NMF

A_preprocessing.nmf_clustering(adata, n_components=10, random_state=42, max_iter=1000, verbose=0, n_top_genes=2000)

Performs NMF clustering on AnnData object.

Parameters:

• adata – AnnData object containing gene expression data

• n_components – Number of NMF components to extract

• random_state – Random seed for reproducibility

• max_iter – Maximum number of iterations for NMF

• verbose – Verbosity level

• n_top_genes – Number of highly variable genes to use

Returns:

AnnData object with NMF results in .obsm[‘X_nmf’] and .uns[‘X_nmf_components’]

A_preprocessing.nmf_consensus(adata, min_clusters=4, max_clusters=10, n_resamples=100, resample_frac=0.8, random_state=42, n_cluster_genes=50)

Performs consensus clustering on NMF results.

Parameters:

• adata – AnnData object with NMF results

• min_clusters – Minimum number of clusters to try

• max_clusters – Maximum number of clusters to try

• n_resamples – Number of resampling iterations

• resample_frac – Fraction of samples to use in each resample

• random_state – Random seed for reproducibility

• n_cluster_genes – Number of top genes to use per cluster

Returns:

AnnData object with cluster scores in .obs