Zhao Chunyan, Boriani Elena, Chana Antonio, Roncaglioni Alessandra, Benfenati Emilio
Department of Chemistry, Lanzhou University, Lanzhou, China.
Chemosphere. 2008 Dec;73(11):1701-7. doi: 10.1016/j.chemosphere.2008.09.033. Epub 2008 Oct 26.
The aim was to develop a reliable and practical quantitative structure-activity relationship (QSAR) model validated by strict conditions for predicting bioconcentration factors (BCF). We built up several QSAR models starting from a large data set of 473 heterogeneous chemicals, based on multiple linear regression (MLR), radial basis function neural network (RBFNN) and support vector machine (SVM) methods. To improve the results, we also applied a hybrid model, which gave better prediction than single models. All models were statistically analysed using strict criteria, including an external test set. The outliers were also examined to understand better in which cases large errors were to be expected and to improve the predictive models. The models offer more robust tools for regulatory purposes, on the basis of the statistical results and the quality check on the input data.
目的是开发一种可靠且实用的定量构效关系（QSAR）模型，该模型通过严格条件验证以预测生物富集因子（BCF）。我们从包含473种不同化学品的大数据集出发，基于多元线性回归（MLR）、径向基函数神经网络（RBFNN）和支持向量机（SVM）方法建立了多个QSAR模型。为了改进结果，我们还应用了一种混合模型，其预测效果优于单一模型。所有模型均使用包括外部测试集在内的严格标准进行统计分析。还对异常值进行了检查，以更好地了解在哪些情况下可能会出现较大误差，并改进预测模型。基于统计结果和对输入数据的质量检查，这些模型为监管目的提供了更强大的工具。
