ProFSA: Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment

TL;DR

ProFSA introduces a self-supervised pocket pretraining method that simulates ligand-receptor interactions using protein fragments and pretrained small molecule representations, significantly improving various biomedical prediction tasks.

Contribution

The paper presents a novel contrastive pretraining approach for pocket representations that leverages high-resolution protein structures and simulated ligand interactions, addressing data scarcity issues.

Findings

Achieves state-of-the-art results in druggability prediction.

Outperforms existing pretraining methods by a large margin.

Demonstrates effective use of protein structure databases for interaction modeling.

Abstract

Pocket representations play a vital role in various biomedical applications, such as druggability estimation, ligand affinity prediction, and de novo drug design. While existing geometric features and pretrained representations have demonstrated promising results, they usually treat pockets independent of ligands, neglecting the fundamental interactions between them. However, the limited pocket-ligand complex structures available in the PDB database (less than 100 thousand non-redundant pairs) hampers large-scale pretraining endeavors for interaction modeling. To address this constraint, we propose a novel pocket pretraining approach that leverages knowledge from high-resolution atomic protein structures, assisted by highly effective pretrained small molecule representations. By segmenting protein structures into drug-like fragments and their corresponding pockets, we obtain a reasonable simulation of ligand-receptor interactions, resulting in the generation of over 5 million complexes. Subsequently, the pocket encoder is trained in a contrastive manner to align with the representation of pseudo-ligand furnished by some pretrained small molecule encoders. Our method, named ProFSA, achieves state-of-the-art performance across various tasks, including pocket druggability prediction, pocket matching, and ligand binding affinity prediction. Notably, ProFSA surpasses other pretraining methods by a substantial margin. Moreover, our work opens up a new avenue for mitigating the scarcity of protein-ligand complex data through the utilization of high-quality and diverse protein structure databases.