Cross-organism toxicogenomics with group factor analysis

The GFAtoxgen package implements the method and the pipeline described in the paper Cross-organism toxicogenomics with group factor analysis (to appear).

The package is based on the research done in the SMLB group, Helsinki Institute for Information Technology HIIT, Department of Information and Computer Science, Aalto University.

When you use this pipeline, please cite the following paper:

Tommi Suvitaival, Juuso A. Parkkinen, Seppo Virtanen, and Samuel Kaski. Cross-organism toxicogenomics with group factor analysis. Systems Biomedicine, to appear.

When you use group factor analysis (GFA), please cite the publication referred to in the CCAGFA package.

Contents

• Licence (COPYING.txt)
• Demo script for running group factor analysis for a toxicogenomic data set and for analyzing the result (demo-exploratory_analysis.R)
• Pipeline script for loading the toxicogenomic data set (script-load_camda13_data.R)
• Group factor analysis source code (source)

Installing and running

The software package runs under R, a free language and environment for statistical computing. The package is tested with the R version 3.0.2 in the Linux environment.

Download

• GFAtoxgen package
• Documentation
• Licence: GPL
• Publication (pre-print PDF)
• Citation (TBA)

Additional material related to the publication:

• Toxicogenomic data on the CAMDA 2013 website, used in the demo
• CCAGFA package, implementing the vanilla group factor analysis

Documentation and support

This package implements the group factor analysis (GFA) with element-wise sparsity for factors and factor loadings, and presents a pipeline for cross-organism toxicogenomics.

For documentation and examples, see the README.txt file included in the package.

This is experimental software provided as is; we welcome any comments and corrections but cannot give any guarantees about the code. If you have any comments or bug reports, please direct them to Tommi Suvitaival or Seppo Virtanen.

Acknowledgement

Funding: The Academy of Finland (Finnish Centre of Excellence in Computational Inference Research COIN, 251170)