Fuzzy mutual information based grouping and new fitness function for PSO in selection of miRNAs in cancer
| Autor: | Shubhra Sankar Ray, Sankar K. Pal, Jayanta Kumar Pal |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
Male
0301 basic medicine Source code Computer science media_common.quotation_subject Health Informatics Machine learning computer.software_genre Models Biological Set (abstract data type) 03 medical and health sciences 0302 clinical medicine Fuzzy Logic Neoplasms Humans RNA Neoplasm Selection (genetic algorithm) media_common Soft computing Fitness function business.industry Particle swarm optimization Computer Science Applications Gene Expression Regulation Neoplastic MicroRNAs 030104 developmental biology Ranking 030220 oncology & carcinogenesis Pattern recognition (psychology) Female Artificial intelligence business computer |
| Zdroj: | Computers in Biology and Medicine. 89:540-548 |
| ISSN: | 0010-4825 |
| DOI: | 10.1016/j.compbiomed.2017.08.013 |
| Popis: | MicroRNAs (miRNA) are one of the important regulators of cell division and also responsible for cancer development. Among the discovered miRNAs, not all are important for cancer detection. In this regard a fuzzy mutual information (FMI) based grouping and miRNA selection method (FMIGS) is developed to identify the miRNAs responsible for a particular cancer. First, the miRNAs are ranked and divided into several groups. Then the most important group is selected among the generated groups. Both the steps viz., ranking of miRNAs and selection of the most relevant group of miRNAs, are performed using FMI. Here the number of groups is automatically determined by the grouping method. After the selection process, redundant miRNAs are removed from the selected set of miRNAs as per user's necessity. In a part of the investigation we proposed a FMI based particle swarm optimization (PSO) method for selecting relevant miRNAs, where FMI is used as a fitness function to determine the fitness of the particles. The effectiveness of FMIGS and FMI based PSO is tested on five data sets and their efficiency in selecting relevant miRNAs are demonstrated. The superior performance of FMIGS to some existing methods are established and the biological significance of the selected miRNAs is observed by the findings of the biological investigation and publicly available pathway analysis tools. The source code related to our investigation is available at http://www.jayanta.droppages.com/FMIGS.html. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect