HeMeNet: Heterogeneous Multichannel Equivariant Network for Protein Multitask Learning

TL;DR

HeMeNet is a novel E(3) equivariant graph neural network designed for multi-task learning on 3D protein structures, improving performance by leveraging heterogeneous relationships and task-specific mechanisms across multiple biological tasks.

Contribution

The paper introduces HeMeNet, a new multi-task graph neural network that captures heterogeneous atomic relationships and enables task-specific learning for 3D protein structure analysis.

Findings

HeMeNet outperforms existing models on the Protein-MT benchmark.

Multi-task learning enhances performance across multiple protein-related tasks.

The model effectively captures heterogeneous atomic relationships in 3D structures.

Abstract

Understanding and leveraging the 3D structures of proteins is central to a variety of biological and drug discovery tasks. While deep learning has been applied successfully for structure-based protein function prediction tasks, current methods usually employ distinct training for each task. However, each of the tasks is of small size, and such a single-task strategy hinders the models' performance and generalization ability. As some labeled 3D protein datasets are biologically related, combining multi-source datasets for larger-scale multi-task learning is one way to overcome this problem. In this paper, we propose a neural network model to address multiple tasks jointly upon the input of 3D protein structures. In particular, we first construct a standard structure-based multi-task benchmark called Protein-MT, consisting of 6 biologically relevant tasks, including affinity prediction and property prediction, integrated from 4 public datasets. Then, we develop a novel graph neural network for multi-task learning, dubbed Heterogeneous Multichannel Equivariant Network (HeMeNet), which is E(3) equivariant and able to capture heterogeneous relationships between different atoms. Besides, HeMeNet can achieve task-specific learning via the task-aware readout mechanism. Extensive evaluations on our benchmark verify the effectiveness of multi-task learning, and our model generally surpasses state-of-the-art models.