BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation

TL;DR

BatmanNet is a novel bi-branch masked graph transformer autoencoder that effectively learns molecular representations by reconstructing missing nodes and edges, leading to state-of-the-art results in drug discovery tasks.

Contribution

The paper introduces BatmanNet, a simple yet effective self-supervised model with dual autoencoders for local and global molecular structure learning, improving over complex existing methods.

Findings

Achieves state-of-the-art results on 13 benchmark datasets.

Effectively captures molecular structure and semantic information.

Improves performance in multiple drug discovery tasks.

Abstract

Although substantial efforts have been made using graph neural networks (GNNs) for AI-driven drug discovery (AIDD), effective molecular representation learning remains an open challenge, especially in the case of insufficient labeled molecules. Recent studies suggest that big GNN models pre-trained by self-supervised learning on unlabeled datasets enable better transfer performance in downstream molecular property prediction tasks. However, the approaches in these studies require multiple complex self-supervised tasks and large-scale datasets, which are time-consuming, computationally expensive, and difficult to pre-train end-to-end. Here, we design a simple yet effective self-supervised strategy to simultaneously learn local and global information about molecules, and further propose a novel bi-branch masked graph transformer autoencoder (BatmanNet) to learn molecular representations. BatmanNet features two tailored complementary and asymmetric graph autoencoders to reconstruct the missing nodes and edges, respectively, from a masked molecular graph. With this design, BatmanNet can effectively capture the underlying structure and semantic information of molecules, thus improving the performance of molecular representation. BatmanNet achieves state-of-the-art results for multiple drug discovery tasks, including molecular properties prediction, drug-drug interaction, and drug-target interaction, on 13 benchmark datasets, demonstrating its great potential and superiority in molecular representation learning.