Etiology-guided mutational signature learning from DNA repair knockouts in cell lines using supervised NMF
NAR Genomics and Bioinformatics · 27.06.2026 · 8 (3)
DOI: 10.1093/nargab/lqag078 ↗Kurz gefasst
Fachartikel in der Zeitschrift NAR Genomics and Bioinformatics, online erschienen am 06.08.2026. Verfasst von Sander Goossens und 3 weiteren Autor:innen. Beteiligte Einrichtung: Pattern Recognition & Bioinformatics, Intelligent Systems Department, EEMCS Faculty, Delft University of Technology, Van Mourik Broekmanweg 6, 2628 X…. Hauptthemen laut MEDLINE: DNA Repair, Mutation, Neoplasms. Die Arbeit nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIA NIH HHS, NIDDK NIH HHS, NEI NIH HHS.
Abstract (Originalsprache)
Many tumours show deficiencies in DNA damage response (DDR), not only driving tumorigenesis but also exposing vulnerabilities with therapeutic potential. Assessing which patients might benefit from DDR-targeting therapy requires knowledge of tumour DDR deficiency (DDRd) status, with mutational signatures reportedly better predictors than loss-of-function mutations. Existing DDRd models offer effective prediction for pathways with well-characterized processes and mutational signatures. Nevertheless, development of models for additional DDRd and clinically relevant mechanisms could be hampered by the fact that most mutational signatures have unknown etiology. Using supervised non-negative matrix factorization (SNMF), we integrate mutational signature learning with multiclass DDR-deficiency prediction to enable etiology-guided learning of signatures from cell lines with confirmed gene knockouts. Applied to DDR gene knockout human-induced pluripotent stem cell lines, SNMF identified etiology-aligned representations of deficiency in homologous recombination, mismatch repair, and base excision repair. Even guided by pathway-level labels, SNMF captured gene-specific base excision repair submechanisms, showing the integration offered added granularity. Learned cell line signatures showed high similarity to tumour-derived COSMIC signatures, revealed associations with mutations in DDR genes, and enabled high recall of tumours with DDR deficiencies. We envision that SNMF-like methods could leverage knockout screens to learn etiology-guided signatures for improved DDRd annotation and treatment optimization. SNMF is available at: https://github.com/joanagoncalveslab/SNMF.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Pattern Recognition & Bioinformatics, Intelligent Systems Department, EEMCS Faculty, Delft University of Technology, Van Mourik Broekmanweg 6, 2628 XE Delft, Netherlands.
- Holland Proton Therapy Center (HollandPTC), 2600 AC Delft, Netherlands.
ORCID-Profile: Sander Goossens, Yasin I Tepeli, Colm Seale, Joana P Gonçalves
Förderung
- NIA NIH HHS
- NIDDK NIH HHS
- NEI NIH HHS
- Convergence of Health and Technology
- US National Institutes of Health
Zitieren
APA
Goossens, S., Tepeli, Y. I., Seale, C., & Gonçalves, J. P. (2026). Etiology-guided mutational signature learning from DNA repair knockouts in cell lines using supervised NMF. NAR Genomics and Bioinformatics, 8(3). https://doi.org/10.1093/nargab/lqag078
Vancouver
Goossens S, Tepeli YI, Seale C, Gonçalves JP. Etiology-guided mutational signature learning from DNA repair knockouts in cell lines using supervised NMF. NAR Genomics and Bioinformatics. 2026;8(3). doi:10.1093/nargab/lqag078
BibTeX
@article{Goossens2026,
author = {Goossens, Sander and Tepeli, Yasin I and Seale, Colm and Gonçalves, Joana P},
title = {Etiology-guided mutational signature learning from DNA repair knockouts in cell lines using supervised NMF},
journal = {NAR Genomics and Bioinformatics},
year = {2026},
volume = {8},
number = {3},
doi = {10.1093/nargab/lqag078}
}
EUVIMED