Virtual screening with support vector machines and structure kernels

TL;DR

This paper discusses the application of support vector machines and novel structure kernels for virtual screening in chemoinformatics, enabling direct comparison of molecular structures without explicit vectorization, showing promising results in toxicity and activity prediction.

Contribution

It introduces new structure kernels for molecules that allow direct structural comparison, enhancing virtual screening methods in chemoinformatics.

Findings

Support vector machines perform well in molecular classification tasks.

New structure kernels improve direct comparison of 2D/3D molecular structures.

Applications show relevance in toxicity and structure-activity relationship predictions.

Abstract

Support vector machines and kernel methods have recently gained considerable attention in chemoinformatics. They offer generally good performance for problems of supervised classification or regression, and provide a flexible and computationally efficient framework to include relevant information and prior knowledge about the data and problems to be handled. In particular, with kernel methods molecules do not need to be represented and stored explicitly as vectors or fingerprints, but only to be compared to each other through a comparison function technically called a kernel. While classical kernels can be used to compare vector or fingerprint representations of molecules, completely new kernels were developed in the recent years to directly compare the 2D or 3D structures of molecules, without the need for an explicit vectorization step through the extraction of molecular descriptors. While still in their infancy, these approaches have already demonstrated their relevance on several toxicity prediction and structure-activity relationship problems.