A fully differentiable ligand pose optimization framework guided by deep learning and traditional scoring functions

TL;DR

This paper introduces a fully differentiable ligand pose optimization framework combining deep learning and traditional scoring functions, significantly improving docking success rates in virtual drug screening.

Contribution

The work presents a novel hybrid scoring function that is fully differentiable, enabling end-to-end ligand pose optimization with superior accuracy over existing methods.

Findings

Achieved 95.4% success rate on CASF-2016 dataset

Significantly improved docking success rate by 15% in redocking and crossdocking

Demonstrated high potential for drug discovery applications

Abstract

The machine learning (ML) and deep learning (DL) techniques are widely recognized to be powerful tools for virtual drug screening. The recently reported ML- or DL-based scoring functions have shown exciting performance in predicting protein-ligand binding affinities with fruitful application prospects. However, the differentiation between highly similar ligand conformations, including the native binding pose (the global energy minimum state), remains challenging which could greatly enhance the docking. In this work, we propose a fully differentiable framework for ligand pose optimization based on a hybrid scoring function (SF) combined with a multi-layer perceptron (DeepRMSD) and the traditional AutoDock Vina SF. The DeepRMSD+Vina, which combines (1) the root mean square deviation (RMSD) of the docking pose with respect to the native pose and (2) the AutoDock Vina score, is fully differentiable thus is capable of optimizing the ligand binding pose to the energy-lowest conformation. Evaluated by the CASF-2016 docking power dataset, the DeepRMSD+Vina reaches a success rate of 95.4%, which is by far the best reported SF to date. Based on this SF, an end-to-end ligand pose optimization framework was implemented to improve the docking pose quality. We demonstrated that this method significantly improves the docking success rate (by 15%) in redocking and crossdocking tasks, revealing the high potentialities of this framework in drug design and discovery.