# Compressing Biology: Evaluating the Stable Diffusion VAE for Phenotypic Drug Discovery

arXiv: https://arxiv.org/abs/2510.19887 · HTML: https://mlsanity.com/paper/2510.19887/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Flow matching, time series and science, one of 14 directions in Diffusion models.
- Builds on 11 of its 31 references that are in the map.
- First posted on arXiv 22 Oct 2025.

## Placed in

- Diffusion models / [Flow matching, time series and science](https://mlsanity.com/diffusion/flow-matching-time-series-and-science/)

## Builds on (most cited first, 11 of 11)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers](https://mlsanity.com/paper/2504.10483/) (2025)
- [EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling](https://mlsanity.com/paper/2502.09509/) (2025)
- [Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology](https://mlsanity.com/paper/2404.10242/) (2024)
- [CellFlux: Simulating Cellular Morphology Changes via Flow Matching](https://mlsanity.com/paper/2502.09775/) (2025)
- [PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real Images](https://mlsanity.com/paper/2312.08290/) (2023)
- [RxRx3-core: Benchmarking drug-target interactions in High-Content Microscopy](https://mlsanity.com/paper/2503.20158/) (2025)
- [Class-Guided Image-to-Image Diffusion: Cell Painting from Brightfield Images with Class Labels](https://mlsanity.com/paper/2303.08863/) (2023)

## Built on by (most cited first, 1 of 1)

- [Mutual Information Collapse Explains Disentanglement Failure in β-VAEs](https://mlsanity.com/paper/2602.09277/) (2026)

## Abstract (arXiv)

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.