Deep learning models for RNA secondary structure prediction (probably) do not generalize across families.

Journal: Bioinformatics (Oxford, England)
Published Date: Aug 10, 2022

Abstract

MOTIVATION: The secondary structure of RNA is of importance to its function. Over the last few years, several papers attempted to use machine learning to improve de novo RNA secondary structure prediction. Many of these papers report impressive results for intra-family predictions but seldom address the much more difficult (and practical) inter-family problem.

Authors

  • Marcell Szikszai
    Department of Computer Science & Software Engineering, The University of Western Australia, Perth, WA 6009, Australia.
  • Michael Wise
    Department of Computer Science & Software Engineering, The University of Western Australia, Perth, WA 6009, Australia.
  • Amitava Datta
    Department of Computer Science & Software Engineering, The University of Western Australia, Perth, WA 6009, Australia.
  • Max Ward
    Neurological Surgery, Donald and Barbara Zucker School of Medicine at Hofstra/Northwell, Hempstead, USA.
  • David H Mathews
    Department of Biochemistry & Biophysics, Center for RNA Biology, and Department of Biostatistics & Computational Biology, University of Rochester, Rochester, NY 14642, USA.

Keywords

External Resources

Popular Topics
Recent Journals