Language selection

Government of Canada / Gouvernement du Canada

Search

Protein structure generation using a variational autoencoder with Lévy noise and quantum graph transformer

DOIResolve DOI: https://doi.org/10.1109/IJCNN64981.2025.11227807
AuthorSearch for: 1ORCID identifier: https://orcid.org/0000-0001-6515-2556; Search for: 2; Search for: 2
Affiliation
  1. National Research Council Canada. Digital Technologies
  2. University of Ottawa
FunderSearch for: National Research Council Canada
FormatText, Article
Conference2025 International Joint Conference on Neural Networks (IJCNN), June 30 - July 5, 2025, Rome, Italy
Subjectdeep learning; machine learning; protein generation; variational autoencoder; Lévy noise; quantum graph transformer attention mechanism
Abstract
Protein generation has a wide range of applications in the design of therapeutic antibodies and the creation of new drugs. Nevertheless, it is a challenging endeavour, largely due to the complexities intrinsic to protein structures and the constraints of current generative models. The complex three-dimensional structure of proteins and the vast number of potential conformations that they can adopt present significant challenges for sampling. This paper introduces a novel variational autoencoder based on Lévy noise and a quantum graph transformer attention mechanism, which enables a more effective exploration of the conformational space. The method was applied to two protein datasets, resulting in enhanced outcomes in terms of Fréchet distance by a factor of up to 168 in comparison to a variational autoencoder using Gaussian noise and a bilinear attention mechanism.
Date published
PublisherInstitute of Electrical and Electronics Engineers
In
  • 2025 International Joint Conference on Neural Networks (IJCNN), 11227807 (14 November 2025): 1–10.
LanguageEnglish
Peer reviewedYes
Export citationExport as RIS
Report a correctionReport a correction (opens in a new tab)
Record identifiereee34fd1-b370-43a4-a371-a65b2e09d51f
Record created2026-04-17
Record modified2026-06-08

Page details

From:

Date modified: