Two-layer SVM classifier for remote protein homology detection and fold recognition

Advances in molecular biology in the past years have yielded an unprecedented amount of new protein sequences. The resulting sequences describe a protein in terms of the amino acids that constitute them without structural or functional protein information. Therefore, remote protein homology detectio...

Full description

Saved in:
Bibliographic Details
Main Author: Muda, Mohd. Hilmi
Format: Thesis
Language:English
Published: 2009
Subjects:
Online Access:http://eprints.utm.my/id/eprint/11488/6/MohdHilmiMudaMFSKSM2009.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
id my-utm-ep.11488
record_format uketd_dc
spelling my-utm-ep.114882017-09-18T10:11:02Z Two-layer SVM classifier for remote protein homology detection and fold recognition 2009-11 Muda, Mohd. Hilmi QA75 Electronic computers. Computer science Advances in molecular biology in the past years have yielded an unprecedented amount of new protein sequences. The resulting sequences describe a protein in terms of the amino acids that constitute them without structural or functional protein information. Therefore, remote protein homology detection and fold recognition algorithms have become increasingly important to detect the structural homology in proteins where there are small or no similarity at all in the sequences compared. However, it is a challenging task to detect and classify this similarity with more biological meaning in the context of Structural Classification of Proteins (SCOP) database. This study presents a new computational framework based on two-layer SVM classifier that uses protein sequences as a primary source. The first layer is used to detect up to superfamily level in the SCOP hierarchy using one-versus-all SVM binary classifiers and the Bio-kernel function. The second layer uses SVM with fold recognition codes and the profile-string kernel to leverage the unlabeled data and to detect up to fold level in the SCOP hierarchy. The proposed framework is tested using SCOP 1.53, 1.67 and 1.73 datasets and the results are evaluated using mean Receiver Operating Characteristics (ROC) and mean Median Rate of False Positives (MRFP). In terms of mean ROC, the experiment shows 4.19% improvement in SCOP 1.53 dataset, 4.75% in SCOP 1.67 dataset and 4.03% in SCOP 1.73 dataset compared to the existing SVM-based classifiers and kernel functions. This result shows that the proposed framework is capable to perform well using different versions of datasets and has outperformed existing methods, which implies the reliability of the framework. 2009-11 Thesis http://eprints.utm.my/id/eprint/11488/ http://eprints.utm.my/id/eprint/11488/6/MohdHilmiMudaMFSKSM2009.pdf application/pdf en public masters Universiti Teknologi Malaysia, Faculty of Computer Science and Information Systems Faculty of Computer Science and Information System
institution Universiti Teknologi Malaysia
collection UTM Institutional Repository
language English
topic QA75 Electronic computers
Computer science
spellingShingle QA75 Electronic computers
Computer science
Muda, Mohd. Hilmi
Two-layer SVM classifier for remote protein homology detection and fold recognition
description Advances in molecular biology in the past years have yielded an unprecedented amount of new protein sequences. The resulting sequences describe a protein in terms of the amino acids that constitute them without structural or functional protein information. Therefore, remote protein homology detection and fold recognition algorithms have become increasingly important to detect the structural homology in proteins where there are small or no similarity at all in the sequences compared. However, it is a challenging task to detect and classify this similarity with more biological meaning in the context of Structural Classification of Proteins (SCOP) database. This study presents a new computational framework based on two-layer SVM classifier that uses protein sequences as a primary source. The first layer is used to detect up to superfamily level in the SCOP hierarchy using one-versus-all SVM binary classifiers and the Bio-kernel function. The second layer uses SVM with fold recognition codes and the profile-string kernel to leverage the unlabeled data and to detect up to fold level in the SCOP hierarchy. The proposed framework is tested using SCOP 1.53, 1.67 and 1.73 datasets and the results are evaluated using mean Receiver Operating Characteristics (ROC) and mean Median Rate of False Positives (MRFP). In terms of mean ROC, the experiment shows 4.19% improvement in SCOP 1.53 dataset, 4.75% in SCOP 1.67 dataset and 4.03% in SCOP 1.73 dataset compared to the existing SVM-based classifiers and kernel functions. This result shows that the proposed framework is capable to perform well using different versions of datasets and has outperformed existing methods, which implies the reliability of the framework.
format Thesis
qualification_level Master's degree
author Muda, Mohd. Hilmi
author_facet Muda, Mohd. Hilmi
author_sort Muda, Mohd. Hilmi
title Two-layer SVM classifier for remote protein homology detection and fold recognition
title_short Two-layer SVM classifier for remote protein homology detection and fold recognition
title_full Two-layer SVM classifier for remote protein homology detection and fold recognition
title_fullStr Two-layer SVM classifier for remote protein homology detection and fold recognition
title_full_unstemmed Two-layer SVM classifier for remote protein homology detection and fold recognition
title_sort two-layer svm classifier for remote protein homology detection and fold recognition
granting_institution Universiti Teknologi Malaysia, Faculty of Computer Science and Information Systems
granting_department Faculty of Computer Science and Information System
publishDate 2009
url http://eprints.utm.my/id/eprint/11488/6/MohdHilmiMudaMFSKSM2009.pdf
_version_ 1747814862574059520