llrs / sgcca_hyperparameters

Evaluating the effect of SGCCA hyperparameters

SGCCA hyperparameters

The goal of SGCCA_hyperparameters is to evaluate the influence of the hyperparameters tau, and weight in the Sparse Generalized Canonical Correlation Analysis

The 014850_D_GeneList20070207.txt file was downloaded from Agilent on 2018/07/18 from here, uncompressed and stored for mapping the ids of the genes with the names of the proteins.

The original data is stored here with the annotation for each microarray.

(the downloaded file and the original in ebi seem to match after randomly checking some GE identifiers)

sgcca_hyperparameters's Issues

The most important parameter: Data

The main issue is that we don't know what to expect on the visualizations, weights on random data. So we don't know what it looks like when there is a good signal.
If there is random data how it would look like?