Prediction of Protein Three-dimensional Structures via a Hardware-Executable Quantum Computing Framework

2025-06-27

AI Summary

Accurate 3D structure prediction of short peptides remains challenging due to their high conformational flexibility, rendering classical methods ineffective. Method: This work introduces the first end-to-end quantum computing framework executable on real quantum hardware. It formulates peptide conformational search as an energy minimization problem and establishes a full mapping from atomic coordinates to quantum processor: amino acid connectivity is encoded via a tetrahedral lattice model; stereochemical, geometric, and chiral constraints are integrated to construct a sparse Pauli Hamiltonian; and a two-stage VQE optimization architecture is designed. Contribution/Results: Experimental validation on the IBM-Cleveland Clinic quantum processor demonstrates superior performance over AlphaFold3 on 23 short peptides and 7 therapeutically relevant fragments from PDBbind, achieving lower RMSD and improved molecular docking accuracy. This constitutes the first empirical demonstration of engineering feasibility and practical advantage of real quantum devices for biomolecular structure prediction.

Technology Category

• Machine Learning: Quantum Machine Learning
• Search and Optimization: Learning to Search
• Computer Vision: 3D Computer Vision

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Accurate prediction of protein active site structures remains a central challenge in structural biology, particularly for short and flexible peptide fragments where conventional methods often fail. Here, we present a quantum computing framework specifically developed for utility-level quantum processors to address this problem. Starting from an amino acid sequence, we formulate the structure prediction task as a ground-state energy minimization problem using the Variational Quantum Eigensolver (VQE). Amino acid connectivity is encoded on a tetrahedral lattice model, and structural constraints-including steric, geometric, and chirality terms-are mapped into a problem-specific Hamiltonian expressed as sparse Pauli operators. The optimization is executed via a two-stage architecture separating energy estimation and measurement decoding, allowing noise mitigation under realistic quantum device conditions. We evaluate the framework on 23 randomly selected real protein fragments from the PDBbind dataset, as well as 7 real fragments from proteins with therapeutic potential, and run the experiments on the IBM-Cleveland Clinic quantum processor. Structural predictions are benchmarked against AlphaFold3 (AF3) using identical postprocessing and docking procedures. Our quantum method outperformed AF3 in both RMSD (Root-Mean-Square Deviation) and docking efficacy. This work demonstrates, for the first time, a complete end-to-end pipeline for biologically relevant structure prediction on real quantum hardware, highlighting its engineering feasibility and practical advantage over existing classical and deep learning approaches.

Problem

• Predict protein 3D structures using quantum computing
• Overcome limitations in active site prediction for peptides
• Benchmark quantum method against AlphaFold3 for accuracy

Innovation

• Quantum computing framework for protein structure prediction
• VQE for ground-state energy minimization problem
• Two-stage architecture for noise mitigation