Improved Conditional Flow Models for Molecule to Image Synthesis

TL;DR

This paper introduces Mol2Image, a flow-based model that synthesizes cell microscopy images conditioned on molecular interventions, utilizing a multi-scale architecture and contrastive learning to capture biological effects.

Contribution

It presents a novel multi-scale flow architecture with a Haar wavelet pyramid and a contrastive training strategy for molecule-to-image synthesis in biological contexts.

Findings

Model learns meaningful molecular intervention embeddings

Generated images reflect biological effects accurately

Proposed metrics are robust and interpretable

Abstract

In this paper, we aim to synthesize cell microscopy images under different molecular interventions, motivated by practical applications to drug development. Building on the recent success of graph neural networks for learning molecular embeddings and flow-based models for image generation, we propose Mol2Image: a flow-based generative model for molecule to cell image synthesis. To generate cell features at different resolutions and scale to high-resolution images, we develop a novel multi-scale flow architecture based on a Haar wavelet image pyramid. To maximize the mutual information between the generated images and the molecular interventions, we devise a training strategy based on contrastive learning. To evaluate our model, we propose a new set of metrics for biological image generation that are robust, interpretable, and relevant to practitioners. We show quantitatively that our method learns a meaningful embedding of the molecular intervention, which is translated into an image representation reflecting the biological effects of the intervention.