A new Quantitative Structure-Activity Relationship model is introduced for reliable prediction of the toxicity of organic aromatic compounds based on the logarithm of 50 % growth inhibitory concentration of Tetrahymena pyriformis (log(IGC₅₀⁻¹)), which have extensive use in ecotoxicology and environmental safety applications. The largest experimental data set of log(IGC₅₀⁻¹) for 892 organic aromatic compounds is used to derive and test the new model. A core correlation based on additive variables is introduced by the number of nitro groups, carbon and halogen atoms as well as some specific polar groups and molecular weight. An improved correlation based on two non-additive correcting functions is developed for the increment of the reliability of the core correlation. The reliability of the improved correlation is tested and compared with two of the best available methods, which require complex descriptors. The predicted results for 661 and 231 of training and test sets have been confirmed by internal and external validations. The values of correlation coefficient (R²), mean error (ME), root mean squared error (RMSE), and maximum of errors (Max Error) for 661/231 of training/test aromatic compounds are 0.8442/0.7771, 0.0000/0.0149, 0.3166/0.3603, and 0.9732/0.9825, respectively, which are good results as compared to extra complex models with lower reported data. Various statistical parameters confirm the goodness-of-fit, high reliability, precision, and accuracy of the novel model.

引入了一种新的定量构效关系模型，该模型基于吡喃四膜虫生长抑制浓度为50％的对数（log（IGC ₅₀ ^-1））的对数进行了可靠的预测，该模型已广泛应用于生态毒理学和环境安全应用。log的最大实验数据集（IGC ₅₀ ^-1）用于892种有机芳香化合物的新模型的推导和测试。通过硝基，碳原子和卤素原子的数量以及某些特定的极性基团和分子量来引入基于加和变量的核心相关性。为了提高核心相关性的可靠性，开发了基于两个非相加校正函数的改进相关性。测试了改进的相关性的可靠性，并与需要复杂描述符的两种最佳可用方法进行了比较。内部和外部验证已确认661和231训练集和测试集的预测结果。相关系数的值（R ²），平均误差（ME），均方根误差（RMSE）和661/231训练/测试芳香族化合物的最大误差（Max Error）为0.8442 / 0.7771、0.0000 / 0.0149、0.3166 / 0.3603和0.9732 /分别为0.9825，与报告数据较少的额外复杂模型相比，这是一个很好的结果。各种统计参数证实了新模型的拟合优度，高可靠性，精度和准确性。