Discretization of gene expression data revised

GALLO CRISTIAN; CECCHINI ROCIO; CARBALLIDO JESSICA; MICHELETTO SANDRA; PONZONI IGNACIO

BRIEFINGS IN BIOINFORMATICS

OXFORD UNIV PRESS

Lugar: Oxford; Año: 2015 p. 1 - 13

1467-5463

Gene expression measurements represent the most important source of biological data used to unveil theinteraction and functionality of genes. In this regard, several data mining and machine learning algorithms havebeen proposed that require, in a number of cases, some kind of data discretization in order to perform theinference. Selection of an appropriate discretization process has a major impact on the design and outcome of theinference algorithms, since there are a number of relevant issues that need to be considered. This study presents arevision of the current state of the art discretization techniques, together with the key subjects that need to beconsidered when designing or selecting a discretization approach for gene expression data.