Comparison of global and mode of action-based models for aquatic toxicity

The ability to estimate aquatic toxicity is a critical need for ecological risk assessment and chemical regulation. The consensus in the literature is that mode of action (MOA) based toxicity models yield the most toxicologically meaningful and, theoretically, the most accurate results. In this study, a two-step prediction methodology was developed to estimate acute aquatic toxicity from molecular structure. In the first step, one-against-the-rest linear discriminant analysis (LDA) models were used to predict the MOA. The LDA models were able to predict the MOA with 85.8–88.8% accuracy for broad and specific MOAs, respectively. In the second step, a multiple linear regression (MLR) model corresponding to the predicted MOA was used to predict the acute aquatic toxicity value. The MOA-based approach was found to yield similar external prediction accuracy (<i>r</i>² = 0.529–0.632) to a single global MLR model (<i>r</i>² = 0.551–0.562) fit to the entire training set. Overall, the global hierarchical clustering approach yielded a higher combination of accuracy and prediction coverage (<i>r</i>² = 0.572, coverage = 99.3%) than the other approaches. Utilizing multiple two-dimensional chemical descriptors in MLR models yielded comparable results to using only the octanol–water partition coefficient (log <i>K</i>_ow).

开展水生毒性估算，是生态风险评估与化学品监管领域的关键需求。学界普遍共识指出，基于作用模式（mode of action, MOA）的毒性模型能够产出最具毒理学意义、且理论精度最高的预测结果。本研究开发了一种两步预测方法，用于从分子结构出发估算急性水生毒性。第一步采用一对多线性判别分析（linear discriminant analysis, LDA）模型预测作用模式，该模型针对宽泛型与特定型作用模式的预测准确率分别可达85.8%~88.8%。第二步则针对预测得到的作用模式，采用对应的多元线性回归（multiple linear regression, MLR）模型预测急性水生毒性数值。研究发现，基于作用模式的方法，其外部预测准确率（<i>r</i>² = 0.529~0.632）与仅拟合全部训练集的单一全局多元线性回归模型（<i>r</i>² = 0.551~0.562）相当。整体而言，全局层级聚类方法在预测准确率与覆盖度两方面的综合表现（<i>r</i>² = 0.572，覆盖度=99.3%）优于其余各类方法。在多元线性回归模型中使用多种二维化学描述符，所得到的预测效果与仅采用正辛醇-水分配系数（octanol–water partition coefficient, log <i>K</i>_ow）的方案不相上下。