Efficiency of metaheuristics in the context of feature selection in gene expression database

• Grant number: 17/24539-7
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: February 01, 2018
• End date: January 31, 2019
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: André Carlos Ponce de Leon Ferreira de Carvalho
• Grantee: Juliano Decico Negri
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Associated research grant: 13/07375-0 - CeMEAI - Center for Mathematical Sciences Applied to Industry, AP.CEPID

Abstract

Studies of various pathologies, such as cancer, may benefit from technologies capable of capturing the expression of genes in tissues, such as RNA-Seq and Microarray, which can correlate the development of the disease with the patient's gene's expression. However, working with a large volume of data creates new challenges. In this context, the feature selection, the pre-processing of the data, becomes very important, especially when there is a high dimensionality, which is the case of the aforementioned data. Several techniques for selecting attributes can be found in the literature, but few have been tested with RNA-Seq. This project investigates the functionality of different techniques based on metaheuristics for feature selection in expression datasets (AU)