One-step Structure Prediction and Screening for Protein-Ligand Complexes using Multi-Task Geometric Deep Learning

TL;DR

This paper introduces LigPose, a multi-task geometric deep learning model that predicts protein-ligand complex structures and binding affinity in a single step, surpassing traditional docking methods in accuracy and efficiency.

Contribution

The novel LigPose model integrates structure prediction and screening into one unified framework using graph-based deep learning, eliminating the need for docking procedures.

Findings

LigPose achieves state-of-the-art accuracy in structure prediction.

The model significantly improves screening efficiency.

It demonstrates robust performance across major drug research tasks.

Abstract

Understanding the structure of the protein-ligand complex is crucial to drug development. Existing virtual structure measurement and screening methods are dominated by docking and its derived methods combined with deep learning. However, the sampling and scoring methodology have largely restricted the accuracy and efficiency. Here, we show that these two fundamental tasks can be accurately tackled with a single model, namely LigPose, based on multi-task geometric deep learning. By representing the ligand and the protein pair as a graph, LigPose directly optimizes the three-dimensional structure of the complex, with the learning of binding strength and atomic interactions as auxiliary tasks, enabling its one-step prediction ability without docking tools. Extensive experiments show LigPose achieved state-of-the-art performance on major tasks in drug research. Its considerable improvements indicate a promising paradigm of AI-based pipeline for drug development.