Filter observations (samples or cells) in-place using any column in .obs or in .X.
More details on the muon documentation
Filter variables (features, e.g. genes) in-place using any column in .var or row in .X.
More details on the muon documentation
Subset observations (samples or cells) in-place taking observations present only in all modalities.
More details on the muon documentation
Normalize observations to unit L2 norm.
More details on the muon documentation
Multimodal nearest neighbor search by implementing the multimodal nearest neighbor method of Hao et al. and Swanson et al. The neighbor search efficiency on this heavily relies on UMAP. In particular, you may want to decrease n_multineighbors for large data set to avoid excessive peak memory use. To achieve results as close as possible to the Seurat implementation, observations must be normalized to unit L2 norm prior to running per-modality nearest-neighbor search.
More details on the muon documentation