Soft Computing Methods for Prediction of Replication Origins in Caudoviruses

Author

Cruz-Cano, Raul ; Aizenberg, Igor

Author_Institution

Dept. of Comput. Sci., Texas A&M Univ.-Texarkana, Texarkana, TX

fYear

2008

Firstpage

156

Lastpage

162

Abstract

Prediction methods that can be reduced to learning of partially defined multiple-valued functions have become very popular. In this paper, we consider a prediction problem related to DNA replication, which is essential for the reproduction of many viruses. Procedures to find replication origins are important for controlling such viruses. This paper focuses on the order of caudovirales and proposes a new prediction approach based on least-squares support vector machine (LS-SVM) and a multilayer feedforward neural network with multi-valued neurons (MLMVN). The results suggest that this method will be a useful tool for the prediction of viral replication origins.

Keywords

DNA; biology computing; feedforward neural nets; least mean squares methods; molecular biophysics; neural nets; support vector machines; DNA replication; caudoviruses; least-squares support vector machine; multi-valued neurons; multilayer feedforward neural network; multiple-valued functions; soft computing methods; Artificial neural networks; Bioinformatics; DNA; Genomics; Multi-layer neural network; Prediction methods; Sequences; Support vector machine classification; Support vector machines; Viruses (medical); Caudoviruses; Replication Origins; least-squares support vector machine; multilayer feedforward neural network with multi-valued neurons;

fLanguage

English

Publisher

ieee

Conference_Titel

Multiple Valued Logic, 2008. ISMVL 2008. 38th International Symposium on

Conference_Location

Dallas, TX

ISSN

0195-623X

Print_ISBN

978-0-7695-3155-7

Type

conf

DOI

10.1109/ISMVL.2008.29

Filename

4539419