squidpy.experimental.im.VahadaneParams

class squidpy.experimental.im.VahadaneParams(beta=0.15, lambda1=0.1, n_iter=200, random_state=0)[source]

Tuning knobs for Vahadane (sparse-NMF) stain-matrix fitting.

Methods

Attributes

`beta`	Mean-absorbance cutoff selecting tissue pixels (optical-density space).
`lambda1`	L1 sparsity regularisation on the concentration factor of the NMF.
`n_iter`	Maximum NMF iterations.
`random_state`	Seed for NMF initialisation tie-breaking; fixed for reproducible fits.