Skip to content
netNMF-sc: A network regularization algorithm for dimensionality reduction and imputation of single-cell expression data
Jupyter Notebook Python
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Type Name Latest commit message Commit time
Failed to load latest commit information.
netNMFsc_example.ipynb Add files via upload Mar 26, 2019


netNMF-sc: Leveraging gene-gene interactions for imputation and dimensionality reduction in single-cell expression analysis.

Preprint is available at


netNMF-sc is installable through pip: pip3 install netNMFsc

Or by cloning this repository

Running netNMF-sc

See netNMFsc_example.ipynb for a jupyter notebook tutorial for importing and running netNMF-sc. netNMF-sc can also be run from the command line using the following command:

python3 -m netNMFsc.run_netNMF-sc -x <path_to_10X_directory> --network netNMFsc/refdata/coexpedia_network_human.mtx (or a network of your choice) --netgenes netNMFsc/refdata/coexpedia_gene_names_human.npy --dimensions --max_iters --direc <directory_to_save_output> --method GD

Command line arguments

-x,--tenXdir, data is from 10X. Only required to provide directory containing matrix.mtx, genes.tsv, barcodes.tsv files or .hdf5 file
-g,--gene_names, path to file containing gene names (.npy or .tsv)
-net,--network, path to network file (.npy or .mtx)
-netgenes,--netgenes, path to file containing gene names for network (.npy or .tsv)
-n,--normalize, normalize data? 1 = yes, 0 = no,default=1
-sparse,--sparsity, sparsity for network,default=0.75
-mi,--max_iters, max iters for netNMF,default=10000)
-t,--tol, tolerence for netNMF,default=1e-2
-d,--direc, directory to save files
-D,--dimensions, number of latent dimension, default = 10
-a,--alpha, lambda parameter from NMF,default = 10
You can’t perform that action at this time.