TriGen: A genetic algorithm to mine triclusters in temporal gene expression data

Abstract

Analyzing microarray data represents a computational challenge due to the characteristics of these data. Clustering techniques are widely applied to create groups of genes that exhibit a similar behavior under the conditions tested. Biclustering emerges as an improvement of classical clustering since it relaxes the constraints for grouping genes to be evaluated only under a subset of the conditions and not under all of them. However, this technique is not appropriate for the analysis of longitudinal experiments in which the genes are evaluated under certain conditions at several time points. We present the TriGen algorithm, a genetic algorithm that finds triclusters of gene expression that take into account the experimental conditions and the time points simultaneously. We have used TriGen to mine datasets related to synthetic data, yeast (Saccharomyces cerevisiae) cell cycle and human inflammation and host response to injury experiments. TriGen has proved to be capable of extracting groups of genes with similar patterns in subsets of conditions and times, and these groups have shown to be related in terms of their functional annotations extracted from the Gene Ontology.

A Novel Method for Seismogenic Zoning Based on Triclustering: Application to the Iberian Peninsula

“…TriGen [6] is an algorithm that applies a triclustering technique based on the paradigm of evolutionary algorithms, in particular genetic algorithms [48]. Genetic algorithms perform a heuristic search that mimics the process of natural selection, since a population of individuals is created and evolves throughout several generations using crossover and mutation operators, and the individuals are evaluated based on a function to optimize.…”

“…Each of these operators are now briefly described; for further details please refer to [6]. The initial population is randomly generated.…”

“…The fitness of each individual allows the algorithm to determine the best candidates to remain in subsequent generations. For this particular case, the authors in [6] proposed a measure based on a three-dimensional adaptation of the mean square residue measure (MSR), which is a classical clustering measure for gene expression analysis [50], referred to as f M SR . This measure maximizes the coherence in the behavior of the seven features for all of the cells contained in the zoning.…”

“…In this context, the third dimension is composed of the seven features calculated for every latitude and longitude. In other words, these seven features could be considered seven time stamps for the tuple {longitude, latitude} introduced in [6]. Since TriGen is a general-purpose algorithm, it can be applied to any problem formulated on three dimensions.…”

“…For that purpose, a computational technique based on triclustering, TriGen [6,7], has been applied. Triclustering mines 3D datasets in order to extract patterns of coherent behavior.…”