search

Teichlab / bbknn

Batch balanced KNN
MIT License
149 stars 25 forks source link

bbknn spark error when runing with data integrated from scRNA data #29

Closed honghh2018 closed 4 years ago

honghh2018 commented 4 years ago

Hi @Teichlab, The weird condition occurred from data integrated through scanpy using bbknn. The samples can be integrated by umap plot, but the tsne plotting showing the data that can not be integrated.

image UMAP showing integrated

image TSNE showing no integrated

  The different showing below between umap and tsne.
   Based on this, how can i get same integrated effect on tsne when using bbknn to integrated. if it should not been done,
   whether had another way to replace this selection?

Best hanhuihong

ktpolanski commented 4 years ago

I'd like to defer you to the innards of sc.tl.tsne(), wherein you'll see that the TSNE operates in a manner independent of the neighbour graph. BBKNN's output isn't seen by the algorithm.