Skip to the content

Using mRNA secondary structure predictions improves recognition of known yeast functional uORFs

Selpi, Selpi, Bryant, CH and Kemp, GJL 2008, 'Using mRNA secondary structure predictions improves recognition of known yeast functional uORFs' , in: Proceedings of 2nd International Workshop on Machine Learning in Systems Biology , University of Liege, pp. 85-94.

[img]
Preview
PDF
Download (171kB) | Preview

Abstract

We are interested in using inductive logic programming ILP)to generate rules for recognising functional upstream open reading frames (uORFs) in the yeast Saccharomyces cerevisiae. This paper empirically investigates whether providing an ILP system with predicted mRNA secondary structure can increase the performance of the resulting rules. Two sets of experiments, with and without mRNA secondary structure predictions as part of the background knowledge, were run. For each set, stratified 10-fold cross-validation experiments were run 100 times, each time randomly permuting the order of the positive training examples, and the performance of the resulting hypotheses were measured. Our results demonstrate that the performance of an ILP system in recognising known functional uORFs in the yeast S.cerevisiae significantly increases when mRNA secondary structure predictions are added to the background knowledge and suggest that mRNA secondary structure can affect the ability of uORFs to regulate gene expression.

Item Type: Book Section
Editors: Wehenkel, L., Geurts, P., Moreau, Y. and d'Alche-Buc, F
Themes: Subjects / Themes > Q Science > QA Mathematics > QA075 Electronic computers. Computer science
Subjects / Themes > Q Science > QH Natural history > QH301 Biology
Subjects outside of the University Themes
Schools: Colleges and Schools > College of Science & Technology
Colleges and Schools > College of Science & Technology > School of Computing, Science and Engineering
Colleges and Schools > College of Science & Technology > School of Computing, Science and Engineering > Data Mining and Pattern Recognition Research Centre
Publisher: University of Liege
Refereed: Yes
Related URLs:
Depositing User: Dr Chris H. Bryant
Date Deposited: 16 Feb 2009 13:34
Last Modified: 20 Aug 2013 15:55
URI: http://usir.eprints.org/id/eprint/1752

Actions (login required)

Edit record (repository staff only) Edit record (repository staff only)

Downloads

Downloads per month over past year