Drug Theoretics and Cheminformatics Laboratory, Department of Pharmaceutical Technology, Jadavpur University, Kolkata, 700032, India.
Environ Sci Pollut Res Int. 2022 Dec;29(58):88302-88317. doi: 10.1007/s11356-022-21937-w. Epub 2022 Jul 13.
Soil invertebrates serve as an outstanding biological indicator of the terrestrial ecosystem and overall soil quality, considering their high sensitivity when compared to other indicators of soil quality. In this study, the available soil ecotoxicity data (pEC50) against the soil invertebrate Folsomia candida (C. name: Springtail) (n = 45) were collated from the database of ECOTOX (cfpub.epa.gov/ecotox) and subjected to QSAR analysis using 2D descriptors. Four partial least squares (PLS) models were built based on the features selected through genertic algorithm followed by the best subset selection. These four models were then used as inputs for Intelligent Consensus Predictor version 1.2 (PLS version) to get the final consensus predictions, using the best selection of predictions (compound-wise) from four "qualified" individual models. Both internal and external validations metrics of the consensus predictions are well- balanced and within the acceptable range as per the OECD criteria. The consensus model was found to be better than the previous developed models for this endpoint. Predictions were also made using the Chemical Read-across approach, which showed even better external validation metric values than the consensus predictions. From the selected features in the QSAR models, it has been found out that molecular weight and presence of a di-thiophosphate group, electron donor groups, and polyhalogen substitutions have a significant impact on the soil ecotoxicity. The soil ecotoxicological risk assessment of organic chemicals can therefore be prioritized by these features. The models developed from diverse structural organic compounds can be applied to any new query compound for data gap filling.
土壤无脊椎动物是陆地生态系统和整体土壤质量的杰出生物指标，考虑到它们与其他土壤质量指标相比具有较高的敏感性。在本研究中，从 ECOTOX 数据库（cfpub.epa.gov/ecotox）中整理了针对土壤无脊椎动物 Folsomia candida（C. name：Springtail）（n = 45）的可用土壤生态毒性数据（pEC50），并使用 2D 描述符进行 QSAR 分析。基于遗传算法选择的特征构建了四个偏最小二乘（PLS）模型，然后通过最佳子集选择进行了分析。然后，将这四个模型用作 Intelligent Consensus Predictor 版本 1.2（PLS 版本）的输入，以获得最终的共识预测，方法是从四个“合格”的单个模型中（化合物-wise）选择最佳预测。根据 OECD 标准，共识预测的内部和外部验证指标均平衡且在可接受范围内。与之前为此终点开发的模型相比，共识模型表现更好。还使用化学读通方法进行了预测，其外部验证指标值甚至优于共识预测。从 QSAR 模型中选择的特征表明，分子量和存在二硫代磷酸酯基团、电子供体基团和多卤代取代对土壤生态毒性有重大影响。因此，可以通过这些特征对有机化学品的土壤生态毒理学风险进行优先排序。可以将从不同结构有机化合物开发的模型应用于任何新的查询化合物，以填补数据空白。
