Most quantitative structure-property/activity relationships (QSPRs/QSARs) techniques involve using different programs separately for generating molecular descriptors and separately for building models based on available descriptors. Here, the capabilities of the CORAL program are evaluated. A user of the program should apply as the basis for models the representation of the molecular structure by means of the simplified molecular input-line entry system (SMILES) as well as experimental data on the endpoint of interest. The local symmetry of SMILES is a novel composition of symmetrically represented symbols, which are three ‘xyx’, four ‘xyyx’, or five symbols ‘xyzyx’. We updated our CORAL software using this optimal, new flexible descriptor, sensitive to the symmetric composition of a specific part of the molecule. Computational experiments have shown that taking account of these attributes of SMILES can improve the predictive potential of models for the mutagenicity of nitroaromatic compounds. In addition, the above computational experiments have confirmed the advantage of using the index of ideality of correlation (IIC) and the correlation intensity index (CII) for Monte Carlo optimization of the correlation weights for various attributes of SMILES, including the local symmetry. The average value of the coefficient of determination for the validation set (five different models) without fragments of local symmetry is 0.8589 ± 0.025, whereas using fragments of local symmetry improves this criterion of the predictive potential up to 0.9055 ± 0.010.

大多数定量结构-性质/活性关系 (QSPR/QSAR) 技术涉及分别使用不同的程序来生成分子描述符，并分别根据可用的描述符构建模型。这里评估了 CORAL 程序的功能。该程序的用户应通过简化的分子输入线输入系统（SMILES）以及感兴趣终点的实验数据应用分子结构表示作为模型的基础。SMILES 的局部对称性是一种新颖的对称表示符号的组合，即三个“ xyx ”、四个“ xyyx ”或五个符号“ xyzyx ”。我们使用这种最佳的、新的灵活描述符更新了 CORAL 软件，该描述符对分子特定部分的对称组成敏感。计算实验表明，考虑 SMILES 的这些属性可以提高硝基芳香族化合物致突变性模型的预测潜力。此外，上述计算实验证实了使用相关理想指数（IIC）和相关强度指数（CII）对SMILES各种属性（包括局部对称性）的相关权重进行蒙特卡罗优化的优势。没有局部对称片段的验证集（五个不同模型）的决定系数平均值为 0.8589 ± 0.025，而使用局部对称片段可将预测潜力的标准提高到 0.9055 ± 0.010。