English

PLANTAIN: Diffusion-inspired Pose Score Minimization for Fast and Accurate Molecular Docking

Quantitative Methods 2023-07-27 v2

Abstract

Molecular docking aims to predict the 3D pose of a small molecule in a protein binding site. Traditional docking methods predict ligand poses by minimizing a physics-inspired scoring function. Recently, a diffusion model has been proposed that iteratively refines a ligand pose. We combine these two approaches by training a pose scoring function in a diffusion-inspired manner. In our method, PLANTAIN, a neural network is used to develop a very fast pose scoring function. We parameterize a simple scoring function on the fly and use L-BFGS minimization to optimize an initially random ligand pose. Using rigorous benchmarking practices, we demonstrate that our method achieves state-of-the-art performance while running ten times faster than the next-best method. We release PLANTAIN publicly and hope that it improves the utility of virtual screening workflows.

Keywords

Cite

@article{arxiv.2307.12090,
  title  = {PLANTAIN: Diffusion-inspired Pose Score Minimization for Fast and Accurate Molecular Docking},
  author = {Michael Brocidiacono and Konstantin I. Popov and David Ryan Koes and Alexander Tropsha},
  journal= {arXiv preprint arXiv:2307.12090},
  year   = {2023}
}

Comments

Camera-ready submission to ICML CompBio workshop. 5 pages and 1 figure

R2 v1 2026-06-28T11:37:41.178Z