olink_lmer {OlinkAnalyze}

Function which performs a linear mixed model per protein

Description

Fits a linear mixed effects model for every protein (by OlinkID) in every panel, using lmerTest::lmer and stats::anova. The function handles both factor and numerical variables and/or covariates.

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 = TRUE). 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.

Crossed analysis, i.e. A*B formula notation, is inferred from the variable argument in the following cases:

• c('A','B')

• c('A:B')

• c('A:B', 'B') or c('A:B', 'A')

Inference is specified in a message if verbose = TRUE.
For covariates, crossed analyses need to be specified explicitly, i.e. two main effects will not be expanded with a c('A','B') notation. Main effects present in the variable takes precedence.
The random variable only takes main effect(s).
The formula notation of the final model is specified in a message if verbose = TRUE.

Output p-values are adjusted by stats::p.adjust according to the Benjamini-Hochberg method (“fdr”). Adjusted p-values are logically evaluated towards adjusted p-value<0.05.

Usage

olink_lmer(
  df,
  variable,
  outcome = "NPX",
  random,
  covariates = NULL,
  model_formula,
  return.covariates = FALSE,
  verbose = TRUE
)

Arguments

df

NPX data frame in long format with at least protein name (Assay), OlinkID, UniProt, 1-2 variables with at least 2 levels.

variable

Single character value or character array. Variable(s) to test. If length > 1, the included variable names will be used in crossed analyses . Also takes ':' or '*' notation.

outcome

Character. The dependent variable. Default: NPX.

random

Single character value or character array.

covariates

Single character value or character array. Default: NULL.Covariates to include. Takes ':' or '*' notation. Crossed analysis will not be inferred from main effects.

model_formula

(optional) Symbolic description of the model to be fitted in standard formula notation (e.g. "NPX~A*B + (1|ID)"). If provided, this will override the outcome, variable and covariates arguments. Can be a string or of class stats::formula().

return.covariates

Boolean. Default: False. Returns results for the covariates. Note: Adjusted p-values will be NA for the covariates.

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 results of fitting the linear mixed effects model to every protein by OlinkID, ordered by ascending p-value. 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

• sumsq: "numeric" sum of square

• meansq: "numeric" mean of square

• NumDF: "integer" numerator of degrees of freedom

• DenDF: "numeric" denominator of decrees of freedom

• statistic: "numeric" value of the statistic

• p.value: "numeric" nominal p-value

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

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

Examples

# Results in model NPX~Time*Treatment+(1|Subject)+(1|Site)
lmer_results <- olink_lmer(df = npx_data1,
variable=c("Time", 'Treatment'),
random = c('Subject', 'Site'))