eval.test: Evaluate the results of different tests

In zellerlab/SIMBA: Simulation of Microbiome Data with Biological Accuracy

Evaluate the results of different tests

Description

This function takes the results of the apply.test function and calculates different evaluation measures (see Details).

Usage

eval.test(sim.location, group, res.mat, adjust='BH', alpha = 0.05)

Arguments

sim.location	file name for the .h5 file containing the simulations
group	character, name of the group within the .h5 file containing the simulated features
res.mat	matrix, output from the apply.test function
adjust	character, indicate the multiple hypothesis testing to be performed on the P-values, defaults to "BH"
alpha	numeric, significance threshold at which the test will be evaluated, defaults to 0.05

Details

This function will check that tests ran successfully and calculate how well the supplied P-values can distinguish between the true differential abudance features and background features. The measures computed are:

• AUROC: measure for the separation of true and background features

• TP: number of true positives detected at alpha

• FP: number of false positives detected at alpha

• TN: number of true negatives at alpha

• FN: number of false negatives detected at alpha

• PR: precision, calculated as TP/(FP+TP)

• R: recall, calculated as TP/(TP+FN)

• FDR: false discovery rate, calculated as FP/(FP+TP)

Value

A dataframe containing the evaluation measures at the given alpha value for the different test runs.

zellerlab/SIMBA documentation built on June 2, 2025, 6:25 a.m.