Compressing Biology: Evaluating the Stable Diffusion VAE for Phenotypic Drug Discovery
This work addresses the need for practical evaluation guidelines and efficient models in phenotypic drug discovery, though it is incremental as it focuses on benchmarking existing methods rather than introducing new ones.
The paper tackled the problem of evaluating Stable Diffusion's variational autoencoder (SD-VAE) for reconstructing high-dimensional microscopy images in phenotypic drug discovery, finding that it preserves phenotypic signals with minimal loss and that general-purpose feature extractors like InceptionV3 perform competitively in retrieval tasks.
High-throughput phenotypic screens generate vast microscopy image datasets that push the limits of generative models due to their large dimensionality. Despite the growing popularity of general-purpose models trained on natural images for microscopy data analysis, their suitability in this domain has not been quantitatively demonstrated. We present the first systematic evaluation of Stable Diffusion's variational autoencoder (SD-VAE) for reconstructing Cell Painting images, assessing performance across a large dataset with diverse molecular perturbations and cell types. We find that SD-VAE reconstructions preserve phenotypic signals with minimal loss, supporting its use in microscopy workflows. To benchmark reconstruction quality, we compare pixel-level, embedding-based, latent-space, and retrieval-based metrics for a biologically informed evaluation. We show that general-purpose feature extractors like InceptionV3 match or surpass publicly available bespoke models in retrieval tasks, simplifying future pipelines. Our findings offer practical guidelines for evaluating generative models on microscopy data and support the use of off-the-shelf models in phenotypic drug discovery.