BACK TO CONTENTS   |    PDF   |    PREVIOUS   |    NEXT

Title

Prediction of antisense oligonucleotides using structural and thermodynamic motifs

 

Authors

Abdul Rahiman Anusha1* & Vinod Chandra1, 2

 

Affiliation

1Department of Computational Biology and Bioinformatics, University of Kerala, Thiruvananthapuram - 695581, India; 2College of Engineering Trivandrum - 695016, Kerala, India.

 

Email

anushapraveenkhan@gmail.com; *Corresponding author

 

Article Type

Hypothesis

 

Date

Received September 24, 2012; Accepted October 27, 2012; Published November 23, 2012

Abstract

Specific gene expression regulation strategy using antisense oligonucleotides occupy significant space in recent clinical trials. The therapeutical potential of oligos lies in the identification and prediction of accurate oligonucleotides against specific target mRNA. In this work we present a computational method that is built on Artificial Neural Network (ANN) which could recognize and predict oligonucleotides effectively. In this study first we identified 11 major parameters associated with oligo:mRNA duplex linkage. A feed forward multilayer perceptron ANN classifier is trained with a set of experimentally proven feature vectors. The classifier gives an exact prediction of the input sequences under 2 classes oligo or non-oligo. On validation, our tool showed comparatively significant accuracy of 92.48% with 91.7% sensitivity and 92.09% specificity. This study was also able to reveal the relative impact of individual parameters we considered on antisense oligonucleotide predictions.

 

Citation

Anusha & Chandra, Bioinformation 8(23): 1162-1166 (2012)
 

Edited by

P Kangueane

 

ISSN

0973-2063

 

Publisher

Biomedical Informatics

 

License

This is an Open Access article which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly credited. This is distributed under the terms of the Creative Commons Attribution License.