QDockBank: A Dataset for Ligand Docking on Protein Fragments Predicted on Utility-Level Quantum Computers

TL;DR

QDockBank is a pioneering large-scale dataset of protein fragments generated using quantum computers, designed to advance quantum-based protein-ligand docking and benchmarking.

Contribution

It introduces the first quantum-computer-generated protein fragment dataset specifically for docking, enabling new evaluation standards in quantum structural biology.

Findings

QDockBank structures outperform AlphaFold2 and AlphaFold3 in RMSD and affinity scores.

The dataset was generated with over one million USD worth of quantum computing resources.

QDockBank establishes a new benchmark for quantum-based protein structure prediction.

Abstract

Protein structure prediction is a core challenge in computational biology, particularly for fragments within ligand-binding regions, where accurate modeling is still difficult. Quantum computing offers a novel first-principles modeling paradigm, but its application is currently limited by hardware constraints, high computational cost, and the lack of a standardized benchmarking dataset. In this work, we present QDockBank-the first large-scale protein fragment structure dataset generated entirely using utility-level quantum computers, specifically designed for protein-ligand docking tasks. QDockBank comprises 55 protein fragments extracted from ligand-binding pockets. The dataset was generated through tens of hours of execution on superconducting quantum processors, making it the first quantum-based protein structure dataset with a total computational cost exceeding one million USD. Experimental evaluations demonstrate that structures predicted by QDockBank outperform those predicted by AlphaFold2 and AlphaFold3 in terms of both RMSD and docking affinity scores. QDockBank serves as a new benchmark for evaluating quantum-based protein structure prediction.