EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Chromatin structures from integrated AI and polymer physics model

Eric R Schultz iD, Soren Kyhl, Rebecca Willett, Juan J de Pablo iD

PLOS Computational Biology · 2025

DOI: 10.1371/journal.pcbi.1012912 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS Computational Biology, 2025. Verfasst von Eric R Schultz und 3 weiteren Autor:innen. Beteiligte Einrichtung: Pritzker School of Molecular Engineering, The University of Chicago, Chicago, Illinois, United States of America. Hauptthemen laut MEDLINE: Chromatin. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, Division of Mathematical Sciences, Division of Physics.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The physical organization of the genome in three-dimensional space regulates many biological processes, including gene expression and cell differentiation. Three-dimensional characterization of genome structure is critical to understanding these biological processes. Direct experimental measurements of genome structure are challenging; computational models of chromatin structure are therefore necessary. We develop an approach that combines a particle-based chromatin polymer model, molecular simulation, and machine learning to efficiently and accurately estimate chromatin structure from indirect measures of genome structure. More specifically, we introduce a new approach where the interaction parameters of the polymer model are extracted from experimental Hi-C data using a graph neural network (GNN). We train the GNN on simulated data from the underlying polymer model, avoiding the need for large quantities of experimental data. The resulting approach accurately estimates chromatin structures across all chromosomes and across several experimental cell lines despite being trained almost exclusively on simulated data. The proposed approach can be viewed as a general framework for combining physical modeling with machine learning, and it could be extended to integrate additional biological data modalities. Ultimately, we achieve accurate and high-throughput estimations of chromatin structure from Hi-C data, which will be necessary as experimental methodologies, such as single-cell Hi-C, improve.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ChromatinMachine LearningHumansNeural Networks, ComputerComputational BiologyPolymersComputer SimulationModels, Molecular

Substanzen

ChromatinPolymers

Autor:innen und Institutionen

  • Pritzker School of Molecular Engineering, The University of Chicago, Chicago, Illinois, United States of America.
  • Department of Statistics and Computer Science, The University of Chicago, Chicago, Illinois, United States of America.
  • Tandon School of Engineering, New York University, Brooklyn, New York, United States of America.
  • Materials Science Division, Argonne National Laboratory, Lemont, Illinois, United States of America.

ORCID-Profile: Eric R Schultz, Juan J de Pablo

Förderung

  • National Science Foundation
  • Division of Mathematical Sciences
  • Division of Physics
  • Simons Foundation

Zitieren

APA

Schultz, E. R., Kyhl, S., Willett, R., & de Pablo, J. J. (2025). Chromatin structures from integrated AI and polymer physics model. PLOS Computational Biology. https://doi.org/10.1371/journal.pcbi.1012912

Vancouver

Schultz ER, Kyhl S, Willett R, de Pablo JJ. Chromatin structures from integrated AI and polymer physics model. PLOS Computational Biology. 2025. doi:10.1371/journal.pcbi.1012912

BibTeX
@article{Schultz2025,
  author = {Schultz, Eric R and Kyhl, Soren and Willett, Rebecca and de Pablo, Juan J},
  title = {Chromatin structures from integrated AI and polymer physics model},
  journal = {PLOS Computational Biology},
  year = {2025},
  doi = {10.1371/journal.pcbi.1012912}
}
Kostenlos starten →