Deep learning captures the effect of epistasis in multifactorial diseases.

Journal: Frontiers in medicine
Published Date:

Abstract

BACKGROUND: Polygenic risk score (PRS) prediction is widely used to assess the risk of diagnosis and progression of many diseases. Routinely, the weights of individual SNPs are estimated by the linear regression model that assumes independent and linear contribution of each SNP to the phenotype. However, for complex multifactorial diseases such as Alzheimer's disease, diabetes, cardiovascular disease, cancer, and others, association between individual SNPs and disease could be non-linear due to epistatic interactions. The aim of the presented study is to explore the power of non-linear machine learning algorithms and deep learning models to predict the risk of multifactorial diseases with epistasis.

Authors

  • Vladislav Perelygin
    International Laboratory of Bioinformatics, AI and Digital Sciences Institute, Faculty of Computer Science, HSE University, Moscow, Russia.
  • Alexey Kamelin
    International Laboratory of Bioinformatics, AI and Digital Sciences Institute, Faculty of Computer Science, HSE University, Moscow, Russia.
  • Nikita Syzrantsev
    Genotek Ltd., Moscow, Russia.
  • Layal Shaheen
    Genotek Ltd., Moscow, Russia.
  • Anna Kim
    Genotek Ltd., Moscow, Russia.
  • Nikolay Plotnikov
    Genotek Ltd., Moscow, Russia.
  • Anna Ilinskaya
    Eligens SIA, Mārupe, Latvia.
  • Valery Ilinsky
    Eligens SIA, Mārupe, Latvia.
  • Alexander Rakitko
    International Laboratory of Bioinformatics, AI and Digital Sciences Institute, Faculty of Computer Science, HSE University, Moscow, Russia.
  • Maria Poptsova
    International Laboratory of Bioinformatics, AI and Digital Sciences Institute, Faculty of Computer Science, HSE University, Moscow, Russia.

Keywords

No keywords available for this article.