Ordinal Classification Using Comparative Molecular Field Analysis

详细信息    查看全文

• 作者：Takanori Ohgaru ; Ryo Shimizu ; Kousuke Okamoto ; Masaya Kawase ; Yuko Shirakuni ; Rika Nishikiori ; Tatsuya Takagi
• 刊名：Journal of Chemical Information and Modeling
• 出版年：2008
• 出版时间：January 2008
• 年：2008
• 卷：48
• 期：1
• 页码：207 - 212
• 全文大小：246K
• 年卷期：v.48,no.1(January 2008)
• ISSN：1549-960X

文摘

Comparative Molecular Field Analysis (CoMFA) is most widely used as one of the 3-dimensional QSAR(3D-QSAR) methods to identify the relationship between chemical structure and biological activity.Conventional CoMFA requires at least 3 orders of experimental data, such as IC₅₀ and K_i, to obtain a goodmodel, although practically there are many screening assays where biological activity is measured only bya rating scale. Hence, rating classification-oriented CoMFA coupled with ordinal logistic regression hasbeen developed, and its predictive ability and 3D graphical analysis ability have been investigated. As aresult, this novel CoMFA (Logistic CoMFA) has been found to be more robust than conventional CoMFAsin both predictive and 3D graphical analysis abilities. Furthermore, Logistic CoMFA is useful since it canprovide the probability of each rank.