broadinstitute/cell-painting-vae

Predicting drug polypharmacology from cell morphology readouts using variational autoencoder latent space arithmetic

Variational Autoencoder on Cell Painting Data

Computational Environment

First install conda (https://docs.conda.io/en/latest/).

Then, to create the computational environment, run:

conda env create -f environment.yml
conda activate cell-painting-vae

To reproduce results, follow the instructions in each analysis module in the following order:

0.preprocessing

1.optimize

2.train

3.application