Artificial neural network modeling of pH dependent structural descriptor-mobility relationship for capillary zone electrophoresis of tripeptides

M. Olajos, T. Chován, S. Mittermayr, T. Kenesei, P. Hajos, I. Molnár, F. Darvas, A. Guttman

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

The aim of this work was to study the structural descriptor-mobility relationship of representative tripeptides in capillary zone electrophoresis (CZE) with the change of such separation parameters as pH, applied voltage and separation length in respect to their influence on electrophoretic migration properties. At the present stage of the work, the ionic charge was considered as structural descriptor. A multivariable linear regression (MLR) model and a back-propagation artificial neural network (BP-ANN) were applied to predict the electrophoretic mobilities of the model tripeptides with non-polar, polar, positively charged, negatively charged and aromatic R group characteristics. Here we present a comprehensive analysis on electrophoretic mobilities measured at pHs 2.5, 4.5, 7.5 and 9.5 at two different capillary lengths of 10 cm and 30 cm, as well as four applied electric field strengths ranging from 100 to 400 V/cm to teach and evaluate our mobility predicting models. The anticipated mobilities predicted by MLR and BP-ANN were compared to each other and to the experimental data, respectively. The BP-ANN model resulted in considerable higher precision in predictability that of the MLR method.

Original languageEnglish
Pages (from-to)2348-2362
Number of pages15
JournalJournal of Liquid Chromatography and Related Technologies
Volume31
Issue number15
DOIs
Publication statusPublished - Sep 2008

Fingerprint

Capillary Electrophoresis
Electrophoresis
Linear Models
Backpropagation
Linear regression
Neural networks
Electrophoretic mobility
Neural Networks (Computer)
Electric fields
Electric potential

Keywords

  • Back-propagation artificial neural network
  • Capillary zone electrophoresis
  • Multivariable linear regression
  • Peptide mobility modeling

ASJC Scopus subject areas

  • Analytical Chemistry
  • Clinical Biochemistry

Cite this

Artificial neural network modeling of pH dependent structural descriptor-mobility relationship for capillary zone electrophoresis of tripeptides. / Olajos, M.; Chován, T.; Mittermayr, S.; Kenesei, T.; Hajos, P.; Molnár, I.; Darvas, F.; Guttman, A.

In: Journal of Liquid Chromatography and Related Technologies, Vol. 31, No. 15, 09.2008, p. 2348-2362.

Research output: Contribution to journalArticle

@article{585f234a05dc44de974733c0f9a00852,
title = "Artificial neural network modeling of pH dependent structural descriptor-mobility relationship for capillary zone electrophoresis of tripeptides",
abstract = "The aim of this work was to study the structural descriptor-mobility relationship of representative tripeptides in capillary zone electrophoresis (CZE) with the change of such separation parameters as pH, applied voltage and separation length in respect to their influence on electrophoretic migration properties. At the present stage of the work, the ionic charge was considered as structural descriptor. A multivariable linear regression (MLR) model and a back-propagation artificial neural network (BP-ANN) were applied to predict the electrophoretic mobilities of the model tripeptides with non-polar, polar, positively charged, negatively charged and aromatic R group characteristics. Here we present a comprehensive analysis on electrophoretic mobilities measured at pHs 2.5, 4.5, 7.5 and 9.5 at two different capillary lengths of 10 cm and 30 cm, as well as four applied electric field strengths ranging from 100 to 400 V/cm to teach and evaluate our mobility predicting models. The anticipated mobilities predicted by MLR and BP-ANN were compared to each other and to the experimental data, respectively. The BP-ANN model resulted in considerable higher precision in predictability that of the MLR method.",
keywords = "Back-propagation artificial neural network, Capillary zone electrophoresis, Multivariable linear regression, Peptide mobility modeling",
author = "M. Olajos and T. Chov{\'a}n and S. Mittermayr and T. Kenesei and P. Hajos and I. Moln{\'a}r and F. Darvas and A. Guttman",
year = "2008",
month = "9",
doi = "10.1080/10826070802281935",
language = "English",
volume = "31",
pages = "2348--2362",
journal = "Journal of Liquid Chromatography and Related Technologies",
issn = "1082-6076",
publisher = "Taylor and Francis Ltd.",
number = "15",

}

TY - JOUR

T1 - Artificial neural network modeling of pH dependent structural descriptor-mobility relationship for capillary zone electrophoresis of tripeptides

AU - Olajos, M.

AU - Chován, T.

AU - Mittermayr, S.

AU - Kenesei, T.

AU - Hajos, P.

AU - Molnár, I.

AU - Darvas, F.

AU - Guttman, A.

PY - 2008/9

Y1 - 2008/9

N2 - The aim of this work was to study the structural descriptor-mobility relationship of representative tripeptides in capillary zone electrophoresis (CZE) with the change of such separation parameters as pH, applied voltage and separation length in respect to their influence on electrophoretic migration properties. At the present stage of the work, the ionic charge was considered as structural descriptor. A multivariable linear regression (MLR) model and a back-propagation artificial neural network (BP-ANN) were applied to predict the electrophoretic mobilities of the model tripeptides with non-polar, polar, positively charged, negatively charged and aromatic R group characteristics. Here we present a comprehensive analysis on electrophoretic mobilities measured at pHs 2.5, 4.5, 7.5 and 9.5 at two different capillary lengths of 10 cm and 30 cm, as well as four applied electric field strengths ranging from 100 to 400 V/cm to teach and evaluate our mobility predicting models. The anticipated mobilities predicted by MLR and BP-ANN were compared to each other and to the experimental data, respectively. The BP-ANN model resulted in considerable higher precision in predictability that of the MLR method.

AB - The aim of this work was to study the structural descriptor-mobility relationship of representative tripeptides in capillary zone electrophoresis (CZE) with the change of such separation parameters as pH, applied voltage and separation length in respect to their influence on electrophoretic migration properties. At the present stage of the work, the ionic charge was considered as structural descriptor. A multivariable linear regression (MLR) model and a back-propagation artificial neural network (BP-ANN) were applied to predict the electrophoretic mobilities of the model tripeptides with non-polar, polar, positively charged, negatively charged and aromatic R group characteristics. Here we present a comprehensive analysis on electrophoretic mobilities measured at pHs 2.5, 4.5, 7.5 and 9.5 at two different capillary lengths of 10 cm and 30 cm, as well as four applied electric field strengths ranging from 100 to 400 V/cm to teach and evaluate our mobility predicting models. The anticipated mobilities predicted by MLR and BP-ANN were compared to each other and to the experimental data, respectively. The BP-ANN model resulted in considerable higher precision in predictability that of the MLR method.

KW - Back-propagation artificial neural network

KW - Capillary zone electrophoresis

KW - Multivariable linear regression

KW - Peptide mobility modeling

UR - http://www.scopus.com/inward/record.url?scp=49449099400&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=49449099400&partnerID=8YFLogxK

U2 - 10.1080/10826070802281935

DO - 10.1080/10826070802281935

M3 - Article

VL - 31

SP - 2348

EP - 2362

JO - Journal of Liquid Chromatography and Related Technologies

JF - Journal of Liquid Chromatography and Related Technologies

SN - 1082-6076

IS - 15

ER -