Assessing the potential of deep learning for protein-ligand docking

TL;DR

This paper introduces PoseBench, a comprehensive benchmark for evaluating deep learning methods in protein-ligand docking, highlighting current strengths and challenges in the field for real-world biomedical applications.

Contribution

The paper presents PoseBench, the first systematic benchmark for assessing DL methods on apo-to-holo docking and multi-ligand prediction, including new datasets and evaluation protocols.

Findings

DL co-folding methods outperform traditional docking algorithms.

AlphaFold 3 struggles with novel binding poses.

Sensitivity of DL methods to multiple sequence alignments.

Abstract

The effects of ligand binding on protein structures and their in vivo functions carry numerous implications for modern biomedical research and biotechnology development efforts such as drug discovery. Although several deep learning (DL) methods and benchmarks designed for protein-ligand docking have recently been introduced, to date no prior works have systematically studied the behavior of the latest docking and structure prediction methods within the broadly applicable context of (1) using predicted (apo) protein structures for docking (e.g., for applicability to new proteins); (2) binding multiple (cofactor) ligands concurrently to a given target protein (e.g., for enzyme design); and (3) having no prior knowledge of binding pockets (e.g., for generalization to unknown pockets). To enable a deeper understanding of docking methods' real-world utility, we introduce PoseBench, the first comprehensive benchmark for broadly applicable protein-ligand docking. PoseBench enables researchers to rigorously and systematically evaluate DL methods for apo-to-holo protein-ligand docking and protein-ligand structure prediction using both primary ligand and multi-ligand benchmark datasets, the latter of which we introduce for the first time to the DL community. Empirically, using PoseBench, we find that (1) DL co-folding methods generally outperform comparable conventional and DL docking baseline algorithms, yet popular methods such as AlphaFold 3 are still challenged by prediction targets with novel binding poses; (2) certain DL co-folding methods are highly sensitive to their input multiple sequence alignments, while others are not; and (3) DL methods struggle to strike a balance between structural accuracy and chemical specificity when predicting novel or multi-ligand protein targets. Code, data, tutorials, and benchmark results are available at https://github.com/BioinfoMachineLearning/PoseBench.