Does the accounting of the local symmetry fragments in quasi-SMILES improve the predictive potential of the QSAR models of toxicity toward tadpoles?

Models of toxicity to tadpoles have been developed as single parameters based on special descriptors which are sums of correlation weights, molecular features, and experimental conditions. This information is presented by quasi-SMILES. Fragments of local symmetry (FLS) are involved in the development of the model and the use of FLS correlation weights improves their predictive potential. In addition, the index of ideality correlation (<i>IIC</i>) and correlation intensity index (<i>CII</i>) are compared. These two potential predictive criteria were tested in models built through Monte Carlo optimization. The <i>CII</i> was more effective than <i>IIC</i> for the models considered here.

针对蝌蚪毒性的单参数模型已构建，此类模型依托特殊描述符搭建，这类描述符为相关权重、分子特征与实验条件的总和。此类信息以准SMILES（quasi-SMILES）格式呈现。局部对称性片段（Fragments of local symmetry，FLS）被应用于模型构建过程中，使用FLS相关权重可提升模型的预测性能。此外，本研究还对理想相关性指数（index of ideality correlation，IIC）与相关强度指数（correlation intensity index，CII）进行了对比。这两种潜在预测准则均在通过蒙特卡洛（Monte Carlo）优化构建的模型中得到验证。针对本研究涉及的模型而言，CII的表现优于IIC。