ENIGMA_trace_norm: ENIGMA trace norm version

In WWXkenmo/ENIGMA_test: dEcoNvolutIon method based on reGularized MAtrix completion

ENIGMA trace norm version

Description

trace norm version is the alternative version of ENIGMA, which is the regularized weighted matrix completion to constraint the trace norm of inferred cell type-specific gene expression matrix.

Usage

ENIGMA_trace_norm(
  object,
  do_cpm = TRUE,
  alpha = 0.5,
  beta = 1,
  tao_k = 1,
  gamma = 0.5,
  epsilon = 0.001,
  epsilon_ks = 0.001,
  max_ks = 1,
  max.iter = 1000,
  solver = "proximalpoint",
  verbose = FALSE,
  pos = TRUE,
  Normalize = TRUE,
  Norm.method = "frac",
  preprocess = "log",
  loss_his = FALSE,
  print_loss = FALSE,
  model_tracker = FALSE,
  model_name = NULL,
  X_int = NULL,
  calibrate = TRUE
)

Arguments

object	ENIGMA object
do_cpm	if perform cpm normalization to the data, strongly recommand to use to make sure each sample numerical value scale is comparable. Default = TRUE
alpha	ENIGMA is a multi-objective optimization problem involve two object function, the distance function between observed bulk RNA-seq and reconstitute RNA-seq generated by weighted combination of CSE, and the distance function beween average CSE expression and cell type reference matrix. The alpha is used to determine weights of these two objects. If the alpha gets larger, the optimization attach greater importance on the the first object. Default: 0.5
beta	This parameter is used to control the latent dimension of each CSE, if this parameter gets larger, than the latent dimension of each CSE is smaller (lower trace norm value), which means that each sample is more similar with each others. The user need to tune this parameter based on the range of the singular value of the bulk RNA-seq matrix. Default: 1
tao_k	step size for proximal point method. Default: 1
gamma	This parameter is used to control the distance between CSE (X) and auxiliary variable (Y). Default: 1
epsilon	In trace norm based ENIGMA, the epsilon is not necessarily choose a extremly small value, the number of iteration would influence the latent dimensions of CSE, as each step is performing singular value thresholding. Default: 0.0001
epsilon_ks	Minimum error between the conditional number score (see Supplementary Notes for more details) of iteration i and i+1. Default: 0.001
max_ks	The stop criteria for conditional number score (see Supplementary Notes for more details). Default: 1
max.iter	The maximum number of iterations. Default: 1000
solver	The solver for solving trace norm model. method used: admm, admm_fast or proximal point method
verbose	Whether return the information after each step of processing. Default: TRUE
pos	Set all entries in CSE is positive. Default: TRUE
Normalize	Whether perform normalization on resulted expression profile. Default: TRUE
Norm.method	Method used to perform normalization. User could choose PC, frac or quantile. Default: frac
preprocess	Method used to perform variance stablization preprocessing. User could choose sqrt, log or none.sqrt: square root transformation; log: log2(*+1) transformation; none: no data transformation.
loss_his	save the loss value of each round of iteration.
model_tracker	save the model in returned object
model_name	name of the model
X_int	initialization for CSE profiles, an array object with three dimensions (the number of genes * the number of samples * the number of cell types), if user input a matrix (the number of genes * the number of samples), each cell type would be assigned the same start matrix.
calibrate	calibrate the inferred CSE into input bulk gene expression scale. Default: TRUE

Value

ENIGMA object where object@result_CSE contains the inferred CSE profile, object@result_CSE_normalized would contains normalized CSE profile if Normalize = TRUE, object@loss_his would contains the loss values of object functions during model training. If model_tracker = TRUE, then above results would be saved in the object@model.

Examples

## Not run: 
egm = ENIGMA_trace_norm(egm,model_tracker = TRUE, Norm.method="quantile")
egm@result_CSE
egm@result_CSE_normalized

## End(Not run)

WWXkenmo/ENIGMA_test documentation built on March 17, 2023, 4:56 a.m.