suinleelab/CellCLIP

[NeurIPS 2025] CellCLIP – Learning Perturbation Effects in Cell Painting via Text-Guided Contrastive Learning

37
/ 100
Emerging

This project helps biological researchers and drug discovery scientists analyze how different treatments or genetic changes affect cell appearance, using high-throughput Cell Painting images. It takes raw Cell Painting images and associated experimental details (like drug names or genetic perturbations) and produces biologically meaningful representations. These representations allow you to easily find similar cell responses or match specific visual changes to their corresponding treatments.

Use this if you work with Cell Painting data and need to connect specific visual changes in cells to the treatments or genetic perturbations that caused them, for tasks like drug discovery or toxicology screening.

Not ideal if you are working with other types of biological imaging data (e.g., immunohistochemistry, fluorescence microscopy) that are not Cell Painting, or if you don't need to link images to textual descriptions of perturbations.

cell-painting drug-discovery toxicology phenotypic-screening bioimage-analysis
No Package No Dependents
Maintenance 6 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 11 / 25

How are scores calculated?

Stars

12

Forks

2

Language

Python

License

Last pushed

Nov 11, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/suinleelab/CellCLIP"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.