Registro fonte: Feature extraction and selection analysis in biological sequence: a case study with metaheuristics and mathematical models

Feature extraction and selection analysis in biological sequence: a case study with metaheuristics and mathematical models

The number of available biological sequences has increased in large amounts in past years, due to various genomic sequencing projects, creating a huge volume of data. Consequently, new computational methods are needed for the analysis and information extraction from these sequences. Machine learning...

ver descrição completa

Autor principal:	Bonidia, Robson Parmezan
Formato:	Dissertação
Idioma:	Inglês
Publicado em:	Universidade Tecnológica Federal do Paraná 2020
Assuntos:	Machine learning Mathematical models Heuristic programming Aprendizado do computador Modelos matemáticos Programação heurística CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO Engenharia/Tecnologia/Gestão
Acesso em linha:	http://repositorio.utfpr.edu.br/jspui/handle/1/5301
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!

id	riut-1-5301
recordtype	dspace
spelling	riut-1-53012022-08-12T15:44:17Z Feature extraction and selection analysis in biological sequence: a case study with metaheuristics and mathematical models Bonidia, Robson Parmezan Sanches, Danilo Sipoli http://lattes.cnpq.br/6377657274398145 Paschoal, Alexandre Rossi 0000-0002-8887-0582 http://lattes.cnpq.br/5834088144837137 Carvalho, Andre Carlos Ponce de Leon Ferreira de http://lattes.cnpq.br/9674541381385819 Sanches, Danilo Sipoli http://lattes.cnpq.br/6377657274398145 Lopes, Fabricio Martins http://lattes.cnpq.br/1660070580824436 Machine learning Mathematical models Heuristic programming Aprendizado do computador Modelos matemáticos Programação heurística CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO Engenharia/Tecnologia/Gestão The number of available biological sequences has increased in large amounts in past years, due to various genomic sequencing projects, creating a huge volume of data. Consequently, new computational methods are needed for the analysis and information extraction from these sequences. Machine learning methods have shown broad applicability in computational biology and bioinformatics. The application of machine learning methods has helped to extract relevant information from various biological datasets. However, there are still several challenging problems that motivate new algorithms and pipeline proposals. Therefore, this work proposes a generic machine learning pipeline for biological sequence analysis, following two main steps: (1) feature extraction and (2) feature selection. Essentially, we focus our work on the study of dimensionality reduction and feature extraction techniques, using metaheuristics and mathematical models. As a case study, we analyze Long Non-Coding RNA sequences. Moreover, we divided this dissertation into two parts, e.g., Experimental Test I (feature selection) and Experimental Test II (feature extraction). The experimental results indicated four main contributions: (1) A pipeline with five distinct metaheuristics, using a voting scheme and execution rounds, to the feature selection problem in biological sequences; (2) The metaheuristic efficiency, providing competitive classification performance; (3) A feature extraction pipeline using nine mathematical models and (4) its generalization and robustness for distinct biological sequence classification. Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) O número de sequências biológicas disponíveis aumentou em grandes quantidades nos últimos anos, devido a vários projetos de sequenciamento genômico, criando um alto volume de dados. Consequentemente, novos métodos computacionais são necessários para a análise e extração de informações a partir dessas sequências. Métodos de aprendizado de máquina têm apresentado ampla aplicabilidade em biologia computacional e bioinformática. A aplicação desses métodos tem ajudado a extrair informações relevantes de vários conjuntos de dados biológicos. No entanto, ainda existem vários problemas desafiadores que motivam novas propostas de algoritmos e pipelines. Portanto, este trabalho propõe um pipeline genérico de aprendizado de máquina para análise de sequência biológica, seguindo duas etapas principais: (1) extração e (2) seleção de características. Essencialmente, concentramos nosso trabalho no estudo de técnicas de redução de dimensionalidade e extração de recursos, usando metaheurísticas e modelos matemáticos. Como estudo de caso, analisamos sequências de RNAs longos não codificantes. Além disso, dividimos esta dissertação em duas partes: Teste Experimental I (seleção de características) e Teste Experimental II (extração de características). Os resultados experimentais indicam quatro contribuições principais: (1) Um pipeline com 5 metaheurísticas diferentes, usando um esquema de votação e rodadas de execução, ao problema de seleção de características em sequências biológicas; (2) A eficiência metaheurística, proporcionando desempenho de classificação competitiva; (3) Um pipeline de extração de recursos usando 9 modelos matemáticos e (4) sua generalização e robustez para classificação de sequências biológicas distintas. 2020-10-27T00:30:26Z 2020-10-27T00:30:26Z 2020-02-12 masterThesis BONIDIA, Robson Parmezan. Feature extraction and selection analysis in biological sequence: a case study with metaheuristics and mathematical models. 2020. Dissertação (Mestrado em Bioinformática) - Universidade Tecnológica Federal do Paraná, Cornélio Procópio, 2020. http://repositorio.utfpr.edu.br/jspui/handle/1/5301 eng openAccess application/pdf Universidade Tecnológica Federal do Paraná Cornelio Procopio Brasil Programa de Pós-Graduação em Bioinformática UTFPR
institution	Universidade Tecnológica Federal do Paraná
collection	RIUT
language	Inglês
topic	Machine learning Mathematical models Heuristic programming Aprendizado do computador Modelos matemáticos Programação heurística CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO Engenharia/Tecnologia/Gestão
spellingShingle	Machine learning Mathematical models Heuristic programming Aprendizado do computador Modelos matemáticos Programação heurística CNPQ::CIENCIAS EXATAS E DA TERRA::CIENCIA DA COMPUTACAO Engenharia/Tecnologia/Gestão Bonidia, Robson Parmezan Feature extraction and selection analysis in biological sequence: a case study with metaheuristics and mathematical models
description	The number of available biological sequences has increased in large amounts in past years, due to various genomic sequencing projects, creating a huge volume of data. Consequently, new computational methods are needed for the analysis and information extraction from these sequences. Machine learning methods have shown broad applicability in computational biology and bioinformatics. The application of machine learning methods has helped to extract relevant information from various biological datasets. However, there are still several challenging problems that motivate new algorithms and pipeline proposals. Therefore, this work proposes a generic machine learning pipeline for biological sequence analysis, following two main steps: (1) feature extraction and (2) feature selection. Essentially, we focus our work on the study of dimensionality reduction and feature extraction techniques, using metaheuristics and mathematical models. As a case study, we analyze Long Non-Coding RNA sequences. Moreover, we divided this dissertation into two parts, e.g., Experimental Test I (feature selection) and Experimental Test II (feature extraction). The experimental results indicated four main contributions: (1) A pipeline with five distinct metaheuristics, using a voting scheme and execution rounds, to the feature selection problem in biological sequences; (2) The metaheuristic efficiency, providing competitive classification performance; (3) A feature extraction pipeline using nine mathematical models and (4) its generalization and robustness for distinct biological sequence classification.
format	Dissertação
author	Bonidia, Robson Parmezan
author_sort	Bonidia, Robson Parmezan
title	Feature extraction and selection analysis in biological sequence: a case study with metaheuristics and mathematical models
title_short	Feature extraction and selection analysis in biological sequence: a case study with metaheuristics and mathematical models
title_full	Feature extraction and selection analysis in biological sequence: a case study with metaheuristics and mathematical models
title_fullStr	Feature extraction and selection analysis in biological sequence: a case study with metaheuristics and mathematical models
title_full_unstemmed	Feature extraction and selection analysis in biological sequence: a case study with metaheuristics and mathematical models
title_sort	feature extraction and selection analysis in biological sequence: a case study with metaheuristics and mathematical models
publisher	Universidade Tecnológica Federal do Paraná
publishDate	2020
citation	BONIDIA, Robson Parmezan. Feature extraction and selection analysis in biological sequence: a case study with metaheuristics and mathematical models. 2020. Dissertação (Mestrado em Bioinformática) - Universidade Tecnológica Federal do Paraná, Cornélio Procópio, 2020.
url	http://repositorio.utfpr.edu.br/jspui/handle/1/5301
_version_	1805316649454141440
score	10,814766

Feature extraction and selection analysis in biological sequence: a case study with metaheuristics and mathematical models

Registros relacionados