Multiway analysis of high throughput genomic data

High throughput data can be generated by developing techniques and represented in large matrices. Analysis of such data has become one of the major tool but it has brought along many challenges for biological data mining such as process complexities and difficulties in information retrieval. In recent years these challenges have become critic since huge amount of data is produced especially in life sciences and standard techniques may not be used in analysing of such data. This kind of data structure may be multi-way and/or multi-source by used test and devices. In this study based on the specified motivation, a novel method and software tool are developed to increase proficency of data analysis techniques. The developed method aims to make cross species (multi sources) analysis using mRNA expression values obtained from different organisms (human, mouse, monkey etc.) under same conditions. To achieve this goal a novel three way clustering method named TriClustering is introduced and the method has been applied to three different gene expression data obtained from NCBI?s GEO data collection. Biological and statistical significance of the results are evaluated using Gene Ontology (GO) term enrichment analysis and Dunn index (DI) metric, respectively. The experimental results indicate that TriClustering on multi-organism data can be resulted with better gene clusters in comparison to biclustering on single-organism data. The method also promote a useful tool for cross species gene regulation analysis.