A training algorithm for optimal margin classifiers
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
A Tutorial on Support Vector Machines for Pattern Recognition
Data Mining and Knowledge Discovery
Sparse Regression Ensembles in Infinite and Finite Hypothesis Spaces
Machine Learning
An introduction to kernel-based learning algorithms
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
The cytochrome P450 (CYP) is a superfamily of enzymes with oxidative function responsible for the metabolism of xenobiotics especially drug metabolism. CYP3A4, an extensive studied CYP isoform, plays crucial role in the metabolism of structurally diverse drugs. Furthermore, the drug-drug interaction resulted from the inhibition of CYP3A4 activity is of extreme importance for the treatment of disease and the development of new drug. In this study, using the method of the support vector machine (SVM) and three descriptors selected from the 153 descriptors we construct the models that can predict accurately the inhibitory effect of a compound on the activity of CYP3A4. By optimizing the parameters related to SVM, the cross validation correlation efficient of the model can achieve 0.71, which is higher than those of other models obtained using Artifical Neutral Network (ANN) and Partial least square (PLS) methods to our knowledge, and thus our model can present the important application in assessment of the potential toxicity of a drug as well as prediction of drug-drug interactions.