Language selection

Government of Canada / Gouvernement du Canada

Search

ProVolOne: protein volume prediction using a multi-attention, multi-resolution deep neural network and finite element analysis

From National Research Council Canada

DOIResolve DOI: https://doi.org/10.1007/978-3-031-53969-5_21
AuthorSearch for: 1ORCID identifier: https://orcid.org/0000-0001-6515-2556; Search for: ORCID identifier: https://orcid.org/0000-0003-1914-5077; Search for: ORCID identifier: https://orcid.org/0000-0002-9198-6439; Search for: ORCID identifier: https://orcid.org/0000-0002-8985-4920
Affiliation
  1. National Research Council of Canada. Digital Technologies
FormatText, Article
ConferenceThe 9th Annual Conference on Machine Learning, Optimization and Data Science, LOD 2023, September 22–26, 2023, Grasmere, UK
Subjectdeep learning; multi-attention learning; protein volume prediction; multi-resolution learning
Abstract
Protein structural properties are often determined by experimental techniques such as X-ray crystallography and nuclear magnetic resonance. However, both approaches are time-consuming and expensive. Conversely, protein amino acid sequences may be readily obtained from inexpensive high-throughput techniques, although such sequences lack structural information, which is essential for numerous applications such as gene therapy, in which maximisation of the payload, or volume, is required. This paper proposes a novel solution to volume prediction, based on deep learning and finite element analysis. We introduce a multi-attention, multi-resolution deep learning architecture that predicts protein volumes from their amino acid sequences. Experimental results demonstrate the efficiency of the ProVolOne framework.
Publication date
PublisherSpringer
In
  • Machine Learning, Optimization, and Data Science: 9th International Conference, LOD 2023, Grasmere, UK, September 22–26, 2023, Revised Selected Papers, Part I (2024): 274–287.
Series
  • Lecture Notes in Computer Science 14505.
LanguageEnglish
Peer reviewedYes
Export citationExport as RIS
Report a correctionReport a correction (opens in a new tab)
Record identifier34cfab5f-d7ab-4027-9b7a-077938310e96
Record created2024-07-03
Record modified2024-07-04
Date modified: