MaskMol: Knowledge-guided Molecular Image Pre-Training Framework for Activity Cliffs

TL;DR

MaskMol is a knowledge-guided molecular image pre-training framework that effectively captures subtle structural differences in molecules, improving activity cliff estimation and drug discovery applications.

Contribution

The paper introduces MaskMol, a novel self-supervised learning framework that leverages molecular images and multiple levels of molecular knowledge for better activity cliff detection.

Findings

Outperforms 25 state-of-the-art models in activity cliff estimation.

Demonstrates high transferability across 20 macromolecular targets.

Provides high interpretability in identifying relevant molecular substructures.

Abstract

Activity cliffs, which refer to pairs of molecules that are structurally similar but show significant differences in their potency, can lead to model representation collapse and make the model challenging to distinguish them. Our research indicates that as molecular similarity increases, graph-based methods struggle to capture these nuances, whereas image-based approaches effectively retain the distinctions. Thus, we developed MaskMol, a knowledge-guided molecular image self-supervised learning framework. MaskMol accurately learns the representation of molecular images by considering multiple levels of molecular knowledge, such as atoms, bonds, and substructures. By utilizing pixel masking tasks, MaskMol extracts fine-grained information from molecular images, overcoming the limitations of existing deep learning models in identifying subtle structural changes. Experimental results demonstrate MaskMol's high accuracy and transferability in activity cliff estimation and compound potency prediction across 20 different macromolecular targets, outperforming 25 state-of-the-art deep learning and machine learning approaches. Visualization analyses reveal MaskMol's high biological interpretability in identifying activity cliff-relevant molecular substructures. Notably, through MaskMol, we identified candidate EP4 inhibitors that could be used to treat tumors. This study not only raises awareness about activity cliffs but also introduces a novel method for molecular image representation learning and virtual screening, advancing drug discovery and providing new insights into structure-activity relationships (SAR).