You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
This works well for label transfer and projection (ref.umap), but it only gives a mapped embedding, not a new integrated space.
Is there a way in Seurat to:
obtain a joint latent space after bridge integration, and
cluster all cells together in that space?
Or is bridge intended mainly for mapping/annotation, with clustering expected to be done separately (e.g. ATAC-only integration)?
In my data, the bridge projection reveals meaningful structure that other integrations don’t capture, so I’d ideally like to cluster in a bridge-informed space if possible.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
Hi,
I am using bridge integration (multiome + scATAC) and had a question about obtaining a joint embedding for clustering.
I followed the standard workflow:
This works well for label transfer and projection (
ref.umap), but it only gives a mapped embedding, not a new integrated space.Is there a way in Seurat to:
Or is bridge intended mainly for mapping/annotation, with clustering expected to be done separately (e.g. ATAC-only integration)?
In my data, the bridge projection reveals meaningful structure that other integrations don’t capture, so I’d ideally like to cluster in a bridge-informed space if possible.
Thanks!
All reactions