Beyond the Scope of Free-Wilson Analysis. 2: Can Distance Encoded R-Group Fingerprints Provide Interpretable Nonlinear Models?

详细信息    查看全文

• 作者：Mats Eriksson ; Hongming Chen ; Lars Carlsson ; J. Willem M. Nissink ; John G. Cumming ; Ingemar Nilsson
• 刊名：Journal of Chemical Information and Modeling
• 出版年：2014
• 出版时间：April 28, 2014
• 年：2014
• 卷：54
• 期：4
• 页码：1117-1128
• 全文大小：509K
• 年卷期：v.54,no.4(April 28, 2014)
• ISSN：1549-960X

文摘

In a recent study, we presented a novel quantitative-structure鈥揳ctivity-relationship (QSAR) approach, combining R-group signatures and nonlinear support-vector-machines (SVM), to build interpretable local models for congeneric compound sets. Here, we outline further refinements in the fingerprint scheme for the purpose of analyzing and visualizing structure鈥揳ctivity relationships (SAR). The concept of distance encoded R-group signature descriptors is introduced, and we explore the influence of different signature encoding schemes on both interpretability and predictive power of the SVM models using ten public data sets. The R-group and atomic gradients provide a way to interpret SVM models and enable detailed analysis of structure鈥揳ctivity relationships within substituent groups. We discuss applications of the method and show how it can be used to analyze nonadditive SAR and provide intuitive and powerful SAR visualizations.