snfpy

snfpy copied to clipboard

results of "snf.snf" is not consistent with the orginal SNFtool R package

2

I just used `snf.snf()` to get a similarity matrix. When I set the same K value, I just found the returning matrix is not same with the original R package.Could...

szz65

value error

1

Dear developer, I tried a real dataset GBM from original paper but got the following error. Could you please help? Thanks! mirna = pd.read_csv('GLIO_Mirna_Expression.txt', index_col=0, sep='\t') exp = pd.read_csv('GLIO_Gene_Expression.txt', index_col=0,...

QUEST2179

initial virtualization draft

1

This PR introduces an initial virtualization draft for `snfpy`. It adds the following files: - `generate_snfpy_images.sh` : a small `bash` script that uses [neurodocker](https://github.com/ReproNim/neurodocker) to create `Docker` and `Singularity` files...

PeerHerholz

Currently the function calculates the graph laplacian and attempts to find the optimal number of clusters via the "eigengap" method, but: 1. We should probably be using ``scipy.sparse.csgraph.laplacian()`` to generate...

rmarkello

Run for large number of samples

1

Is it possible to speed up SNF for more than 10,000 samples, like single cells?

YYT1002

Created an snf_sparse function that allows the use of sparse affinity matrices (CSR matrices) rather than dense matrices. This reduces the memory constraints from O(NxN) to O(NxK), which will make...

James-Mc1ntyre