Classification of the Carcinogenicity of N-Nitroso Compounds Based on Support Vector Machines and Linear Discriminant Analysis

详细信息    查看全文

• 作者：Feng Luan ; Ruisheng Zhang ; Chunyan Zhao ; Xiaojun Yao ; Mancang Liu ; Zhide Hu ; and Botao Fan
• 刊名：Chemical Research in Toxicology
• 出版年：2005
• 出版时间：February 2005
• 年：2005
• 卷：18
• 期：2
• 页码：198 - 203
• 全文大小：167K
• 年卷期：v.18,no.2(February 2005)
• ISSN：1520-5010

文摘

The support vector machine (SVM), as a novel type of learning machine, was used to developa classification model of carcinogenic properties of 148 N-nitroso compounds. The sevendescriptors calculated solely from the molecular structures of compounds selected by forwardstepwise linear discriminant analysis (LDA) were used as inputs of the SVM model. Theobtained results confirmed the discriminative capacity of the calculated descriptors. The resultof SVM (total accuracy of 95.2%) is better than that of LDA (total accuracy of 89.8%).