Power-law penalties correct distance bias in single-cell co-accessibility and deep-learning chromatin interaction predictions
NAR Genomics and Bioinformatics · 27.03.2026 · 8 (2)
DOI: 10.1093/nargab/lqag063 ↗Kurz gefasst
Fachartikel in der Zeitschrift NAR Genomics and Bioinformatics, online erschienen am 24.06.2026. Verfasst von Luca Schlegel und 3 weiteren Autor:innen. Beteiligte Einrichtung: Plant Epigenomics, TUM School of Life Sciences Weihenstephan, Technical University of Munich, Freising 85354, Germany. Hauptthemen laut MEDLINE: Chromatin, Single-Cell Analysis, Deep Learning. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NIGMS NIH HHS, Technical University of Munich, National Institutes of Health.
Abstract (Originalsprache)
Scalable proxies for 3D genome contacts—such as single-cell co-accessibility and deep learning predictions—have emerged as powerful alternatives to chromatin capture-based methods, but predictions systematically overestimate long-range interactions. Here we show how to correct this bias using distance-based penalty functions informed by Gaussian mixture modeling and polymer-physics scaling. Using Hi-C datasets from maize, rice, and soybean, we derive tissue-specific and global consensus penalties parameterized by multiregime power-law exponents. Applying these corrections to single-cell ATAC sequencing co-accessibility scores improves their distance profiles in concordance with Hi-C and reduces long-range false positives by an average of 73% with tissue-specific penalties and 66% with the global consensus. We provide open-source code and fitted parameters to support adoption in maize, rice, and soybean.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Plant Epigenomics, TUM School of Life Sciences Weihenstephan, Technical University of Munich, Freising 85354, Germany.
- Department of Molecular, Cellular, and Developmental Biology, University of Michigan, Ann Arbor, MI 48109, United States.
ORCID-Profile: Luca Schlegel, Fabio Gómez Cano, Frank Johannes
Förderung
- NIGMS NIH HHS
- Technical University of Munich
- National Institutes of Health
- University of Michigan
Zitieren
APA
Schlegel, L., Gómez Cano, F., Marand, A. P., & Johannes, F. (2026). Power-law penalties correct distance bias in single-cell co-accessibility and deep-learning chromatin interaction predictions. NAR Genomics and Bioinformatics, 8(2). https://doi.org/10.1093/nargab/lqag063
Vancouver
Schlegel L, Gómez Cano F, Marand AP, Johannes F. Power-law penalties correct distance bias in single-cell co-accessibility and deep-learning chromatin interaction predictions. NAR Genomics and Bioinformatics. 2026;8(2). doi:10.1093/nargab/lqag063
BibTeX
@article{Schlegel2026,
author = {Schlegel, Luca and Gómez Cano, Fabio and Marand, Alexandre P and Johannes, Frank},
title = {Power-law penalties correct distance bias in single-cell co-accessibility and deep-learning chromatin interaction predictions},
journal = {NAR Genomics and Bioinformatics},
year = {2026},
volume = {8},
number = {2},
doi = {10.1093/nargab/lqag063}
}
EUVIMED