Evolving Hidden Markov Models for Protein Secondary Structure Prediction
Evolving Hidden Markov Models for Protein Secondary Structure Prediction
New results are presented for the prediction of secondary structure information for protein sequences using Hidden Markov Models (HMMs) evolved using a Genetic Algorithm (GA). We achieved a Q3 measure of 75% using one of the most stringent data set ever used for protein secondary structure prediction. Our results beat the best hand-designed HMM currently available and are comparable to the best known techniques for this problem. A hybrid GA incorporating the Baum-Welch algorithm was used. The topology of the HMM was restricted to biologically meaningful building blocks. Mutation and crossover operators were designed to explore this space of topologies.
block HMM, protein secondary structure, genetic algorithm
0-7803-9364-3
33-40
Won, Kyoung Jae
3e4dfff9-c3c9-407d-8dfa-63be6f65485b
Hamelryck, Thomas
7caaa3c9-9744-4d42-a574-96e79e88373a
Prugel-Bennett, Adam
b107a151-1751-4d8b-b8db-2c395ac4e14e
Krogh, Anders
4a5cfccf-5403-45fb-96c5-61f60bef7d79
2005
Won, Kyoung Jae
3e4dfff9-c3c9-407d-8dfa-63be6f65485b
Hamelryck, Thomas
7caaa3c9-9744-4d42-a574-96e79e88373a
Prugel-Bennett, Adam
b107a151-1751-4d8b-b8db-2c395ac4e14e
Krogh, Anders
4a5cfccf-5403-45fb-96c5-61f60bef7d79
Won, Kyoung Jae, Hamelryck, Thomas, Prugel-Bennett, Adam and Krogh, Anders
(2005)
Evolving Hidden Markov Models for Protein Secondary Structure Prediction.
IEEE Congress on Evolutionary Computation, Edinburgh.
02 - 05 Sep 2005.
.
Record type:
Conference or Workshop Item
(Other)
Abstract
New results are presented for the prediction of secondary structure information for protein sequences using Hidden Markov Models (HMMs) evolved using a Genetic Algorithm (GA). We achieved a Q3 measure of 75% using one of the most stringent data set ever used for protein secondary structure prediction. Our results beat the best hand-designed HMM currently available and are comparable to the best known techniques for this problem. A hybrid GA incorporating the Baum-Welch algorithm was used. The topology of the HMM was restricted to biologically meaningful building blocks. Mutation and crossover operators were designed to explore this space of topologies.
More information
Published date: 2005
Additional Information:
Event Dates: September 2-5
Venue - Dates:
IEEE Congress on Evolutionary Computation, Edinburgh, 2005-09-02 - 2005-09-05
Keywords:
block HMM, protein secondary structure, genetic algorithm
Organisations:
Southampton Wireless Group
Identifiers
Local EPrints ID: 261195
URI: http://eprints.soton.ac.uk/id/eprint/261195
ISBN: 0-7803-9364-3
PURE UUID: 1c82f61d-8457-40f6-bae8-ca04386798df
Catalogue record
Date deposited: 06 Sep 2005
Last modified: 14 Mar 2024 06:49
Export record
Contributors
Author:
Kyoung Jae Won
Author:
Thomas Hamelryck
Author:
Adam Prugel-Bennett
Author:
Anders Krogh
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics