APPLICATION OF SUPPORT VECTOR MACHINES IN VIRTUAL SCREENING

Sanghamitra Bandyopadhyay,Soumi Sengupta

doi:10.34040/ijcb.1.1.2012.20

Sanghamitra Bandyopadhyay, Soumi Sengupta

Open Access

https://doi.org/10.34040/ijcb.1.1.2012.20

Copy DOI

Abstract

Traditionally drug discovery has been a labor intensive effort, since it is difficult to identify a possible drug candidate from an extremely large small molecule library for any given target. Most of the small molecules fail to show any activity against the target because of electrochemical, structural and other incompatibilities. Virtual screening is an in-silico approach to identify drug candidates which are unlikely to show any activity against a given target, thus reducing an enormous amount of experimentation which is most likely to end up as failures. Important approaches in virtual screening have been through docking studies and using classification techniques. Support vector machines based classifiers, based on the principles of statistical learning theory have found several applications in virtual screening. In this paper, first the theory and main principles of SVM are briefly outlined. Thereafter a few successful applications of SVM in virtual screening have been discussed. It further underlines the pitfalls of the existing approaches and highlights the area which needs further contribution to improve the state of the art for application of SVM in virtual screening.

Highlights

Rational drug design is a focused approach to aid traditional drug discovery to reduce experimental cost and time
Several approaches used for virtual screening includes Hansch analysis, Free-Wilson analysis, Hansch FreeWilson mixed approach[1], [2], active site interactions[3] or de novo models[4], [5], 3D-pharmacophore based design[6], comparative molecular field analysis Comparative Molecular Field Analysis (CoMFA)[7], [8] and molecular docking[9], [10]
In the present article we would emphasize on the use of support vector machines (SVM) for these virtual screening approaches

Summary

INTRODUCTION

Rational drug design is a focused approach to aid traditional drug discovery to reduce experimental cost and time. Virtual screening is basically an approach to search the whole known chemical space with the aid of computational techniques It strives to find novel molecular scaffold which can act as drug against a particular given target protein. A docking problem can be broken to basic three steps as shown in Fig. 2: (i) defining the potential drug target and identification of its active site to which the drug molecule must bind, (ii) modeling a drug like small molecule and study of its interaction with the receptor protein, and (iii) performing the conformational and orientation search to find low energy states of the system that can correlate to the original binding model. In the present article we would emphasize on the use of support vector machines (SVM) for these virtual screening approaches

SUPPORT VECTOR MACHINES

APPLICATION OF SVM IN VIRTUAL SCREENING

Findings

CONCLUSION