Strong-association-rule mining for large-scale gene-expression data analysis: a case study on human SAGE data

Abstract

Correspondence: Olivier Gandrillon. E-mail: Gandrillon@maccgmc.univ-lyon1.fr AbstractBackground: The association-rules discovery (ARD) technique has yet to be applied to geneexpression data analysis. Even in the absence of previous biological knowledge, it should identify sets of genes whose expression is correlated. The first association-rule miners appeared six years ago and proved efficient at dealing with sparse and weakly correlated data. A huge international research effort has led to new algorithms for tackling difficult contexts and these are particularly suited to analysis of large gene-expression matrices. To validate the ARD technique we have applied it to freely available human serial analysis of gene expression (SAGE) data.

Global transcription analysis of immature avian erythrocytic progenitors: from self-renewal to differentiation

“…The transcriptional regulation of genes encoding proteins involved in the translation process is an emerging pattern in numerous biological systems (Becquet et al, 2002). In addition, during differentiation, we discovered a reduction in the expression of several genes coding for proteins involved in metabolic functions, suggesting an important role of variations in metabolic pathways during the first steps of erythroid differentiation.…”

Mining confident minimal rules with fixed-consequents

“…The work in [4] [7] [15] support our claim of the importance of minimal rules. [4] uses the notion of non-redundant or minimal rules to refer to rules with the smallest possible antecedents and largest possible consequents.…”

“…This matches our rule minimality definition to a large extent since we also require the antecedent to be as small as possible; however, we relax the requirement on the consequent because we are dealing with fixed consequents. [7] emphasizes the importance of "small" rules in the context of genome analysis while [15] extends it to medical data.…”

MIDClass: Microarray Data Classification by Association Rules and Gene Expression Intervals

“…Association Rule Mining has been proven to be effective in many microarray applications[18]–[20]. In [18], authors extract significant relations among microarray genes annotated with metabolic pathways, transcriptional regulators and Gene Ontologies.…”

“…Association Rule Mining has been proven to be effective in many microarray applications[18]–[20]. In [18], authors extract significant relations among microarray genes annotated with metabolic pathways, transcriptional regulators and Gene Ontologies. In [19], McIntosh and Chawla employ quantitative association rules capable of dealing with numeric data representing cumulative effects of variables.…”