cell-painting

Anomaly detection for high-content image-based phenotypic cell profiling

Validate the semantic correctness, metadata completeness, provenance and AI readiness of Cell Painting datasets represented in AnnData.

Cell Painting-based phenotypic similarity search pipeline for drug mechanism discovery, comparing CNN-derived morphology embeddings with mechanism labels and chemical structure similarity.

Data repository for Sivagurunathan et al., 2025, "Alternate dyes for image-based profiling assays"

A bilingual work-in-progress book on AI-driven phenotypic drug discovery, from high-throughput screening and Cell Painting to machine learning and drug development.

RF models for the prediction of cell viability in muscle cells from Cell Painting profiles.

cpg0011-lipocyteprofiler - Batch1 and Batch3

Locked reanalysis of matched ORF and CRISPR Cell Painting profiles with manuscript, source data, and compact evidence bundle.

This repository contains code for using semi-supervised contrastive learning to learn phenotypical representations from Cell Painting image data for multi-label bioactivity classification

Phenomics perturbation profiling and MoA retrieval from morphological cell-painting profiles (UMAP + HDBSCAN + cosine similarity). POC: LINCS Cell Painting — recall@5 = 3.0× random baseline on 111 compounds across 20 MoA classes.

Predict a compound's mechanism of action from cell images. End-to-end reproducible pipeline on open Cell Painting data: 5-channel microscopy → segmentation → morphological fingerprints → MoA retrieval.

quickly generate overviews of Cell Painting image plates

Leakage-aware benchmark and research prototype for natural-language retrieval over Cell Painting perturbation profiles.

Framework for end-to-end processing of high throughput microscopy.

Text-supervised contrastive learning that aligns Cell Painting microscopy embeddings with biological perturbation descriptions for cross-modal perturbation matching.

🛠️ Use me to version control Pooled Cell Painting data and processing pipelines

A morphology scout for discovering representative cell phenotypes with Stable Diffusion

Image-based profiling and machine learning to predict failing vs. non-failing cardiac fibroblasts

Single cell analysis of the JUMP Cell Painting consortium pilot data (cpg0000)

Benchmarking data processing strategies for Cell Painting data of NF1 Schwann cells. See analysis repository (https://github.com/WayScience/NF1_SchwannCell_data_analysis) for information on how the data was interpreted.