Prediction of milk/plasma drug concentration (M/P) ratio using support vector machine (SVM) method

Abstract

Purpose: Development of reliable computational models to predict/classify milk-to-plasma (M/P) drug concentration ratio remains a challenging object. Support vector machine (SVM) method, as a new algorithm, was constructed to distinguish the potential risk of drugs to nursing infants.

Methods: Each drug was represented by a large pool of descriptors, of which five were found to be most important for constructing the predictive models. Next, two classification models, linear discriminant analysis (LDA) and SVM, were developed with bootstrapping validation based on the selected molecular descriptors.

Results and conclusions: The classification accuracy of training set and test set for SVM was 90.63 and 90.00%, respectively. The total accuracy for SVM was 90.48%, which was higher than that of LDA (77.78%). Comparison of the two methods shows that the performance of SVM was better than that of LDA, which implies that the SVM method is an effective tool in evaluating the risk of drugs when experimental M/P ratios have not been investigated.