Liquid-liquid equilibrium data prediction using large margin nearest neighbor

Document Type: Full article


1 Faculty of Chemical Engineering, Babol University of Technology, PO Box, 484, Babol, Iran

2 Department of Chemical Engineering, Faculty of Chemical Engineering and Environmental Protection,“Gheorghe Asachi” Technical University of Iaşi, Str. Prof. dr. Doc. DimitrieMangeron, nr. 73, 700050, Iaşi, Romania

3 Department of Computer Science and Engineering, Faculty of Automatic Control and Computer Engineering, “Gheorghe Asachi” Technical University of Iaşi, Str. Prof. dr. Doc. DimitrieMangeron, nr. 27, 700050, Iaşi, Romania

4 Biotechnology research lab, Chemical Engineering Department, Faculty of Engineering, Razi University, Kermanshah 67149-67346, Iran


Guanidine hydrochloride has been widely used in the initial recovery steps of active protein from the inclusion bodies in aqueous two-phase system (ATPS). The knowledge of the guanidine hydrochloride effects on the liquid-liquid equilibrium (LLE) phase diagram behavior is still inadequate and no comprehensive theory exists for the prediction of the experimental trends. Therefore the effect the guanidine hydrochloride on the phase behavior of PEG4000+ potassium phosphate+ water system at different guanidine hydrochloride concentrations and pH was investigated in this study. To fill the theoretical gaps, the typical of support vector machines was applied to the k-nearest neighbor method in order to develop a regression model to predict the LLE equilibrium of guanidine hydrochloride in the above mentioned system. Its advantage is its simplicity and good performance, with the disadvantage of an increase the execution time. The results of our method are quite promising: they were clearly better than those obtained by well-established methods such as Support Vector Machines, k-Nearest Neighbour and Random Forest. It is shown that the obtained results are more adequate than those provided by other common machine learning algorithms.


Main Subjects

[1]   Albertsson, P. Å., Partition of cell particles and macromolecules, 3rd ed., New York, Wiley, USA, (1986).

[2]   Raghavarao, K., Ravganathan, T., Srinivas, N. and Barhate, R., “Aqueous two phase extraction: An environmentally benign technique”, Clean Technol. Environ. Policy.,5(2), 136 (2003).

[3]   Biazus, J. P., Santana, J. C., Souza, R. R.,  Jordao, E. and  Tambourgi, E. B.,  “Continous extraction of alpha- and beta-amylases from Zea mays malt in a PEG4000/CaCl2 ATPS”, J. Chromatogr. B., 85(1-2),227 (2007).

[4]   Cavalcanti, M.T.H., Carneiro-da-Cunha, M. G., Brandi, I.V.,  Porto, T.S.,   Converti, A.,  Lima Filho, J.L.,  Porto, A.L.F. and Pessoa, A., “Continuous extraction of á- toxin from a fermented broth of Clostridium perfringens Type A in perforated rotating disc contactor using aqueous two-phase PEG–phosphate system”, Chem. Eng. Prog., 47,1771 (2008).

[5]   Vázquez-Villegas, P., Aguilar, O. and Rito-Palomares, M., “Study of biomolecules partition coefficients on a novel continuous separator using polymer-salt aqueous two-phase systems”, Sep. Purif. Technol., 78(1),69(2011).

[6]   Rosa, P.,  Azevedo, A.,  Sommerfeld, S., Bäcker, W. and Aires-Barros, M.,  “Continuous aqueous two-phase extraction of human antibodies using a packed column”, J. Chromatogr. B., 880,148(2012).

[7]   Rosa, P.A.J.,  Azevedo, A.M.,  Mutter, M., Bäcker, W. and Aires-Barros, M.R., “Continuous purification of antibodies form cell culture supernatant with aqueous two-phase systems: From concept to process”, Biotechnol. J., 8 (3),352 (2013).

[8]   Espitia-Saloma, E., Vázquez-Villegas, P., Aguilar, O. and Rito-Palomares, M., “Continuous aqueous two-phase systems devices for the recovery of biological products”, Food Bioprod. Process,92 (2),101 (2014).

[9]   Luechaua, F., Ling, T. and ChandLyddiatt, A., “A descriptive model and methods for up-scaled process routes for interfacial partition of bioparticles in aqueous two-phase systems”, Biochem. Eng.  J., 50(3),122 (2010).

[10]     Hu, R., Feng, X., Chen, P., Fu, M., Chen, H., Guo, L. and  Liu, B-F., “Rapid, highly efficient extraction and purification of membrane proteins using a microfluidic continuous-flow based aqueous two-phase system”, J.Chromatogr. A., 1218 (1),171 (2011).

[11]  Rodrigues, G.D., Teixeira, L.D., Ferreira, G.M.D., da Silva, M.D.H.,  da Silva, L.H.M. and de Carvalho, R.M.M., “Phase diagrams of aqueous two-phase systems with organic salts and F68 triblock copolymer at different temperatures”, J. Chem. Eng. Data., 55(3),1158(2010).

[12]  Rosa, P.A.J., Azevedo, A.M., Sommerfeld, S., Bäcker, W. and Aires-Barros, M.R., “Aqueous two-phase extraction as a platform in the biomanufacturing industry: Economical and environmental sustainability”, Biotech. Adv., 29(6),559 (2011).

[13]  Naganagouda, K. and Mulimani, V.H., “Aqueous two-phase extraction (ATPE): An attractive and economically viable technology for downstream processing of Aspergillusoryzae á-galactosidase”, Process Biochem., 43 (11),1293(2008).

[14]  Hatti-Kaul, R., Aqueous two-phase systems: Methods and protocols, methods in biotechnology, 11, Humana Press, (2000).

[15]  Bradoo, S., Saxena, R.K. and Gupta, R., “Partitioning and resolution of mixture of two lipases from Bacillus stearothermophilus SB-1 in aqueous two-phase system”, Process Biochem., 35 (1-2),57(1999).

[16]  Rito-Palomares, M., “Practical application of aqueous two-phase partition to process development for the recovery of biological products”,  J. Chromatogr. B., 807 (1),3(2004).

[17]  Asenjo, J.A. and Andrews, B.A., “Aqueous two-phase systems for protein separation: Phase separation and applications”, J. Chromatogr. A., 1238,1(2012).

[18]  Selber, K., Tjerneld, F., Collén, A.,  Hyytiä, T.,  Nakari-Setälä, T., Bailey, M., Fagerström, R., Kan, J.,  van der Laan, J., Penttilä, M. and  Kula, M. R.,  “Large-scale separation and production of engineered proteins, designed for facilitated recovery in detergent-based aqueous two-phase extraction systems”, Process Biochem., 39 (7),889(2004).

[19]  Yan-Min, L., Yan-Zhao, Y., Xi-Dan, Z. and Chuan-Bo, X., “Bovine serum albumin partitioning in polyethylene glycol (PEG)/potassium citrate aqueous two-phase systems”, Food  Bioprod. Process., 88 (1),40 (2010).

[20]  Rocha, M.V. and Nerli, B.B., “Molecular features determining different partitioning patterns of papain and bromelain in aqueous two-phase systems”, Int. J. Bio. Macromol., 61,204 (2013).

[21]  Rodrigues, G.D.,  de Lemos, L.R., da Silva, L.H.M. and  da Silva, M.C.H., “Application of hydrophobic extractant in aqueous two-phase systems for selective extraction of cobalt, nickel and cadmium”, J. Chromatogr. A., 1279,13(2013).

[22]  Wang, Z.H.,  Song, M. and Ma, Q., “Two-phase aqueous extraction of chromium and its application to speciation analysis of chromium in plasma”, Mikrochim. Acta., 134(1),95(2000).

[23]  Gao, Y.T. and Wang, W.W., “Distribution behavior and extraction mechanism of gold(III) in polyethylene glycol ammonium sulphate aqueous biphasic system”, Chin. J. Appl. Chem., 19(6),578 (2002).

[24]  Patrício, P.R.,  Mesquita, M.C.,  da Silva, L.H.M. and da Silva, M.C.H. “Application of aqueous two-phase systems for the development of a new method of cobalt(II), iron(III) and nickel(II) extraction: A green chemistry approach”, J. Hazard Mater., 193,311(2011).

[25]  Bulgariu, L. and Bulgariu, D., “Selective extraction of Hg(II), Cd(II) and Zn(II) ions from aqueous media by a green chemistry procedure using aqueous two-phase systems”, Sep. Purif. Technol., 118,209(2013).

[26]  Rahimpour, F., Feyzi, F., Maghsodi S. and Kaul, R.H., “Purification of plasmid DNA with polymer-salt aqueous two-phase system: Optimization using response surface methodology”, Biotech. Bioeng., 95 (4),627 (2006).

[27]  Rahimpour, F., Mamo, G., Feyzi, F., Maghsoudi, S. and Kaul, R.H., “Optimization refolding and recovery of active recombinant bacillus haloduransxylanase in polymer-salt aqueous two-phase system using surface response analysis”, J. Chromatogr. A., 1141(1),32 (2007).

[28]  Zaveckas, M., Zvirblieñe, A., Zvirblis, A. Chmieliauskaite, V.,  Bumelis, V. and Pesliakas, H., “Effect of surface histidine mutations and their number on the partitioning and refolding of recombinant human granulocyte-colony stimulating factor (Cys17Ser) in aqueous two-phase systems containing chelated metal ions”, J. Chromatogr B., 852 (1-2),409 (2007).

[29]  Shahbaz Mohamadia, H. and Omidinia, E., “Purification of recombinant phenylalanine dehydrogenase by partitioning in aqueous two-phase systems”, J. Chromatogr. B., 854(1-2),273 (2007).

[30]  Shahbaz Mohamadia, H. and Omidinia, E., “Process integration for the recovery and purification of recombinant Pseudomonas fluorescensproline dehydrogenase using aqueous two-phase systems”, J. Chromatogr. B., 929,11 (2013).

[31]  Lan, J. Ch-W., Yeh, C-Y.,  Wang, C-C., Yang, Y-H. and Wu, H-S., “Partition separation and characterization of the poly hydroxyalkanoates synthase produced from recombinant Escherichia coli using an aqueous two-phase system”, J. Biosci. Bioeng., 116 (4),499 (2013).

[32]  Ibarra-Herrera, C., Aguilar, O. and Rito-Palomares, M., “Application of an aqueous two-phase system strategy for the potential recovery of a recombinant protein from alfalfa (Medicago sativa)”, Sep. Purif. Technol., 77 (1),94(2011).

[33]  Clark, ED., “Protein refolding for industrial processes”, Curr. Opin. Biotechnol., 12 (2),202 (2001).

[34]  Rämsch, C., Kleinelanghorst, L. B., Knieps, E., Thommes, M. R. and Kula, A. J. “Aqueous two-phase systems containing urea: Influence of protein structure on Protein Partitioning”, Biotechnol. Bioeng.,  69,83 (2001).

[35]  Salvi, G., De Los Rios, P. and Vendruscolo, M., “Effective interactions between chaotropic agents and proteins”, protein., 61 (3),492(2005).

[36]  Vemić, A., Stojanović, B. J., Stamenković, I. and Malenović, A., “Chaotropic agents in liquid chromatographic method development for the simultaneous analysis of levodopa, carbidopa, entacapone and their impurities”, J. Pharm. Biomed. Anal., 77,9 (2013).

[37]  Parnica, J. and Antalika, M. “Urea and guanidine salts as novel components for deep eutectic solvents”, J. Mol. Liq., 197,23(2014).

[38]  Hagel, P., Gerding, J.J.T., Fieggen, Wand Bloemendal, H., “Cyanate formation in solutions of urea I. Calculation of cyanate concentrations at different temperature and pH”, Biochim. Biophys. Acta., 243 (3),366(1971).

[39]  Cejka, J., Vodražkaand, Z. and Salgk, J., “Carbamylation of globin in electrophoresis and chromatography in the presence of urea”, Biochim. Biophys. Acta., 154(3),589 (1968).

[40]  Rämsch, Ch., Kleinelanghorst, L.B., Knieps., E.A., Homes, J. and Kula, M.R.,  “Aqueous two-phase system containing urea; Influence on phase separation and stabilization of protein conformation by  phase components”, Bitechnol. Prog., 15(3),493(1999).

[41]  Rahimpour, F. and  Pirdashti, M., “The effect of guanidine hydrochloride on phase diagram of PEG-phosphate aqueous two-phase system”, World Academy of Science, Engineering and Technology, 1 (5), 29(2007).

[42]  Rahimpour, F. and Pirdashti, M. “Effective parameters on the partition coefficient of guanidine hydrochloride in the poly ethylene glycol + phosphate + water system at 298.15 K”. Iranian J. Chem. Eng., 7(1),67 (2010).

[43]  Gautam, G. and Simon, L. “Prediction of equilibrium phase compositions and â-glucosidase partition coefficient in aqueous two-phase systems”, Chem. Eng. Commun., 194 (1),117 (2007).

[44]  Pazuki, G.R., Taghikhani, V. and Vossoughi, M., “Prediction the partition coefficients of biomolecules in polymer- polymer aqueous two-phase systems using the artificial neural network”, Particulate Sci. Technol., 28 (1),67 (2010).

[45]  Pazuki, Gh. and Seyfi Kakhki, S., “A hybrid GMDH neural network to investigate partition coefficients of Penicillin G Acylase in polymer–salt aqueous two-phase systems”, J. Mol. Liq., 188,131 (2013).

[46]  Abdolrahimi, Sh., Nasernejad, B., Pazuki, Gh., “Prediction of partition coefficients of alkaloids in ionic liquids based aqueous biphasic systems using hybrid group method of data handling (GMDH) neural network”, J. Mol. Liq., 191,79(2014).

[47]  Pirdashti, M., Movagharnejad, K.,  Curteanu, S.,  Dragoi, E.N.,   Rahimpour, F., “Prediction of partition coefficients of guanidine hydrochloride in  PEG–phosphate systems using neural networks developed with  differential evolution algorithm”, J. Ind. Eng. Chem., 27,268(2015).

[48]  Thomas Cover, M. and Hart, P.E., “Nearest neighbor pattern classification”. IEEE T Inform Theory, 13(1),21(1967).

[49]  Shental, N., Hertz, T., Weinshall, D. and Pavel, M., “Adjustment learning and relevant component analysis”, Proceedings of the 7th European Conference on Computer Vision, ECCV-02,4,776-792, London, UK, Springer-Verlag,776(2002).

[50]  Shalev-Shwartz, Sh., Singer, Y. and Ng, A.Y., “Online and batch learning of pseudo-metrics”, Proceedings of the 21st International Conference on Machine Learning, ICML-04, Banff, Canada, pp. 94–101 (2004).

[51]  Chopra, S., Hadsell, R. and LeCun, Y., “Learning a similarity metric discriminatively, with application to face verification”, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, CVPR-05, San Diego, CA, USA, pp. 349-356 (2005).

[52]  ElSehiemy, R.,  Abou El-Ela, A. and  Shaheen, A., ”Multi-objective fuzzy-based procedure for enhancing reactive power management”, IET Gener. Transm. Dis., 7(12),1453 (2013).

[53]  Precup, R.E.,  Rdac, M.B.,  Tomescu, M.L., Petriu, E.M. and Preitl, S., ”Stable and convergent iterative feedback tuning of fuzzy controllers for discrete-time SISO systems”, Expert Syst.  Appl., 40 (1), 188 (2013).

[54]  Khmelev, A. and Kochetov, Yu., ”A hybrid local search for the split delivery vehicle routing problem”, IJ-AI., 13(1), 147(2015).

[55]  Kazakov, A. L. and  Lempert, A. A., ” On mathematical models for optimization problem of logistics infrastructure, IJ-AI., 13(1), 200( 2015).

[56]  Haghtalab, A. and Mokhtarani, B., “The new experimental data and a new thermodynamic model based on group contribution for correlation liquid-liquid equilibria in aqueous two-phase systems of PEG and (K2HPO4 or Na2SO4)”, Fluid Phase Equilib., 215(2),151 (2004).

[57]  Goldberger, J., Roweis, S., Hinton, G. and Salakhutdinov, R., Neighbourhood components analysis, Advances in Neural Information Processing Systems, 17, Cambridge, MA, USA, MIT Press, pp.513-520(2005).

[58]  Weinberger, K.Q.,  Blitzer, J. and Saul, L.K.,  Distance metric learning for large margin nearest neighbor classification, Advances in Neural Information Processing Systems, 18, MIT Press, Cambridge, MA, USA, pp. 1473-1480 (2006).

[59]  Weinberger, K.Q. and  Saul, L.K., “Fast solvers and efficient implementations for distance metric learning”, Proceedings of the 25th International Conference on Machine Learning, Helsinki, Finland, pp. 1160-1167(2008).

[60]  Weinberger, K.Q. and Saul, L.K., “Distance metric learning for large margin nearest neighbor classification”, J. Mach. Learn Res.,10,207 (2009).

[61]  Moore, R.C. and  DeNero, J. “L1 and L2 regularization for multiclass hinge loss models”, Proceedings of the Symposium on Machine Learning in Speech and Language
Processing, pp. 1-5 (2011).

[62]  Leon, F. and Curteanu, S., “Evolutionary algorithm for large margin nearest neighbour regression”, 7th International Conference on Computational Collective Intelligence Technologies and Applications, ICCCI, Spain. Madrid, pp. 21-23 (2015).

[63]  Estapé, D., Rinas, U., “Optimized procedures for purification and solubilization of basic fibroblast growth factor inclusion bodies”, Biotechnol. Tech., 10 (7),481 (1996).

[64]  Annuziata, O., Asherie, N., Lomakin, A., Pande, J.,  Ogun, O., Benedek, G.B.,  “Effect of polyethylene glycol on the liquid-liquid phase transition in aqueous protein solutions”, Proc. Natl. Acad. Sci., 99 (22),14165(2002).

[65]  Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P. and Witten, I. H.,  “The WEKA data mining software: An update”. ACM SIGKDD Explor., 11(1),10(2009).

[66]  Breiman, L., “Random Forests”, Mach. Lear., 45 (1),5 (2001).

[67]  Holmes, G., Hall, M. and Frank, E., “Generating rule sets from model trees”, Twelfth Australian Joint Conference on Artificial Intelligence, p. 1-12 (1999).