olink_one_non_parametric {OlinkAnalyze}

Function which performs a Kruskal-Wallis Test or Friedman Test per protein

Description

Performs an Kruskal-Wallis Test for each assay (by OlinkID) in every panel using stats::kruskal.test. Performs an Friedman Test for each assay (by OlinkID) in every panel using rstatix::friedman_test. The function handles factor variable.

Samples that have no variable information or missing factor levels are automatically removed from the analysis (specified in a message if verbose = TRUE). Character columns in the input dataframe are automatically converted to factors (specified in a message if verbose = T). Numerical variables are not converted to factors. If a numerical variable is to be used as a factor, this conversion needs to be done on the dataframe before the function call.

Inference is specified in a message if verbose = TRUE.
The formula notation of the final model is specified in a message if verbose = TRUE.

Adjusted p-values are calculated by stats::p.adjust according to the Benjamini & Hochberg (1995) method (“fdr”). The threshold is determined by logic evaluation of Adjusted_pval < 0.05.

Usage

olink_one_non_parametric(
  df,
  variable,
  dependence = FALSE,
  subject = NULL,
  verbose = TRUE
)

Arguments

df

NPX or Quantified_value data frame in long format with at least protein name (Assay), OlinkID, UniProt, Panel and a factor with at least 3 levels.

variable

Single character value.

dependence

Boolean. Default: FALSE. When the groups are independent, the kruskal-Wallis will run, when the groups are dependent, the Friedman test will run.

subject

Group information for the repeated measurement. If (dependence = TRUE), this parameter need to be specified.

verbose

Boolean. Default: True. If information about removed samples, factor conversion and final model formula is to be printed to the console.

Value

A tibble containing the Kruskal-Wallis Test or Friedman Test results for every protein.

Columns include:

• Assay: "character" Protein symbol

• OlinkID: "character" Olink specific ID

• UniProt: "character" UniProt ID

• Panel: "character" Name of Olink Panel

• term: "character" term in model

• df: "numeric" degrees of freedom

• method: "character" which method was used

• statistic: "named numeric" the value of the test statistic with a name describing it

• p.value: "numeric" p-value for the test

• Adjusted_pval: "numeric" adjusted p-value for the test (Benjamini&Hochberg)

• Threshold: "character" if adjusted p-value is significant or not (< 0.05)

Examples

library(dplyr)

# One-way Kruskal-Wallis Test
try({ # May fail if dependencies are not installed
kruskal_results <- olink_one_non_parametric(df = npx_data1,
                                            variable = "Site")
})

#Friedman Test
friedman_results <- olink_one_non_parametric(df = npx_data1,
                                             variable = "Time",
                                             subject = "Subject",
                                             dependence = TRUE)