Molecule-Morphology Contrastive Pretraining for Transferable Molecular Representation

TL;DR

This paper introduces MoCoP, a contrastive pretraining framework that leverages large-scale cellular morphology data to enhance molecular property prediction models, showing consistent improvements across multiple datasets and regimes.

Contribution

The authors develop MoCoP, a novel multi-modal contrastive pretraining method that integrates cellular morphology data with molecular graphs for better QSAR modeling.

Findings

MoCoP improves GNN performance on ChEMBL20 tasks.

Pretrained GNNs show 2.6% and 6.3% AUPRC improvements on GSK data.

Scaling MoCoP to large datasets enhances molecular property prediction.

Abstract

Image-based profiling techniques have become increasingly popular over the past decade for their applications in target identification, mechanism-of-action inference, and assay development. These techniques have generated large datasets of cellular morphologies, which are typically used to investigate the effects of small molecule perturbagens. In this work, we extend the impact of such dataset to improving quantitative structure-activity relationship (QSAR) models by introducing Molecule-Morphology Contrastive Pretraining (MoCoP), a framework for learning multi-modal representation of molecular graphs and cellular morphologies. We scale MoCoP to approximately 100K molecules and 600K morphological profiles using data from the JUMP-CP Consortium and show that MoCoP consistently improves performances of graph neural networks (GNNs) on molecular property prediction tasks in ChEMBL20 across all dataset sizes. The pretrained GNNs are also evaluated on internal GSK pharmacokinetic data and show an average improvement of 2.6% and 6.3% in AUPRC for full and low data regimes, respectively. Our findings suggest that integrating cellular morphologies with molecular graphs using MoCoP can significantly improve the performance of QSAR models, ultimately expanding the deep learning toolbox available for QSAR applications.