EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AxialTAD: an axial contrast architecture for TAD boundary prediction from Hi-C

Woo-Young Choi, Je-Keun Rhee iD

Briefings in Bioinformatics · 02.11.2026 · 27 (6)

DOI: 10.1093/bib/bbag603 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Briefings in Bioinformatics, online erschienen am 02.11.2026. Verfasst von Woo-Young Choi und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Bioinformatics & Life Science, Soongsil University, 369, Sangdo-ro, Dongjak-gu, Seoul 06978, Republic of Korea. Hauptthemen laut MEDLINE: Deep Learning, Chromatin. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, Ministry of Science and ICT, Ministry of Education.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Topologically associating domains (TADs) are fundamental units of 3D chromatin organization, and accurate identification of TAD boundaries from Hi-C contact matrices remains an active challenge. Recent deep learning approaches have advanced substantially, but these rely on increasingly large architectures, raising the question of how much of this capacity boundary-centric analysis requires. Here we propose AxialTAD, a compact deep learning model centered on an Axial Contrast Module (ACM) that explicitly encodes directional contrast in contact intensity along the row and column axes of local Hi-C patches, an operator aligned with the geometric signature of TAD boundaries. Evaluated on four human cell lines (GM12878, HeLa-S3, IMR-90, K562) within cell lines and under leave-one-cell-out generalization, AxialTAD performed comparably with a recent convolutional neural network (CNN)+Transformer baseline (deepTAD) while using 76%–80% fewer trainable parameters (113K–137K versus 571K). A parameter-matched conventional CNN achieved similar F1 to AxialTAD in the human 25 kb experiments. When trained and evaluated within each of two mouse datasets, AxialTAD outperformed both this control and deepTAD. Orthogonal validation against CTCF and cohesin ChIP-seq supported the biological plausibility of the predicted boundaries. These results indicate that, within the range of architectures examined, a large architecture is not necessary to reach this level of boundary prediction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningChromatinHumansConvolutional Neural Networks

Stichwörter der Autor:innen

Hi-CTAD boundary predictionchromatin organizationdeep learninginductive biastopologically associating domains

Substanzen

Chromatin

Autor:innen und Institutionen

  • Department of Bioinformatics & Life Science, Soongsil University, 369, Sangdo-ro, Dongjak-gu, Seoul 06978, Republic of Korea.
  • AI-Bio Convergence Research Institute, Soongsil University, 369, Sangdo-ro, Dongjak-gu, Seoul 06978, Republic of Korea.

ORCID-Profile: Je-Keun Rhee

Förderung

  • National Research Foundation of Korea
  • Ministry of Science and ICT
  • Ministry of Education

Zitieren

APA

Choi, W. Y., & Rhee, J. K. (2026). AxialTAD: an axial contrast architecture for TAD boundary prediction from Hi-C. Briefings in Bioinformatics, 27(6). https://doi.org/10.1093/bib/bbag603

Vancouver

Choi WY, Rhee JK. AxialTAD: an axial contrast architecture for TAD boundary prediction from Hi-C. Briefings in Bioinformatics. 2026;27(6). doi:10.1093/bib/bbag603

BibTeX
@article{Choi2026,
  author = {Choi, Woo-Young and Rhee, Je-Keun},
  title = {AxialTAD: an axial contrast architecture for TAD boundary prediction from Hi-C},
  journal = {Briefings in Bioinformatics},
  year = {2026},
  volume = {27},
  number = {6},
  doi = {10.1093/bib/bbag603}
}
Kostenlos starten →