Modelling transcription with explainable AI uncovers context-specific epigenetic gene regulation at promoters and gene bodies
PLOS Genetics · 2025
DOI: 10.1371/journal.pgen.1011908 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS Genetics, 2025. Verfasst von Kashyap Chhatbar und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Informatics, University of Edinburgh, Edinburgh, United Kingdom. Hauptthemen laut MEDLINE: Promoter Regions, Genetic, Epigenesis, Genetic, Transcription, Genetic. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 69 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wellcome Trust, HORIZON EUROPE European Research Council, Next Generation EU.
Abstract (Originalsprache)
Transcriptional regulation involves complex interactions with chromatin-associated proteins, but disentangling these mechanistically remains challenging. Here, we generate deep learning models to predict RNA Pol-II occupancy from chromatin-associated protein profiles in unperturbed conditions. We evaluate the suitability of Shapley Additive Explanations (SHAP), a widely used explainable AI (XAI) approach, to infer functional relevance and analyse regulatory mechanisms across diverse datasets. We aim to validate these insights using data from degron-based perturbation experiments. Remarkably, genes ranked by SHAP importance predict direct targets of perturbation even from unperturbed data, enabling inference without costly experimental interventions. Our analysis reveals that SHAP not only predicts differential gene expression but also captures the magnitude of transcriptional changes. We validate the cooperative roles of SET1A and ZC3H4 at promoters and uncover novel regulatory contributions of ZC3H4 at gene bodies in influencing transcription. Cross-dataset validation uncovers unexpected connections between ZC3H4, a component of the Restrictor complex, and INTS11, part of the Integrator complex, suggesting crosstalk mediated by H3K4me3 and the SET1/COMPASS complex in transcriptional regulation. These findings highlight the power of integrating predictive modelling and experimental validation to unravel complex context-dependent regulatory networks and generate novel biological hypotheses.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- School of Informatics, University of Edinburgh, Edinburgh, United Kingdom.
- Institute of Cell Biology, University of Edinburgh, Edinburgh, United Kingdom.
- International School for Advanced Studies (SISSA), Trieste, Italy.
ORCID-Profile: Kashyap Chhatbar, Adrian Bird, Guido Sanguinetti
Förderung
- Wellcome Trust
- HORIZON EUROPE European Research Council
- Next Generation EU
Zitieren
APA
Chhatbar, K., Bird, A., & Sanguinetti, G. (2025). Modelling transcription with explainable AI uncovers context-specific epigenetic gene regulation at promoters and gene bodies. PLOS Genetics. https://doi.org/10.1371/journal.pgen.1011908
Vancouver
Chhatbar K, Bird A, Sanguinetti G. Modelling transcription with explainable AI uncovers context-specific epigenetic gene regulation at promoters and gene bodies. PLOS Genetics. 2025. doi:10.1371/journal.pgen.1011908
BibTeX
@article{Chhatbar2025,
author = {Chhatbar, Kashyap and Bird, Adrian and Sanguinetti, Guido},
title = {Modelling transcription with explainable AI uncovers context-specific epigenetic gene regulation at promoters and gene bodies},
journal = {PLOS Genetics},
year = {2025},
doi = {10.1371/journal.pgen.1011908}
}
EUVIMED