buildFeatTable: Models util function

In Fjeanneret/multiSight: Multi-omics Classification, Functional Enrichment and Network Inference analysis

Models util function

Description

To build detailed feature tables outputs for selected ones by machine learning models. Relative mean values by label class then log2FoldChange and p.adj values if DESeq2 have been computed are indicated.

Usage

buildFeatTable(featVec, omicBlock, Y, deTable = NULL)

Arguments

featVec	Selected features vector of one omic dataset.
omicBlock	Omic dataset of selected features.
Y	Omic sample classes.
deTable	(optional) Deseq2 results table for an omic dataset.

Value

Returns table of features selected by classification model and relative values.

Examples

data("omic2", package = "multiSight")
splitData <- splitDatatoTrainTest(omic2, 0.8)
data.train <- splitData$data.train
data.test <- splitData$data.test

#diabloRes <- runSPLSDA(data.train)
data("diabloRes", package = "multiSight")
diabloModels <- diabloRes$model #sPLS-DA model using all omics.
diabloFeats <- diabloRes$biosignature #selected features for each omic.
diabloFeatTable <- buildFeatTable(diabloFeats[[1]], 
  omic2[[1]], 
  omic2$Y)
diabloFeatTable

Fjeanneret/multiSight documentation built on April 6, 2022, 7:59 a.m.