Application of data mining algorithms to classify biological data: The coffea canephora genome case

Abstract

Bioinformatics is now one of the most important fields of modern sciences grouping different fields of research such as Biology, Genomics, Genetics and Molecular evolution. These fields generate a large amount of information via the utilization of the new generations of sequencing techniques (NGS). This amount of data requires the development of a new generation of tools able to store and analyze efficiently and rapidly the information. Coffea canephora also called the Robusta coffee is one of the most important tree for tropical countries. This genome has been recently sequenced. One of the characteristics of this genome is the presence of numerous repeated elements, representing more than 50% of the genome sequence. The analysis and classification of such amount of repeated sequences require innovative approaches. Here, we present how data mining and machine learning can contribute to process sequencing data for the fast classification of a class of repeated sequences, called transposable elements.