ICAcomputing: Using Independent Component Analysis to decompose scRNA-seq...

In WWXkenmo/ICAnet: What the Package Does (One Line, Title Case)

Using Independent Component Analysis to decompose scRNA-seq gene expression matrix

Description

We introduced independent component analysis (ICA) into single cell clustering to decompose the gene expression matrix into a number of independent components. Each independent component was characterized by a co-expression pattern and was associated with certain meaningful biological pathway.

Usage

ICAcomputing(
  obj,
  center = TRUE,
  scale = FALSE,
  RMT = TRUE,
  nc.vec = NULL,
  nc.global.mode = NULL,
  global.mode = FALSE,
  ICA.type = "JADE",
  nbIt = 10,
  funClus = "hclust",
  two.stage = TRUE,
  two.stage.ICA = "JADE"
)

Arguments

obj	a seurat object which contain the gene expression matrix of all batches, meanwhile it also contain the batch ID which document the batch label information
center	a boolean variable to determine whether perform centralization to each batch
scale	a boolean variable to determine whether perform scaling to each batch
RMT	a boolean variable to determine whether perform random matrix theory based number of components estimation
nc.vec	a numrical vector to determine the number of independent components for each batch
nc.global.mode	a numeric vector to determine the number of components of all batches when running global mode.
global.mode	a boolean variable to determine whether running global mode based ICA
ICA.type	an optional character string given a method for computing independent components. One of "JADE" (default), "FastICA", or "MineICA": can be abbreviated
nbIt	The number of iterations of FastICA in MineICA
funClus	The clustering function to be used to cluster the estimates in MineICA. One of "hclust"(default),"kmeans", "pam", "agnes" can be abbreviated
two.stage	Whether running ICA+RMT based components number estimation
two.stage.ICA	Which type of ICA methods shall be applied in ICA+RMT estimate. One can select "FastICA" or "JADE"

Value

a list object which containing the ica-components

WWXkenmo/ICAnet documentation built on April 11, 2022, 5:44 a.m.