Improved Conditional Flow Models for Molecule to Image Synthesis
This work addresses a domain-specific problem in drug development by enabling image synthesis from molecular data, though it is incremental as it builds on existing graph neural networks and flow-based models.
The paper tackles the problem of synthesizing cell microscopy images from molecular interventions for drug development, proposing Mol2Image, a flow-based generative model with a multi-scale architecture and contrastive learning, and introduces new evaluation metrics for biological image generation.
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.