In this repository, we apply the phenotypic profiling model, which predicts phenotypic class of single cells using nuclei features, to the JUMP-Target pilot data from the JUMP consortium.
In this dataset, there are 51 plates with one of three perturbation types (Clustered Regularly Interspaced Short Palindromic Repeats [CRISPR], Open Reading Frame [ORF], and Compound) for two cell lines (A549 and U2OS).
Each perturbation type has it's own platemap and metadata file that can be found in the reference_plate_data folder. A barcode platemap is include which associates each plate to the correct platemap file.
We segment a total of 20,959,860 single cells in all plates.
To reproduce this project, please ensure adequate storage as the CellProfiler SQLite database files are approximately 1.1 TB.
Traditional image-based profiling pipelines aggregate single-cells into well-level profiles. While, this process removes outliers that might dampen signal, it also removes potentially interesting biologically-meaningful heterogeneity.
By predicting single-cell phenotypes with our phenotypic profiling model, we hope to uncover important patterns of biology that would be missed with the traditional methodology. Specifically, the benefits of single-cell phenotyping include:
- Granular phenotypic mechanisms of perturbations regarding (A) the impact perturbations have on a specific phenotype (e.g., disrupting mitosis) and (B) impact on phenotype prevalence (e.g., a gene knockout that causes apoptosis or stalls cells in a specific cell cycle phase).
- Filter and/or combine cells of the same phenotypic class to purify and/or improve the traditional image-based profiling pipeline.
- Adding knowledge to specific combinations of morphology features allows for self-referential interpretation, without the need for database signature lookup or other guilt-by-association methods.
- When combined with different experimental designs (e.g., targeted fluorescence marker), we can test specific hypotheses regarding single-cell phenotype distributions (and other important hypotheses that would otherwise be impossible without single-cell phenotypes).
| Module | Purpose | Description |
|---|---|---|
| 0.download_data | Download JUMP-Target SQLite files and process them with CytoTable | We download the CellProfiler SQLite outputs for 51 plates from AWS and process them into Parquet files which combine compartment and image metadata as a single table. |
| 1.process_data | Process SQLite files | We use pycytominer on the SQLite outputs to merge single-cells and normalize features |
| 2.evaluate_data | Apply phenotypic profiling model | We generate phenotypic predictions for single-cells using the phenotypic profiling model |
| 3.analyze_data | Analyze phenotypic predictions | We perform multiple analyses to validate the phenotypic predicted class for each perturbation compared to control |
| reference_plate_data | Platemaps per perturbation type | This folder holds the platemap files with metadata based on perturbation type and the barcode platemap file |
We use a justfile to specify just commands for use with this project.
Please see just installation details for configuration on your system.
For all modules, we use conda environments that includes all necessary packages.
To create the environment from terminal, run the code line below:
# Make sure you are in the same directory as the environment file
conda env create -f environment.ymlAlternatively, use the following just command.
# setup or update conda envs
just setup-conda-envsjust commands are provided for processing each step.
There also is a command which can run all processing steps.
Individual steps:
# run step 0.download_data
just run-step-0Run all steps:
# run all steps
just run-all-steps