Memory usage increases when using scanpy clustering

JonathanShor / DoubletDetection

Doublet detection in single-cell RNA-seq data.

https://doubletdetection.readthedocs.io/en/stable/

MIT License

79 stars 23 forks source link

Memory usage increases when using scanpy clustering #142

Open kaylahardwick opened 3 years ago

kaylahardwick commented 3 years ago

Hello- Thanks so much for putting together this useful tool! I've tried both the phenograph clustering and the scanpy clustering, and I've noticed that memory usage creeps up across iterations when I use scanpy. As a result I have not been able to use the louvain method for certain datasets where higher numbers of iterations are required for convergence. Is this something that can be addressed in a future release?

Thanks again!

adamgayoso commented 2 years ago

We can look into this, thanks.

adamgayoso commented 2 years ago

@kaylahardwick I think the problem may be fixed. Would be great if you could confirm!