batch_kruskal: Batch Kruskal-Wallis Test

In IOBR: Immune Oncology Biological Research

Batch Kruskal-Wallis Test

Description

Performs Kruskal-Wallis rank sum tests on multiple continuous features across different groups. Computes p-values, adjusts for multiple testing, and ranks features by significance.

Usage

batch_kruskal(data, group, feature = NULL, feature_manipulation = FALSE)

Arguments

data	Data frame containing the dataset for analysis.
group	Character string specifying the name of the grouping variable.
feature	Character vector specifying the names of feature variables to test. If 'NULL', the user is prompted to select features (interactive mode only). Default is 'NULL'.
feature_manipulation	Logical indicating whether to apply feature manipulation to filter valid features. Default is 'FALSE'.

Value

Tibble containing:

sig_names

Feature name

p.value

Raw p-value from Kruskal-Wallis test

statistic

Test statistic (chi-squared)

p.adj

Adjusted p-value (Benjamini-Hochberg)

log10pvalue

Negative log10-transformed p-value

stars

Significance stars: **** p<0.0001, *** p<0.001, ** p<0.01, * p<0.05, + p<0.5

group columns

Mean-centered values for each group

Author(s)

Dongqiang Zeng

Examples

# Create small example data
set.seed(123)
test_data <- data.frame(
  Gender = rep(c("Male", "Female"), each = 50),
  Signature1 = rnorm(100),
  Signature2 = rnorm(100)
)
# Test features by gender
res <- batch_kruskal(
  data = test_data,
  group = "Gender",
  feature = c("Signature1", "Signature2")
)
head(res)

IOBR documentation built on May 30, 2026, 5:07 p.m.