PermuteIntLIM: Run permutations of the IntLIM code to search for random...

In IntLIM: Integration of Omics Data Using Linear Modeling

Run permutations of the IntLIM code to search for random cross-omic associations in dataset

Description

This function allows users to test different permutations of the metadata with their analytes to ensure that any pairs being deemed significant by IntIM are not being suggested due to random chance, as is sometimes a problem in correlative associations.

Usage

PermuteIntLIM(
  data,
  stype = "",
  outcome = 1,
  independent.var.type = 1,
  covar = c(),
  save.covar.pvals = FALSE,
  continuous = FALSE,
  pvalcutoff = 0.05,
  interactionCoeffPercentile = 0,
  rsquaredCutoff = 0,
  num.permutations = 1,
  seed = 1
)

Arguments

data	IntLimData object (output of ReadData()) with analylte levels and associated sample meta-data
stype	column name that represents sample type (by default, it will be used in the interaction term). Only 2 categories are currently supported.
outcome	'1' or '2' must be set as outcome/independent variable (default is '1')
independent.var.type	'1' or '2' must be set as independent variable (default is '1')
covar	Additional variables from the phenotypic data that be integrated into linear model
save.covar.pvals	boolean to indicate whether or not to save the p-values of all covariates, which can be analyzed later but will also lengthen computation time. The default is FALSE.
continuous	boolean to indicate whether the data is continuous or discrete
pvalcutoff	FDR adjusted p-value cutoff for number of significant multi-omic pairs (default = 0.20)
interactionCoeffPercentile	Interaction coefficient cutoff for the IntLIM linear model (default = 0.10)
rsquaredCutoff	Cutoff for the R-squared values for the models as a quality control (default = 0.50)
num.permutations	Number of permutations to be ran (default = 1)
seed	set.seed paramter allowing for custom random number generation seeds

Value

List object with 1st slot populated with dataframe containing the R^2 values of the models, and number of significant pairs before and after p-value adjustment. The 2nd slot in the list contains a string vector of the IDs of the significant pairs.

IntLIM documentation built on Aug. 22, 2022, 5:05 p.m.