Simulating and predicting entangled DNA contours via deep learning

Maged F. Serag*, Satoshi Habuchi

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

We developed a computational model to simulate contours of entangled lambda DNA. These simulations were used to generate super-resolution DNA images for training a deep neural network (ANNA-PALM) to reconstruct DNA contours from localization images. Our approach enabled reliable contour prediction from microscopy images captured at fast time scale. Analysis of experimental data revealed bright and dark DNA segments, potentially linked to local microviscosity effects imposed by entanglement loci. Our integrated computational modeling and deep learning workflow can provide mapping of topological constraints on polymer motion in diverse materials.

Original languageEnglish (US)
Title of host publicationEmerging Topics in Artificial Intelligence, ETAI 2024
EditorsGiovanni Volpe, Joana B. Pereira, Daniel Brunner, Aydogan Ozcan
PublisherSPIE
ISBN (Electronic)9781510678965
DOIs
StatePublished - 2024
Event2024 Emerging Topics in Artificial Intelligence, ETAI 2024 - San Diego, United States
Duration: Aug 18 2024Aug 23 2024

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume13118
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference2024 Emerging Topics in Artificial Intelligence, ETAI 2024
Country/TerritoryUnited States
CitySan Diego
Period08/18/2408/23/24

Keywords

  • Deep learning
  • DNA
  • Dynamics
  • Entanglement
  • Single-Molecule Localization microscopy

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Simulating and predicting entangled DNA contours via deep learning'. Together they form a unique fingerprint.

Cite this