A study on prediction of the bio-toxicity of substituted benzene based on artificial neural network

作者：Gao DW; Wang P^*; Liang H; Peng YZ

来源：Journal of Environmental Science and Health - Part B: Pesticides, Food Contaminants, and Agricultural Wastes , 2003, 38(5): 571-579.

DOI：10.1081/PFC-120023515

• substituted benzene
• yeast Saccharomyces cerevisiae
• bio-toxicity
• autocoffelation descriptor
• quantitative structure-activity relationship

Quantitative Structure-Activity Relationship (QSAR) between the bio-toxicity of seventy-eight kinds of substituted benzene chemicals to yeast Saccharomyces cerevisiae (1g(1/C-miz)) and the components of vertex degree autocorrelation vectors (values of A, B, C and D) was studied by using the software of Artificial Neural Network (ANN). The key factors of the autocorrelation descriptors for the 1g (1/C-miz) value of yeast Saccharomyces cerevisiae, A [0], A [1], C [3], C [5] and D [3] were selected from twenty-four descriptors, and were explained theoretically in this paper. The QSAR-ANN model has been used to predict. the bio-toxicity of twenty-three substituted benzene chemicals. The correlation between C-miz and LC50 was also discussed, and the liner correlation equation between them was established.

• 出版日期2003
• 单位哈尔滨工业大学; 东北林业大学; 北京工业大学