Using the DNA language model, GROVER, to parse effects of sequence, chromatin and regulatory features on genome stability
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag602 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Pierre M Joubert und 4 weiteren Autor:innen. Beteiligte Einrichtung: Biomedical Genomics, Biotechnology Center, Center for Molecular and Cellular Bioengineering, Technische Universität, Dresden, Germany. Hauptthemen laut MEDLINE: Chromatin, Genomic Instability, Sequence Analysis, DNA, Models, Genetic. Die Arbeit nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Center for Scalable data analytics and artificial intelligence, the Center for Advanced Systems Understanding (CASUS), Germany's Federal Ministry of Education and Research (BMBF).
Abstract (Originalsprache)
Motivation Genome stability is shaped by DNA sequence and chromatin context, but their relative contributions to double-strand break (DSB) sensitivity remain unclear. Results We show that the DNA language model, GROVER, can infer DSB location based on sequence. DSB hotspots tend to contain GC-rich sequences that belong to promoters, genes and short interspersed nuclear elements (SINEs). Additionally, we identified several specific short sequences (tokens) that are associated with modulating DSB sensitivity. Another model using chromatin and genome regulatory features outperforms the sequence-only model, highlighting complementary and cell-type specific information. Integrating sequence and genome biological features yields the best performance, demonstrating their synergy. Analyzing this model revealed that, dependent on the sample, genome stability information encoded in H3K36me3 and DNase-seq can be learned from the sequence, but not H3K27ac or H3K9me3. Embedding chromatin data directly into the GROVER architecture enabled cell-type specific modeling with performance matching the full chromatin feature model. Our results suggest that while chromatin and regulatory context provides important information, such as cell-type specificity, much of the information shaping DSB patterns is already encoded in the DNA sequence itself. Our integrative modeling approach not only reveals DSB patterns but also provides a generalizable strategy for tracing predictions in genomic data. Availability Data, models, and a tutorial are available on Zenodo.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Biomedical Genomics, Biotechnology Center, Center for Molecular and Cellular Bioengineering, Technische Universität, Dresden, Germany.
- Center for Advanced Systems Understanding (CASUS), Görlitz, Germany.
- Helmholtz Zentrum Dresden-Rossendorf (HZDR), Dresden, Germany.
- Institute for Genetics, University of Cologne, Cologne, Germany.
- Cologne Excellence Cluster for Cellular Stress Responses in Aging-Associated Diseases (CECAD), University of Cologne, Cologne, Germany.
- Institute for Genome Stability in Aging and Disease (IGSAD), University of Cologne, Cologne, Germany.
ORCID-Profile: Anna R Poetsch
Förderung
- Center for Scalable data analytics and artificial intelligence
- the Center for Advanced Systems Understanding (CASUS)
- Germany's Federal Ministry of Education and Research (BMBF)
- Saxon Ministry for Science, Culture, and Tourism (SMWK)
- Mildred Scheel Early Career Center Dresden P2
- German Cancer Aid
- FOSTER-Funds for Student Research
- Germany’s Federal Ministry of Education and Research
Zitieren
APA
Joubert, P. M., Vlasov, A., Janakievski, N., Sanabria, M., & Poetsch, A. R. (2026). Using the DNA language model, GROVER, to parse effects of sequence, chromatin and regulatory features on genome stability. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag602
Vancouver
Joubert PM, Vlasov A, Janakievski N, Sanabria M, Poetsch AR. Using the DNA language model, GROVER, to parse effects of sequence, chromatin and regulatory features on genome stability. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag602
BibTeX
@article{Joubert2026,
author = {Joubert, Pierre M and Vlasov, Anton and Janakievski, Nikola and Sanabria, Melissa and Poetsch, Anna R},
title = {Using the DNA language model, GROVER, to parse effects of sequence, chromatin and regulatory features on genome stability},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag602}
}
EUVIMED