Digenic variant interpretation with hypothesis-driven explainable AI.

Journal: NAR genomics and bioinformatics
PMID:

Abstract

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.

Authors

  • Federica De Paoli
    enGenome Srl, Via Ferrata 5, 27100, Pavia, Italy.
  • Giovanna Nicora
    Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy.
  • Silvia Berardelli
    enGenome Srl, Via Ferrata 5, 27100, Pavia, Italy.
  • Andrea Gazzo
    Interuniversity Institute for Bioinformatics in Brussels, ULB-VUB, 1050 Brussels, Belgium; Machine Learning Group, Université Libre de Bruxelles, 1050 Brussels, Belgium; Center for Medical Genetics, Reproduction and Genetics, Reproduction Genetics and Regenerative Medicine, Vrije Universiteit Brussel, UZ Brussel, 1050 Brussels, Belgium.
  • Riccardo Bellazzi
    Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy.
  • Paolo Magni
    Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy. paolo.magni@unipv.it.
  • Ettore Rizzo
    enGenome Srl, Via Ferrata 5, 27100, Pavia, Italy.
  • Ivan Limongelli
    IRCCS Policlinico S. Matteo, Pzz.le Volontari del Sangue 2, 27100, Pavia, Italy. ivan.limongelli@unipv.it.
  • Susanna Zucca
    enGenome S.R.L., Pavia, Italy.