inmoose.deseq2.estimateBetaPriorVar

inmoose.deseq2.estimateBetaPriorVar(obj, betaPriorMethod='weighted', upperQuantile=0.05, modelMatrix=None)

steps for estimating the beta prior variance

This lower-level function is called within DESeq() or nbinomWaldTest(). End users should use those higher-level functions.

Parameters:

  • obj (DESeqDataSet) – a DESeqDataSet

  • betaPriorMethod ({ "weighted", "quantile" }) –

    the method for calculating the beta prior variance:

    • "quantile" matches a normal distribution using the upper quantile of the finite MLE betas.

    • "weighted" matches a normal distribution using the upper quantile, but weighting by the variance of the MLE betas.

  • upperQuantile (float) – the upper quantile to be used for the method of beta prior variance estimation

  • modelMatrix (design matrix) – an optional design matrix, typically left None and built within the function

Returns:

the vector of variances for the prior on the beta in the DESeq() GLM

Return type:

ndarray