Assessing interaction recovery of predicted protein-ligand poses.

Journal: Journal of cheminformatics
Published Date: May 19, 2025

Abstract

The field of protein-ligand pose prediction has seen significant advances in recent years, with machine learning-based methods now being commonly used in lieu of classical docking methods or even to predict all-atom protein-ligand complex structures. Most contemporary studies focus on the accuracy and physical plausibility of ligand placement to determine pose quality, often neglecting a direct assessment of the interactions observed with the protein. In this work, we demonstrate that ignoring protein-ligand interaction fingerprints can lead to overestimation of model performance, most notably in recent protein-ligand cofolding models which often fail to recapitulate key interactions.Scientific Contribution The interaction analysis used in this study is provided as a python package at https://github.com/Exscientia/plif_validity .

Authors

  • David Errington
    Recursion, Oxford, UK.
  • Constantin Schneider
    Department of Statistics, University of Oxford, Oxford, OX1 3LB, UK.
  • Cédric Bouysset
    Université Côte d'Azur, CNRS, Institut de Chimie de Nice UMR7272, 06108 Nice, France.
  • Frédéric A Dreyer
    Exscientia, Oxford Science Park, Oxford, OX4 4GE, UK. dreyer.frederic@gene.com.

Keywords

No keywords available for this article.

External Resources

Popular Topics
Recent Journals