inmoose.deseq2.results.filtered_p

inmoose.deseq2.results.filtered_p(filter_, test, theta, method, data=None)

compute and adjust p-values, with filtering

Given filter and test statistics in the form of unadjusted p-values, or functions able to compute these statistics from the data, filter and then correct the p-values across a range of filtering stringencies.

NB: this function is copied and ported from the R package genefilter. This copy was already done in the original DESeq2 R code.

Parameters:

  • filter – a list of stage-one filter statistics, or a function which is able to compute such a list from data, if data is supplied

  • test – a list of unadjusted p-values, or a function which is able to compute such a list from the filtered portions of data, if data is supplied. The option to supply a function is useful when the value of the test statistic depends on which hypotheses are filtered out at stage one.

  • theta – a list with one or more filtering fractions to consider. Actual cutoffs are then computed internally by applying quantile to the filter statistics contained in (or produced by) the filter_ argument.

  • method – the unadjusted p-values contained in (or produced by) test will be adjusted for multiple testing after filtering, using p_adjust(). See the method argument of this function for more options.

  • data – if filter_ and/or test are functions rather than lists of statistics, they will be applied to data. The functions will be passed the whole data object, and must work over rows etc. themselves as appropriate.

Returns:

a matrix of p-values, possibly adjusted for multiple testing, with one row per null hypothesis and one column per filtering fraction given in theta. For a given column, entries which have been filtered out are nan.

Return type:

ndarray