PharmacoNet: Accelerating Large-Scale Virtual Screening by Deep Pharmacophore Modeling

TL;DR

PharmacoNet introduces a deep learning framework for rapid, structure-based pharmacophore modeling and protein-ligand binding prediction, significantly accelerating virtual screening processes for large compound libraries.

Contribution

It is the first to frame pharmacophore modeling as an instance segmentation problem and protein-ligand prediction as graph matching, enabling faster virtual screening.

Findings

PharmacoNet is significantly faster than existing methods.

It maintains reasonable accuracy with a simple scoring function.

It effectively retains hit candidates under high pre-screening filtration.

Abstract

As the size of accessible compound libraries expands to over 10 billion, the need for more efficient structure-based virtual screening methods is emerging. Different pre-screening methods have been developed for rapid screening, but there is still a lack of structure-based methods applicable to various proteins that perform protein-ligand binding conformation prediction and scoring in an extremely short time. Here, we describe for the first time a deep-learning framework for structure-based pharmacophore modeling to address this challenge. We frame pharmacophore modeling as an instance segmentation problem to determine each protein hotspot and the location of corresponding pharmacophores, and protein-ligand binding pose prediction as a graph-matching problem. PharmacoNet is significantly faster than state-of-the-art structure-based approaches, yet reasonably accurate with a simple scoring function. Furthermore, we show the promising result that PharmacoNet effectively retains hit candidates even under the high pre-screening filtration rates. Overall, our study uncovers the hitherto untapped potential of a pharmacophore modeling approach in deep learning-based drug discovery.