search

satijalab / seurat

R toolkit for single cell genomics
http://www.satijalab.org/seurat
Other
2.31k stars 919 forks source link

Reproducing scVI result in Seurat v5 vignette #9406

Open shwong-tw opened 1 month ago

shwong-tw commented 1 month ago

Dear developers,

I was going through this vignette Integrative analysis in Seurat v5 and would like to reproduce the figures, mainly to ensure that different integration methods were all configured properly in my pc.

When it comes to comparing CCA and scVI results side by side in this section, the first figure in the vignette suggested that both CCA and scVI managed to have cells from different technologies mixed together rather nicely. However in my hand scVI result did not show similar performance.

The vignette's session info did not contain information about conda environment (where scVI was installed), therefore I ran the vignette under two different conda environment (scVI version 1.0.4 vs 1.2.0), with the results shown below: (A) the figure in the origial vignette

SCVI_Seurat

(B) running vignette under conda installed with scVI version 1.0.4

SCVI_1 0 4

(C) (B) running vignette under conda installed with scVI version 1.2.0

SCVI_1 2 0

It seems to me both (B) scVI v1.0.4 and (C) scVI 1.2.0 did not have all technologies integrated very well as in the vignette (A), e.g. looking at the reddish cells.

It would be great to hear some feedback from the developers, whether you'd be able to provide more information about the scVI conda environment used in the vignette, or whether you (or anyone) would observe the same phenomenon when you re-run this vignette.

Thank you very much!

longmanz commented 1 week ago

Hi, Thank you for reporting this. Can you share your full conda env information with us if possible? Also, did you run the same commands as in the vignette? If not, could you share your full commands with us? Many thanks.

shwong-tw commented 1 week ago

Hi,

In order to reproduce the tutorial result, I used the same data and code as in the tutorial; I've also tried two scVI versions in the backend (current release v 1.2.0, vs v1.0.4 to match the date the tutorial was written)

Currently I only keep the conda environment for scVI 1.2.0, please find all packages in the file: SCVI_Conda_Env.txt. You can also find the scVI version release date here Unfortunately I no longer keep the scVI v1.0.4 environment and it will be painful to construct different conda environments again (I've tried different versions which already used up all my patience ...)

Would it be possible that you could offer some feedback regarding whether the figure is reproducible from your side? If yes, which scVI version are you using? That might be most straitforward to figure out the cause.

Thank you very much!