Comparison of Different Classification Methods Applied to a Mode of Toxic Action Data Set

Simon Spycher, Monika Nendza, Johann Gasteiger

doi:10.1002/qsar.200430877

Comparison of Different Classification Methods Applied to a Mode of Toxic Action Data Set

DOI Web Site Web Site 被引用文献1件

書誌事項

公開日: 2004-11

権利情報

http://onlinelibrary.wiley.com/termsAndConditions#vor

DOI

10.1002/qsar.200430877

公開者: Wiley

この論文をさがす

CiNii Books

説明

<jats:title>Abstract</jats:title><jats:p>Successful discrimination of compounds by mode of toxic action (MOA) is a prerequisite for process‐based quantitative structure‐activity relationship (QSAR) approaches. A data set of 115 compounds comprising nine MOA classes and 24 descriptors has been studied with several classification methods: multinomial logistic regression (multinom), linear discriminant analysis (LDA), partial least squares (PLS), and counter‐propagation neural networks (CPG NN). Variables were selected with stepwise methods and with a genetic algorithm (GA) for the CPG NN. Five‐fold cross‐validation was used for validating the models and the advantages and disadvantages of this validation method are critically discussed. Without variable selection the predictive power of the models ranges between 51% and 53% cross‐validated overall correct classification. With appropriate parameter selection the predictive power slightly increased to 52–59%.</jats:p>