Solving protein fold prediction problem using fusion of heterogeneous classifiers

Abdollah Dehzangi; Sasan Karamizadeh

Solving protein fold prediction problem using fusion of heterogeneous classifiers

Research output: Contribution to journal › Article › peer-review

Abstract

Protein fold prediction problem is considered as one of the most challenging tasks for molecular biology and Bioinformatics. In this study, a fusion of heterogeneous Meta classifiers namely: LogitBoost, Random Forest, and Rotation Forest, is proposed to solve this problem. The proposed approach aims at enhancing the protein fold prediction accuracy by enforcing diversity among its individual members by employing divers and accurate base classifiers. Our experimental results show that our proposed approach enhances the protein fold prediction accuracy using Ding and Dubchak's dataset and Dubchak and her coworkers' feature set, better than the previous works found in the literature.

Original language	English (US)
Pages (from-to)	3611-3621
Number of pages	11
Journal	Information
Volume	14
Issue number	11
State	Published - Nov 2011
Externally published	Yes

ASJC Scopus subject areas

Information Systems

Keywords

Feature extraction
Fusion of heterogeneous classifiers
LogitBoost
Majority voting
Protein fold prediction problem
Random Forest
Rotation Forest

Cite this

@article{23abe3a1fde24a518780a86b18d71f93,

title = "Solving protein fold prediction problem using fusion of heterogeneous classifiers",

abstract = "Protein fold prediction problem is considered as one of the most challenging tasks for molecular biology and Bioinformatics. In this study, a fusion of heterogeneous Meta classifiers namely: LogitBoost, Random Forest, and Rotation Forest, is proposed to solve this problem. The proposed approach aims at enhancing the protein fold prediction accuracy by enforcing diversity among its individual members by employing divers and accurate base classifiers. Our experimental results show that our proposed approach enhances the protein fold prediction accuracy using Ding and Dubchak's dataset and Dubchak and her coworkers' feature set, better than the previous works found in the literature.",

keywords = "Feature extraction, Fusion of heterogeneous classifiers, LogitBoost, Majority voting, Protein fold prediction problem, Random Forest, Rotation Forest",

author = "Abdollah Dehzangi and Sasan Karamizadeh",

year = "2011",

month = nov,

language = "English (US)",

volume = "14",

pages = "3611--3621",

journal = "Information",

issn = "1343-4500",

publisher = "International Information Institute",

number = "11",

}

TY - JOUR

T1 - Solving protein fold prediction problem using fusion of heterogeneous classifiers

AU - Dehzangi, Abdollah

AU - Karamizadeh, Sasan

PY - 2011/11

Y1 - 2011/11

N2 - Protein fold prediction problem is considered as one of the most challenging tasks for molecular biology and Bioinformatics. In this study, a fusion of heterogeneous Meta classifiers namely: LogitBoost, Random Forest, and Rotation Forest, is proposed to solve this problem. The proposed approach aims at enhancing the protein fold prediction accuracy by enforcing diversity among its individual members by employing divers and accurate base classifiers. Our experimental results show that our proposed approach enhances the protein fold prediction accuracy using Ding and Dubchak's dataset and Dubchak and her coworkers' feature set, better than the previous works found in the literature.

AB - Protein fold prediction problem is considered as one of the most challenging tasks for molecular biology and Bioinformatics. In this study, a fusion of heterogeneous Meta classifiers namely: LogitBoost, Random Forest, and Rotation Forest, is proposed to solve this problem. The proposed approach aims at enhancing the protein fold prediction accuracy by enforcing diversity among its individual members by employing divers and accurate base classifiers. Our experimental results show that our proposed approach enhances the protein fold prediction accuracy using Ding and Dubchak's dataset and Dubchak and her coworkers' feature set, better than the previous works found in the literature.

KW - Feature extraction

KW - Fusion of heterogeneous classifiers

KW - LogitBoost

KW - Majority voting

KW - Protein fold prediction problem

KW - Random Forest

KW - Rotation Forest

UR - http://www.scopus.com/inward/record.url?scp=84860179168&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860179168&partnerID=8YFLogxK

M3 - Article

SN - 1343-4500

VL - 14

SP - 3611

EP - 3621

JO - Information

JF - Information

IS - 11

ER -

Solving protein fold prediction problem using fusion of heterogeneous classifiers

Abstract

ASJC Scopus subject areas

Keywords

Other files and links

Fingerprint

Cite this