Filter-wrapper approach to feature selection of GPCR protein

Nor Ashikin Mohamad Kamal, Azuraliza Abu Bakar, Suhaila Zainudin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Protein dataset contains high dimensional feature space. These features may encompass of noise and not relatively to protein function. Therefore, we need to select the appropriate features to improve the efficiency and performance of the classifier. Feature selection is an important step in any classification tasks. Filter methods are important in order to obtain only the relevant features to the class and to avoid redundancy. While wrapper methods are applied to get optimized features and better classification accuracy. This paper proposed a feature selection strategy for hierarchical classification of G-Protein-Coupled Receptors (GPCR) based on hybridization of correlation feature selection (CFS) filter and genetic algorithm (GA) wrapper methods. The optimum features were then classified using K-nearest neighbor algorithm. These methods are capable to reduce the features and achieved comparable classification accuracy at every hierarchy level. The results also shown that the integration between CFS and GA is capable of searching the optimum features for hierarchical protein classification.

Original languageEnglish
Title of host publicationProceedings - 5th International Conference on Electrical Engineering and Informatics: Bridging the Knowledge between Academic, Industry, and Community, ICEEI 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages693-698
Number of pages6
ISBN (Print)9781467373197
DOIs
Publication statusPublished - 10 Dec 2015
Event5th International Conference on Electrical Engineering and Informatics, ICEEI 2015 - Legian-Bali, Indonesia
Duration: 10 Aug 201511 Aug 2015

Other

Other5th International Conference on Electrical Engineering and Informatics, ICEEI 2015
CountryIndonesia
CityLegian-Bali
Period10/8/1511/8/15

Fingerprint

Feature extraction
Proteins
Genetic algorithms
Redundancy
Classifiers

Keywords

  • CFS
  • Feature selection
  • GA
  • GPCR Proteins
  • Hierarchical classification

ASJC Scopus subject areas

  • Computer Science Applications
  • Information Systems
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Kamal, N. A. M., Abu Bakar, A., & Zainudin, S. (2015). Filter-wrapper approach to feature selection of GPCR protein. In Proceedings - 5th International Conference on Electrical Engineering and Informatics: Bridging the Knowledge between Academic, Industry, and Community, ICEEI 2015 (pp. 693-698). [7352587] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICEEI.2015.7352587

Filter-wrapper approach to feature selection of GPCR protein. / Kamal, Nor Ashikin Mohamad; Abu Bakar, Azuraliza; Zainudin, Suhaila.

Proceedings - 5th International Conference on Electrical Engineering and Informatics: Bridging the Knowledge between Academic, Industry, and Community, ICEEI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. p. 693-698 7352587.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kamal, NAM, Abu Bakar, A & Zainudin, S 2015, Filter-wrapper approach to feature selection of GPCR protein. in Proceedings - 5th International Conference on Electrical Engineering and Informatics: Bridging the Knowledge between Academic, Industry, and Community, ICEEI 2015., 7352587, Institute of Electrical and Electronics Engineers Inc., pp. 693-698, 5th International Conference on Electrical Engineering and Informatics, ICEEI 2015, Legian-Bali, Indonesia, 10/8/15. https://doi.org/10.1109/ICEEI.2015.7352587
Kamal NAM, Abu Bakar A, Zainudin S. Filter-wrapper approach to feature selection of GPCR protein. In Proceedings - 5th International Conference on Electrical Engineering and Informatics: Bridging the Knowledge between Academic, Industry, and Community, ICEEI 2015. Institute of Electrical and Electronics Engineers Inc. 2015. p. 693-698. 7352587 https://doi.org/10.1109/ICEEI.2015.7352587
Kamal, Nor Ashikin Mohamad ; Abu Bakar, Azuraliza ; Zainudin, Suhaila. / Filter-wrapper approach to feature selection of GPCR protein. Proceedings - 5th International Conference on Electrical Engineering and Informatics: Bridging the Knowledge between Academic, Industry, and Community, ICEEI 2015. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 693-698
@inproceedings{e3d80adc1b6a4da4966db0d70a4b4006,
title = "Filter-wrapper approach to feature selection of GPCR protein",
abstract = "Protein dataset contains high dimensional feature space. These features may encompass of noise and not relatively to protein function. Therefore, we need to select the appropriate features to improve the efficiency and performance of the classifier. Feature selection is an important step in any classification tasks. Filter methods are important in order to obtain only the relevant features to the class and to avoid redundancy. While wrapper methods are applied to get optimized features and better classification accuracy. This paper proposed a feature selection strategy for hierarchical classification of G-Protein-Coupled Receptors (GPCR) based on hybridization of correlation feature selection (CFS) filter and genetic algorithm (GA) wrapper methods. The optimum features were then classified using K-nearest neighbor algorithm. These methods are capable to reduce the features and achieved comparable classification accuracy at every hierarchy level. The results also shown that the integration between CFS and GA is capable of searching the optimum features for hierarchical protein classification.",
keywords = "CFS, Feature selection, GA, GPCR Proteins, Hierarchical classification",
author = "Kamal, {Nor Ashikin Mohamad} and {Abu Bakar}, Azuraliza and Suhaila Zainudin",
year = "2015",
month = "12",
day = "10",
doi = "10.1109/ICEEI.2015.7352587",
language = "English",
isbn = "9781467373197",
pages = "693--698",
booktitle = "Proceedings - 5th International Conference on Electrical Engineering and Informatics: Bridging the Knowledge between Academic, Industry, and Community, ICEEI 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Filter-wrapper approach to feature selection of GPCR protein

AU - Kamal, Nor Ashikin Mohamad

AU - Abu Bakar, Azuraliza

AU - Zainudin, Suhaila

PY - 2015/12/10

Y1 - 2015/12/10

N2 - Protein dataset contains high dimensional feature space. These features may encompass of noise and not relatively to protein function. Therefore, we need to select the appropriate features to improve the efficiency and performance of the classifier. Feature selection is an important step in any classification tasks. Filter methods are important in order to obtain only the relevant features to the class and to avoid redundancy. While wrapper methods are applied to get optimized features and better classification accuracy. This paper proposed a feature selection strategy for hierarchical classification of G-Protein-Coupled Receptors (GPCR) based on hybridization of correlation feature selection (CFS) filter and genetic algorithm (GA) wrapper methods. The optimum features were then classified using K-nearest neighbor algorithm. These methods are capable to reduce the features and achieved comparable classification accuracy at every hierarchy level. The results also shown that the integration between CFS and GA is capable of searching the optimum features for hierarchical protein classification.

AB - Protein dataset contains high dimensional feature space. These features may encompass of noise and not relatively to protein function. Therefore, we need to select the appropriate features to improve the efficiency and performance of the classifier. Feature selection is an important step in any classification tasks. Filter methods are important in order to obtain only the relevant features to the class and to avoid redundancy. While wrapper methods are applied to get optimized features and better classification accuracy. This paper proposed a feature selection strategy for hierarchical classification of G-Protein-Coupled Receptors (GPCR) based on hybridization of correlation feature selection (CFS) filter and genetic algorithm (GA) wrapper methods. The optimum features were then classified using K-nearest neighbor algorithm. These methods are capable to reduce the features and achieved comparable classification accuracy at every hierarchy level. The results also shown that the integration between CFS and GA is capable of searching the optimum features for hierarchical protein classification.

KW - CFS

KW - Feature selection

KW - GA

KW - GPCR Proteins

KW - Hierarchical classification

UR - http://www.scopus.com/inward/record.url?scp=84961724216&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84961724216&partnerID=8YFLogxK

U2 - 10.1109/ICEEI.2015.7352587

DO - 10.1109/ICEEI.2015.7352587

M3 - Conference contribution

AN - SCOPUS:84961724216

SN - 9781467373197

SP - 693

EP - 698

BT - Proceedings - 5th International Conference on Electrical Engineering and Informatics: Bridging the Knowledge between Academic, Industry, and Community, ICEEI 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -