EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Challenges in predicting chromatin accessibility differences between species

Amy Z M Stephen iD, Arian Raje, Heather H Sestili, Morgan E Wirthlin, Alyssa J Lawler, Ashley R Brown iD, Junjie Ma, William R Stauffer, Andreas R Pfenning, Irene M Kaplow iD

NAR Genomics and Bioinformatics · 27.03.2026 · 8 (2)

DOI: 10.1093/nargab/lqag059 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NAR Genomics and Bioinformatics, online erschienen am 24.06.2026. Verfasst von Amy Z M Stephen und 9 weiteren Autor:innen. Beteiligte Einrichtung: Mathematical Sciences Department, Carnegie Mellon University, Pittsburgh, PA 15213, United States. Hauptthemen laut MEDLINE: Chromatin, Enhancer Elements, Genetic. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Alfred P. Sloan Foundation Research Fellowship, National Science Foundation.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Differences in enhancer activity between species can help drive phenotypic diversity, yet enhancers often have conserved functions despite rapid sequence evolution, posing a challenge for quantifying their functional differences between species. Previous machine learning models have focused on the binary task of predicting differences in the presence of enhancers between species but have yet to demonstrate an ability to predict continuous differences in enhancer activity. Here, we trained convolutional neural networks on a regression task to predict chromatin accessibility—a proxy for enhancer activity—in the liver across five mammals, and we developed a novel framework to evaluate cross-species performance. We demonstrated that training on multiple species improves model generalization to both species used in training and held-out species. However, the models consistently achieved poor performance in predicting quantitative differences in accessibility between species at orthologous regions. Our study highlights the challenges in using regression models to predict chromatin accessibility changes between species. All data and code are available at http://daphne.compbio.cs.cmu.edu/files/azstephe/liver_regression_resource/ and https://figshare.com/projects/liverRegression/274293.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ChromatinEnhancer Elements, GeneticAnimalsSpecies SpecificityLiverConvolutional Neural NetworksPrediction AlgorithmsPredictive Learning ModelsHumansMachine Learning

Substanzen

Chromatin

Autor:innen und Institutionen

  • Mathematical Sciences Department, Carnegie Mellon University, Pittsburgh, PA 15213, United States.
  • Ray and Stephanie Lane Computational Biology Department, Carnegie Mellon University, Pittsburgh, PA 15213, United States.
  • Computer Science Department, Carnegie Mellon University, Pittsburgh, PA 15213, United States.
  • Neuroscience Institute, Carnegie Mellon University, Pittsburgh, PA 15213, United States.
  • Biological Sciences Department, Carnegie Mellon University, Pittsburgh, PA 15213, United States.
  • Department of Neurobiology, University of Pittsburgh School of Medicine, Pittsburgh, PA 15213,United States.

ORCID-Profile: Amy Z M Stephen, Ashley R Brown, Irene M Kaplow

Förderung

  • Alfred P. Sloan Foundation Research Fellowship
  • National Science Foundation

Zitieren

APA

Stephen, A. Z. M., Raje, A., Sestili, H. H., Wirthlin, M. E., Lawler, A. J., Brown, A. R., Ma, J., Stauffer, W. R., Pfenning, A. R., & Kaplow, I. M. (2026). Challenges in predicting chromatin accessibility differences between species. NAR Genomics and Bioinformatics, 8(2). https://doi.org/10.1093/nargab/lqag059

Vancouver

Stephen AZM, Raje A, Sestili HH, Wirthlin ME, Lawler AJ, Brown AR, et al. Challenges in predicting chromatin accessibility differences between species. NAR Genomics and Bioinformatics. 2026;8(2). doi:10.1093/nargab/lqag059

BibTeX
@article{Stephen2026,
  author = {Stephen, Amy Z M and Raje, Arian and Sestili, Heather H and Wirthlin, Morgan E and Lawler, Alyssa J and Brown, Ashley R and Ma, Junjie and Stauffer, William R and Pfenning, Andreas R and Kaplow, Irene M},
  title = {Challenges in predicting chromatin accessibility differences between species},
  journal = {NAR Genomics and Bioinformatics},
  year = {2026},
  volume = {8},
  number = {2},
  doi = {10.1093/nargab/lqag059}
}
Kostenlos starten →