clean_stats_results: Statistics cleaning

In antonvsdata/notame: Workflow for non-targeted LC-MS metabolic profiling

Statistics cleaning

Description

Uses regexp to remove unnecessary columns from statistics results data frame. Can also rename columns effectively.

Usage

clean_stats_results(
  df,
  remove = c("Intercept", "CI95", "Std_error", "t_value", "z_value", "R2"),
  rename = NULL,
  summary = TRUE,
  p_limit = 0.05,
  fdr = TRUE
)

Arguments

df	data frame, statistics results
remove	list, should contain strings that are matching to unwanted columns
rename	named list, names should contain matches that are replaced with values
summary	logical, should summary columns be added
p_limit	numeric, limit for p-values to be counted
fdr	logical, should summary be done with fdr-fixed values

Examples

# Simple manipulation to linear model results
lm_results <- perform_lm(drop_qcs(example_set), formula_char = "Feature ~ Group + Time")
lm_results <- clean_stats_results(lm_results,
  rename = c("GroupB" = "GroupB_vs_A", "Time2" = "Time2_vs_1")
)

antonvsdata/notame documentation built on Sept. 14, 2024, 11:09 p.m.