Prediction of Activity Cliffs Using Support Vector Machines

详细信息    查看全文

• 作者：Kathrin Heikamp ; Xiaoying Hu ; Aixia Yan ; J眉rgen Bajorath
• 刊名：Journal of Chemical Information and Modeling
• 出版年：2012
• 出版时间：September 24, 2012
• 年：2012
• 卷：52
• 期：9
• 页码：2354-2365
• 全文大小：445K
• 年卷期：v.52,no.9(September 24, 2012)
• ISSN：1549-960X

文摘

Activity cliffs are formed by pairs of structurally similar compounds that act against the same target but display a significant difference in potency. Such activity cliffs are the most prominent features of activity landscapes of compound data sets and a primary focal point of structure鈥揳ctivity relationship (SAR) analysis. The search for activity cliffs in various compound sets has been the topic of a number of previous investigations. So far, activity cliff analysis has concentrated on data mining for activity cliffs and on their graphical representation and has thus been descriptive in nature. By contrast, approaches for activity cliff prediction are currently not available. We have derived support vector machine (SVM) models to successfully predict activity cliffs. A key aspect of the approach has been the design of new kernels to enable SVM classification on the basis of molecule pairs, rather than individual compounds. In test calculations on different data sets, activity cliffs have been accurately predicted using specifically designed structural representations and kernel functions.