HCP: HCP

In wgmao/DataRemix: DataRemix: a universal data transformation for optimal inference from gene expression datasets

Description

Hidden Covariates with Prior (HCP) implementation

Usage

  HCP(data, covariates, k, L1, L2, L3, max.iter, trace=F, return.all=F)

Arguments

data	The data to be processed
covariates	Covariate matrix associated with samples
k	Specify number of hidden factors
L1	Model parameter-penalty on ||Z-CU||_2^2. Here C denotes the scaled covariates
L2	Model parameter-penalty on ||B||_2^2
L3	Model parameter-penalty on ||U||_2^2
max.iter	Maximum number of iterations to perform
trace	Displace progress information or not
return.all	Return all reuslts or only the residual

Value

res	Residual out of decomposition
B	Latent factors (if return.all=T)
Z	Loading matrix (if return.all=T)
U	Coefficient matrix for covariates (if return.all=T)

wgmao/DataRemix documentation built on Aug. 6, 2020, 4:49 p.m.