Related Experiment Video
Updated: Nov 18, 2025
A Multimodal Imaging Framework to Advance Phenotyping of Living Label-free Breast Cancer Cells
Published on: August 22, 2025
Predicting cell health phenotypes using image-based morphology profiling
Gregory P Way1, Maria Kost-Alimova2, Tsukasa Shibue2
1Imaging Platform, Cambridge, MA 02142.
Abstract:
Genetic and chemical perturbations impact diverse cellular phenotypes, including multiple indicators of cell health. These readouts reveal toxicity and antitumorigenic effects relevant to drug discovery and personalized medicine. We developed two customized microscopy assays, one using four targeted reagents and the other three targeted reagents, to collectively measure 70 specific cell health phenotypes including proliferation, apoptosis, reactive oxygen species, DNA damage, and cell cycle stage. We then tested an approach to predict multiple cell health phenotypes using Cell Painting, an inexpensive and scalable image-based morphology assay. In matched CRISPR perturbations of three cancer cell lines, we collected both Cell Painting and cell health data. We found that simple machine learning algorithms can predict many cell health readouts directly from Cell Painting images, at less than half the cost. We hypothesized that these models can be applied to accurately predict cell health assay outcomes for any future or existing Cell Painting dataset. For Cell Painting images from a set of 1500+ compound perturbations across multiple doses, we validated predictions by orthogonal assay readouts. We provide a web app to browse predictions: http://broad.io/cell-health-app. Our approach can be used to add cell health annotations to Cell Painting datasets.
Insights
We developed a cost-effective method using Cell Painting images and machine learning to predict cell health phenotypes, aiding drug discovery and personalized medicine.
Area of Science:
- Cellular biology
- Computational biology
- Drug discovery
Background:
- Cellular phenotypes, including health indicators, are affected by genetic and chemical perturbations.
- These phenotypes are crucial for understanding drug toxicity and antitumorigenic effects in drug discovery and personalized medicine.
- Existing methods for measuring cell health phenotypes can be costly and complex.
Purpose of the Study:
- To develop and validate an approach for predicting multiple cell health phenotypes using Cell Painting, an image-based morphology assay.
- To assess the cost-effectiveness and scalability of using Cell Painting for cell health profiling.
- To enable the annotation of existing and future Cell Painting datasets with cell health information.
Main Methods:
- Developed two customized microscopy assays to measure 70 specific cell health phenotypes.
- Collected matched Cell Painting and cell health data from CRISPR perturbations in three cancer cell lines.
- Applied simple machine learning algorithms to predict cell health readouts from Cell Painting images.
- Validated predictions using orthogonal assay readouts on a dataset of over 1500 compound perturbations.
Main Results:
- Machine learning models accurately predicted numerous cell health readouts directly from Cell Painting images.
- The Cell Painting approach achieved predictions at less than half the cost of traditional methods.
- Predictions were validated across a large dataset of compound perturbations, demonstrating robustness.
- A web application was developed to allow browsing of the predictions.
Conclusions:
- Cell Painting combined with machine learning offers a cost-effective and scalable method for predicting cell health phenotypes.
- This approach can significantly enhance the value of existing and future Cell Painting datasets by adding cell health annotations.
- The findings have implications for accelerating drug discovery and advancing personalized medicine through comprehensive cell health profiling.
