An introduction to network inference and mining

Basic description of this course

This course is part of a full series of statistics classes, organized by Genotoul - Biostatistics in the INRA of Toulouse during the years 2011, 2012, 2013 and (coming soon) 2015. Its aim is to introduce statistical methods to infer networks from gene expression data and then to analyze them. It is divided into

• a presentation of the topic (approximately 3 hours);
• practical applications using the free statistical software environment R and the free graph visualization platform .

The course is organized as follows:

• basic introduction to networks;
• network inference with a focus on the GGM;
• graph mining.

The following R packages are used in the applications:

• mixOmics (to have access to the nutrimouse data set);
• huge (network inference using GGM, graphical LASSO and relevance network);
• igraph (working with graphs in R).

Also, the open source graph visualization platform Gephi is used in the applications.

2015 material

• Lecture PDF, using the wikistat format. This file is organized as a vignette with theoretical framework first and the illustration of the concepts on two datasets, one showing how to perform network inferrence and the second providing an example of network mining with a facebook network;
• data: the edge list of my facebook network and the nodes’ names (initials) that have to be renamed fbnet-el.txt and fbnet-name.txt, respectively;
• R scripts: for network inference and for network mining;
• you may also want to have a look at this interface to download your own facebook network;
• Slides: theoretical part and practical applications (the video on page 17/24 can be watched at this link).