HDlarsbivariate: lars algorithm for bivariate signal

In MPAgenomics: Multi-Patient Analysis of Genomic Markers

Description

This function transforms the two matrices CN and fracB in one matrix which is used in the lars algorithm. Each signal is weighted

Usage

HDlarsbivariate(
  CN,
  fracB,
  y,
  weightsCN = 1/apply(CN, 1, sd),
  weightsFracB = 1/apply(fracB, 1, sd),
  meanCN = 2,
  maxSteps,
  eps
)

Arguments

CN	matrix containing copy-number signals. Each row corresponds to a different signal.
fracB	matrix containing copy-number signals. Each row corresponds to a different signal.
y	vector containing the response associated to each signal
weightsCN	vector of length nrow(CN); weights associated to each signal for the copy-number signal
weightsFracB	vector of length nrow(fracB); weights associated to each signal for the copy-number signal
meanCN	value for centering the copy-number signal (default value = 2)
maxSteps	maximum number of steps for the lars algorithm
eps	tolerance

Value

a LarsPath object

Author(s)

Quentin Grimonprez

MPAgenomics documentation built on March 30, 2021, 5:13 p.m.