Regulators of homologous recombination deficiency identified by machine learning using somatic multi-omics data
Life Science Alliance · 2026-02 · 9 (2) · e202503531
DOI: 10.26508/lsa.202503531 ↗Kurz gefasst
Fachartikel in der Zeitschrift Life Science Alliance, online erschienen am 19.11.2025. Verfasst von Renan Valieris und 8 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Computational Biology and Bioinformatics, A.C. Camargo Cancer Center, São Paulo, Brazil. Hauptthemen laut MEDLINE: Machine Learning, Neoplasms, Homologous Recombination. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Fundação de Amparo à Pesquisa do Estado de São Paulo, Conselho Nacional de Desenvolvimento Científico e Tecnológico.
Abstract (Originalsprache)
Homologous recombination deficiency (HRD) is a critical biomarker for guiding targeted therapies, yet the full range of somatic alterations driving HRD across cancers remains incompletely characterized. Here, we present a tumor-agnostic machine learning framework that integrates somatic multi-omics data, including copy-number variations, single-nucleotide variants, DNA methylation, and gene expression from over 8,000 patients in The Cancer Genome Atlas. Using a genome-wide mutational signature–based HRD score as ground truth, our model achieved high predictive performance and leveraged SHAP-based explainability to uncover HRD regulators beyond BRCA1/2 . Cross-tumor analysis revealed both shared and cancer type–specific molecular determinants, whereas functional enrichment highlighted key molecular and cellular processes. These findings expand the known repertoire of HRD-associated alterations, provide a resource for mechanistic investigation, and demonstrate the potential of integrative AI approaches to improve patient stratification for HR-targeted therapies across diverse malignancies.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Laboratory of Computational Biology and Bioinformatics, A.C. Camargo Cancer Center, São Paulo, Brazil.
- Clinical and Functional Genomics Group, A.C. Camargo Cancer Center, São Paulo, Brazil.
- Division of Cancer Biology, Department of Radiation Oncology, Rutgers New Jersey Medical School, Newark, NJ, USA.
- Departamento de Computação e Matemática, Universidade de São Paulo, São Paulo, Brazil.
- Laboratory of Computational Biology and Bioinformatics, A.C. Camargo Cancer Center, São Paulo, Brazil itojal@accamargo.org.br.
- Fred Hutchinson Cancer Center, Vaccine and Infectious Disease Division, Seattle, WA, USA.
ORCID-Profile: Renan Valieris, Lucas Rosa, Rafael Rosales, Israel Tojal da Silva
Förderung
- Fundação de Amparo à Pesquisa do Estado de São Paulo
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
Zitieren
APA
Valieris, R., Rosa, L., Martins, L., Defelicibus, A., Carraro, D. M., Nunes, D. N., Dias-Neto, E., Rosales, R., & da Silva, I. T. (2026). Regulators of homologous recombination deficiency identified by machine learning using somatic multi-omics data. Life Science Alliance, 9(2), e202503531. https://doi.org/10.26508/lsa.202503531
Vancouver
Valieris R, Rosa L, Martins L, Defelicibus A, Carraro DM, Nunes DN, et al. Regulators of homologous recombination deficiency identified by machine learning using somatic multi-omics data. Life Science Alliance. 2026;9(2):e202503531. doi:10.26508/lsa.202503531
BibTeX
@article{Valieris2026,
author = {Valieris, Renan and Rosa, Lucas and Martins, Luan and Defelicibus, Alexandre and Carraro, Dirce Maria and Nunes, Diana Noronha and Dias-Neto, Emmanuel and Rosales, Rafael and da Silva, Israel Tojal},
title = {Regulators of homologous recombination deficiency identified by machine learning using somatic multi-omics data},
journal = {Life Science Alliance},
year = {2026},
volume = {9},
number = {2},
pages = {e202503531},
doi = {10.26508/lsa.202503531}
}
EUVIMED