constructFeatures: Feature construction

In lulizou/boostme: BoostMe - DNA methylation prediction within WGBS

Feature construction

Description

Helper function to make a data frame ready for training/validation/testing from a bsseq object that contains the CpG/DNA features for the model

Usage

constructFeatures(bs, sample = 1, minCov = 10, sampleAvg = TRUE,
  neighbMeth = TRUE, neighbDist = TRUE, featureBEDs = NULL)

Arguments

bs	a BSseq object
sample	which sample to construct features for; default is 1, the first sample.
minCov	the minimum coverage, below which values will be set to NA. Default is 10.
sampleAvg	boolean of whether to not to include the sample average as a feature. Default is TRUE.
neighbMeth	boolean of whether or not to include nearest non-missing neighboring CpG methylation values. Default is TRUE.
neighbDist	boolean of whether or not to include nearest non-missing neighboring CpG distances. Default is TRUE.
featureBEDs	optional named list of paths to BED files to be included as features in the model. Names are used as the feature name; e.g. list(chromState = "chromatinStates.bed")

Value

a data.frame, each row is a CpG; first column is the actual beta value, subsequent columns are features

lulizou/boostme documentation built on March 16, 2023, 7:35 a.m.