A Memetic Cellular Genetic Algorithm for Cancer Data Microarray Feature Selection

Authors

Keywords:

feature selection, microarray classification, Cellular Genetic Algorithm, memetic algorithms

Abstract

Gene selection aims at identifying a -small- subset of informative genes from the initial data to obtain high predictive accuracy for classification in human cancers. Gene selection can be considered as a combinatorial search problem and thus be conveniently handled with optimization methods. This paper focuses on feature subset selection for dimensionality reduction in cancer classification and prediction. In this work, a Memetic Cellular Genetic Algorithm (MCGA) to solve the Feature Selection problem of cancer microarray dataset is presented. Benchmark gene expression datasets, i.e., colon, lymphoma, and leukaemia available in the literature were used for experimentation. MCGA is compared with other well-known metaheuristic' strategies. The results demonstrate that our proposal can provide efficient solutions to find a minimal subset of the genes.

Author Biographies

Matías Gabriel Rojas

Matías Gabriel Rojas is an informatic engineer graduated at the Gastón Dachary University in Posadas, Misiones, Argentina. His research topic belongs to bioinformatics algorithms area, focusing on optimization algorithms for feature selection. ORCID: 0000-0003-3881-0888

Ana Carolina Olivera, ITIC-UNCuyo

Ph.D. in Computer Science, Ana Carolina Olivera is an Adjunct Researcher at National Council of Scientifics and Technological Researches (CONICET: http://www.conicet.gov.ar/ ) from the Ministerio de Ciencia y Tecnología de la Nación. She is Associate Professor of Facultad de Ingeniería of Universidad Nacional de Cuyo (FING-UNCuyo http://ingenieria.uncuyo.edu.ar/) and Adjunct Professor at the Department of Exact and Natural Sciences of Universidad Nacional de la Patagonia Austral - Unidad Académica Caleta Olivia (UNPA-UACO http://www.uaco.unpa.edu.ar/ ). She participates and coordinates several national and international projects.

Research Interests

  • Bio-Inspired Algorithms
  • Metaheuristics
  • Optimization
  • Traffic and Transit Urban Problems
  • Urban Quality Air
  • Smart Cities
  • Graphics Processing Unit
  • Parallel Processing
  • Bioinformatics

Pablo Javier Vidal, Instituto Universitario para las Tecnologías de la Información y las Comunicaciones, Universidad Nacional de Cuyo, Facultad de Ingeniería (UNCuyo). CONICET, Mendoza, Argentina.

Pablo Javier Vidal is an Adjunct Professor at the Universidad Nacional de Cuyo, and at the Universidad Nacional de la Patagonia Austral, Argentine. Dr. in Software Engineering and Artificial Intelligence, from Universidad de Málaga, Spain. He is an Assistant Researcher at National Council of Scientifics and Technological Researches from the Ministerio de Ciencia y Tecnología de la Nación, Argentine. His main research topics are parallel and distributed computing, bioinformatics and metaheuristics.
ORCID: 0000-0001-6502-8010

Jessica Andrea Carballido, Instituto de Ciencias e Ingeniería de la Computación, CONICET, Universidad Nacional del Sur, Bahía Blanca, Argentina

Jessica Andrea Carballido is an Adjunct Researcher at National Council of Scientifics and Technological Researches from the Ministerio de Ciencia y Tecnología de la Nación, Argentine. Dr. in Computer Science from Universidad Nacional del Sur. She is an Associate Professor at the Dpto. de Cs. e Ing. de la Computación from Universidad Nacional del Sur. Her research focuses on evolutionary computation applied to bioinformatics, mainly for cancer studies from microarray and RNA-seq experiments. She has published several book chapters, articles in indexed journals and proceedings of refereed international conferences.

Published

2020-09-28
Bookmark and Share