Approaches based on tree-structures classifiers to protein fold prediction

2.50
Hdl Handle:
http://hdl.handle.net/10757/622536
Title:
Approaches based on tree-structures classifiers to protein fold prediction
Authors:
Shiguihara-Juarez, Pedro; Mauricio-Sanchez, David; de Andrade Lopes, Alneu
Publisher:
Institute of Electrical and Electronics Engineers Inc.
Issue Date:
Aug-2017
URI:
http://hdl.handle.net/10757/622536
DOI:
10.1109/INTERCON.2017.8079723
Additional Links:
http://ieeexplore.ieee.org/document/8079723/
Abstract:
Protein fold recognition is an important task in the biological area. Different machine learning methods such as multiclass classifiers, one-vs-all and ensemble nested dichotomies were applied to this task and, in most of the cases, multiclass approaches were used. In this paper, we compare classifiers organized in tree structures to classify folds. We used a benchmark dataset containing 125 features to predict folds, comparing different supervised methods and achieving 54% of accuracy. An approach related to tree-structure of classifiers obtained better results in comparison with a hierarchical approach.
Type:
info:eu-repo/semantics/conferenceObject
Rights:
info:eu-repo/semantics/restrictedAccess
Language:
eng
Description:
El texto completo de este trabajo no está disponible en el Repositorio Académico UPC por restricciones de la casa editorial donde ha sido publicado.
Keywords:
Learning systems; Protein folding; Proteins; Trees (mathematics); Benchmark datasets; Hierarchical approach; Machine learning methods; Multi-class classifier; Nested dichotomies; Protein fold recognition; Supervised methods; Tree structures

Full metadata record

DC FieldValue Language
dc.contributor.authorShiguihara-Juarez, Pedroes
dc.contributor.authorMauricio-Sanchez, Davides
dc.contributor.authorde Andrade Lopes, Alneues
dc.date.accessioned2018-01-16T20:34:41Z-
dc.date.available2018-01-16T20:34:41Z-
dc.date.issued2017-08-
dc.identifier.doi10.1109/INTERCON.2017.8079723-
dc.identifier.urihttp://hdl.handle.net/10757/622536-
dc.descriptionEl texto completo de este trabajo no está disponible en el Repositorio Académico UPC por restricciones de la casa editorial donde ha sido publicado.es_PE
dc.description.abstractProtein fold recognition is an important task in the biological area. Different machine learning methods such as multiclass classifiers, one-vs-all and ensemble nested dichotomies were applied to this task and, in most of the cases, multiclass approaches were used. In this paper, we compare classifiers organized in tree structures to classify folds. We used a benchmark dataset containing 125 features to predict folds, comparing different supervised methods and achieving 54% of accuracy. An approach related to tree-structure of classifiers obtained better results in comparison with a hierarchical approach.es
dc.formatapplication/pdfes
dc.language.isoenges
dc.publisherInstitute of Electrical and Electronics Engineers Inc.es
dc.relation.urlhttp://ieeexplore.ieee.org/document/8079723/es
dc.rightsinfo:eu-repo/semantics/restrictedAccesses
dc.subjectLearning systemses
dc.subjectProtein foldinges
dc.subjectProteinses
dc.subjectTrees (mathematics)es
dc.subjectBenchmark datasetses
dc.subjectHierarchical approaches
dc.subjectMachine learning methodses
dc.subjectMulti-class classifieres
dc.subjectNested dichotomieses
dc.subjectProtein fold recognitiones
dc.subjectSupervised methodses
dc.subjectTree structureses
dc.titleApproaches based on tree-structures classifiers to protein fold predictiones
dc.typeinfo:eu-repo/semantics/conferenceObjectes
dc.description.peerreviewRevisión por pareses_PE
All Items in UPC are protected by copyright, with all rights reserved, unless otherwise indicated.