QFold: Quantum Walks and Deep Learning to Solve Protein Folding

TL;DR

QFold is a hybrid quantum-classical algorithm that leverages quantum walks and deep learning to predict protein structures more efficiently, demonstrating a polynomial quantum advantage and practical implementation on IBMQ hardware.

Contribution

It introduces QFold, a scalable quantum algorithm for protein folding that avoids lattice simplifications and combines quantum walks with deep learning.

Findings

QFold shows a polynomial quantum advantage over classical methods.

Successful implementation of quantum Metropolis on IBMQ Casablanca.

QFold does not require lattice model simplifications.

Abstract

Predicting the 3D structure of proteins is one of the most important problems in current biochemical research. In this article, we explain how to combine recent deep learning advances with the well known technique of quantum walks applied to a Metropolis algorithm. The result, QFold, is a fully scalable hybrid quantum algorithm that, in contrast to previous quantum approaches, does not require a lattice model simplification and instead relies on the much more realistic assumption of parameterization in terms of torsion angles of the amino acids. We compare it with its classical analog for different annealing schedules and find a polynomial quantum advantage, and implement a minimal realization of the quantum Metropolis in the IBMQ Casablanca quantum system.