{"title":"Machine learning-driven QSAR models for predicting the cytotoxicity of five common microplastics","authors":"","doi":"10.1016/j.tox.2024.153918","DOIUrl":null,"url":null,"abstract":"<div><p>In the field of microplastics (MPs) toxicity prediction, machine learning (ML) computer simulation techniques are showing great potential. In this study, six ML algorithms were utilized to predict the toxicity of MPs on BEAS-2B cells based on quantitative structure-activity relationship (QSAR) models. Comparing the models of different algorithms, the extreme gradient boosting model showed the best fit and prediction performance (R<sup>2</sup><sub>tra</sub> = 0.9876, R<sup>2</sup><sub>test</sub> = 0.9286). Additionally, Williams plot analysis showed that the six models developed were able to predict stably within their applicability domain, with few outliers. Finally, the three feature importance methods—Embedded Feature Importance (EFI), Recursive Feature Elimination (RFE), and SHapley Additive exPlanations (SHAP)—consistently identified particle size as the most critical feature affecting toxicity prediction. The proposed QSAR model can be utilized for preliminary environmental exposure assessments of MPs and to better understand the associated health risks.</p></div>","PeriodicalId":23159,"journal":{"name":"Toxicology","volume":null,"pages":null},"PeriodicalIF":4.8000,"publicationDate":"2024-08-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Toxicology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0300483X24001999","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PHARMACOLOGY & PHARMACY","Score":null,"Total":0}
引用次数: 0
Abstract
In the field of microplastics (MPs) toxicity prediction, machine learning (ML) computer simulation techniques are showing great potential. In this study, six ML algorithms were utilized to predict the toxicity of MPs on BEAS-2B cells based on quantitative structure-activity relationship (QSAR) models. Comparing the models of different algorithms, the extreme gradient boosting model showed the best fit and prediction performance (R2tra = 0.9876, R2test = 0.9286). Additionally, Williams plot analysis showed that the six models developed were able to predict stably within their applicability domain, with few outliers. Finally, the three feature importance methods—Embedded Feature Importance (EFI), Recursive Feature Elimination (RFE), and SHapley Additive exPlanations (SHAP)—consistently identified particle size as the most critical feature affecting toxicity prediction. The proposed QSAR model can be utilized for preliminary environmental exposure assessments of MPs and to better understand the associated health risks.
期刊介绍:
Toxicology is an international, peer-reviewed journal that publishes only the highest quality original scientific research and critical reviews describing hypothesis-based investigations into mechanisms of toxicity associated with exposures to xenobiotic chemicals, particularly as it relates to human health. In this respect "mechanisms" is defined on both the macro (e.g. physiological, biological, kinetic, species, sex, etc.) and molecular (genomic, transcriptomic, metabolic, etc.) scale. Emphasis is placed on findings that identify novel hazards and that can be extrapolated to exposures and mechanisms that are relevant to estimating human risk. Toxicology also publishes brief communications, personal commentaries and opinion articles, as well as concise expert reviews on contemporary topics. All research and review articles published in Toxicology are subject to rigorous peer review. Authors are asked to contact the Editor-in-Chief prior to submitting review articles or commentaries for consideration for publication in Toxicology.