Predicting dynamic behavior of a biological system using ANNs

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, artificial neural networks (ANNs) are applied to predict protein concentrations of a biological system. The input data are generated from a nonlinear mathematical model of the protein concentration. The protein concentrations from CDC6 data with actual kinetic parameter are taken as the target output. The data are then trained using multilayer perceptron (MLP) neural network with a 6-6-6 configuration. The allocation of the data will be distributed into 3 categories that are 80% as training data, 10% as validation data, and 10% as test data. The learning rules used in this work to determine the best model are gradient descent, conjugate gradient, scaled conjugate gradient. It is found that the MLP with scaled conjugate gradient learning rule gives the best prediction rate.

Original languageEnglish
Title of host publicationAIP Conference Proceedings
Pages47-54
Number of pages8
Volume971
DOIs
Publication statusPublished - 2007
EventInternational Conference on Mathematical Biology, ICMB 2007 - Putrajaya
Duration: 4 Sep 20076 Sep 2007

Other

OtherInternational Conference on Mathematical Biology, ICMB 2007
CityPutrajaya
Period4/9/076/9/07

Fingerprint

gradients
self organizing systems
proteins
learning
descent
mathematical models
education
output
kinetics
configurations
predictions

Keywords

  • Artificial neural networks
  • Bioinformatics
  • Data mining
  • Machine learning

ASJC Scopus subject areas

  • Physics and Astronomy(all)

Cite this

Predicting dynamic behavior of a biological system using ANNs. / Osman, Mohd Haniff; Ibrahim, Ratnawati; Hashim, Ishak; Liong, Choong Yeun; Abu Bakar, Azuraliza; Mohamed Hussein, Zeti Azura.

AIP Conference Proceedings. Vol. 971 2007. p. 47-54.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Osman, MH, Ibrahim, R, Hashim, I, Liong, CY, Abu Bakar, A & Mohamed Hussein, ZA 2007, Predicting dynamic behavior of a biological system using ANNs. in AIP Conference Proceedings. vol. 971, pp. 47-54, International Conference on Mathematical Biology, ICMB 2007, Putrajaya, 4/9/07. https://doi.org/10.1063/1.2883866
@inproceedings{63f1dfbf7b4844d58a746c176c24a407,
title = "Predicting dynamic behavior of a biological system using ANNs",
abstract = "In this paper, artificial neural networks (ANNs) are applied to predict protein concentrations of a biological system. The input data are generated from a nonlinear mathematical model of the protein concentration. The protein concentrations from CDC6 data with actual kinetic parameter are taken as the target output. The data are then trained using multilayer perceptron (MLP) neural network with a 6-6-6 configuration. The allocation of the data will be distributed into 3 categories that are 80{\%} as training data, 10{\%} as validation data, and 10{\%} as test data. The learning rules used in this work to determine the best model are gradient descent, conjugate gradient, scaled conjugate gradient. It is found that the MLP with scaled conjugate gradient learning rule gives the best prediction rate.",
keywords = "Artificial neural networks, Bioinformatics, Data mining, Machine learning",
author = "Osman, {Mohd Haniff} and Ratnawati Ibrahim and Ishak Hashim and Liong, {Choong Yeun} and {Abu Bakar}, Azuraliza and {Mohamed Hussein}, {Zeti Azura}",
year = "2007",
doi = "10.1063/1.2883866",
language = "English",
isbn = "9780735404892",
volume = "971",
pages = "47--54",
booktitle = "AIP Conference Proceedings",

}

TY - GEN

T1 - Predicting dynamic behavior of a biological system using ANNs

AU - Osman, Mohd Haniff

AU - Ibrahim, Ratnawati

AU - Hashim, Ishak

AU - Liong, Choong Yeun

AU - Abu Bakar, Azuraliza

AU - Mohamed Hussein, Zeti Azura

PY - 2007

Y1 - 2007

N2 - In this paper, artificial neural networks (ANNs) are applied to predict protein concentrations of a biological system. The input data are generated from a nonlinear mathematical model of the protein concentration. The protein concentrations from CDC6 data with actual kinetic parameter are taken as the target output. The data are then trained using multilayer perceptron (MLP) neural network with a 6-6-6 configuration. The allocation of the data will be distributed into 3 categories that are 80% as training data, 10% as validation data, and 10% as test data. The learning rules used in this work to determine the best model are gradient descent, conjugate gradient, scaled conjugate gradient. It is found that the MLP with scaled conjugate gradient learning rule gives the best prediction rate.

AB - In this paper, artificial neural networks (ANNs) are applied to predict protein concentrations of a biological system. The input data are generated from a nonlinear mathematical model of the protein concentration. The protein concentrations from CDC6 data with actual kinetic parameter are taken as the target output. The data are then trained using multilayer perceptron (MLP) neural network with a 6-6-6 configuration. The allocation of the data will be distributed into 3 categories that are 80% as training data, 10% as validation data, and 10% as test data. The learning rules used in this work to determine the best model are gradient descent, conjugate gradient, scaled conjugate gradient. It is found that the MLP with scaled conjugate gradient learning rule gives the best prediction rate.

KW - Artificial neural networks

KW - Bioinformatics

KW - Data mining

KW - Machine learning

UR - http://www.scopus.com/inward/record.url?scp=39049120279&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=39049120279&partnerID=8YFLogxK

U2 - 10.1063/1.2883866

DO - 10.1063/1.2883866

M3 - Conference contribution

AN - SCOPUS:39049120279

SN - 9780735404892

VL - 971

SP - 47

EP - 54

BT - AIP Conference Proceedings

ER -