Molecular Docking via Weighted Subgraph Isomorphism on Quantum Annealers

2024-04-19

arXiv.org

AI Summary

This work addresses the NP-hard conformational search problem in molecular docking by proposing, for the first time, a quantum optimization framework based on weighted subgraph isomorphism. The flexible ligand is modeled as a geometry-aware graph, while the protein binding pocket is discretized into a 3D weighted spatial grid; their matching is formalized as a weighted subgraph isomorphism problem and encoded into a Quadratic Unconstrained Binary Optimization (QUBO) model compatible with D-Wave quantum annealers. The method integrates graph representation learning with quantum optimization, enabling a paradigm shift from classical sampling-based docking to quantum-native modeling. Experimental results demonstrate that the approach achieves docking search performance comparable to classical simulated annealing on small-molecule benchmarks and—critically—provides the first experimental validation of quantum annealing for molecular docking on real quantum hardware. This work establishes a novel pathway for leveraging quantum computing in computer-aided drug discovery.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Combinatorial Optimization
• Constraint Satisfaction and Optimization: Search

Application Category

• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Web Mining and Content Analysis: Interdisciplinary science discovery with web data mining

Abstract

Molecular docking is an essential step in the drug discovery process involving the detection of three-dimensional poses of a ligand inside the active site of the protein. In this paper, we address the Molecular Docking search phase by formulating the problem in QUBO terms, suitable for an annealing approach. We propose a problem formulation as a weighted subgraph isomorphism between the ligand graph and the grid of the target protein pocket. In particular, we applied a graph representation to the ligand embedding all the geometrical properties of the molecule including its flexibility, and we created a weighted spatial grid to the 3D space region inside the pocket. Results and performance obtained with quantum annealers are compared with classical simulated annealing solvers.

Problem

• Molecular docking optimization via quantum annealing.
• Weighted subgraph isomorphism for ligand-protein interaction.
• Comparison of quantum and classical annealing solvers.

Innovation

• Quantum annealing for molecular docking
• Weighted subgraph isomorphism approach
• QUBO formulation in drug discovery