runSupervised_Harmony: Run supervised harmony integration

In supatt-lab/SingCellaR: SingCellaR: an integrative analysis tool for single-cell RNA sequencing (scRNA-seq) data

Run supervised harmony integration

Description

Run supervised harmony integration

Usage

runSupervised_Harmony(
  object,
  n.dims.use = 30,
  fGSEA.minSize = 10,
  fGSEA.maxSize = 500,
  fGSEA.eps = 0,
  fGSEA.nPermSimple = 1000,
  hcl.height.cutoff = 0.25,
  covariates = c("data_set"),
  harmony.sigma = 0.1,
  harmony.tau = 0,
  harmony.block.size = 0.05,
  harmony.max.iter = 10,
  harmony.max.iter.cluster = 20,
  harmony.epsilon.cluster = 1e-05,
  harmony.epsilon.harmony = 1e-04,
  n.seed = 1
)

Arguments

object	The SingCellaR object.
n.dims.use	The number of PCA dimensions used for the input for harmony. Default 30
fGSEA.minSize	The cutoff minimum number of genes in each gene set. Gene set that contains the number of genes lower than this number will be excluded. Default 10
fGSEA.maxSize	The cutoff maxiumum number of genes in each gene set. Gene set that contains the number of genes higher than this number will be excluded. Default 500
fGSEA.eps	The eps paramenter for fgsea, this parameter sets the boundary for calculating the p value. Default 0
fGSEA.nPermSimple	The number of permutations in the simple fgsea implementation for preliminary estimation of P-values.
hcl.height.cutoff	The cutree cutoff value for hierarchical clustering. Default 0.25
covariates	The unwanted source of variations (e.g. batch, sample_id, etc).
harmony.sigma	The harmony sigma parameter. Default 0.1
harmony.tau	The harmony tau parameter. Default 0
harmony.block.size	The harmony block.size parameter. Default 0.05
harmony.max.iter	The harmony max iteration parameter. Default 10
harmony.max.iter.cluster	The harmony max iteration cluster. Default 200
harmony.epsilon.cluster	The harmony epsilon.cluster parameter. Default 1e-05
harmony.epsilon.harmony	The harmony epsilon parameter. Default 1e-04
n.seed	The set seed number.

supatt-lab/SingCellaR documentation built on Aug. 24, 2023, 5:49 p.m.