article-title":"The association between HLA-B*15:02 and phenytoin-induced severe cutaneous adverse reactions: A meta-analysis","volume":"23","author":"Phung","year":"2022","journal-title":"Pharmacogenomics"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"7847","DOI":"10.1021\/acs.jcim.3c01055","article-title":"Two-Step Covalent Docking with Attracting Cavities","volume":"63","author":"Goullieux","year":"2023","journal-title":"J. Chem. Inf. Model."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1186\/s13321-019-0402-3","article-title":"Learning important features from multi-view data to predict drug side effects","volume":"11","author":"Liang","year":"2019","journal-title":"J. Cheminform."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1186\/s13321-025-01134-w","article-title":"Summarizing relationships between chemicals, genes, proteins, and diseases in PubChem using analysis of their co-occurrences in patents","volume":"17","author":"Zaslavsky","year":"2025","journal-title":"J. Cheminform."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"D1053","DOI":"10.1093\/nar\/gkac1011","article-title":"The IPD-IMGT\/HLA Database","volume":"51","author":"Barker","year":"2023","journal-title":"Nucleic Acids Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1093\/molbev\/mst010","article-title":"MAFFT Multiple Sequence Alignment Software Version 7: Improvements in Performance and Usability","volume":"30","author":"Katoh","year":"2013","journal-title":"Mol. Biol. Evol."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"D1356","DOI":"10.1093\/nar\/gkae726","article-title":"DDInter 2.0: An enhanced drug interaction resource with expanded data coverage, new interaction types, and improved user interface","volume":"53","author":"Tian","year":"2025","journal-title":"Nucleic Acids Res."},{"key":"ref_25","unstructured":"CBDD Team of Central South University (2025, January 16). the Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University. Curated Drug-Drug Interactions Database. Available online: https:\/\/ddinter.scbdd.com\/explanation\/."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"baab068","DOI":"10.1093\/database\/baab068","article-title":"Mining drug\u2013target and drug\u2013adverse drug reaction databases to identify target\u2013adverse drug reaction relationships","volume":"2021","author":"Galletti","year":"2021","journal-title":"Database"},{"key":"ref_27","unstructured":"(2025, January 16). Target\u2014Adverse Reaction Database Integrated Search. Available online: http:\/\/www.bioinsilico.org\/T-ARDIS\/."},{"key":"ref_28","unstructured":"(2025, March 19). NetworkX (Network Analysis in Python). Available online: https:\/\/networkx.org\/en\/."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1875","DOI":"10.2147\/CIA.S545906","article-title":"Evaluation of Potential Drug-Drug Interactions, Polypharmacy, and Prescribing Patterns of NSAIDs Among the Older Adults in a Secondary Care Setting","volume":"20","author":"Shareef","year":"2025","journal-title":"Clin. Interv. Aging"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Jeong, E., Malin, B., Nelson, S.D., Su, Y., Li, L., and Chen, Y. (2023). Revealing the dynamic landscape of drug-drug interactions through network analysis. Front. Pharmacol., 14.","DOI":"10.3389\/fphar.2023.1211491"},{"key":"ref_31","unstructured":"Cournapeau, D. (2024, December 14). Scikit-Learn Machine Learning in Python. Available online: https:\/\/scikit-learn.org\/stable\/."}],"container-title":["International Journal of Molecular Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1422-0067\/27\/10\/4187\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T04:13:44Z","timestamp":1779336824000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1422-0067\/27\/10\/4187"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,8]]},"references-count":31,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2026,5]]}},"alternative-id":["ijms27104187"],"URL":"https:\/\/doi.org\/10.3390\/ijms27104187","relation":{},"ISSN":["1422-0067"],"issn-type":[{"value":"1422-0067","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,8]]}}}