Abstract
In the present work, a quantitative structure–property relationship (QSPR) treatment of temperature of five percent of decomposition (T 5) of a number of totally 30 optically active polymers was performed by means of a genetic algorithm-based partial least squares (GA–PLS) and artificial neural network (ANN). Suitable set of molecular descriptors were calculated by dragon package and the important descriptors were selected by GA–PLS methods. These descriptors were served as inputs to generate ANN. After optimization and training of the networks, they were used for the calculation of T 5 for the validation set. By comparing of the results obtained from PLS and ANN models, it can be seen that statistical parameters (Fisher ratio, correlation coefficient, and standard error) of the ANN model are better than PLS one, which indicates that nonlinear model can simulate the relationship between the structural descriptors and T 5 of the investigated macromolecules more accurately.
Similar content being viewed by others
References
Gabbott P (2008) Principles and applications of thermal analysis. Blackwell Publishing Ltd., Oxford, pp 87–88
Menczel JD, Prime BR (2009) Thermal analysis of polymers: fundamentals and applications. Wiley, New York, pp 241–314
Wunderlich B (2005) Thermal analysis of polymeric materials. Springer, Berlin, pp 279–448
Ahn C, Ohk CW, Kim JH, Zin WC (2009) Glass transition temperature of polymer nanocomposites: prediction from the continuous-multilayer model. J Polym Sci, Part B: Polym Phys 47:2281–2287
Chen X, Sztandera L, Cartwright HM (2008) A neural network approach to prediction of glass transition temperature of polymers. Int J Intell Syst 23:22–32
Bertinetto C, Duce C, Micheli A, Solaro R, Starita A, Tine MR (2007) Prediction of the glass transition temperature of (meth)acrylic polymers containing phenyl groups by recursive neural network. Polymer 48:7121–7129
Funar-Timofei S, KuruncziL Iliescu S (2005) Structure–property study of some phosphorus containing polymers by computational methods. Polym Bull 54:443–449
Schut J, Bolikal D, Khan IJ, Pesnell A, Rege A, Rojas R, Sheihet L, Murthy NS, Kohn J (2007) Glass transition temperature prediction of polymers through the mass-per-flexible-bond principle. Polymer 48:6115–6124
Afantitis A, Melagraki G, Makridima K, Alexandridis A, Sarimveis H, Iglessi-Markopoulou O (2005) Prediction of high weight polymers glass transition temperature using RBF neural networks. J Mol Struct THEOCHEM 716:193–198
Yu X, Xie Z, Yi B, Wang X, Liu F (2007) Prediction of the thermal decomposition property of polymers using quantum chemical descriptors. Eur Polym J 43:818–823
Katrizky AR, Rachwal P, Law KW, Karelson M, Lobanov VS (1996) Prediction of polymer glass transition temperatures using a general quantitative structure–property relationship treatment. J Chem Inf Comput Sci 36:879–884
Cao C, Lin Y (2003) Correlation between the glass transition temperatures and repeating unit structure for high molecular weight polymers. J Chem Inf Model 43:643–650
Ajloo D, Sharifian A, Behniafar H (2008) Prediction of thermal decomposition temperature of polymers using QSPR methods. Bull Korean Chem Soc 29:2009–2016
Cameilio P, Lazzeri V, Waegell B (1995) QSPR in polymers: a straightforward new approach to calculate the glass transition temperature. Polym Preprints: Am Chem Soc Div Polym Chem 36:661–662
Mallakpour S, Hatami M, Golmohammadi H (2010) Prediction of inherent viscosity for polymers containing natural amino acids from the theoretical derived molecular descriptors. Polymer 51:3568–3574
Golmohammadi H, Fatemi MH (2005) Artificial neural network prediction of retention factors of some benzene derivatives and heterocyclic compounds in micellar electrokinetic chromatography. Electrophoresis 26:3438–3444
Baher E, Fatemi MH, Konoz E, Golmohammadi H (2007) Prediction of retention factors in micellar electrokinetic chromatography from theoretically derived molecular descriptors. Microchim Acta 158:117–122
Konoz E, Golmohammadi H (2008) Prediction of air-to-blood partition coefficients of volatile organic compounds using genetic algorithm and artificial neural network. Anal Chim Acta 619:157–164
Golmohammadi H (2009) Prediction of octanol–water partition coefficients of organic compounds by multiple linear regression, partial least squares, and artificial neural network. J Comput Chem 30:2455–2465
Golmohammadi H, Konoz E, Dashtbozorgi Z (2009) Prediction of gas-to-olive oil partition coefficients of ioganic compounds using an artificial neural network. Anal Sci 25:1137–1142
Mallakpour S, Hajipour A, Khoee S (2002) Rapid synthesis of optically active poly(amide–imide)s by direct polycondensation of aromatic dicarboxylic acid with aromatic diamines. Eur Polym J 38:2011–2016
Mallakpour SE, Moghaddam E (2006) Preparation of new poly(ester–imide)s from N,N′-(4,4′-hexafluoroisopropylidendiphthaloyl)-bis-l-isoleucine and aromatic diols with TsCl/Py/DMF as a condensing agent. Iran Polym J 15:547–554
Mallakpour SE, Hajipour A, Khoee S (2000) Microwave-assisted polycondensation of 4,4′-(hexafluoroisopropylidene)-N,N′-bis(phthaloyl-l-leucine) diacid chloride with aromatic diols. J Appl Polym Sci 77:3003–3009
Mallakpour SE, Hajipour A, Khoee S (1999) Synthesis and characterization of novel optically active poly(amide–imide)s. Polym Int 48:1133–1140
Mallakpour S, Kowsari E (2006) Thermally stable and optically active poly(amide–imide)s derived from 4,4′-(hexafluoroisopropylidene)-N,N′-bis-(phthaloyl-l-methionine) diacid chloride and various aromatic diamines: synthesis and characterization. Polym Bull 57:169–178
Mallakpour S, Kowsari E (2006) Preparation and characterization of new thermally stable and optically active poly(ester–imide)s by direct polycondensation with thionyl chloride in pyridine. Polym Adv Technol 17:174–179
Mallakpour S, Kowsari E (2005) Polycondensation reaction of N,N’-(4,4′-oxydiphthaloyl)-bis-l-isoleucine diacid chloride with aromatic diamines. Iran Polym J 14(9):799–806
Mallakpour S, Kowsari E (2006) Thionyl chloride/pyridine system as a condensing agent for the polyesterification reaction of N,N′-(4,4′-oxydiphthaloyl)-bis-l-leucine and aromatic diols. Iran Polym J 15(6):457–465
Mallakpour S, Habibi S (2003) Microwave-promoted synthesis of new optically active poly(ester–imide)s derived from N,N0-(pyromellitoyl)-bis-l-leucine diacid chloride and aromatic diols. Eur Polym J 39:1823–1829
Mallakpour SE, Hajipour A, Zamanlou MR (2001) Synthesis of optically active poly(amide-imide)s derived from N,N’-(4,4′-arbonyldiphthaloyl)-bis-l-leucine diacid chloride and aromatic diamines by microwave radiation. J Polym Sci 39:177–186
Brandrup J, Immergut EH, Grulke EA (1999) Polymer handbook, 4th edn. Wiley, New York
Yu XL, Wang XY, Gao JW, Li XB, Wang HL (2006) Prediction of glass transition temperatures for polystyrenes by a four descriptors QSPR model. Macromol Theory Simul 15:94–99
Lili S, Liping Z, Yu Y, Yukun L, Zhiliang L (2007) QSPR study of polychlorinated diphenyl ethers by molecular electronegativity distance vector (MEDV-4). Chemosphere 66:1039–1051
Yovani MP (2004) Total and local (atom and atom type) molecular quadratic indices: significance interpretation, comparison to other molecular descriptors, and QSPR/QSAR applications. Bioorg Med Chem 12:6351–6369
Hyperchem (1995) re. 4. for Windows, Autodesk, Sansalito, CA
Mopac for Windows (2009) Stewart computational chemistry
Mauri A, Consonni V, Pavan M, Todeschini R (2006) DRAGON software: an easy approach to molecular descriptor calculations. MATCH Commun Math Comput Chem 56:237–248
Goldberg DE (1989) Genetic algorithms in search, optimization and machine learning. Addison-Wesley, New York
Hoskuldsson A (1996) Prediction methods in science and technology. Vol. 1: basic theory. Thur Publishing, Denmark
Leardi R, Boggia R, Terrile M (1992) Genetic algorithms as a strategy for feature selection. J Chemom 6:267–281
Leardi R, Gonzalez AL (1998) Genetic algorithms applied to feature selection in PLS regression: how and when to use them. Chemom Intell Lab Syst 41:195–207
Geladi P, Kowalski BR (1986) Partial least squares regression: a tutorial. Anal Chim Acta 185:1–17
Lorber A, Wangen L, Kowalsky BR (1987) Theoretical foundation for the PLS algorithm. J Chemom 1:19–31
Khayamian T, Ensafi AA, Hemmateenejad B (1999) Simultaneous spectrophotometric determinations of cobalt, nickel and copper using partial least squares based on singular value decomposition. Talanta 49:587–596
Shamsipur M, Hemmateenejad B, Akhond M (2001) Quantitative structure–property relationship study of acidity constants of some 9,10-anthraquinone derivatives using multiple linear regression and partial least-squares procedures. Talanta 54:1113–1120
Hoskuldsson A (2001) Variable and subset selection in PLS regression. Chemom Intell Lab Syst 55:23–38
MATLAB 7.0, The Mathworks Inc., Natick, MA, USA, http://www.mathworks.com
Zupan J, Gasteiger J (1999) Neural network in chemistry and drug design. Wiley-VCH, Weinheim
Beal TM, Hagan HB, Demuth M (1996) Neural network design. PWS, Boston
Zupan J, Gasteiger J (1993) Neural networks for chemists: an introduction. VCH, Weinheim
Golbraikh A, Tropsha A (2002) Beware of q2! J Mol Graphics Modell 20:269–276
Roy PP, Roy K (2008) On some aspects of variable selection for partial least squares regression models. QSAR Comb Sci 27:302–313
Maldonado AG, Doucet JP, Petitjean M (2006) Molecular similarity and diversity in chemoinformatics: from theory to applications. Mol Divers 10:39–79
Todeschini R, Lasagni M, Marengo E (1994) New molecular descriptors for 2D- and 3D-structures theory. J Chemom 8:263–273
Todeschini R, Gramatica P (1998) New 3D molecular descriptors: the WHIM theory and QSAR applications. In: Kubinyi H, Folkers G, Martin YC (eds) e30 QSAR in drug design, vol 2. Kluwer/ESCOM, Dordrecht, pp 355–380
Balaban AT (1993) Benzenoid catafusenes: perfect matchings, isomerization, automerization. Pure Appl Chem 65:1–9
Balaban AT (1993) Lowering the intra and intermolecular degeneracy of topological invariants. Croat Chem Acta 66:447–458
Jalali-Heravi M, Fatemi MH (1998) Prediction of flame ionization detector response factors using an artificial neural network. J Chromatogr A 825:161–169
Jalali-Heravi M, Fatemi MH (2000) Prediction of thermal conductivity detection response factors using an artificial neural network. J Chromatogr A 897:227–235
Fatemi MH, Jalali-Heravi M, Knouze E (2003) Prediction of bioconcentration factor using genetic algorithm and artificial neural network. Anal Chim Acta 486:101–108
Acknowledgments
We wish to express our gratitude to the Research Affairs Division Isfahan University of Technology (IUT), Isfahan, for partial financial support. Further financial support from National Elite Foundation (NEF) and Center of Excellency in Sensors and Green Chemistry Research (IUT) is gratefully acknowledged.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mallakpour, S., Hatami, M. & Golmohammadi, H. QSPR prediction of thermal decomposition property of non-vinyl polymers having α-amino acids moieties. Polym. Bull. 70, 715–732 (2013). https://doi.org/10.1007/s00289-013-0906-3
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00289-013-0906-3