Refining sequence-to-expression modelling with chromatin accessibility
Bioinformatics · 03.05.2026 · 42 (5)
DOI: 10.1093/bioinformatics/btag199 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 26.04.2026. Verfasst von Orsolya Lapohos und 2 weiteren Autor:innen. Beteiligte Einrichtung: Department of Quantitative Life Sciences, McGill University, Montreal, Quebec, H3A 0G4, Canada. Hauptthemen laut MEDLINE: Chromatin, Sequence Analysis, DNA, Models, Genetic. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Sciences and Engineering Research Council of Canada, Canada Foundation for Innovation (CFI) JELF, Digital Research Alliance of Canada.
Abstract (Originalsprache)
Motivation Sequence-to-expression models typically do not consider chromatin accessibility, a major factor limiting gene regulation. We hypothesized that supplying accessibility as an input feature would allow a sequence-to-expression model to focus on important open regions of the genome. Results We found that the performance of such an augmented model was significantly better than that of sequence-only or accessibility-only models with similar architectures. Specifically, its ability to predict the expression of highly variable genes and gene expression in other cell types improved, and higher attribution scores in the input DNA sequences of the augmented model conformed to accessibility, enabling the learning of cell type-specific sequence patterns. Additionally, we show that fine-tuning a pre-trained sequence-only model with both sequence and accessibility can boost performance further and highlight the importance of sequencing depth in sequence-to-expression prediction. Availability and Implementation Source code is available on GitHub at https://github.com/lapohosorsolya/accessible_seq2exp.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Quantitative Life Sciences, McGill University, Montreal, Quebec, H3A 0G4, Canada.
- Meakins-Christie Laboratories, Research Institute of the McGill University Health Centre, Montreal, Quebec, H4A 3J1, Canada.
- Mila, Quebec AI Institute, Montreal, H2S 3H1, Canada.
- Department of Medical Sciences, Khalifa University, Abu Dhabi, 127788, United Arab Emirates.
- Department of Electrical and Computer Engineering, McGill University, Montreal, Quebec, H3A 0G4, Canada.
- The Rosalind and Morris Goodman Cancer Institute, Montreal, Quebec, H3A 1A3, Canada.
ORCID-Profile: Orsolya Lapohos, Gregory J Fonseca, Amin Emad
Förderung
- Natural Sciences and Engineering Research Council of Canada
- Canada Foundation for Innovation (CFI) JELF
- Digital Research Alliance of Canada
Zitieren
APA
Lapohos, O., Fonseca, G. J., & Emad, A. (2026). Refining sequence-to-expression modelling with chromatin accessibility. Bioinformatics, 42(5). https://doi.org/10.1093/bioinformatics/btag199
Vancouver
Lapohos O, Fonseca GJ, Emad A. Refining sequence-to-expression modelling with chromatin accessibility. Bioinformatics. 2026;42(5). doi:10.1093/bioinformatics/btag199
BibTeX
@article{Lapohos2026,
author = {Lapohos, Orsolya and Fonseca, Gregory J and Emad, Amin},
title = {Refining sequence-to-expression modelling with chromatin accessibility},
journal = {Bioinformatics},
year = {2026},
volume = {42},
number = {5},
doi = {10.1093/bioinformatics/btag199}
}
EUVIMED