GFA: Exploratory Analysis of Multiple Data Sources with Group Factor Analysis

TL;DR

GFA is an R package that performs exploratory factor analysis on multiple co-occurring data sources, revealing dependencies and interpretable biclusters through sparse priors.

Contribution

The paper introduces GFA, a comprehensive R package for multi-source data factor analysis with dependency learning and sparse priors for interpretability.

Findings

Successfully identifies dependencies between data sources

Produces interpretable biclusters of multi-source data

Provides a complete analysis pipeline in R

Abstract

The R package GFA provides a full pipeline for factor analysis of multiple data sources that are represented as matrices with co-occurring samples. It allows learning dependencies between subsets of the data sources, decomposed into latent factors. The package also implements sparse priors for the factorization, providing interpretable biclusters of the multi-source data