Recognition of exon/intron boundaries using dynamic ensembles

Computational Systems BioinformaticsPublished 16 August 2004

Xuanfu Wu, Zhengxin Chen

DOI10.1109/csb.2004.143

Citations7

Abstract

Many studies have been carried out in recognition of exon/intron boundaries. For example, PROCRUSTES uses similarity-based approach to gene recognition. Other examples include GRAIL (Gene Recognition and Assembly Internet Link) http://compbio.ornl.gov/Grail-1.3/help/(1996) and Glimmer (Gene Locator and Interpolated Markov Modeler). Since the problem of recognition of exon/intron boundaries can be cast as a classification task, ensemble learning can be applied. An ensemble consists of a set of organized individual trained classifiers whose individual decisions are combined in a certain way for classification purpose. However, existing studies typically take static approaches which hampered flexibility for improved accuracy. To overcome this problem we have proposed the concept of dynamic ensemble and developed a new algorithm, BAGA, which combines bagging and genetic algorithm techniques.

Keywords

Biochemistry, Genetics and Molecular Biology

Lecture notes in computer scienceEnsemble Methods in Machine Learning

7,862 Citations2000Thomas G. Dietterich

Journal of Artificial Intelligence ResearchPopular Ensemble Methods: An Empirical Study

2,972 Citations1999David W. Opitz, Richard Maclin

This work suggests that most of the gain in an ensemble's performance comes in the first few classifiers combined; however, relatively large gains can be seen up to 25 classifiers when Boosting decision trees.

View PDF

Nucleic Acids ResearchImproved microbial gene identification with GLIMMER

2,520 Citations1999Art L. Delcher

Significant technical improvements to GLIMMER are reported that improve its accuracy still further, and a comprehensive evaluation demonstrates that the accuracy of the system is likely to be higher than previously recognized.

View PDF

IEEE Transactions on Evolutionary ComputationA novel evolutionary data mining algorithm with applications to churn prediction

351 Citations2003Wai-Ho Au, Keith C. C. Chan +1 more

A new data mining algorithm, called data mining by evolutionary learning (DMEL), to handle classification problems of which the accuracy of each predictions made has to be estimated and is able to predict churn accurately under different churn rates when applied to real telecom subscriber data.

Proceedings of the National Academy of SciencesGene recognition via spliced sequence alignment.

310 Citations1996Mikhail S. Gelfand, Andrey A. Mironov +1 more

A spliced alignment algorithm and software tool that explores all possible exon assemblies in polynomial time and finds the multiexon structure with the best fit to a related protein.

Nucleic Acids ResearchExInt: an Exon/Intron database

70 Citations2000Meena Kishore Sakharkar

The Exon/Intron (ExInt) database incorporates information on the exon/intron structure of eukaryotic genes and can be searched by keywords, locus name, NID, accession number or length of the protein.

View PDF

Series in machine perception and artificial intelligenceDESIGN OF MULTIPLE CLASSIFIER SYSTEMS

62 Citations2002Fabio Roli, Giorgio Giacinto