Clustering and Classification Techniques for Gene Expression Profile Pattern Analysis

• Published in: Pattern Recognition in Computational Molecular Biology pp. 347 - 370
• Main Authors: Weitschek, Emanuel, Fiscon, Giulia, Fustaino, Valentina, Felici, Giovanni, Bertolazzi, Paola
• Format: Book Chapter
• Language: English
• Published: Hoboken, NJ, USA John Wiley & Sons, Inc 19.11.2015
• Subjects: experiment classification; gene clustering; gene expression profile pattern analysis; microarray technology; RNA sequencing technologies; transcriptome analysis
• ISBN: 9781118893685; 1118893689
• DOI: 10.1002/9781119078845.ch19

The analysis of gene expression profiles from microarray/RNA sequencing (RNA‐Seq) experimental samples demands new efficient methods from statistics and computer science. This chapter considers two main types of gene expression data analysis such as gene clustering and experiment classification. It introduces the transcriptome analysis, highlighting the widespread approaches to handle it. The chapter provides an overview of the microarray and RNA‐Seq technologies. In addition, the integrated software packages GenePattern, Gene Expression Logic Analyzer (GELA), TM4 software suite, and other common analysis tools are illustrated. For gene expression profile pattern discovery and experiment classification, the software packages are tested on four real case studies: Alzheimer's disease versus healthy mice; multiple sclerosis samples; psoriasis tissues; and breast cancer patients. The performed experiments and the described techniques provide an effective overview to the field of gene expression profile classification and clustering through pattern analysis.