search

theislab / chemCPA

Code for "Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution", NeurIPS 2022.
https://arxiv.org/abs/2204.13545
MIT License
88 stars 23 forks source link

Fix control + (+)-JQ1 #51

Closed siboehm closed 2 years ago

siboehm commented 2 years ago

I added the SMILES for control and renamed the one weird drug. @MxMstrmn Can you run this once on the cluster? I'm getting permission denied errors when I try to save the the dataset directory in storage

review-notebook-app[bot] commented 2 years ago

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB

siboehm commented 2 years ago

@MxMstrmn There's another issue, the control column in trapnell_cpa.h5ad is all-0. This is because in linc_trapnell_gene_matching.ipynb, the control is matched against Vehicle_1.0, which doesn't exists (it's called control_1.0 I think. Can you check this? Feel free to add commits to this PR.

MxMstrmn commented 2 years ago

@siboehm , the last commit fixes the above issues. h5ad files are updated on the server