Modelling of Normal Boiling Points of Hydroxyl Compounds by Radial Basis Networks

Liangjie Jin; Peng Bai

doi:doi:10.11648/j.mc.20160402.12

| Peer-Reviewed

Modelling of Normal Boiling Points of Hydroxyl Compounds by Radial Basis Networks

Liangjie Jin, Peng Bai

Published in Modern Chemistry (Volume 4, Issue 2)

Received: 3 May 2016 Published: 4 May 2016

Views: Downloads:

Download PDF

Share This Article

Twitter
Linked In
Facebook

Abstract

Radial basis networks (RBN) were applied to link molecular descriptor and boiling points of 168 hydroxyl compounds. The total database was randomly divided into a training set(134), a validation set(17) and a testing set(17). Each compound in the lowest energy conformation was numerically characterized with E-dragon software. Then 8 molecular descriptors were selected to develop the RBN model. Simulated with the final optimum RBN model [8-35₍₆₄₎-1], the root mean square errors (RMSE) for the training, the validation and the testing set were 5.55, 4.28, and 5.33, and the correlation coefficients R=0.994(training), 0.994(validation), 0.993(testing). The final RBN model was compared with the multiple linear regression approach and showed more satisfactory results.

Published in	Modern Chemistry (Volume 4, Issue 2)
DOI	10.11648/j.mc.20160402.12
Page(s)	24-29
Creative Commons	This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright	Copyright © The Author(s), 2016. Published by Science Publishing Group

Keywords

Radial Basis Networks, Normal Boiling Point, Hydroxyl Compounds, QSPR Model

References

[1]	S. Gamba, G.S. Soave, L.A. Pellegrini, “Use of normal boiling point correlations for predicting critical parametersof paraffins for vapour–liquid equilibrium calculations with the SRK equation of state,” Fluid Phase Equil., 2009, vol. 276, pp. 133–141.
[2]	E. Panteli, E. Voutsas, K. Magoulas, et al., “Prediction of vapor pressures and enthalpies of vaporization of organic compounds from the normal boiling point temperature,” Fluid Phase Equil., 2006, vol. 248, pp.70-77.
[3]	J. Marrero, and R. Gani, “Group-contribution based estimation of pure component properties,” Fluid Phase Equil., 2001, vol. 183/184, pp. 183-208.
[4]	J. Guilherme, J. Maximo, J.A. Antonio, et al, “Boiling point of aqueous d-glucose and d-fructose solutions: Experimental determination and modeling with group-contribution method,” Fluid Phase Equil., 2010, vol. 299, pp. 32-41.
[5]	D. Sola, A. Ferri, M. Banchero, et al, “QSPR prediction of N-boiling point and critical properties of organic compounds and comparison with a group-contribution method,” Fluid Phase Equil., 2008, vol. 263, pp. 33–42.
[6]	I. Oprisiu, G. Marcou, D. Horvath, S., et al, “Publicly available models to predict normal boiling point of organic compounds,” Thermochim. Acta, 2013, vol. 553, pp. 60-67.
[7]	Y.M. Dai, Z.P. Zhu, Z. Cao, et. al, “Prediction of boiling points of organic compounds by QSPR tools,” J. Mol. Graph. Model., 2013, vol. 44, pp. 113-119.
[8]	D. Abooali, M.A. Sobati, “Novel method for prediction of normal boiling point and enthalpy of vaporization at normal boiling point of pure refrigerants: A QSPR approach,” Int. J. Refrig., 2014, vol. 40, pp. 282-293.
[9]	V. Zare-Shahabadi, M. Lotfizadeh, A.R.A. Gandomani, “Determination of boiling points of azeotropic mixtures using quantitative structure–property relationship (QSPR) strategy,” J. Mol. Liq., 2013, vol. 188, pp. 222-229
[10]	Q.F, Li, X.G. Chen, Z.D. Hu, “Quantitative structure-property relationship studies for estimating boiling points of alcohols using calculated molecular descriptors with radial basis function neural networks,” Chemometr. Intell. Lab., 2004, vol. 72, pp. 93-100.
[11]	F. Gharagheizi, S.A. Mirkhani, P. Ilani-Kashkouli, et al, “Determination of the normal boiling point of chemical compounds using a quantitative structure-property relationship strategy: Application to a very large dataset.” Fluid Phase Equil., 2013, vol. 354, pp. 250-258.
[12]	G.Q. Liu, L.X. Ma, S.G. Xiang, “Handbook of chemistry and chemical properties data”, 4rd ed, Beijing: Chemical Industry Press, 2013.
[13]	F. Gharagheizi, and M. Sattari. “Prediction of triple point temperature of pure components using their chemical structure,” Ind. Eng. Chem. Res., 2010, vol. 49, pp. 929-932.
[14]	VCCLAB, http://www.vcclab.org, 2005
[15]	I.V. Tetko, J. Gasteiger, J., R. Todeschini, R. et al. “Virtual computational chemistry laboratory - design and description,” J. Comput. Aid. Mol. Des., 2005, vol. 19, pp. 453-63.
[16]	R. Todeschini, and V. Consonni, “Molecular descriptors for chemoinformatics,” 2rd ed. Weinheim: Wiley-VCH, 2009.
[17]	N.S. Sapre, N. Pancholi, S. Gupta, “Computational modeling of substitution effect on HIV–1non-nucleoside reverse transcriptase inhibitors with Kier–Hall electrotopological state (E–state) indice,” Int. Electron. J. Mol. Des., 2008, vol. 7, pp. 55–67.
[18]	V. Consonni, R. Todeschini,M. Pavan, “Structure/Response correlations and similarity/diversity analysis by GETAWAY descriptors. 1. Theory of the novel 3D molecular descriptors,” J. Chem. Inf. Comput. Sci., 2002, vol. 42, pp. 682-692.
[19]	V. Consonni, R. Todeschini, M. Pavan, et al, “Structure/Response correlations and similarity/diversity analysis by GETAWAY descriptors. 2. Application of the novel 3D molecular descriptors to QSAR/QSPR studies,” J. Chem. Inf. Comput. Sci., 2002, vol. 42, pp. 693-705.
[20]	R. Todeschini, P. Gramatica, E. Marengor, et al, “Weighted holistic invariant molecular descriptors. Part 2. Theory development and applications on modeling physicochemical properties of polyaromatic hydrocarbons.” Intell. Lab. Syst, 1995, vol. 27, pp. 221-229.
[21]	O. Devinyak, D. Havrylyuk, R. Lesyk, “3D-MoRSE descriptors explained,” J. Mol. Graph. Model., 2014, vol. 54, pp. 194–203.

Cite This Article

Plain Text BibTeX RIS

APA Style

Liangjie Jin, Peng Bai. (2016). Modelling of Normal Boiling Points of Hydroxyl Compounds by Radial Basis Networks. Modern Chemistry, 4(2), 24-29. https://doi.org/10.11648/j.mc.20160402.12

Copy | Download

ACS Style

Liangjie Jin; Peng Bai. Modelling of Normal Boiling Points of Hydroxyl Compounds by Radial Basis Networks. Mod. Chem. 2016, 4(2), 24-29. doi: 10.11648/j.mc.20160402.12

Copy | Download

AMA Style

Liangjie Jin, Peng Bai. Modelling of Normal Boiling Points of Hydroxyl Compounds by Radial Basis Networks. Mod Chem. 2016;4(2):24-29. doi: 10.11648/j.mc.20160402.12

Copy | Download

@article{10.11648/j.mc.20160402.12,
  author = {Liangjie Jin and Peng Bai},
  title = {Modelling of Normal Boiling Points of Hydroxyl Compounds by Radial Basis Networks},
  journal = {Modern Chemistry},
  volume = {4},
  number = {2},
  pages = {24-29},
  doi = {10.11648/j.mc.20160402.12},
  url = {https://doi.org/10.11648/j.mc.20160402.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.mc.20160402.12},
  abstract = {Radial basis networks (RBN) were applied to link molecular descriptor and boiling points of 168 hydroxyl compounds. The total database was randomly divided into a training set(134), a validation set(17) and a testing set(17). Each compound in the lowest energy conformation was numerically characterized with E-dragon software. Then 8 molecular descriptors were selected to develop the RBN model. Simulated with the final optimum RBN model [8-35(64)-1], the root mean square errors (RMSE) for the training, the validation and the testing set were 5.55, 4.28, and 5.33, and the correlation coefficients R=0.994(training), 0.994(validation), 0.993(testing). The final RBN model was compared with the multiple linear regression approach and showed more satisfactory results.},
 year = {2016}
}

Copy | Download

TY  - JOUR
T1  - Modelling of Normal Boiling Points of Hydroxyl Compounds by Radial Basis Networks
AU  - Liangjie Jin
AU  - Peng Bai
Y1  - 2016/05/04
PY  - 2016
N1  - https://doi.org/10.11648/j.mc.20160402.12
DO  - 10.11648/j.mc.20160402.12
T2  - Modern Chemistry
JF  - Modern Chemistry
JO  - Modern Chemistry
SP  - 24
EP  - 29
PB  - Science Publishing Group
SN  - 2329-180X
UR  - https://doi.org/10.11648/j.mc.20160402.12
AB  - Radial basis networks (RBN) were applied to link molecular descriptor and boiling points of 168 hydroxyl compounds. The total database was randomly divided into a training set(134), a validation set(17) and a testing set(17). Each compound in the lowest energy conformation was numerically characterized with E-dragon software. Then 8 molecular descriptors were selected to develop the RBN model. Simulated with the final optimum RBN model [8-35(64)-1], the root mean square errors (RMSE) for the training, the validation and the testing set were 5.55, 4.28, and 5.33, and the correlation coefficients R=0.994(training), 0.994(validation), 0.993(testing). The final RBN model was compared with the multiple linear regression approach and showed more satisfactory results.
VL  - 4
IS  - 2
ER  -

Copy | Download

Author Information

Liangjie Jin

School of Chemical Engineering and Technology, Tianjin University, Tianjin, PR China
Peng Bai

School of Chemical Engineering and Technology, Tianjin University, Tianjin, PR China

Download PDF

Sections

Plain Text BibTeX RIS

APA Style

Liangjie Jin, Peng Bai. (2016). Modelling of Normal Boiling Points of Hydroxyl Compounds by Radial Basis Networks. Modern Chemistry, 4(2), 24-29. https://doi.org/10.11648/j.mc.20160402.12

Copy | Download

ACS Style

Liangjie Jin; Peng Bai. Modelling of Normal Boiling Points of Hydroxyl Compounds by Radial Basis Networks. Mod. Chem. 2016, 4(2), 24-29. doi: 10.11648/j.mc.20160402.12

Copy | Download

AMA Style

Liangjie Jin, Peng Bai. Modelling of Normal Boiling Points of Hydroxyl Compounds by Radial Basis Networks. Mod Chem. 2016;4(2):24-29. doi: 10.11648/j.mc.20160402.12

Copy | Download

@article{10.11648/j.mc.20160402.12,
  author = {Liangjie Jin and Peng Bai},
  title = {Modelling of Normal Boiling Points of Hydroxyl Compounds by Radial Basis Networks},
  journal = {Modern Chemistry},
  volume = {4},
  number = {2},
  pages = {24-29},
  doi = {10.11648/j.mc.20160402.12},
  url = {https://doi.org/10.11648/j.mc.20160402.12},
  eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.mc.20160402.12},
  abstract = {Radial basis networks (RBN) were applied to link molecular descriptor and boiling points of 168 hydroxyl compounds. The total database was randomly divided into a training set(134), a validation set(17) and a testing set(17). Each compound in the lowest energy conformation was numerically characterized with E-dragon software. Then 8 molecular descriptors were selected to develop the RBN model. Simulated with the final optimum RBN model [8-35(64)-1], the root mean square errors (RMSE) for the training, the validation and the testing set were 5.55, 4.28, and 5.33, and the correlation coefficients R=0.994(training), 0.994(validation), 0.993(testing). The final RBN model was compared with the multiple linear regression approach and showed more satisfactory results.},
 year = {2016}
}

Copy | Download

TY  - JOUR
T1  - Modelling of Normal Boiling Points of Hydroxyl Compounds by Radial Basis Networks
AU  - Liangjie Jin
AU  - Peng Bai
Y1  - 2016/05/04
PY  - 2016
N1  - https://doi.org/10.11648/j.mc.20160402.12
DO  - 10.11648/j.mc.20160402.12
T2  - Modern Chemistry
JF  - Modern Chemistry
JO  - Modern Chemistry
SP  - 24
EP  - 29
PB  - Science Publishing Group
SN  - 2329-180X
UR  - https://doi.org/10.11648/j.mc.20160402.12
AB  - Radial basis networks (RBN) were applied to link molecular descriptor and boiling points of 168 hydroxyl compounds. The total database was randomly divided into a training set(134), a validation set(17) and a testing set(17). Each compound in the lowest energy conformation was numerically characterized with E-dragon software. Then 8 molecular descriptors were selected to develop the RBN model. Simulated with the final optimum RBN model [8-35(64)-1], the root mean square errors (RMSE) for the training, the validation and the testing set were 5.55, 4.28, and 5.33, and the correlation coefficients R=0.994(training), 0.994(validation), 0.993(testing). The final RBN model was compared with the multiple linear regression approach and showed more satisfactory results.
VL  - 4
IS  - 2
ER  -

Copy | Download