search

QUST-AIBBDRC / scGMAI

scGMAI: a Gaussian mixture model for clustering single-cell RNA-seq data based on deep autoencoder
15 stars 4 forks source link

Transform vs. Reconstruct #2

Open maese005 opened 2 years ago

maese005 commented 2 years ago

Hello,

Thank you for providing such a novel tool for clustering scRNAseq data.

I saw in your autoencoder python scripts that two variables are generated using the two lines below: X_test_transform=autoencoder.transform(X_train) X_test_reconstruct=autoencoder.reconstruct(X_train)

I also saw that the reconstructed X_test is passed forward into NMF, FastICA, etc. May you please clarify the difference between the X_test_transform and X_test_reconstruct?

Thank you.

Sincerely, Danielle

handesome commented 1 year ago

Hello,

Thank you for providing such a novel tool for clustering scRNAseq data.

I saw in your autoencoder python scripts that two variables are generated using the two lines below: X_test_transform=autoencoder.transform(X_train) X_test_reconstruct=autoencoder.reconstruct(X_train)

I also saw that the reconstructed X_test is passed forward into NMF, FastICA, etc. May you please clarify the difference between the X_test_transform and X_test_reconstruct?

Thank you.

Sincerely, Danielle

have you figured out? i'm confused about the code,so could you give some advice?Thanks