Predictive Models for Human Organ Toxicity Based on In Vitro Bioactivity Data and Chemical Structure

CORC > 生态环境研究中心 > 中国科学院生态环境研究中心 > 环境化学与生态毒理学国家重点实验室

	Predictive Models for Human Organ Toxicity Based on In Vitro Bioactivity Data and Chemical Structure
	Xu, Tuan; Ngan, Deborah K.; Ye, Lin; Xia, Menghang; Xie, Heidi Q.; Zhao, Bin; Simeonov, Anton; Huang, Ruili
刊名	CHEMICAL RESEARCH IN TOXICOLOGY
	2020-03-16
卷号	33 期号:3 页码:731-741
ISSN号	0893-228X
英文摘要	Traditional toxicity testing reliant on animal models is costly and low throughput, posing a significant challenge with the increasing numbers of chemicals that humans are exposed to in the environment. The purpose of this investigation was to build optimal prediction models for various human in vivo/organ-level toxicity end points (extracted from ChemIDPlus) using chemical structure and Tox21 in vitro quantitative high-throughput screening (qHTS) bioactivity assay data. Several supervised machine learning algorithms were applied to model 14 human toxicity end points pertaining to vascular, kidney, ureter and bladder, and liver organ systems. Three metrics were used to evaluate model performance: area under the receiver operating characteristic curve (AUC-ROC), balanced accuracy (BA), and Matthews correlation coefficient (MCC). The top four models, with AUC-ROC values >0.8, were derived for endocrine (0.90 +/- 0.00), musculoskeletal (0.88 +/- 0.02), peripheral nerve and sensation (0.85 +/- 0.01), and brain and coverings (0.83 +/- 0.02) toxicities, whereas the best model AUC-ROC values were >0.7 for the remaining 10 toxicities. Model performance was found to be dependent on the specific data set, model type, and feature selection method used. In addition, chemical structure and assay data showed different levels of contribution to the prediction of different toxicity end points. Although in vitro assay data, when combined with chemical structure, slightly improved the predictive accuracy for most end points (11 out of 14), a noteworthy finding was the near equal success of the structure-only models, which do not require Tox21 qHTS screening data, and the relatively poor performance of assay-only models. Thus, the top-performing structureonly models from this study could be applied for hazard screening of large sets of chemicals for potential human toxicity, whereas the largest assay contributions to models (i.e., cellular targets) could be used, along with the top-contributing structural features, to provide insight into toxicity mechanisms.
内容类型	期刊论文
源URL	[http://ir.rcees.ac.cn/handle/311016/44783]
专题	生态环境研究中心_环境化学与生态毒理学国家重点实验室
推荐引用方式 GB/T 7714	Xu, Tuan,Ngan, Deborah K.,Ye, Lin,et al. Predictive Models for Human Organ Toxicity Based on In Vitro Bioactivity Data and Chemical Structure[J]. CHEMICAL RESEARCH IN TOXICOLOGY,2020,33(3):731-741.
APA	Xu, Tuan.,Ngan, Deborah K..,Ye, Lin.,Xia, Menghang.,Xie, Heidi Q..,...&Huang, Ruili.(2020).Predictive Models for Human Organ Toxicity Based on In Vitro Bioactivity Data and Chemical Structure.CHEMICAL RESEARCH IN TOXICOLOGY,33(3),731-741.
MLA	Xu, Tuan,et al."Predictive Models for Human Organ Toxicity Based on In Vitro Bioactivity Data and Chemical Structure".CHEMICAL RESEARCH IN TOXICOLOGY 33.3(2020):731-741.