Configurable pattern-based evolutionary biclustering of gene expression data

Abstract

BackgroundBiclustering algorithms for microarray data aim at discovering functionally related gene sets under different subsets of experimental conditions. Due to the problem complexity and the characteristics of microarray datasets, heuristic searches are usually used instead of exhaustive algorithms. Also, the comparison among different techniques is still a challenge. The obtained results vary in relevant features such as the number of genes or conditions, which makes it difficult to carry out a fair comparison. Moreover, existing approaches do not allow the user to specify any preferences on these properties.ResultsHere, we present the first biclustering algorithm in which it is possible to particularize several biclusters features in terms of different objectives. This can be done by tuning the specified features in the algorithm or also by incorporating new objectives into the search. Furthermore, our approach bases the bicluster evaluation in the use of expression patterns, being able to recognize both shifting and scaling patterns either simultaneously or not. Evolutionary computation has been chosen as the search strategy, naming thus our proposal Evo-Bexpa (Evolutionary Biclustering based in Expression Patterns).ConclusionsWe have conducted experiments on both synthetic and real datasets demonstrating Evo-Bexpa abilities to obtain meaningful biclusters. Synthetic experiments have been designed in order to compare Evo-Bexpa performance with other approaches when looking for perfect patterns. Experiments with four different real datasets also confirm the proper performing of our algorithm, whose results have been biologically validated through Gene Ontology.

A structured view on pattern mining-based biclustering

“…Comparison: We selected 15 state-of-the-art approaches 9 : FABIA method with sparse prior option [67], ISA [70], OPSM [15], CC [29], Samba [119], xMotifs [94], OP-Clustering [78], BicSPAM [63], Bexpa [106], BCPlaid [123] and the PM-based BiModule [96], DeBi [111], RAP [101], BicPAM [62] and BiP [60] biclustering approaches. We used the following software: R packages fabia 10 and biclust 11 , BicAT [10], Expander 12 , (Evo-)Bexpa [106], RAP 13 and BicPAMS 14 .…”

“…We used the following software: R packages fabia 10 and biclust 11 , BicAT [10], Expander 12 , (Evo-)Bexpa [106], RAP 13 and BicPAMS 14 .…”

Quality Measures for Gene Expression Biclusters

“…For this purpose, the biclusters generated by EvoBexpa in [32] have been used, where one hundred biclusters were found for each datasets.…”

Time-Lagged Co-Expression Gene Analysis Based on Biclustering Technology

“…the basis of this analysis method is that genes with the same (or similar) functions have the same (or similar) expression values under all conditions. Recently, biclustering has been put forward based on the assumption that similar functions have the same expression values under certain conditions (5,6,9,10,12,13,14).…”

“…the conditions of gene expression are independent. Recently, some authors have applied the biclustering method for analysis of a time-series gene expression matrix (1,3,5,6,7,9,10,12,13,14,15,16,18). With a time-series gene expression matrix, the measuring condition is one cycle of cell activity or another biological process.…”