Skip to main navigation Skip to search Skip to main content

Using Autoencoders to Explore the Conformational Space of the Cdc42 Protein

  • University of Massachusetts Boston

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Understanding protein structure and dynamics is essential for understanding their function. This is a challenging task due to the high complexity of the conformational landscapes of proteins and their rugged energy levels. In particular, it is important to detect highly populated regions which could correspond to intermediate structures or local minima. In this work we train a neural network model on the MD simulations data to create a low-dimensional latent space. The latent space is further used to explore the protein’s conformational space. It can be used to be interpolated or extrapolated to produce new intermediate protein conformations that might not have been previously seen. The latent space visualization also assists in visualizing the conformational path of the respective proteins. We compare the performance of a linear autoencoder and a variational autoencoder and discuss their advantages and shortcomings for exploring the pathways of the Cdc42 protein.

Original languageEnglish
Title of host publicationComputational Structural Bioinformatics - International Workshop, CSBW 2024, Proceedings
EditorsNurit Haspel, Kevin Molloy
PublisherSpringer Science and Business Media Deutschland GmbH
Pages45-57
Number of pages13
ISBN (Print)9783031854347
DOIs
StatePublished - 2025
EventComputational Structural Bioinformatics Workshop, CMSB 2024 - Boston, United States
Duration: Nov 16 2024Nov 16 2024

Publication series

NameCommunications in Computer and Information Science
Volume2396 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

ConferenceComputational Structural Bioinformatics Workshop, CMSB 2024
Country/TerritoryUnited States
CityBoston
Period11/16/2411/16/24

ASJC Scopus Subject Areas

  • General Computer Science
  • General Mathematics

Keywords

  • Autoencoders
  • Cdc42
  • MD simulations
  • Protein conformational search

Fingerprint

Dive into the research topics of 'Using Autoencoders to Explore the Conformational Space of the Cdc42 Protein'. Together they form a unique fingerprint.

Cite this