Lei Xiong

Hi, SCALE model can accommodate over 100k features/peaks, though the default for the current version is select 30,000 highly variable peaks. To include the all the peaks, just git clone...

It sounds like a good idea, maybe you could try that. However, adaptting our model on scRNA-seq with zero-inflated negative binomial with no improvements on the latent representation, neither the...

Thanks for you suggestions. 1. UMAP is enabled in the code, replace the method parameters 'TSNE' to 'UMAP' "scale.plot.plot_embedding" function, however, the option is not available to the user in...

Hi, it is normal if the metrics e.g. ARI, NMI are same or close since there have been several updates of the SCALE version, dependent packages and random seed, it...

Apologies for the inconvenience with the data download. Please find below the alternative links to download the files. https://www.dropbox.com/scl/fi/dnwpv29kcfl449a8aikqi/pancreas.h5ad?rlkey=9me8xa0n1f3lz8qqornkh0ae0&dl=0 https://www.dropbox.com/scl/fi/obdt0ecjjlis6tyekyzyy/pancreas_query.h5ad?rlkey=cwik9m5kqrookmi84vdmwhnqk&dl=0 Let me know if you have any questions.

Hi, thank you for your interest in SCALEX. The original link is broken. You can use this link to download the data you need https://www.dropbox.com/scl/fi/affgmiktg49s3ogmzq8ss/mouse_brain_atac.h5ad?rlkey=iejewl06wuvnflyqfj2rgabwi&dl=0.

You can follow this tutorial https://scalex.readthedocs.io/en/latest/tutorial/Integration_cross-modality.html to get the processed data you want.

The lr is 0.0002 for the Forebrain dataset, you can refer to the Supplementary of our paper for the detail. The results may not be the exact same since the...

Hi Steffen, SCALE has been updated for supporting scanpy that all results are saved in h5ad format file. You should find the binary imputed output in adata.obsm['binary'] after reading the...

Hi Steffen, the 'binary' is obtained after calculating the 'impute' in SCALE, I can del 'impute' if you don't need it. To get a 'binary' without 'impute', you just need...