Literature Review: Graph Kernels in Chemoinformatics

TL;DR

This review introduces graph kernels and their application in chemoinformatics, highlighting their role in molecular property inference and drug design, while noting the emergence of alternative methods like graph neural networks.

Contribution

It provides a comprehensive overview of graph kernels in chemoinformatics, focusing on their use for molecular similarity and property prediction, and discusses recent developments.

Findings

Graph kernels enable molecular similarity assessment.

They facilitate property inference in chemoinformatics.

Alternative methods like graph neural networks are emerging.

Abstract

The purpose of this review is to introduce the reader to graph kernels and the corresponding literature, with an emphasis on those with direct application to chemoinformatics. Graph kernels are functions that allow for the inference of properties of molecules and compounds, which can help with tasks such as finding suitable compounds in drug design. The use of kernel methods is but one particular way two quantify similarity between graphs. We restrict our discussion to this one method, although popular alternatives have emerged in recent years, most notably graph neural networks.