Multiobjective Approach to Cancer-Associated MicroRNA Module Detection

MicroRNAs (miRNAs) are tiny RNA molecules that, while not directly involved in the protein translation process, indirectly regulate protein production by targeting specific genes or messenger RNAs (mRNAs). Some miRNAs play crucial roles in various human diseases like cancer, diabetes, viral infections, and cardiovascular issues. Understanding the regulatory relationships between genes and miRNAs is essential for identifying potential drug targets for these serious diseases. This chapter introduces a multiobjective miRNA module detection algorithm designed to identify groups of miRNAs associated with different cancer types. The algorithm optimizes two objective functions simultaneously, based on changes in miRNA coexpression patterns across different conditions and functional similarities within miRNA pairs. The non-dominated sorting genetic algorithm-II (NSGA-II) is employed for optimization. The technique’s superiority over existing algorithms in identifying microRNA markers is demonstrated through experiments based on several real-life miRNA expression datasets. The chapter also explores the biological significance of the mRNA targets of the identified miRNA markers.