In the last decade, the interest in microarray technology has exponentially increased due to its ability to monitor the expression of thousands of genes simultaneously. The reconstruction of gene association networks from gene expression profiles is a relevant task and several statistical techniques have been proposed to build them. The problem lies in the process to discover which genes are more relevant and to identify the direct regulatory relationships among them. We developed a multi-objective evolutionary algorithm for mining quantitative association rules to deal with this problem. We applied our methodology named GarNet to a well-known microarray data of yeast cell cycle. The performance analysis of GarNet was organized in three steps similarly to the study performed by Gallo et al. GarNet outperformed the benchmark methods in most cases in terms of quality metrics of the networks, such as accuracy and precision, which were measured using YeastNet database as true network. Furthermore, the results were consistent with previous biological knowledge.
1.IntroductionSince late 1990s, the interest in microarray technology has exponentially increased due to its ability to monitor the expression of thousands of genes simultaneously. Microarray technology has revolutionized the biological research because it allows to study thousand of genes or even whole genomes [1].As molecular biology is rapidly evolving into a quantitative science, it increasingly relies on computational algorithms to make sense of high-throughput data. One of the main goals in Microarray analysis is the reconstruction of gene regulatory processes and a key task is the inference of regulatory interactions among genes from gene expression data [2].Our aimisto infer the relationships between genes from an organism in a particular biological process. This relationships can be modeled in several levels of abstraction, these levels range from the detailed gene regulatory processes (where a chain of intracellular reaction activates a regulatory molecule, transcription factors until a protein is synthesized) to the high models of abstraction named gene association networks. In the reconstruction of gene regulatory processes, building gene association networks has been proven to provide useful insights for such task, the reconstruction of gene regulatory processes. A gene association network can be defined as a graph in which nodes represent genes and edges represent the influence between them. Our goal in this work is the inference of gene association networks from Microarray datasets.There are several statistical methods to infer gene association networks from Microarray data. A microarray dataset is a bidimensional data structure where conditions are experiments or sources and the columns are gene expression values. In our problem the conditions will be the instances and the gene expression values will be the attributes or features. These methods range from relatively straightforward correlation-based methods to more sophisticated methods based on