Spatio-temporal learning from molecular dynamics simulations for protein-ligand binding affinity prediction.

Journal: Bioinformatics (Oxford, England)
Published Date: Aug 19, 2025

Abstract

MOTIVATION: The field of protein-ligand binding affinity prediction continues to face significant challenges. While deep learning (DL) models can leverage 3D structural information of protein-ligand complexes, they perform well only on heavily biased test sets containing information leaked from training sets. This lack of generalization arises from the limited availability of training data and the models' inability to effectively learn from protein-ligand interactions. Since these interactions are inherently time-dependent, molecular dynamics (MD) simulations offer a potential solution by incorporating conformational sampling and providing interaction rich information.

Authors

  • Pierre-Yves Libouban
    Institute of Organic and Analytical Chemistry (ICOA), UMR7311, Université d'Orléans, CNRS, Pôle de Chimie rue de Chartres, 45067 Orléans, CEDEX 2, France.
  • Camille Parisel
    Institute for Development and Resources in Intensive Scientific Computing (IDRIS), CNRS, France.
  • Maxime Song
    Institute for Development and Resources in Intensive Scientific Computing (IDRIS), CNRS, France.
  • Samia Aci-Sèche
    Institute of Organic and Analytical Chemistry (ICOA), UMR7311, Université d'Orléans, CNRS, Pôle de Chimie rue de Chartres, 45067 Orléans, CEDEX 2, France.
  • Jose C Gómez-Tamayo
    Computational Chemistry, Janssen Research & Development, Janssen Pharmaceutica N. V, Beerse, B-2340, Belgium.
  • Gary Tresadern
    Janssen Research and Development , Turnhoutseweg 30 , 2340 Beerse , Belgium.
  • Pascal Bonnet
    Institute of Organic and Analytical Chemistry (ICOA), UMR7311, Université d'Orléans, CNRS, Pôle de Chimie rue de Chartres, 45067 Orléans, CEDEX 2, France.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals