Consistent significance threshold naming

[LuisHeinzlmeier]

Description of feature

I added consistent naming for most of the significance thresholds in #974, but wasn't sure if we should do the same with the following parameter names:

anova_alpha and empirical_alpha:

pertpy/pertpy/tools/_dialogue.py

Lines 365 to 379 in 8a5c178

	class Dialogue:
	"""Multicellular program discovery (DIALOGUE).
	Args:
	celltype_key: Column of ``adata.obs`` with the cell-type assignment.
	sample_key: Column of ``adata.obs`` with the sample / niche identifier.
	cell_quality_key: Column of ``adata.obs`` with the per-cell QC value (typically log-counts) used as a confounder in residualization and in the per-pair HLM (R's ``cellQ``).
	n_programs: Number of multicellular programs to fit (``k`` in the paper).
	feature_space_key: ``adata.obsm`` key for the pre-computed feature space (typically PCA).
	n_components: Number of components of the feature space to use.
	n_genes_per_signature: Number of top-correlated genes kept per program signature (R's ``n.genes``).
	anova_alpha: Per-feature ANOVA significance threshold for filtering uninformative components (R's ``p.anova``).
	winsorize_quantile: Tail clipping fraction applied to pseudobulk components (R's ``cap.mat`` parameter).
	n_permutations: Permutations used to derive empirical PMD p-values (R's ``n1`` in ``DIALOGUE1.PMD.empirical``).
	empirical_alpha: P-value threshold below which a program is considered shared between a pair of cell types (R's implicit ``< 0.1``).

alpha

pertpy/pertpy/tools/_distances/_distance_tests.py

Line 50 in 8a5c178

alpha: float = 0.05,