QFold: quantum walks and deep learning to solve protein folding



Downloads per month over past year

Moreno Casares, Pablo Antonio and Campos, Roberto and Martín Delgado, Miguel Ángel (2022) QFold: quantum walks and deep learning to solve protein folding. Quantum science and technology, 7 (2). ISSN 2058-9565

[thumbnail of Martín Delgado Alcántara MÁ 130 Preprint.pdf]

Official URL: http://dx.doi.org/10.1088/2058-9565/ac4f2f


We develop quantum computational tools to predict the 3D structure of proteins, one of the most important problems in current biochemical research. 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 IBMQ Casablanca quantum system.

Item Type:Article
Additional Information:

© IOP Publishing Ltd 2022
PAMC and RC contributed equally to this work. We would like to thank kind advice from Jaime Sevilla on von Mises distribution and statistical t-tests, Alvaro Martinez del Pozo and Antonio Rey on protein folding, Andrew W Senior on minor details of his AlphaFold article, Carmen Recio, Juan Gomez, Juan Cruz Benito, Kevin Krsulich and Maddy Todd on the usage of Qiskit, and Jessica Lemieux and the late David Poulin on aspects of the quantum Metropolis algorithm. We acknowledge the access to advanced services provided by the IBM Quantum Researchers Program. We also thank Quasar Science for facilitating the access to the AWS resources. We acknowledge financial support from the Spanish MINECO Grants MINECO/FEDER Projects FIS 2017-91460-EXP, PGC2018-099169-B-I00 FIS-2018 and from CAM/FEDER Project No. S2018/TCS-4342 (QUITEMAD-CM). The research of MAM-D has been partially supported by the U.S. Army Research Office through Grant No. W911NF-14-1-0103. PAMC thanks the support of a MECD Grant FPU17/03620, and RC the support of a CAM Grant IND2019/TIC17146.

Uncontrolled Keywords:Structure prediction
Subjects:Sciences > Physics
ID Code:71548
Deposited On:19 Apr 2022 16:28
Last Modified:20 Apr 2022 07:47

Origin of downloads

Repository Staff Only: item control page