search

jianhuupenn / SpaGCN

SpaGCN: Integrating gene expression, spatial location and histology to identify spatial domains and spatially variable genes by graph convolutional network
MIT License
199 stars 60 forks source link

Batch effect issue for multiple 10X visium samples #54

Open archanabhardwaj opened 2 years ago

archanabhardwaj commented 2 years ago

Hello

I am having batch effect issue for running multiple sample clustering in spaGCN as indicated in previous post https://github.com/jianhuupenn/SpaGCN/issues/37

Would you please help me if you can explain steps to perform z-score normalization for integrated dataset.

I would appreciate all the suggestion.

Thanks in advance

archanabhardwaj commented 1 year ago

For integrated samples , I used following steps :

1) QC Filteration 2) Integrated four samples with scanpy as suggested in https://nbisweden.github.io/workshop-scRNAseq/labs/compiled/scanpy/scanpy_07_spatial.html using scanorama method.

Is it ok if I run clf=spg.multiSpaGCN on the integrated adata object ?