Relevant Articles

Integrating deep learning and unbiased automated high-content screening to identify complex disease signatures in human fibroblasts - Nature Communications

This paper discusses how high-content image analysis can be used to discover effective drugs for Parkinson's disease by identifying cell phenotypes following treatment.

https://doi.org/10.1038/s41467-022-28423-4

Building, benchmarking, and exploring perturbative maps of transcriptional and morphological data

This paper explains how to build and benchmark perturbative maps to examine and compare cellular responses to different drug treatments.

https://doi.org/10.1016/j.coisb.2019.03.008

Cell Painting, a high-content image-based assay for morphological profiling using multiplexed fluorescent dyes - Nature Protocols

This paper gives a great explanation of Cell Painting protocol, and goes into detail about how staining with fluorescent dyes can can reveal the morphology of a cell.

https://doi.org/10.1038/nprot.2016.105

Predicting cell health phenotypes using image-based morphology profiling | Molecular Biology of the Cell

This paper shows an example of a trained model that can predict around 70 different cell health phenotypes from cell painting features. We might do something similar to ask how each proteostasis compound influences cell health readouts.

https://doi.org/10.1091/mbc.E20-12-0784