question for cell embedding with multiomics data

gao-lab / GLUE

Graph-linked unified embedding for single-cell multi-omics data integration

MIT License

376 stars 56 forks source link

question for cell embedding with multiomics data #49

Closed Dragonlongzhilin closed 1 year ago

Dragonlongzhilin commented 2 years ago

Thanks for developing a nice tool! I used glue to integrate scRNA-seq and scATAC-seq datasets from multiple samples. I want to get clustering results covering both modalities in the umap plot. What can I do to get this information? Can I do clustering on embedding space？ Can I come up with batch-corrected data for clustering？

Jeff1995 commented 2 years ago

Thanks for your interest in GLUE! Yes you can use the cell embeddings for clustering. E.g., in scanpy the following should do:

combined = ad.concat([rna, atac])
sc.pp.neighbors(combined, use_rep="X_glue")
sc.tl.leiden(combined)

For batch correction you can specify the batch covariate via use_batch in configure_dataset.

Let me know if there were other issues!