Integration of Pre-trained Protein Language Models into Geometric Deep Learning Networks

TL;DR

This paper demonstrates that integrating pre-trained protein language models into geometric deep learning networks significantly improves their performance on various biomolecular tasks, addressing data scarcity issues.

Contribution

It introduces a method to incorporate protein language model knowledge into geometric neural networks, enhancing their representation power across multiple tasks.

Findings

20% overall performance improvement over baselines

Enhanced capacity of geometric networks with language model knowledge

Generalization to complex biomolecular tasks

Abstract

Geometric deep learning has recently achieved great success in non-Euclidean domains, and learning on 3D structures of large biomolecules is emerging as a distinct research area. However, its efficacy is largely constrained due to the limited quantity of structural data. Meanwhile, protein language models trained on substantial 1D sequences have shown burgeoning capabilities with scale in a broad range of applications. Several previous studies consider combining these different protein modalities to promote the representation power of geometric neural networks, but fail to present a comprehensive understanding of their benefits. In this work, we integrate the knowledge learned by well-trained protein language models into several state-of-the-art geometric networks and evaluate a variety of protein representation learning benchmarks, including protein-protein interface prediction, model quality assessment, protein-protein rigid-body docking, and binding affinity prediction. Our findings show an overall improvement of 20% over baselines. Strong evidence indicates that the incorporation of protein language models' knowledge enhances geometric networks' capacity by a significant margin and can be generalized to complex tasks.