In jennyjyounglee/AclustsCCA: A Cluster Based Sparse Canonical Correlation Analayis to Test Associations Between A Multi-Pollutant Mixture and High-Dimentional DNA Methylation

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

1. What is SparseCCA?

SparseCCA is a statistical method .... [@wilms2016robust, @mai2019iterative].

Fast permutation test ... [@gandy2014mmctest, @gandy2019r]

2. Input Parameters for SparseCCA

| Xmethod A penalty function for the exposure, i.e. penalty function when regressing Y onto X. Options are "lasso", "alasso","gglasso", and "SGL" (default).

| Ymethod A penalty function for the outcome, i.e. penalty function when regressing X onto Y. Options are "lasso", "alasso","gglasso", "SGL", and "OLS" (default).

| init.method Initialization method. Options are "lasso", "OLS", and "SVD" (default).

| X.groupidx A vector of length \eqn{p} that indicates grouping structure of exposure \eqn{X}.

| standardize A logical flag for exposure \eqn{X} and outcome \eqn{Y} standardization, prior to fitting the model.

| max.iter A maximum number of iterations of SparseCCA. The default is $100$.

| conv A tolerance value for convergence \eqn{epsilon} of SparseCCA. The default is $10e-2$.

| maxnum A maximal total number of permutations across all the clusters.

| maxB A maximal number of permutations for a single cluster.

| permute.tmp.filepath Filepath to save intermittent permutation results.

| permute A logical flag for whether to run permutation test or not.

| nthread A number of threads to parallelize permutation test and implementation of SparseCCA across all the clusters.

| FDR.thresh FDR threshold. The default is $0.05$.

3. Implement SparseCCA and permutation test on each cluster identified by A-clustering

As list of clusters are provided and partial residuals are computed, AclustsCCA will only run SparseCCA on each cluster identified by A-clustering.

load("clusters.list.RData")
load("partial.residual.RData")

AclustsCCA.result <- AclustsCCA(X=X.resid,
                                Y=Y.resid,
                                clusters.list=clusters.list,
                                # parameters for SparseCCA
                                Xmethod=Xmethod,
                                Ymethod=Ymethod,
                                X.groupidx=X.groupidx,
                                # parameters for permutation test for AclustsCCA
                                maxB=maxB,
                                permute=TRUE,
                                nthread=nthread) 

summary.AclustsCCA(AclustsCCA.result)

References

jennyjyounglee/AclustsCCA documentation built on June 15, 2022, 7:45 p.m.