wash_cycle: function to perform online rPCA descomposition

In kcygan/dryclean: rPCA based method to de-noise genomic coverage data

Description

Function that calls the online rPCA on sample under question and updates subspace basis and does decomposition

Usage

wash_cycle(m.vec, L.burnin, S.burnin, r, N, U.hat, V.hat, sigma.hat,
  lambda1 = NA, lambda2 = NA, verbose = TRUE)

Arguments

m.vec	numeric vector of length m. Vector of GC corrected coverage data of sample in question
L.burnin	(m markers x n samples) numeric matrix. L matrix of panel of normals after batch rPCA decomposition
S.burnin	(m markers x n samples) numeric matrix. S matrix of panel of normals after batch rPCA decomposition
r	integer. Estimated rank of panel of normals after batch rPCA decomposition
N	(m markers x n samples) numeric matrix. Matrix of GC corrected coverage data of panel of normals for batch rPCA decomposition
U.hat	(m markers x n samples) numeric matrix. Right singular matrix of L.burnin
V.hat	(m markers x n samples) numeric matrix. Left singular matrix of L.burnin
sigma.hat	numeric vector of length r. Singular values of L.burnin
lambda1,	integer. Tuning parameter (default = 1/(sqrt(no. of markers in input vector))
lambda2,	integer. Tuning parameter (default = 1/(sqrt(no. of markers in input vector))
verbose	boolean (default == TRUE). Outputs progress.

Value

S and L numeric vectors each of length m. Vectors for sample in question

Author(s)

Aditya Deshpande

kcygan/dryclean documentation built on Feb. 13, 2020, 12:34 a.m.