optimization: Optimize the parameters of a Negative Binomial regression...

In NewWave: Negative binomial model for scRNA-seq

Description

The parameters of the model given as argument are optimized by penalized maximum likelihood on the count matrix given as argument.

Usage

optimization(
  Y,
  cluster,
  children,
  model,
  max_iter,
  stop_epsilon,
  n_gene_disp,
  n_cell_par,
  n_gene_par,
  commondispersion,
  verbose
)

Arguments

cluster	The PSOCK cluster
children	Number of child process
model	newmodel item
max_iter	maximum number of iterations
stop_epsilon	stopping criterion, when the relative gain in likelihood is below epsilon
n_gene_disp	number of genes used in mini-batch dispersion estimation approach(default NULL > all genes are used)
n_cell_par	number of cells used in mini-batch cell's related parameters estimation approach(default NULL > all cells are used)
n_gene_par	number of genes used in mini-batch gene's related parameters estimation approach(default NULL > all genes are used)
commondispersion	Whether or not a single dispersion for all features is estimated (default TRUE).
verbose	print information (default FALSE)

Value

An object of class newmodel similar to the one given as argument with modified parameters alpha, beta, gamma, W.

NewWave documentation built on Dec. 26, 2020, 6 p.m.