A novel tree kernel partial least squares for modeling the structure–activity relationship

Kernel partial least squares (KPLS) has become a popular technique for regression and classification of complex data sets, which is a nonlinear extension of linear PLS in which training samples are transformed into a feature space via a nonlinear mapping. The PLS algorithm can then be carried out in the feature space. In the present study, we attempt to develop a novel tree KPLS (TKPLS) classification algorithm by constructing an informative kernel on the basis of decision tree ensembles. The constructed tree kernel can effectively discover the similarities of samples and select informative features by variable importance ranking in the process of building the kernel. Simultaneously, TKPLS can also handle nonlinear relationships in the structure–activity relationship data by such a kernel. Finally, three data sets related to different categorical bioactivities of compounds are used to evaluate the performance of TKPLS. The results show that the TKPLS algorithm can be regarded as an alternative and promising classification technique. Copyright © 2013 John Wiley & Sons, Ltd.     

Recognition for avian influenza virus proteins based on support vector machine and linear discriminant analysis

Total 200 properties related to structural characteristics were employed to represent structures of 400 HA coded proteins of influenza virus as training samples. Some recognition models for HA proteins of avian influenza virus (AIV) were developed using support vector machine (SVM) and linear discriminant analysis (LDA). The results obtained from LDA are as follows: the identification accuracy (Ria) for training samples is 99.8% and Ria by leave one out cross validation is 99.5%. Both Ria of 99.8% for training samples and Ria of 99.3% by leave one out cross validation are obtained using SVM model, respectively. External 200 HA proteins of influenza virus were used to validate the external predictive power of the resulting model. The external Ria for them is 95.5% by LDA and 96.5% by SVM, respectively, which shows that HA proteins of AIVs are preferably recognized by SVM and LDA, and the performances by SVM are superior to those by LDA.     

In silico prediction and screening of γ‐secretase inhibitors by molecular descriptors and machine learning methods

γ‐Secretase inhibitors have been explored for the prevention and treatment of Alzheimer's disease (AD). Methods for prediction and screening of γ‐secretase inhibitors are highly desired for facilitating the design of novel therapeutic agents against AD, especially when incomplete knowledge about the mechanism and three‐dimensional structure of γ‐secretase. We explored two machine learning methods, support vector machine (SVM) and random forest (RF), to develop models for predicting γ‐secretase inhibitors of diverse structures. Quantitative analysis of the receiver operating characteristic (ROC) curve was performed to further examine and optimize the models. Especially, the Youden index (YI) was initially introduced into the ROC curve of RF so as to obtain an optimal threshold of probability for prediction. The developed models were validated by an external testing set with the prediction accuracies of SVM and RF 96.48 and 98.83% for γ‐secretase inhibitors and 98.18 and 99.27% for noninhibitors, respectively. The different feature selection methods were used to extract the physicochemical features most relevant to γ‐secretase inhibition. To the best of our knowledge, the RF model developed in this work is the first model with a broad applicability domain, based on which the virtual screening of γ‐secretase inhibitors against the ZINC database was performed, resulting in 368 potential hit candidates. © 2009 Wiley Periodicals, Inc. J Comput Chem, 2010