{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T11:37:00Z","timestamp":1783769820402,"version":"3.55.0"},"reference-count":60,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T00:00:00Z","timestamp":1723593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100009330","name":"Medical Science and Technology Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["A2024082"],"award-info":[{"award-number":["A2024082"]}],"id":[{"id":"10.13039\/501100009330","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Pharmacol."],"abstract":"<jats:p>Agranulocytosis, induced by non-chemotherapy drugs, is a serious medical condition that presents a formidable challenge in predictive toxicology due to its idiosyncratic nature and complex mechanisms. In this study, we assembled a dataset of 759 compounds and applied a rigorous feature selection process prior to employing ensemble machine learning classifiers to forecast non-chemotherapy drug-induced agranulocytosis (NCDIA) toxicity. The balanced bagging classifier combined with a gradient boosting decision tree (BBC + GBDT), utilizing the combined descriptor set of DS and RDKit comprising 237 features, emerged as the top-performing model, with an external validation AUC of 0.9164, ACC of 83.55%, and MCC of 0.6095. The model\u2019s predictive reliability was further substantiated by an applicability domain analysis. Feature importance, assessed through permutation importance within the BBC + GBDT model, highlighted key molecular properties that significantly influence NCDIA toxicity. Additionally, 16 structural alerts identified by SARpy software further revealed potential molecular signatures associated with toxicity, enriching our understanding of the underlying mechanisms. We also applied the constructed models to assess the NCDIA toxicity of novel drugs approved by FDA. This study advances predictive toxicology by providing a framework to assess and mitigate agranulocytosis risks, ensuring the safety of pharmaceutical development and facilitating post-market surveillance of new drugs.<\/jats:p>","DOI":"10.3389\/fphar.2024.1431941","type":"journal-article","created":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T05:32:56Z","timestamp":1723613576000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Predicting non-chemotherapy drug-induced agranulocytosis toxicity through ensemble machine learning approaches"],"prefix":"10.3389","volume":"15","author":[{"given":"Xiaojie","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaochun","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaokai","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lina","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,8,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1093\/bioinformatics\/btq134","article-title":"Permutation importance: a corrected feature importance measure","volume":"26","author":"Altmann","year":"2010","journal-title":"Bioinformatics"},{"key":"B2","doi-asserted-by":"publisher","first-page":"657","DOI":"10.7326\/0003-4819-146-9-200705010-00009","article-title":"Systematic review: agranulocytosis induced by nonchemotherapy drugs","volume":"146","author":"Andersohn","year":"2007","journal-title":"Ann. Intern. Med."},{"key":"B3","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1097\/MOH.0b013e3282f15fb9","article-title":"Idiosyncratic drug-induced agranulocytosis or acute neutropenia","volume":"15","author":"Andr\u00e8S","year":"2008","journal-title":"Curr. Opin. Hematol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"1235","DOI":"10.1080\/14740338.2017.1376645","article-title":"Non-chemotherapy drug-induced neutropenia - an update","volume":"16","author":"Andres","year":"2017","journal-title":"Expert Opin. Drug Saf."},{"key":"B5","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1093\/qjmed\/hcw220","article-title":"Idiosyncratic drug-induced neutropenia and agranulocytosis","volume":"110","author":"Andres","year":"2017","journal-title":"QJM"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.3390\/jcm8091351","article-title":"State of art of idiosyncratic drug-induced neutropenia or agranulocytosis, with a focus on biotherapies","volume":"8","author":"Andres","year":"2019","journal-title":"J. Clin. Med."},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.25080\/MAJORA-8B375195-003","article-title":"Hyperopt: a python library for optimizing the hyperparameters of machine learning algorithms","volume":"20","author":"Bergstra","year":"2013","journal-title":"Proc. 12th Python Sci. Conf."},{"key":"B8","doi-asserted-by":"publisher","first-page":"106839","DOI":"10.1016\/j.csda.2019.106839","article-title":"Benchmark for filter methods for feature selection in high-dimensional classification data","volume":"143","author":"Bommert","year":"2020","journal-title":"Comput. Statistics and Data Analysis"},{"key":"B9","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1145\/130385.130401","article-title":"A training algorithm for optimal margin classifiers","author":"Boser","year":"1992","journal-title":"Proc. fifth Annu. workshop Comput. Learn. theory"},{"key":"B10","doi-asserted-by":"publisher","first-page":"943","DOI":"10.1021\/acs.jcim.7b00641","article-title":"In silico pharmacoepidemiologic evaluation of drug-induced cardiovascular complications using combined classifiers","volume":"58","author":"Cai","year":"2018","journal-title":"J. Chem. Inf. Model"},{"key":"B11","first-page":"24","volume-title":"Using random forest to learn imbalanced data","author":"Chen","year":"2004"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785","article-title":"Xgboost: A scalable tree boosting system","author":"Chen","year":"2016","journal-title":"Proc. 22nd ACM SIGKDD Int. Conf. Knowl. Discov. Data Min"},{"key":"B13","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/s12864-019-6413-7","article-title":"The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation","volume":"21","author":"Chicco","year":"2020","journal-title":"BMC Genomics"},{"key":"B14","volume-title":"Drug-induced neutropenia and agranulocytosis","author":"Coates","year":"2023"},{"key":"B15","volume-title":"Guidance document on the validation of (quantitative) structure-activity relationship [(Q) SAR] models","year":"2014"},{"key":"B16","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/tit.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Trans. Inf. theory"},{"key":"B17","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1182\/asheducation-2017.1.187","article-title":"Non-chemotherapy drug-induced neutropenia: key points to manage the challenges","volume":"2017","author":"Curtis","year":"2017","journal-title":"Hematol. Am. Soc. Hematol. Educ. Program"},{"key":"B18","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1186\/s12863-018-0633-8","article-title":"Using recursive feature elimination in random forest to account for correlated variables in high dimensional data","volume":"19","author":"Darst","year":"2018","journal-title":"BMC Genet."},{"key":"B19","doi-asserted-by":"publisher","first-page":"815","DOI":"10.3390\/app8050815","article-title":"Class imbalance ensemble learning based on the margin theory","volume":"8","author":"Feng","year":"2018","journal-title":"Appl. Sci."},{"key":"B20","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1080\/1062936X.2013.773376","article-title":"Automatic knowledge extraction from chemical structures: the case of mutagenicity prediction","volume":"24","author":"Ferrari","year":"2013","journal-title":"Sar. QSAR Environ. Res."},{"key":"B21","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. statistics"},{"key":"B22","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1517\/14740338.6.3.323","article-title":"Non-chemotherapy drug-induced agranulocytosis","volume":"6","author":"Garbe","year":"2007","journal-title":"Expert Opin. drug Saf."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1015409","DOI":"10.3389\/fimmu.2022.1015409","article-title":"Modeling and insights into the structural characteristics of drug-induced autoimmune diseases","volume":"13","author":"Guo","year":"2022","journal-title":"Front. Immunol."},{"key":"B24","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1023\/a:1012487302797","article-title":"Gene selection for cancer classification using support vector machines","volume":"46","author":"Guyon","year":"2002","journal-title":"Mach. Learn."},{"key":"B25","doi-asserted-by":"crossref","DOI":"10.1145\/3310986.3311023","article-title":"Empirical comparison of area under ROC curve (AUC) and mathew correlation coefficient (MCC) for evaluating machine learning algorithms on imbalanced datasets for binary classification","author":"Halimu","year":"2019"},{"key":"B26","doi-asserted-by":"crossref","DOI":"10.1002\/9781118548387","volume-title":"Applied logistic regression","author":"Hosmer","year":"2013"},{"key":"B27","doi-asserted-by":"publisher","first-page":"8073","DOI":"10.3390\/ijms22158073","article-title":"Prediction of drug-induced liver toxicity using SVM and optimal descriptor sets","volume":"22","author":"Jaganathan","year":"2021","journal-title":"Int. J. Mol. Sci."},{"key":"B28","doi-asserted-by":"publisher","first-page":"832","DOI":"10.3390\/pharmaceutics14040832","article-title":"An explainable supervised machine learning model for predicting respiratory toxicity of chemicals using optimal molecular descriptors","volume":"14","author":"Jaganathan","year":"2022","journal-title":"Pharmaceutics"},{"key":"B29","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1016\/j.neucom.2016.02.006","article-title":"A new sampling method for classifying imbalanced data based on support vector machine ensemble","volume":"193","author":"Jian","year":"2016","journal-title":"Neurocomputing"},{"key":"B30","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1517\/17425255.2015.985649","article-title":"Current understanding of the mechanisms of idiosyncratic drug-induced agranulocytosis","volume":"11","author":"Johnston","year":"2015","journal-title":"Expert Opin. Drug Metab. Toxicol."},{"key":"B31","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1007\/978-1-4939-7899-1_6","article-title":"Applicability domain: a step toward confident predictions and decidability for qsar modeling","volume":"1800","author":"Kar","year":"2018","journal-title":"Methods Mol. Biol."},{"key":"B32","article-title":"Lightgbm: a highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Adv. neural Inf. Process. Syst."},{"key":"B33","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1007\/s13748-016-0094-0","article-title":"Learning from imbalanced data: open challenges and future directions","volume":"5","author":"Krawczyk","year":"2016","journal-title":"Prog. Artif. Intell."},{"key":"B34","doi-asserted-by":"publisher","first-page":"D1075","DOI":"10.1093\/nar\/gkv1075","article-title":"The SIDER database of drugs and side effects","volume":"44","author":"Kuhn","year":"2016","journal-title":"Nucleic Acids Res."},{"key":"B35","first-page":"559","article-title":"Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning","volume":"18","author":"Lema\u00eeTRE","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"B36","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1109\/TSMCB.2008.2007853","article-title":"Exploratory undersampling for class-imbalance learning","volume":"39","author":"Liu","year":"2009","journal-title":"IEEE Trans. Syst. Man. Cybern. B Cybern."},{"key":"B37","volume-title":"Insights into the mechanism of drug-induced agranulocytosis: a study of the immune changes induced by clozapine and amodiaquine","author":"Lobach","year":"2014"},{"key":"B38","doi-asserted-by":"publisher","first-page":"1808","DOI":"10.3390\/jcm9061808","article-title":"Idiosyncratic drug-induced neutropenia and agranulocytosis in elderly patients","volume":"9","author":"Lorenzo-Villalba","year":"2020","journal-title":"J. Clin. Med."},{"key":"B39","first-page":"546","article-title":"An empirical evaluation of bagging and boosting","volume":"1997","author":"Maclin","year":"1997","journal-title":"AAAI\/IAAI"},{"key":"B40","doi-asserted-by":"publisher","first-page":"531","DOI":"10.3233\/ida-130592","article-title":"ROC analysis of classifiers in machine learning: a survey","volume":"17","author":"Majnik","year":"2013","journal-title":"Intell. Data Anal."},{"key":"B41","doi-asserted-by":"publisher","first-page":"1270","DOI":"10.1038\/s41592-021-01302-4","article-title":"The class imbalance problem","volume":"18","author":"Megahed","year":"2021","journal-title":"Nat. Methods"},{"key":"B42","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1093\/toxsci\/kfu233","article-title":"Molecular mechanisms of acrolein toxicity: relevance to human disease","volume":"143","author":"Moghe","year":"2015","journal-title":"Toxicol. Sci."},{"key":"B43","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1016\/0925-2312(91)90023-5","article-title":"Multilayer perceptrons for classification and regression","volume":"2","author":"Murtagh","year":"1991","journal-title":"Neurocomputing"},{"key":"B44","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.cbi.2010.09.011","article-title":"Drug bioactivation and protein adduct formation in the pathogenesis of drug-induced toxicity","volume":"192","author":"Park","year":"2011","journal-title":"Chemico-biological Interact."},{"key":"B45","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"B46","doi-asserted-by":"publisher","first-page":"727717","DOI":"10.3389\/fphar.2021.727717","article-title":"Drug-induced idiosyncratic agranulocytosis - infrequent but dangerous","volume":"12","author":"Rattay","year":"2021","journal-title":"Front. Pharmacol."},{"key":"B47","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.3390\/ijms24021243","article-title":"The role of myeloperoxidase in clozapine-induced inflammation: a mechanistic update for idiosyncratic drug-induced agranulocytosis","volume":"24","author":"Sernoskie","year":"2023","journal-title":"Int. J. Mol. Sci."},{"key":"B48","doi-asserted-by":"publisher","first-page":"793332","DOI":"10.3389\/fphar.2021.793332","article-title":"In silico prediction and insights into the structural basis of drug induced nephrotoxicity","volume":"12","author":"Shi","year":"2021","journal-title":"Front. Pharmacol."},{"key":"B49","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1214\/10-sts330","article-title":"To explain or to predict?","volume":"25","author":"Shmueli","year":"2010","journal-title":"Stat. Sci."},{"key":"B50","doi-asserted-by":"publisher","first-page":"168","DOI":"10.4172\/2157-7609.1000168","article-title":"Biotransformation of hydrazine dervatives in the mechanism of toxicity","volume":"5","author":"Sinha","year":"2014","journal-title":"J. Drug Metab. Toxicol."},{"key":"B51","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1021\/tx6003562","article-title":"Aminoglutethimide-induced protein free radical formation on myeloperoxidase: a potential mechanism of agranulocytosis","volume":"20","author":"Siraki","year":"2007","journal-title":"Chem. Res. Toxicol."},{"key":"B52","doi-asserted-by":"publisher","first-page":"1143","DOI":"10.1021\/tx700415b","article-title":"Procainamide, but not N-acetylprocainamide, induces protein free radical formation on myeloperoxidase: a potential mechanism of agranulocytosis","volume":"21","author":"Siraki","year":"2008","journal-title":"Chem. Res. Toxicol."},{"key":"B53","doi-asserted-by":"publisher","first-page":"880","DOI":"10.1021\/tx900432d","article-title":"Investigating the mechanisms of aromatic amine-induced protein free radical formation by quantitative Structure\u2212 Activity relationships: implications for drug-induced agranulocytosis","volume":"23","author":"Siraki","year":"2010","journal-title":"Chem. Res. Toxicol."},{"key":"B54","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s43188-023-00215-y","article-title":"Efficiency of pharmaceutical toxicity prediction in computational toxicology","volume":"40","author":"Uesawa","year":"2024","journal-title":"Toxicol. Res."},{"key":"B55","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1021\/acs.chemrestox.9b00227","article-title":"An overview of machine learning and big data for drug toxicity evaluation","volume":"33","author":"Vo","year":"2020","journal-title":"Chem. Res. Toxicol."},{"key":"B56","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.cbi.2009.05.014","article-title":"Metabolic activation of the phenothiazine antipsychotics chlorpromazine and thioridazine to electrophilic iminoquinone species in human liver microsomes and recombinant P450s","volume":"181","author":"Wen","year":"2009","journal-title":"Chemico-biological Interact."},{"key":"B57","doi-asserted-by":"publisher","first-page":"30","DOI":"10.3389\/fchem.2018.00030","article-title":"In silico prediction of chemical toxicity for drug design using machine learning methods and structural alerts","volume":"6","author":"Yang","year":"2018","journal-title":"Front. Chem."},{"key":"B58","doi-asserted-by":"publisher","first-page":"1387","DOI":"10.1109\/TNNLS.2019.2920246","article-title":"Hybrid classifier ensemble for imbalanced data","volume":"31","author":"Yang","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn Syst."},{"key":"B59","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.tiv.2017.02.016","article-title":"Novel naive Bayes classification models for predicting the chemical Ames mutagenicity","volume":"41","author":"Zhang","year":"2017","journal-title":"Toxicol Vitro"},{"key":"B60","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1081\/dmr-200028812","article-title":"Drug bioactivation covalent binding to target proteins and toxicity relevance","volume":"37","author":"Zhou","year":"2005","journal-title":"Drug metab. Rev."}],"container-title":["Frontiers in Pharmacology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2024.1431941\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,14]],"date-time":"2024-08-14T05:33:04Z","timestamp":1723613584000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fphar.2024.1431941\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,14]]},"references-count":60,"alternative-id":["10.3389\/fphar.2024.1431941"],"URL":"https:\/\/doi.org\/10.3389\/fphar.2024.1431941","relation":{},"ISSN":["1663-9812"],"issn-type":[{"value":"1663-9812","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,14]]},"article-number":"1431941"}}