环境化合物降解预测模型的研究

为建立化合物降解的计算机预测模型,确定降解和非降解化合物显然不同的参数.选择389个有机分子作为数据集,选其中312个为训练集,其余77个为验证集,每个分子计算195个分子参数,分别采用逐步判别法和主成分分析法建模,并用外部验证集验证模型的预测能力.结果:逐步判别法分析结果中,训练集的降解和非降解化合物的正确率分别为90.6%和69.5%;验证集的降解和非降解化合物的正确率分别为83.9%和63.6%.主成分分析结果在测试集中,降解和非降解化合物的正确率分别为80.4%和31.8%.验证集的降解化合物和非降解化合物的正确率分别为67.9%和50.0%.因此,采用逐步判别法模拟而建立的数学模型,可作为预测化合物降解的模型.以卜研究可以为预测有机物降解提供参考.

A research of prediction model of degradation of environmental compounds

I In order to discriminate degradable compounds and non-degradable compounds,as well as to determine their differences in structure,the authors have built a datasets composed of 389 diverse compounds from database.In the datasets,311 compounds were served as training sets and the rest 78 compounds were test sets.For each molecule,195 molecular indices were calculated.The stepwise discriminant analysis(SDA) method and the principal component analysis(PCA) were used for building the degradation model, and the...