doSGCCA: doSGCCA

In CNRGH/crimmix: Multi-omics Integration

Description

doSGCCA

Usage

doSGCCA(
  data,
  K,
  C = 1 - diag(length(data)),
  c1 = rep(1, length(data)),
  ncomp = rep(1, length(data)),
  scheme = "centroid"
)

Arguments

data	List of matrices.
K	Number of clusters
C	A design matrix that describes the relationships between blocks (default: complete design).
c1	Either a 1*J vector or a max(ncomp) * J matrix encoding the L1 constraints applied to the outer weight vectors. Elements of c1 vary between 1/sqrt(p_j) and 1 (larger values of c1 correspond to less penalization)
ncomp	A 1 * J vector that contains the numbers of c omponents for each block (default: rep(1, length(data), which gives one component per block.)
scheme	The value is "horst", "factorial", "centroid" or any diffentiable convex scheme function g designed by the user (default: "centroid").

Value

a list of clust the clustering of samples and fit the results of the method SGCCA

Examples

set.seed(333)
c_1 <- simulateY(J=100, prop=0.1, noise=1)
c_2 <- simulateY(J=200, prop=0.1, noise=1)
c_3 <- simulateY(J=50, prop=0.1,  noise=0.5)
data <- list(c_1$data , c_2$data , c_3$data)
res <- doSGCCA(data,K=4)

CNRGH/crimmix documentation built on Dec. 11, 2019, 5:27 a.m.