csSAMfit: Fits a csSAM Model

Description Usage Arguments Value Methods (by class)

View source: R/csSAMfit.R View source: R/csSAMfit.R

Description

Fits a csSAM Model

Usage

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
csSAMfit(x, ...)

## S3 method for class 'formula'
csSAMfit(x, data = NULL, ...)

## Default S3 method:
csSAMfit(x, cc, y = NULL, covariates = NULL,
  nperms = 200, alternative = c("all", "two.sided", "greater", "less"),
  fit = c("auto", "block", "lm", "monovariate"), standardize = TRUE,
  medianCenter = TRUE, logRm = FALSE, logBase = 2, nonNeg = NULL,
  keep.all = FALSE, verbose = FALSE, .rng = NULL, ...)

Arguments

x

target matrix assayed on mixed samples.

...

arguments passed down to the relevant S3 method.

cc

Matrix of cell-frequency. (n by k, n samples, k cell-types)

y

A numeric vector of group association of each sample. Either 1 or 2.

covariates

matrix of covariates to include in the model, e.g., for correcting for gender, age or batch effects.

nperms

The number of permutations to perform.

alternative

two.sided less greater

fit

fitting method, that dictates the type of model that is fitted:

  • auto: automatic selection based on input data and model specification (e.g., presence of covariates)

  • block: two linear models are fitted within each group of samples. Only works when the variable of interest is a factor (categorical variable).

  • lm: full interaction linear model.

  • monovariate: model is fitted including one cell type at a time. This could be a work around for when there are many more cell types than samples in a given group.

standardize

Standardize sample or not. Default is TRUE.

medianCenter

Median center rhat distributions. Default is TRUE.

logRm

Exponentiate data for deconvolution stage. Default is FALSE

logBase

Base of logaritm used to determine exponentiation factor. Default is 2

nonNeg

For single channel arrays. Set any cell-specific expression estimated as negative, to a ceiling of 0. It is conservative in its study of differential expression. Default is TRUE.

keep.all

logical that indicates if the statistics of all the permutations should be also returned in slot rhatperm.

verbose

single logical or integer that controls verbosity levels.

.rng

specification of the initial RNG settings, that are set using rngtools::setRNG.

Value

a csSAMfit object, that is a list with the following elements: * * *

Methods (by class)


shenorrLab/csSAM documentation built on May 26, 2017, 8:06 a.m.