Class Decomposition in Bioinformatics Analyzing Omics Data

摘要

This article presents an approach in bioinformatics data analysis and exploration. The diseases studied in bioinformatics (diagnostic, prognosis etc. studies) often have known or yet undiscovered subtypes that can be used while solving bioinformatics tasks providing more information and knowledge. This study tackles the mentioned problem by studying inner c lass structures using cluster analysis to find subclasses and applying it i n classification tasks. The study c oncludes i n c omparison w ith regular c lassification pr ocedure, finding that in most cases the classification results improve after class decomposition is applied.