Binary Classification of CNS and PNS Drugs

摘要

Stable classification predictive models of 626 drugs acting on the central (CNS) and peripheral (PNS) nervous systems were constructed based on linear discriminant analysis, logistic regression, random forest, and support vector machine methods with physicochemical descriptors characterizing the steric factors, electrostatic interactions, and H-bonding features. Internal cross-validations demonstrated that these models possessed satisfactory statistical properties.