Modeling and insights into the structural basis of chemical acute aquatic toxicity

作者：Ruiqiu Zhang, Huizhu Guo, Yuqing Hua, Xueyan Cui, Yinping Shi, Xiao Li · 发表于：Ecotoxicology and Environmental Safety · 年份：2022 · DOI：10.1016/j.ecoenv.2022.113940 · 被引用次数：28 · 研究领域：Computational Drug Discovery Methods、Environmental Toxicology and Ecotoxicology、Statistical and Computational Modeling

It has become a top global regulatory priority to prevent and control pollution from the release of synthetic chemicals, which continues to affect the aquatic communities. In the past decades, computational tools were largely used to significantly reduce the budget and time cost of chemical acute aquatic toxicity assessment. But the structural basis of toxic compounds was rarely analyzed. In the present study, we collected 1438, 485 and 961 chemicals with acute toxicity data records for three representative aquatic species, including Tetrahymena pyriformis, Daphnia magna, and Fathead minnow, respectively. A series of artificial intelligence models were developed using OCHEM tools. For each aquatic toxicity endpoint, a consensus model was developed based on the top performed individual models. The consensus models provided good performance on external validation sets with total accuracy values 96.88 %, 90.63 %, and 84.90 % for Tetrahymena pyriformis toxicity (TPT), Daphnia magna toxicity (DMT), and Fathead minnow toxicity (FMT), respectively. The models can be freely accessed via https://ochem.eu/article/146910. Moreover, the analysis of physical-chemical properties suggested that several key molecular properties of aquatic toxic compounds were significantly different with those of non-toxic compounds. Thus, these descriptors may be associated to chemical acute aquatic toxicity, and may be useful for the understand of chemical aquatic toxicity. Besides, in this study, the stru...