Improved particle swarm optimization and gravitational search algorithm for parameter estimation in aspartate pathways

One of the main issues in biological system is to characterize the dynamic behaviour of the complex biological processes. Usually, metabolic pathway models are used to describe the complex processes that involve many parameters. It is important to have an accurate and complete set of parameters that...

Full description

Saved in:

Bibliographic Details
Main Author:	Ismail, Ahmad Muhaimin
Format:	Thesis
Language:	English
Published:	2017
Subjects:	QA75 Electronic computers Computer science
Online Access:	http://eprints.utm.my/id/eprint/78445/1/AhmadMuhaiminIsmailMFC2017.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-utm-ep.78445
record_format	uketd_dc
spelling	my-utm-ep.784452018-08-26T11:56:22Z Improved particle swarm optimization and gravitational search algorithm for parameter estimation in aspartate pathways 2017-06 Ismail, Ahmad Muhaimin QA75 Electronic computers. Computer science One of the main issues in biological system is to characterize the dynamic behaviour of the complex biological processes. Usually, metabolic pathway models are used to describe the complex processes that involve many parameters. It is important to have an accurate and complete set of parameters that describe the characteristics of a given model. Therefore, the parameter values are estimated by fitting the model with experimental data. However, the estimation on these parameters is typically difficult and even impossible in some cases. Furthermore, the experimental data are often incomplete and also suffer from experimental noise. These shortcomings make it challenging to identify the best-fit parameters that can represent the actual biological processes involved in biological systems. Previously, a computational approach namely optimization algorithms are used to estimate the measurement of the model parameters. Most of these algorithms previously often suffered bad estimation for the biological system models, which resulted in bad fitting (error) the model with the experimental data. This research proposes a parameter estimation algorithm that can reduce the fitting error between the models and the experimental data. The proposed algorithm is an Improved Particle Swarm Optimization and Gravitational Search Algorithm (IPSOGSA) to obtain the near-optimal kinetic parameter values from experimental data. The improvement in this algorithm is a local search, which aims to increase the chances to obtain the global solution. The outcome of this research is that IPSOGSA can outperform other comparison algorithms in terms of root mean squared error (RMSE) and predictive residual error sum of squares (PRESS) for the estimated results. IPSOGSA manages to score the smallest RMSE with 12.2125 and 0.0304 for Ile and HSP metabolite respectively. The predicted results are benefits for the estimation of optimal kinetic parameters to improve the production of desired metabolites. 2017-06 Thesis http://eprints.utm.my/id/eprint/78445/ http://eprints.utm.my/id/eprint/78445/1/AhmadMuhaiminIsmailMFC2017.pdf application/pdf en public http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:110854 masters Universiti Teknologi Malaysia, Faculty of Computing Faculty of Computing
institution	Universiti Teknologi Malaysia
collection	UTM Institutional Repository
language	English
topic	QA75 Electronic computers Computer science
spellingShingle	QA75 Electronic computers Computer science Ismail, Ahmad Muhaimin Improved particle swarm optimization and gravitational search algorithm for parameter estimation in aspartate pathways
description	One of the main issues in biological system is to characterize the dynamic behaviour of the complex biological processes. Usually, metabolic pathway models are used to describe the complex processes that involve many parameters. It is important to have an accurate and complete set of parameters that describe the characteristics of a given model. Therefore, the parameter values are estimated by fitting the model with experimental data. However, the estimation on these parameters is typically difficult and even impossible in some cases. Furthermore, the experimental data are often incomplete and also suffer from experimental noise. These shortcomings make it challenging to identify the best-fit parameters that can represent the actual biological processes involved in biological systems. Previously, a computational approach namely optimization algorithms are used to estimate the measurement of the model parameters. Most of these algorithms previously often suffered bad estimation for the biological system models, which resulted in bad fitting (error) the model with the experimental data. This research proposes a parameter estimation algorithm that can reduce the fitting error between the models and the experimental data. The proposed algorithm is an Improved Particle Swarm Optimization and Gravitational Search Algorithm (IPSOGSA) to obtain the near-optimal kinetic parameter values from experimental data. The improvement in this algorithm is a local search, which aims to increase the chances to obtain the global solution. The outcome of this research is that IPSOGSA can outperform other comparison algorithms in terms of root mean squared error (RMSE) and predictive residual error sum of squares (PRESS) for the estimated results. IPSOGSA manages to score the smallest RMSE with 12.2125 and 0.0304 for Ile and HSP metabolite respectively. The predicted results are benefits for the estimation of optimal kinetic parameters to improve the production of desired metabolites.
format	Thesis
qualification_level	Master's degree
author	Ismail, Ahmad Muhaimin
author_facet	Ismail, Ahmad Muhaimin
author_sort	Ismail, Ahmad Muhaimin
title	Improved particle swarm optimization and gravitational search algorithm for parameter estimation in aspartate pathways
title_short	Improved particle swarm optimization and gravitational search algorithm for parameter estimation in aspartate pathways
title_full	Improved particle swarm optimization and gravitational search algorithm for parameter estimation in aspartate pathways
title_fullStr	Improved particle swarm optimization and gravitational search algorithm for parameter estimation in aspartate pathways
title_full_unstemmed	Improved particle swarm optimization and gravitational search algorithm for parameter estimation in aspartate pathways
title_sort	improved particle swarm optimization and gravitational search algorithm for parameter estimation in aspartate pathways
granting_institution	Universiti Teknologi Malaysia, Faculty of Computing
granting_department	Faculty of Computing
publishDate	2017
url	http://eprints.utm.my/id/eprint/78445/1/AhmadMuhaiminIsmailMFC2017.pdf
_version_	1747817990575882240

Improved particle swarm optimization and gravitational search algorithm for parameter estimation in aspartate pathways

Similar Items