EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Digenic variant interpretation with hypothesis-driven explainable AI

Federica De Paoli iD, Giovanna Nicora, Silvia Berardelli, Andrea Gazzo, Riccardo Bellazzi iD, Paolo Magni, Ettore Rizzo, Ivan Limongelli, Susanna Zucca iD

NAR Genomics and Bioinformatics · 2025

DOI: 10.1093/nargab/lqaf029 ↗

Kurz gefasst

Fachartikel in der Zeitschrift NAR Genomics and Bioinformatics, 2025. Verfasst von Federica De Paoli und 8 weiteren Autor:innen. Beteiligte Einrichtung: enGenome Srl, Via Ferrata 5, 27100, Pavia, Italy. Hauptthemen laut MEDLINE: Machine Learning, Artificial Intelligence, Genetic Variation, Rare Diseases. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: NCI NIH HHS, European Innovation Council Accelerator.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The digenic inheritance hypothesis holds the potential to enhance diagnostic yield in rare diseases. Computational approaches capable of accurately interpreting and prioritizing digenic combinations of variants based on the proband’s phenotypes and family information can provide valuable assistance during the diagnostic process. We developed diVas, a hypothesis-driven machine learning approach that interprets genomic variants across different gene pairs. DiVas demonstrates strong performance in both classifying and prioritizing causative digenic combinations of rare variants within the top positions across 11 cases with the complete list of variants available (73% sensitivity and a median ranking of 3). Furthermore, it achieves a sensitivity of 0.81 when applied to 645 published causative digenic combinations. Additionally, diVas leverages explainable artificial intelligence to elucidate the digenic disease mechanism for predicted positive pairs.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningArtificial IntelligenceGenetic VariationRare DiseasesHumansPhenotype

Autor:innen und Institutionen

  • enGenome Srl, Via Ferrata 5, 27100, Pavia, Italy.
  • Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100, Pavia, Italy.
  • Department of Pathology, Memorial Sloan Kettering Cancer Center, 10065, New York, NY, United States.

ORCID-Profile: Federica De Paoli, Riccardo Bellazzi, Susanna Zucca

Förderung

  • NCI NIH HHS
  • European Innovation Council Accelerator

Zitieren

APA

De Paoli, F., Nicora, G., Berardelli, S., Gazzo, A., Bellazzi, R., Magni, P., Rizzo, E., Limongelli, I., & Zucca, S. (2025). Digenic variant interpretation with hypothesis-driven explainable AI. NAR Genomics and Bioinformatics. https://doi.org/10.1093/nargab/lqaf029

Vancouver

De Paoli F, Nicora G, Berardelli S, Gazzo A, Bellazzi R, Magni P, et al. Digenic variant interpretation with hypothesis-driven explainable AI. NAR Genomics and Bioinformatics. 2025. doi:10.1093/nargab/lqaf029

BibTeX
@article{DePaoli2025,
  author = {De Paoli, Federica and Nicora, Giovanna and Berardelli, Silvia and Gazzo, Andrea and Bellazzi, Riccardo and Magni, Paolo and Rizzo, Ettore and Limongelli, Ivan and Zucca, Susanna},
  title = {Digenic variant interpretation with hypothesis-driven explainable AI},
  journal = {NAR Genomics and Bioinformatics},
  year = {2025},
  doi = {10.1093/nargab/lqaf029}
}
Kostenlos starten →