Mutate and observe: utilizing deep neural networks to investigate the impact of mutations on translation initiation.

Journal: Bioinformatics (Oxford, England)
Published Date:

Abstract

MOTIVATION: The primary regulatory step for protein synthesis is translation initiation, which makes it one of the fundamental steps in the central dogma of molecular biology. In recent years, a number of approaches relying on deep neural networks (DNNs) have demonstrated superb results for predicting translation initiation sites. These state-of-the art results indicate that DNNs are indeed capable of learning complex features that are relevant to the process of translation. Unfortunately, most of those research efforts that employ DNNs only provide shallow insights into the decision-making processes of the trained models and lack highly sought-after novel biologically relevant observations.

Authors

  • Utku Ozbulak
    Department of Applied Mathematics, Computer Science and Statistics, Ghent University, Ghent, Belgium.
  • Hyun Jung Lee
    Center for Biosystems and Biotech Data Science, Ghent University Global Campus, Incheon, South Korea.
  • Jasper Zuallaert
    Center for Biotech Data Science, Department of Environmental Technology, Food Technology and Molecular Biotechnology, Ghent University Global Campus, Songdo, Incheon, South Korea.
  • Wesley De Neve
    Center for Biotech Data Science, Department of Environmental Technology, Food Technology and Molecular Biotechnology, Ghent University Global Campus, Songdo, Incheon, South Korea.
  • Stephen Depuydt
    Lab of Plant Growth Analysis, Ghent University Global Campus, Incheon, South Korea.
  • Joris Vankerschaver
    Department of Applied Mathematics, Computer Science and Statistics, Ghent University, Ghent, Belgium.