MolCLIP: A Molecular-Auxiliary CLIP Framework for Identifying Drug Mechanism of Action Based on Time-Lapsed Mitochondrial Images

TL;DR

MolCLIP is a novel visual language model that integrates time-lapsed mitochondrial videos and molecular data to improve drug mechanism of action identification, outperforming previous methods significantly.

Contribution

This work introduces MolCLIP, the first model combining microscopic cell videos and molecular modalities for MoA recognition, leveraging a molecule-auxiliary CLIP framework and metric learning.

Findings

Achieves 51.2% improvement in drug identification mAP

Achieves 20.5% improvement in MoA recognition mAP

Demonstrates effectiveness on the MitoDataset

Abstract

Drug Mechanism of Action (MoA) mainly investigates how drug molecules interact with cells, which is crucial for drug discovery and clinical application. Recently, deep learning models have been used to recognize MoA by relying on high-content and fluorescence images of cells exposed to various drugs. However, these methods focus on spatial characteristics while overlooking the temporal dynamics of live cells. Time-lapse imaging is more suitable for observing the cell response to drugs. Additionally, drug molecules can trigger cellular dynamic variations related to specific MoA. This indicates that the drug molecule modality may complement the image counterpart. This paper proposes MolCLIP, the first visual language model to combine microscopic cell video- and molecule-modalities. MolCLIP designs a molecule-auxiliary CLIP framework to guide video features in learning the distribution of the molecular latent space. Furthermore, we integrate a metric learning strategy with MolCLIP to optimize the aggregation of video features. Experimental results on the MitoDataset demonstrate that MolCLIP achieves improvements of 51.2% and 20.5% in mAP for drug identification and MoA recognition, respectively.