search

theislab / cpa

The Compositional Perturbation Autoencoder (CPA) is a deep generative framework to learn effects of perturbations at the single-cell level. CPA performs OOD predictions of unseen combinations of drugs, learns interpretable embeddings, estimates dose-response curves, and provides uncertainty estimates.
BSD 3-Clause "New" or "Revised" License
88 stars 17 forks source link

About sciplex3 dataset in Figure 2 #60

Open ranzhran opened 2 months ago

ranzhran commented 2 months ago

Hi, thanks for your nice work! I am interested in the results from Figure 2, but I couldn't find the sciplex dataset: sci-Plex samples (n = 290,889) of A549, K562, and MCF7 cell lines.

Could you please let me know how to obtain the preprocessed dataset as described in your code? adata = sc.read('/home/icb/carlo.dedonno/projects/cpa-reproducibility/datasets/sciplex3_new.h5ad') adata_old = sc.read('/home/icb/carlo.dedonno/projects/cpa-reproducibility/datasets/sciplex3_old_reproduced.h5ad'

Thank you very much!

miladrvahid commented 1 month ago

@Naghipourfar and @ArianAmani Dear Mohsen and Arian, sharing those data would be very helpful for me as well. Thanks a lot!