Skip to contents

Run Linked Non-negative Matrix Factorization

Source: R/R_functions.R
run_linked_nmf.Rd

Run LNMF, initialized from any NMF model, where factors may be "linked" to certain samples.

Usage

run_linked_nmf(
  A,
  w,
  link_h = NULL,
  link_w = NULL,
  tol = 1e-04,
  maxit = 100,
  verbose = TRUE,
  L1 = 0.01,
  L2 = 0,
  threads = 0
)

Arguments

A

sparse matrix (ideally variance-stabilized) of data for genes x cells (rows x columns)

w

initial matrix for 'w', usually taken from the result of run_nmf, of dimensions nrow(A) x rank.

link_h

matrix giving the linkage weight (usually in the range (0, 1)) of dimensions rank x ncol(A).

link_w

matrix giving the linkage weight of dimensions nrow(A) x rank.

tol

tolerance of the fit (1e-5 for publication quality, 1e-3 for cross-validation)

maxit

maximum number of iterations

verbose

verbosity level

L1

L1/LASSO penalty to increase sparsity of model

L2

L2/Ridge penalty to increase angles between factors

threads

number of threads for parallelization across CPUs, 0 = use all available threads