文献类型：期刊文献

英文题名：In silico prediction of ocular toxicity of compounds using explainable machine learning and deep learning approaches

作者：Zhou, Yiqing[1];Wang, Ze[1];Huang, Zejun[1];Li, Weihua[1];Chen, Yuanting[1];Yu, Xinxin[1];Tang, Yun[1,2];Liu, Guixia[1,2]

机构：[1]East China Univ Sci & Technol, Shanghai Frontiers Sci Ctr Optogenet Tech Cell Met, Sch Pharm, Shanghai Key Lab New Drug Design, Shanghai, Peoples R China;[2]East China Univ Sci & Technol, Shanghai Frontiers Sci Ctr Optogenet Tech Cell Met, Sch Pharm, Shanghai Key Lab New Drug Design, 130 Meilong Rd, Shanghai 200237, Peoples R China

年份：2024

卷号：44

期号：6

起止页码：892

外文期刊名：JOURNAL OF APPLIED TOXICOLOGY

收录：;WOS:【SCI-EXPANDED(收录号:WOS:001157742500001)】；

基金：This work was supported by the National Key Research and Development Program of China (Grants 2023YFF1204904 and 2019YFA0904800), the National Natural Science Foundation of China (Grants U23A20530, 82273858, and 82273930), and Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism (Shanghai Municipal Education Commission).

语种：英文

外文关键词：deep learning; feature selection; GCN; machine learning; model interpretability; molecular descriptors; ocular toxicity

摘要：The accurate identification of chemicals with ocular toxicity is of paramount importance in health hazard assessment. In contemporary chemical toxicology, there is a growing emphasis on refining, reducing, and replacing animal testing in safety evaluations. Therefore, the development of robust computational tools is crucial for regulatory applications. The performance of predictive models is heavily reliant on the quality and quantity of data. In this investigation, we amalgamated the most extensive dataset (4901 compounds) sourced from governmental GHS-compliant databases and literature to develop binary classification models of chemical ocular toxicity. We employed 12 molecular representations in conjunction with six machine learning algorithms and two deep learning algorithms to create a series of binary classification models. The findings indicated that the deep learning method GCN outperformed the machine learning models in cross-validation, achieving an impressive AUC of 0.915. However, the top-performing machine learning model (RF-Descriptor) demonstrated excellent performance with an AUC of 0.869 on the test set and was therefore selected as the best model. To enhance model interpretability, we conducted the SHAP method and attention weights analysis. The two approaches offered visual depictions of the relevance of key descriptors and substructures in predicting ocular toxicity of chemicals. Thus, we successfully struck a delicate balance between data quality and model interpretability, rendering our model valuable for predicting and comprehending potential ocular-toxic compounds in the early stages of drug discovery. Effective identification of chemicals causing ocular toxicity is critical to health hazard assessment. In this study, we carefully integrated the largest dataset (4,901 compounds) from official GHS-compliant databases and literature. Machine learning and deep learning classification prediction models were constructed, among which the RF-Descriptor model performed the best. Furthermore, we used the SHAP method and attention weights analysis to enhance the model's interpretability, making it valuable in predicting and understanding potential ocular-toxic compounds in the early stages of drug discovery.