spateo.tools.cci_fdr#

Companion functions for cell-cell communication inference analyses

Module Contents#

Functions#

fdr_correct(→ pandas.DataFrame)

Correct p-values for FDR along specific axis in pvals.
spateo.tools.cci_fdr.fdr_correct(pvals: pandas.DataFrame, corr_method: str, corr_axis: Literal[interactions, clusters] = 'clusters', alpha: float = 0.05) → pandas.DataFrame[source]#

Correct p-values for FDR along specific axis in pvals.

Parameters:
pvals

pd.DataFrame

corr_method

str Correction method, should be one of the options in :func statsmodels.stats.multitest.multipletests (listed below for reference):

  • Named methods:

    • bonferroni

    • sidak

    • holm-sidak

    • holm

    • simes-hochberg

    • hommel

  • Abbreviated methods:

    • fdr_bh: Benjamini-Hochberg correction

    • fdr_by: Benjamini-Yekutieli correction

    • fdr_tsbh: Two-stage Benjamini-Hochberg

    • fdr_tsbky: Two-stage Benjamini-Krieger-Yekutieli method

corr_axis

str Either “interactions” or “clusters”- specifies whether the dataframe given to ‘pvals’ corresponds to samples or interactions. If ‘interactions’, will need to transpose the array first before performing multiple hypothesis correction.