Language selection

Government of Canada / Gouvernement du Canada

Search

Protein sequence generation using denoising probabilistic diffusion model

From National Research Council Canada

DOIResolve DOI: https://doi.org/10.1007/978-3-031-82481-4_5
AuthorSearch for: ; Search for: ORCID identifier: https://orcid.org/0000-0001-8668-0710; Search for: 1ORCID identifier: https://orcid.org/0000-0001-6515-2556; Search for: ORCID identifier: https://orcid.org/0000-0003-1914-5077
Affiliation
  1. National Research Council of Canada. Digital Technologies
FormatText, Book Chapter
Conference10th International Conference on Machine Learning, Optimization, and Data Science, LOD 2024, September 22 – 25, 2024, Castiglione della Pescaia, Italy
Subjectdiffusion models; protein sequence; generative models; autoencoder; Fréchet distance
Abstract
In recent years, the need to rapidly develop vaccines and therapeutic proteins to combat viral outbreaks has highlighted the importance of innovation. This study explores the application of diffusion models in de novo protein sequence synthesis. We present a method wherein an autoencoder is employed to reduce input dimensionality, facilitating subsequent training of the diffusion model on latent vectors. Hyperparameter optimisation through grid search enhances model performance. Evaluation metrics include accuracy for autoencoders and Fréchet distance, density, and coverage for diffusion models. Results indicate that the proposed method outperformed existing state-of-the-art methodologies such as ProteinGAN. These findings highlight the efficacy of diffusion models in the generation of de novo amino acid sequences, offering promising avenues for protein engineering and drug development.
Publication date
PublisherSpringer, Cham
In
  • Machine Learning, Optimization, and Data Science, LOD 2024, Revised Selected Papers, Part I (4 March 2025): 58–72.
Series
  • Lecture Notes in Computer Science 15508.
LanguageEnglish
Peer reviewedYes
Export citationExport as RIS
Report a correctionReport a correction (opens in a new tab)
Record identifiercf19a6e3-d511-49cf-aece-79a4e3bb1b96
Record created2025-04-14
Record modified2025-04-16
Date modified: