- muon.tl.snf(mdata: mudata._core.mudata.MuData, n_neighbors: int = 20, neighbor_keys: Optional[Union[str, Dict[str, Optional[str]]]] = None, key_added: Optional[str] = None, n_iterations: int = 20, sigma: float = 0.5, eps: float = 2.220446049250313e-16, copy: bool = False) Optional[mudata._core.mudata.MuData] #
Similarity network fusion (SNF)
See Wang et al., 2014 (DOI: 10.1038/nmeth.2810).
Reference implementation can be found in the SNFtool R package: https://github.com/cran/SNFtool/blob/master/R/SNF.R
mdata – MuData object
n_neighbors (int (default: 20)) – Number of neighbours to be used in the K-nearest neighbours step
neighbor_keys (Keys in .uns where per-modality neighborhood information is stored. Defaults to
"neighbors".) – If set as a dictionary, only the modalities present in
neighbor_keyswill be used for multimodal nearest neighbor search. If set as a string, has to exist in all modalities.
key_added (If not specified, the multimodal neighbors data is stored in
.uns["neighbors"], distances and) – connectivities are stored in
.obsp["connectivities"], respectively. If specified, the neighbors data is added to
.uns[key_added], distances are stored in
.obsp[key_added + "_distances"]and connectivities in
.obsp[key_added + "_connectivities"].
n_iterations (int (default: 20)) – Number of iterations for the diffusion process
sigma (float (default: 0.5)) – Variance for the local model when calculating affinity matrices
eps (Small number to avoid numerical errors.) –
copy (Return a copy instead of writing to