The application of fusion of heterogeneous meta classifiers to enhance protein fold prediction accuracy

Authors:
Abdollah Dehzangi;Roozbeh Hojabri Foladizadeh;Mohammad Aflaki;Sasan Karamizadeh
Affiliations:
Faculty of Information Technology, Multi Media University, Cyberjaya, Selangor, Malaysia;Faculty of Information Technology, Multi Media University, Cyberjaya, Selangor, Malaysia;Faculty of Engineering, Multi Media University, Cyberjaya, Selangor, Malaysia;Faculty of Information Technology, Multi Media University, Cyberjaya, Selangor, Malaysia
Venue:
ACIIDS'11 Proceedings of the Third international conference on Intelligent information and database systems - Volume Part I
Year:
2011

Citing 20
Cited 0

C4.5: programs for machine learning

C4.5: programs for machine learning
Bagging predictors

Machine Learning
Random Forests

Machine Learning
An Empirical Comparison of Voting Classification Algorithms: Bagging, Boosting, and Variants

Machine Learning
Protein Folding Class Predictor for SCOP: Approach Based on Global Descriptors

Proceedings of the 5th International Conference on Intelligent Systems for Molecular Biology
Ensemble Methods in Machine Learning

MCS '00 Proceedings of the First International Workshop on Multiple Classifier Systems
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Rotation Forest: A New Classifier Ensemble Method

IEEE Transactions on Pattern Analysis and Machine Intelligence
Protein Fold Recognition using a Structural Hidden Markov Model

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
Ensemble classifier for protein fold pattern recognition

Bioinformatics
Support Vector Machine-based classification of protein folds using the structural properties of amino acid residues and amino acid residue pairs

Bioinformatics
Probabilistic multi-class multi-kernel learning

Bioinformatics
Boosting Methods for Protein Fold Recognition: An Empirical Comparison

BIBM '08 Proceedings of the 2008 IEEE International Conference on Bioinformatics and Biomedicine
Improving the protein fold recognition accuracy of a reduced state-space hidden Markov model

Computers in Biology and Medicine
The WEKA data mining software: an update

ACM SIGKDD Explorations Newsletter
Protein Fold Pattern Recognition Using Bayesian Ensemble of RBF Neural Networks

SOCPAR '09 Proceedings of the 2009 International Conference of Soft Computing and Pattern Recognition
Protein fold recognition with adaptive local hyperplane algorithm

CIBCB'09 Proceedings of the 6th Annual IEEE conference on Computational Intelligence in Bioinformatics and Computational Biology
Letters: Ensemble of classifiers for protein fold recognition

Neurocomputing
An experimental study on rotation forest ensembles

MCS'07 Proceedings of the 7th international conference on Multiple classifier systems
Using rotation forest for protein fold prediction problem: an empirical study

EvoBIO'10 Proceedings of the 8th European conference on Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Protein fold prediction problem is considered as one of the most challenging tasks for molecular biology and one of the biggest unsolved problems for science. Recently, varieties of classification approaches have been proposed to solve this problem. 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. Employed classifiers combined using five different algebraic combiners (combinational policies) namely: Majority voting, Maximum of Probability, Minimum of Probability, Product of Probability, and Average of probability. Our experimental results show that our proposed approach enhances the protein fold prediction accuracy using Ding and Dubchak's dataset and Dubchak et al.'s feature set better than the previous works found in the literature.