Integrating genetic variation with deep learning provides context for variants impacting transcription factor binding during embryogenesis
Genome Research · 2025
DOI: 10.1101/gr.279652.124 ↗Kurz gefasst
Fachartikel in der Zeitschrift Genome Research, 2025. Verfasst von Olga M Sigalova und 9 weiteren Autor:innen. Beteiligte Einrichtung: European Molecular Biology Laboratory (EMBL), Genome Biology Unit, D-69117 Heidelberg, Germany. Hauptthemen laut MEDLINE: Transcription Factors, Deep Learning, Embryonic Development, Genetic Variation. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 79 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: European Research Council, Provence-Alpes-Côte d'Azur Regional Council.
Abstract (Originalsprache)
Understanding how genetic variation impacts transcription factor (TF) binding remains a major challenge, limiting our ability to model disease-associated variants. Here, we used a highly controlled system of F 1 crosses with extensive genetic diversity to profile allele-specific binding of four TFs at several time points during Drosophila embryogenesis. Using a combined haplotype test, we identified 9%–18% of TF-bound regions impacted by genetic variation even for essential regulators. By expanding WASP (a tool for allele-specific read mapping) to examine indels, we increased detection of allelically imbalanced peaks by 30%–50%. This fine-grained “mutagenesis” can reconstruct functionalized binding motifs for all factors. To prioritize causal variants, we trained a convolutional neural network (Basenji) to accurately predict binding from DNA sequence. The model can also predict measured allelic imbalance for strong effect variants, providing a mechanistic interpretation for how the variant impacts binding. This reveals unexpected relationships between TFs, including potential cooperative pairs, and mechanisms of tissue-specific recruitment of the ubiquitous factor CTCF.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- European Molecular Biology Laboratory (EMBL), Genome Biology Unit, D-69117 Heidelberg, Germany.
- European Molecular Biology Laboratory (EMBL), Structural and Computational Biology Unit, D-69117 Heidelberg, Germany.
- Collaboration for Joint PhD Degree between EMBL and Heidelberg University, Faculty of Biosciences, D-69117 Heidelberg, Germany.
- Aix Marseille Univ, INSERM, TAGC, 13009 Marseille, France.
- European Molecular Biology Laboratory (EMBL), Structural and Computational Biology Unit, D-69117 Heidelberg, Germany; judith.zaugg@embl.de furlong@embl.de.
- European Molecular Biology Laboratory (EMBL), Genome Biology Unit, D-69117 Heidelberg, Germany; judith.zaugg@embl.de furlong@embl.de.
ORCID-Profile: Olga M Sigalova, Mattia Forneris, Frosina Stojanovska, Bingqing Zhao, Rebecca R Viales, Adam Rabinowitz, Fayrouz Hammal, Benoît Ballester, Judith B Zaugg, Eileen E M Furlong
Förderung
- European Research Council
- Provence-Alpes-Côte d'Azur Regional Council
Zitieren
APA
Sigalova, O. M., Forneris, M., Stojanovska, F., Zhao, B., Viales, R. R., Rabinowitz, A., Hammal, F., Ballester, B., Zaugg, J. B., & Furlong, E. E. M. (2025). Integrating genetic variation with deep learning provides context for variants impacting transcription factor binding during embryogenesis. Genome Research. https://doi.org/10.1101/gr.279652.124
Vancouver
Sigalova OM, Forneris M, Stojanovska F, Zhao B, Viales RR, Rabinowitz A, et al. Integrating genetic variation with deep learning provides context for variants impacting transcription factor binding during embryogenesis. Genome Research. 2025. doi:10.1101/gr.279652.124
BibTeX
@article{Sigalova2025,
author = {Sigalova, Olga M and Forneris, Mattia and Stojanovska, Frosina and Zhao, Bingqing and Viales, Rebecca R and Rabinowitz, Adam and Hammal, Fayrouz and Ballester, Benoît and Zaugg, Judith B and Furlong, Eileen E M},
title = {Integrating genetic variation with deep learning provides context for variants impacting transcription factor binding during embryogenesis},
journal = {Genome Research},
year = {2025},
doi = {10.1101/gr.279652.124}
}
EUVIMED