OpenPhenom EU AI Act Compliance Profile

Model Card for OpenPhenom-S/16

Channel-agnostic image encoding model CA-MAE with a ViT-S/16 encoder backbone designed for microscopy image featurization. The model uses a vision transformer backbone with channelwise cross-attention over patch tokens to create contextualized representations separately for each channel.

Model Details

Model Description

This model is a channel-agnostic masked autoencoder trained to reconstruct microscopy images over three datasets:

1. RxRx3
2. JUMP-CP overexpression
3. JUMP-CP gene-knockouts

• Developed, funded, and shared by: Recursion
• Model type: Vision transformer CA-MAE
• Image modality: Optimized for microscopy images from the CellPainting assay
• License: Non-Commercial End User License Agreement

Installation

Requires Python 3.10.4 or higher. From a clone of the repository:

Model Sources

• Repository: https://github.com/recursionpharma/maes_microscopy
• Paper: Masked Autoencoders for Microscopy are Scalable Learners of Cellular Biology

Uses

NOTE: model embeddings tend to extract features only after using standard batch correction post-processing techniques. We recommend, at a minimum, after inferencing the model over your images, to do the standard PCA-CenterScale pattern or better yet Typical Variation Normalization:

1. Fit a PCA kernel on all the control images (or all images if no controls) from across all experimental batches (e.g. the plates of wells from your assay),
2. T

Your obligations as a OpenPhenom deployer

Track your progress

Sign up to track obligations, receive deadline reminders, and generate audit packages.

Tags

Library