RNAmigos2: accelerated structure-based RNA virtual screening with deep graph learning.

Journal: Nature communications
PMID:

Abstract

RNAs are a vast reservoir of untapped drug targets. Structure-based virtual screening (VS) identifies candidate molecules by leveraging binding site information, traditionally using molecular docking simulations. However, docking struggles to scale with large compound libraries and RNA targets. Machine learning offers a solution but remains underdeveloped for RNA due to limited data and practical evaluations. We introduce a data-driven VS pipeline tailored for RNA, utilizing coarse-grained 3D modeling, synthetic data augmentation, and RNA-specific self-supervision. Our model achieves a 10,000x speedup over docking while ranking active compounds in the top 2.8% on structurally distinct test sets. It is robust to binding site variations and successfully screens unseen RNA riboswitches in a 20,000-compound in-vitro microarray, with a mean enrichment factor of 2.93 at 1%. This marks the first experimentally validated success of structure-based deep learning for RNA VS.

Authors

  • Juan G Carvajal-Patiño
    School of Computer Science, McGill University, Montréal, QC, Canada.
  • Vincent Mallet
    Structural Bioinformatics Unit, Department of Structural Biology and Chemistry, Institut Pasteur, Université de Paris, CNRS UMR3528, Paris F-75015, France.
  • David Becerra
    Donnelly Centre for Cellular and Biomolecular Research, University of Toronto, Toronto, ON M5S 3E1, Canada.
  • Luis Fernando Niño Vasquez
    Universidad Nacional de Colombia - Sede Bogotá - Facultad de Ingeniería - Depto. de Ingeniería de Sistemas e Industrial, Bogotá, Colombia.
  • Carlos Oliver
    Max Planck Institute of Biochemistry, Martinsried, Germany. carlos.oliver@vanderbilt.edu.
  • Jérôme Waldispühl
    School of Computer Science, McGill University, Montréal, QC, Canada. jerome.waldispuhl@mcgill.ca.