A novel prediction model for different post-translational modific | 29175
Journal of Proteomics & Bioinformatics

Journal of Proteomics & Bioinformatics
Open Access

ISSN: 0974-276X

+44 1223 790975

A novel prediction model for different post-translational modifications: GEARS (genetic evolution of classifier by learning residues rules of sequences)

5th International Conference on Proteomics & Bioinformatics

September 01-03, 2015 Valencia, Spain

Zeeshan Iqbal1, 2, Jawaria Munir1, Wajahat M Qazi3 and Nasir Uddin1

1Institute of Molecular Sciences and Bioinformatics, Pakistan 2GC University, Pakistan 3COSMATS Institute of Information Technology, Pakistan

Scientific Tracks Abstracts: J Proteomics Bioinform

Abstract :

Functional switching of proteins is an important challenge in proteomics and genomics. Information about structural dynamics of proteins regulating different functional modulations is helpful in predicting the multi-functionality of the proteins. The function of the protein depends on all levels of conformation (primary-3D) and post-translational modifications. The primary sequence and 3D structure information of the proteins has been utilized to evolve different prediction models by using various machine learning methods. The evolution of the prediction model by using information about the significant residues in surrounding of the modified residues as well as biophysical and biochemical properties of the amino acids are not considered yet. MAPRes (Mining Association Patterns among preferred amino acid residues in the vicinity of amino acids targeted for post-translational modifications) is a useful computational tool to find significant residues in surrounding of modified amino acids and for the development of the association patterns of these significant residues. The information about the primary sequence of the proteins and the association rules for the significant residues are considered to evolve the new dataset. These evolved datasets can play an important role for the development of a reliable prediction model. The current study proposes a classifier rule learning model named as GEARS (Genetic Evolution of CLAssifier by Learning Residues Rules of Sequences). This classifier considered artificial neural network (ANN), hidden Markov model (HMM) and MAPRes to train modified protein dataset. The capacity of the predication of the GEARS model will show improved results by the combination of different evolution models.

Biography :

Zeeshan Iqbal has completed his MPhil from GC University, Lahore. He is the senior research associate at Institute of Molecular Sciences and Bioinformatics, Lahore. He has published 14 papers in reputed journals and serving as an Editorial Board Member of repute.