Ensemble classifier for protein fold pattern recognition

• Published in: Bioinformatics Vol. 22; no. 14; pp. 1717 - 1722
• Main Authors: Shen, Hong-Bin, Chou, Kuo-Chen
• Format: Journal Article
• Language: English
• Published: Oxford Oxford University Press 15.07.2006; Oxford Publishing Limited (England)
• Subjects: Algorithms; Amino Acid Sequence; Artificial Intelligence; Biological and medical sciences; Computer Simulation; Fundamental and applied biological sciences. Psychology; General aspects; Mathematics in biology. Statistical analysis. Models. Metrology. Data processing in biology (general aspects); Models, Chemical; Models, Molecular; Molecular Sequence Data; Pattern Recognition, Automated - methods; Protein Conformation; Protein Folding; Proteins - chemistry; Proteins - ultrastructure; Sequence Analysis, Protein - methods; Learning; Fold; Original document; Nearest neighbour; Weighting; Prediction; Parameter; Classifier; Pattern recognition; Bioinformatics; Comparative study; Protein
• ISSN: 1367-4803; 1460-2059; 1367-4811
• DOI: 10.1093/bioinformatics/btl170

Motivation: Prediction of protein folding patterns is one level deeper than that of protein structural classes, and hence is much more complicated and difficult. To deal with such a challenging problem, the ensemble classifier was introduced. It was formed by a set of basic classifiers, with each trained in different parameter systems, such as predicted secondary structure, hydrophobicity, van der Waals volume, polarity, polarizability, as well as different dimensions of pseudo-amino acid composition, which were extracted from a training dataset. The operation engine for the constituent individual classifiers was OET-KNN (optimized evidence-theoretic k-nearest neighbors) rule. Their outcomes were combined through a weighted voting to give a final determination for classifying a query protein. The recognition was to find the true fold among the 27 possible patterns. Results: The overall success rate thus obtained was 62% for a testing dataset where most of the proteins have <25% sequence identity with the proteins used in training the classifier. Such a rate is 6–21% higher than the corresponding rates obtained by various existing NN (neural networks) and SVM (support vector machines) approaches, implying that the ensemble classifier is very promising and might become a useful vehicle in protein science, as well as proteomics and bioinformatics. Availability: The ensemble classifier, called PFP-Pred, is available as a web-server at for public usage. Contact:lifesci-sjtu@san.rr.com Supplementary information: Supplementary data are available on Bioinformatics online.