pyidr - Python implementation of the irreproducible discovery rate

Python implementation of of the irreproducible discovery rate (short IDR) proposed in [LI2011].

IDR was originally published as R package idr.

Basic usage

The local IDR and the proportion of the reproducibility component can be done as follows:

import pyidr
idr = pyidr.IDR()
idr.fit(dataset1, dataset2)
local_idr = idr.predict(dataset1,dataset2)
proportion_of_reproducibility = idr.proportion

The correspondence profile used for diagnostics can be caluclated and plotted with the :class:`CorrespondenceProfile` class as follows:

import pyidr
profile = pyidr.CorrespondenceProfile(rankx, ranky, t)
profile.plot_diagnostics()

Li, Qunhua, et al. "Measuring reproducibility of high-throughput experiments." The annals of applied statistics 5.3 (2011): 1752-1779.