trainMediator: Train and predict mediator predictive model

In bhattacharya-a-bt/MOSTWAS: Multi-Omic Strategies for Transcriptome-Wide Association Studies

Train and predict mediator predictive model

Description

The function trains a predictive model of a given mediator and then predicts the genetically regulated intensity of it in the training set via cross-validation.

Usage

trainMediator(
  medInt,
  pheno = NULL,
  mediator,
  medLocs,
  snps,
  snpLocs,
  covariates,
  seed,
  k,
  cisDist = 5e+05,
  prune = T,
  windowSize = 50,
  numSNPShift = 5,
  ldThresh = 0.5,
  snpAnnot = NULL
)

Arguments

medInt	character, identifier for mediator of interest
mediator	data frame, mediator intensities
medLocs	data frame, MatrixEQTL locations for mediators
snps	data frame, SNP dosages
snpLocs	data frame, MatrixEQTL locations for SNPs
covariates	data frame, covariates
seed	integer, random seed for splitting
k	integer, number of training-test splits
prune	logical, TRUE/FALSE to LD prune the genotypes
windowSize	integer, window size for PLINK pruning
numSNPShift	integer, shifting window for PLINK pruning
ldThresh	numeric, LD threshold for PLINK pruning
parallel	logical, TRUE/FALSE to run glmnet in parallel
cores	integer, number of parallel cores

Value

final model for mediator along with CV R2 and predicted values

bhattacharya-a-bt/MOSTWAS documentation built on April 6, 2023, 12:20 a.m.