simpleDecomp: Main PLIER function

View source: R/Allfuncs.R

simpleDecompR Documentation

Main PLIER function

Description

Main PLIER function

Usage

simpleDecomp(
  Y,
  k,
  svdres = NULL,
  L1 = NULL,
  L2 = NULL,
  max.iter = 200,
  tol = 5e-06,
  trace = F,
  rseed = NULL,
  B = NULL,
  scale = 1,
  adaptive.frac = 0.05,
  adaptive.iter = 30
)

Arguments

k

The number of latent variables to return, leave as NULL to be set automatically using the num.pc "elbow" method

svdres

Pre-computed result of the svd decomposition for data.

L1

L1 constant, leave as NULL to automatically select a value.

L2

L2 constant, leave as NULL to automatically select a value.

max.iter

maximum number of iterations, default is 200.

tol

tolerance for relative B change, default is 5e-6.

trace

print out trace info, default is false.

rseed

seed for RSVD call. If svdres us given this has no effect.

adaptive.frac

the probability cutoff to use to determine the positive cutoff for loading. Smaller values will return sparser models.

adaptive.iter

the first iteration where adaptive constants are computed, before they are all 0.

data

the data to be processed with genes in rows and samples in columns. Should be z-scored.

scaleL

scale both L1 and L2 by this amount from the default setting. Values less then 1 imply weaker regularization.


wgmao/PLIER documentation built on May 11, 2022, 10:34 p.m.