Abstract：
Fused and non-fused polycyclic aromatic hydrocarbons (FNFPAHs) are a type of organic compounds widely occurring in the environment that pose a potential hazard to ecosystem and public health, and thus receive extensive attention from various regulatory agencies. Here, quantitative structure-activity relationship (QSAR) models were constructed to model the ecotoxicity of FNFPAHs against two aquatic species, Daphnia magna and Oncorhynchus mykiss. According to the stringent OECD guidelines, we used genetic algorithm (GA) plus multiple linear regression (MLR) approach to establish QSAR models of the two aquatic toxicity endpoints: D. magna (48 h LC50) and O. mykiss (96 h LC50). The models were established using simple 2D descriptors with explicit physicochemical significance and evaluated using various internal/external validation metrics. The results clearly show that both models are statistically robust (QLOO2 = 0.7834 for D. magna and QLOO2 = 0.8162 for O. mykiss), have good internal fitness (R2 = 0.8159 for D. magna and R2 = 0.8626 for O. mykiss and external predictive ability (D. magna: Rtest2 = 0.8259, QFn2 = 0.7640∼0.8140, CCCtest = 0.8972; O. mykiss:Rtest2 = 0.8077, QFn2 = 0.7615∼0.7722, CCCtest = 0.8910). To prove the predictive performance of the developed models, an additional comparison with the standard ECOSAR tool obviously shows that our models have lower RMSE values. Subsequently, we utilized the best models to predict the true external set compounds collected from the PPDB database to further fill the toxicity data gap. In addition, consensus models (CMs) that integrate all validated individual models (IMs) were more externally predictive than IMs, of which CM2 has the best prediction performance towards the two aquatic species. Overall, the models presented here could be used to evaluate unknown FNFPAHs inside the domain of applicability (AD), thus being very important for environmental risk assessment under current regulatory frameworks.
摘要：
稠合和非稠合多环芳烃（FNFPAHs）是一类广泛存在于环境中的有机化合物，对生态系统和公共卫生构成潜在危害。因此受到各种监管机构的广泛关注。这里,定量结构-活性关系（QSAR）模型被构建为FNFPAHs对两种水生物种的生态毒性模型，大型水蚤和Oncorhynchusmykiss。根据严格的经合组织准则，我们使用遗传算法（GA）加多元线性回归（MLR）方法建立了两个水生毒性终点的QSAR模型：D.magna（48hLC50）和O.mykiss（96hLC50）。使用具有明确物理化学意义的简单2D描述符建立模型，并使用各种内部/外部验证指标进行评估。结果清楚地表明，两个模型在统计上都是稳健的（D.magna的QLOO2=0.7834，O.mykiss的QLOO2=0.8162），具有良好的内部适应性（D.magna的R2=0.8159，O.mykiss的R2=0.8626和外部预测能力（D.麦格纳：Rtest2=0.8259，QFn2=0.7640~0.8140，CCCtest=0.8972；O.mykiss：Rtest2=0.8077，QFn2=0.7615~0.7722，CCCtest=0.8910）。为了证明所开发模型的预测性能，与标准ECOSAR工具的额外比较显然表明，我们的模型具有较低的RMSE值。随后，我们利用最佳模型来预测从PPDB数据库收集的真实外集化合物,以进一步填补毒性数据空白.此外,整合所有经过验证的单个模型(IM)的共识模型(CM)比IM更具外部预测性，其中CM2对两种水生物种的预测性能最好。总的来说,这里提出的模型可用于评估适用性领域(AD)内的未知FNFPAHs，因此对于当前监管框架下的环境风险评估非常重要。
