Protein contact map prediction using multi-stage hybrid intelligence inference systems

Anas A. Abu-Doleh, Omar M. Al-Jarrah, Asem Alkhateeb

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Proteins are one of the most important molecules in organisms. Protein function can be inferred from its 3D structure. The gap between the number of discovered protein sequences and the number of structures determined by the experimental methods is increasing. Accurate prediction of protein contact map is an important step toward the reconstruction of the protein's 3D structure. In spite of continuous progress in developing contact map predictors, highly accurate prediction is still unresolved problem. In this paper, we introduce a new predictor, JUSTcon, which consists of multiple parallel stages that are based on adaptive neuro-fuzzy inference System (ANFIS) and K nearest neighbors (KNNs) classifier. A smart filtering operation is performed on the final outputs to ensure normal connectivity behaviors of amino acids pairs. The window size of the filter is selected by a simple expert system. The dataset was divided into testing dataset of 50 proteins and training dataset of 450 proteins. The system produced an average accuracy of 45.2% for the sequence separation of six amino acids. In addition, JUSTcon outperformed SVMcon and PROFcon predictors in the cases of large separation distances. JUSTcon produced an average accuracy of 15% for the sequence separation of 24 amino acids after applying it on CASP9 targets.

Original languageEnglish
Pages (from-to)173-183
Number of pages11
JournalJournal of Biomedical Informatics
Volume45
Issue number1
DOIs
Publication statusPublished - Feb 2012
Externally publishedYes

Fingerprint

Intelligence
Proteins
Amino acids
Amino Acids
Expert Systems
Fuzzy inference
Expert systems
Classifiers
Molecules
Testing
Datasets

Keywords

  • Fuzzy inference system
  • Hybrid prediction model
  • Protein contact map prediction

ASJC Scopus subject areas

  • Computer Science Applications
  • Health Informatics

Cite this

Protein contact map prediction using multi-stage hybrid intelligence inference systems. / Abu-Doleh, Anas A.; Al-Jarrah, Omar M.; Alkhateeb, Asem.

In: Journal of Biomedical Informatics, Vol. 45, No. 1, 02.2012, p. 173-183.

Research output: Contribution to journalArticle

Abu-Doleh, Anas A. ; Al-Jarrah, Omar M. ; Alkhateeb, Asem. / Protein contact map prediction using multi-stage hybrid intelligence inference systems. In: Journal of Biomedical Informatics. 2012 ; Vol. 45, No. 1. pp. 173-183.
@article{5e4258aaa0884edca19e79522ecbe435,
title = "Protein contact map prediction using multi-stage hybrid intelligence inference systems",
abstract = "Proteins are one of the most important molecules in organisms. Protein function can be inferred from its 3D structure. The gap between the number of discovered protein sequences and the number of structures determined by the experimental methods is increasing. Accurate prediction of protein contact map is an important step toward the reconstruction of the protein's 3D structure. In spite of continuous progress in developing contact map predictors, highly accurate prediction is still unresolved problem. In this paper, we introduce a new predictor, JUSTcon, which consists of multiple parallel stages that are based on adaptive neuro-fuzzy inference System (ANFIS) and K nearest neighbors (KNNs) classifier. A smart filtering operation is performed on the final outputs to ensure normal connectivity behaviors of amino acids pairs. The window size of the filter is selected by a simple expert system. The dataset was divided into testing dataset of 50 proteins and training dataset of 450 proteins. The system produced an average accuracy of 45.2{\%} for the sequence separation of six amino acids. In addition, JUSTcon outperformed SVMcon and PROFcon predictors in the cases of large separation distances. JUSTcon produced an average accuracy of 15{\%} for the sequence separation of 24 amino acids after applying it on CASP9 targets.",
keywords = "Fuzzy inference system, Hybrid prediction model, Protein contact map prediction",
author = "Abu-Doleh, {Anas A.} and Al-Jarrah, {Omar M.} and Asem Alkhateeb",
year = "2012",
month = "2",
doi = "10.1016/j.jbi.2011.10.008",
language = "English",
volume = "45",
pages = "173--183",
journal = "Journal of Biomedical Informatics",
issn = "1532-0464",
publisher = "Academic Press Inc.",
number = "1",

}

TY - JOUR

T1 - Protein contact map prediction using multi-stage hybrid intelligence inference systems

AU - Abu-Doleh, Anas A.

AU - Al-Jarrah, Omar M.

AU - Alkhateeb, Asem

PY - 2012/2

Y1 - 2012/2

N2 - Proteins are one of the most important molecules in organisms. Protein function can be inferred from its 3D structure. The gap between the number of discovered protein sequences and the number of structures determined by the experimental methods is increasing. Accurate prediction of protein contact map is an important step toward the reconstruction of the protein's 3D structure. In spite of continuous progress in developing contact map predictors, highly accurate prediction is still unresolved problem. In this paper, we introduce a new predictor, JUSTcon, which consists of multiple parallel stages that are based on adaptive neuro-fuzzy inference System (ANFIS) and K nearest neighbors (KNNs) classifier. A smart filtering operation is performed on the final outputs to ensure normal connectivity behaviors of amino acids pairs. The window size of the filter is selected by a simple expert system. The dataset was divided into testing dataset of 50 proteins and training dataset of 450 proteins. The system produced an average accuracy of 45.2% for the sequence separation of six amino acids. In addition, JUSTcon outperformed SVMcon and PROFcon predictors in the cases of large separation distances. JUSTcon produced an average accuracy of 15% for the sequence separation of 24 amino acids after applying it on CASP9 targets.

AB - Proteins are one of the most important molecules in organisms. Protein function can be inferred from its 3D structure. The gap between the number of discovered protein sequences and the number of structures determined by the experimental methods is increasing. Accurate prediction of protein contact map is an important step toward the reconstruction of the protein's 3D structure. In spite of continuous progress in developing contact map predictors, highly accurate prediction is still unresolved problem. In this paper, we introduce a new predictor, JUSTcon, which consists of multiple parallel stages that are based on adaptive neuro-fuzzy inference System (ANFIS) and K nearest neighbors (KNNs) classifier. A smart filtering operation is performed on the final outputs to ensure normal connectivity behaviors of amino acids pairs. The window size of the filter is selected by a simple expert system. The dataset was divided into testing dataset of 50 proteins and training dataset of 450 proteins. The system produced an average accuracy of 45.2% for the sequence separation of six amino acids. In addition, JUSTcon outperformed SVMcon and PROFcon predictors in the cases of large separation distances. JUSTcon produced an average accuracy of 15% for the sequence separation of 24 amino acids after applying it on CASP9 targets.

KW - Fuzzy inference system

KW - Hybrid prediction model

KW - Protein contact map prediction

UR - http://www.scopus.com/inward/record.url?scp=84856366339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84856366339&partnerID=8YFLogxK

U2 - 10.1016/j.jbi.2011.10.008

DO - 10.1016/j.jbi.2011.10.008

M3 - Article

VL - 45

SP - 173

EP - 183

JO - Journal of Biomedical Informatics

JF - Journal of Biomedical Informatics

SN - 1532-0464

IS - 1

ER -