##  Dataset
The competition will use the publicly available 2020_11_04_CPJUMP1 dataset from Chandrasekaran et al (2024). The dataset contains images generated using chemical and genetic perturbation and 2 cell lines: U2OS and A549 in multiple replicates. Images and corresponding CellProfiler features are available. [Here](https://github.com/jump-cellpainting/2024_Chandrasekaran_NatureMethods), participants can find a more detailed description of the dataset and instructions to download it. 

##  Task
Develop a method for transfer of information between cell lines using either CellProfiler features or raw images (Deep Learning method). The representations will be evaluated in a set of 24 plates that contain compound-perturbed cells. 
In the file **metadata_test.csv**, one can find the column **ID**, which identifies each sample for which participants should submit representations and their corresponding plate and well.

The input file should be a csv file and contain a column called **ID**, which matches the plate and the well from the **metadata_test.csv** file, and a set of **float** columns that will be the features. The set of feature columns can have any length and will be used in the given order.  There should be only one feature value per column. Features should not have any missing or infinite values.

## Files

*   **metadata_test.csv** - Identifier of the samples that should be submitted, along with their corresponfing plates and well positions
*   **sample_submission.csv** - A sample submission file in the correct format


## Columns

*   `ID` - Sample identifier, that corresponds with the plate and well in **metadata_test.csv**
*   `feature_1` - First feature 
*   ...
*   `feature_N` - Last feature 

## References 

Chandrasekaran, S.N., Cimini, B.A., Goodale, A. et al. Three million images and morphological profiles of cells treated with matched chemical and genetic perturbations. Nat Methods 21, 1114–1121 (2024). https://doi.org/10.1038/s41592-024-02241-6