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

TL;DR

PLANTAIN introduces a diffusion-inspired neural network approach for rapid and accurate molecular docking, significantly improving speed and performance over existing methods.

Contribution

It combines diffusion-inspired scoring with L-BFGS optimization to create a fast, effective docking method that outperforms current state-of-the-art techniques.

Findings

Achieves state-of-the-art docking accuracy

Runs ten times faster than previous methods

Validated with rigorous benchmarking

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.