Recent Developments in GNNs for Drug Discovery

TL;DR

This paper reviews recent advances in Graph Neural Networks for drug discovery, highlighting their applications in molecule generation, property prediction, and interaction analysis, and discusses datasets and future trends.

Contribution

It provides a comprehensive overview of recent GNN models, their applications, and benchmark datasets in computational drug discovery, emphasizing current capabilities and future directions.

Findings

GNNs effectively model complex molecular structures.

Recent GNN models improve drug property prediction accuracy.

Benchmark datasets facilitate standardized evaluation of GNN methods.

Abstract

In this paper, we review recent developments and the role of Graph Neural Networks (GNNs) in computational drug discovery, including molecule generation, molecular property prediction, and drug-drug interaction prediction. By summarizing the most recent developments in this area, we underscore the capabilities of GNNs to comprehend intricate molecular patterns, while exploring both their current and prospective applications. We initiate our discussion by examining various molecular representations, followed by detailed discussions and categorization of existing GNN models based on their input types and downstream application tasks. We also collect a list of commonly used benchmark datasets for a variety of applications. We conclude the paper with brief discussions and summarize common trends in this important research area.