Approaches based on tree-structures classifiers to protein fold prediction

Pedro Shiguihara-Juarez; David Mauricio-Sanchez; Alneu De Andrade Lopes

doi:10.1109/INTERCON.2017.8079723

Approaches based on tree-structures classifiers to protein fold prediction

Pedro Shiguihara-Juarez, David Mauricio-Sanchez, Alneu De Andrade Lopes

Research output: Contribution to conference › Paper

1 Scopus citations

Abstract

© 2017 IEEE. 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.

Original language	American English
DOIs	https://doi.org/10.1109/INTERCON.2017.8079723
State	Published - 20 Oct 2017
Event	Proceedings of the 2017 IEEE 24th International Congress on Electronics, Electrical Engineering and Computing, INTERCON 2017 - Duration: 20 Oct 2017 → …

Conference

Conference	Proceedings of the 2017 IEEE 24th International Congress on Electronics, Electrical Engineering and Computing, INTERCON 2017
Period	20/10/17 → …

Access to Document

10.1109/INTERCON.2017.8079723

Cite this

@conference{86d58b85bfd54231a8d751c28e1c3044,

title = "Approaches based on tree-structures classifiers to protein fold prediction",

abstract = "{\textcopyright} 2017 IEEE. 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.",

author = "Pedro Shiguihara-Juarez and David Mauricio-Sanchez and {De Andrade Lopes}, Alneu",

year = "2017",

month = oct,

day = "20",

doi = "10.1109/INTERCON.2017.8079723",

language = "American English",

note = "Proceedings of the 2017 IEEE 24th International Congress on Electronics, Electrical Engineering and Computing, INTERCON 2017 ; Conference date: 20-10-2017",

}

TY - CONF

T1 - Approaches based on tree-structures classifiers to protein fold prediction

AU - Shiguihara-Juarez, Pedro

AU - Mauricio-Sanchez, David

AU - De Andrade Lopes, Alneu

PY - 2017/10/20

Y1 - 2017/10/20

N2 - © 2017 IEEE. 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.

AB - © 2017 IEEE. 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.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85040015320&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85040015320&origin=inward

U2 - 10.1109/INTERCON.2017.8079723

DO - 10.1109/INTERCON.2017.8079723

M3 - Paper

T2 - Proceedings of the 2017 IEEE 24th International Congress on Electronics, Electrical Engineering and Computing, INTERCON 2017

Y2 - 20 October 2017

ER -

Approaches based on tree-structures classifiers to protein fold prediction

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this