Predicting Molecular Functions in Plants using Wavelet-based Motifs

G. Arango-Argoty, A. F. Giraldo-Forero, J. A. Jaramillo-Garzón, L. Duque-Muñoz, G. Castellanos-Dominguez

2013

Abstract

Predicting molecular functions of proteins is a fundamental challenge in bioinformatics. Commonly used algorithms are based on sequence alignments and fail when the training sequences have low percentages of identity with query proteins, as it is the case for non-model organisms such as land plants. On the other hand, machine learning-based algorithms offer a good alternative for prediction, but most of them ignore that molecular functions are conditioned by functional domains instead of global features of the whole sequence. This work presents a novel application of theWavelet Transform in order to detect discriminant sub-sequences (motifs) and use them as input for a pattern recognition classifier. The results show that the continuous wavelet transform is a suitable tool for the identification and characterization of motifs. Also, the proposed classification methodology shows good prediction capabilities for datasets with low percentage of identity among sequences, outperforming BLAST2GO on about 11,5% and PEPSTATS-SVMon 16,4%. Plus, it offers major interpretability of the obtained results.

Paper Citation

in Harvard Style

Arango-Argoty G., F. Giraldo-Forero A., A. Jaramillo-Garzón J., Duque-Muñoz L. and Castellanos-Dominguez G. (2013). Predicting Molecular Functions in Plants using Wavelet-based Motifs . In Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms - Volume 1: BIOINFORMATICS, (BIOSTEC 2013) ISBN 978-989-8565-35-8, pages 140-145. DOI: 10.5220/0004234201400145

in Bibtex Style

@conference{bioinformatics13,
author={G. Arango-Argoty and A. F. Giraldo-Forero and J. A. Jaramillo-Garzón and L. Duque-Muñoz and G. Castellanos-Dominguez},
title={Predicting Molecular Functions in Plants using Wavelet-based Motifs},
booktitle={Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms - Volume 1: BIOINFORMATICS, (BIOSTEC 2013)},
year={2013},
pages={140-145},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004234201400145},
isbn={978-989-8565-35-8},
}

in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Bioinformatics Models, Methods and Algorithms - Volume 1: BIOINFORMATICS, (BIOSTEC 2013)
TI - Predicting Molecular Functions in Plants using Wavelet-based Motifs
SN - 978-989-8565-35-8
AU - Arango-Argoty G.
AU - F. Giraldo-Forero A.
AU - A. Jaramillo-Garzón J.
AU - Duque-Muñoz L.
AU - Castellanos-Dominguez G.
PY - 2013
SP - 140
EP - 145
DO - 10.5220/0004234201400145