Orthogonal projection to latent structures and first derivative for manipulation of PLSR and SVR chemometric models' prediction: A case study

Autoři: Fatma F. Abdallah aff001;  Hany W. Darwish aff002;  Ibrahim A. Darwish aff002;  Ibrahim A. Naguib aff001
Působiště autorů: Pharmaceutical Analytical Chemistry Department, Faculty of Pharmacy, Beni-Suef University, Alshaheed Shehata Ahmad Hegazy St., Beni-Suef, Egypt aff001;  Department of Pharmaceutical Chemistry, College of Pharmacy, King Saud University, Kingdom of Saudi Arabia aff002;  Analytical Chemistry Department, Faculty of Pharmacy, Cairo University, Kasr El-Aini St., Cairo, Egypt aff003;  Department of Pharmaceutical Chemistry, College of Pharmacy, Taif University, Al-Hawiah, Taif, Saudi Arabia aff004
Vyšlo v časopise: PLoS ONE 14(9)
Kategorie: Research Article
doi: 10.1371/journal.pone.0222197


Novel manipulations of the well-established multivariate calibration models namely; partial least square regression (PLSR) and support vector regression (SVR) are introduced in the presented comparative study. Two preprocessing methods comprising first derivatization and orthogonal projection to latent structures (OPLS) are implemented prior to modeling with PLSR and SVR. Quantitative determination of pyridostigmine bromide (PR) in existence of its two associated substances; impurity a (IMP A) and impurity b (IMP B); was utilized as a case study for achieving comparison. A series consisting of 16 mixtures with numerous percentages of the studied compounds was applied for implementation of a 3 factor 4 level experimental design. Additionally, a series consisting of 9 mixtures was employed in an independent test to verify the predictive power of the suggested models. Significant improvement of predictive abilities of the two studied chemometric models was attained via implementation of OPLS processing method. The root mean square error of prediction RMSEP for the test set mixtures was employed as a key comparison tool. About PLSR model, RMSEP was found 0.5283 without preprocessing method, 1.1750 when first derivative data was used and 0.2890 when OPLS preprocessing method was applied. With regard to SVR model, RMSEP was found 0.2173 without preprocessing method, 0.3516 when first derivative data was used and 0.1819 when OPLS preprocessing method was applied.

Klíčová slova:

Absorption spectra – Bromides – Drug research and development – Experimental design – High performance liquid chromatography – Mathematical functions – Preprocessing – Spectrophotometers


1. "The British Pharmacopoeia", Her Majesty's, The Stationary Office, London (2013).

2. The United States Pharmacopeia, 34 Ed., National Formulary 29, United States Pharmacopeia convention INC, USA (2011).

3. Index Merck, thirteenth ed. Merck Research Laboratories Division of MERCK & CO., Inc, Whitehouse Station, NJ, USA, (2001).

4. Martindale- Extra Pharmacopoeia 34th Ed., "The Complete Drug References".The pharmaceutical Press, London, UK, (2005).

5. Breyer‐Pfaff U, Maier U, Brinkmann AM, Schumm F. Pyridostigmine kinetics in healthy subjects and patients with myasthenia gravis. Clin Pharmacol Ther. 1985;37(5):495–501. doi: 10.1038/clpt.1985.78 3987173

6. Sapolsky RM. Molecular neurobiology: The stress of Gulf War syndrome. Nature. 1998;393(6683):308–309. doi: 10.1038/30606 9620793

7. Xu M, Tan Q, Liu S, Zhang L, Zhang J. Content determination of pyridostigmine bromide in tablets by UV spectrophotometry. J Zhangguo Yaofang. 2011;22:743–745.

8. Yakatan GJ, Tien J-Y. Quantitation of pyridostigmine in plasma using high-performance liquid chromatography. J Chromatogr B: Biomed Sci Appl. 1979;164(3):399–403.

9. Blick DW, Murphy MR, Brown GC, Yochmowitz MG, Fanton JW, Hartgraves SL. Acute behavioral toxicity of pyridostigmine or soman in primates. Toxicol Appl pharmacol. 1994;126(2):311–318. doi: 10.1006/taap.1994.1121 8209384

10. Needham SR, Ye B, Smith JR, Korte WD. Development and validation of a liquid chromatography–tandem mass spectrometry method for the determination of pyridostigmine bromide from guinea pig plasma. J Chromatogr B Analyt Technol Biomed Life Sci. 2003;796(2):347–354. 14581074

11. Cherstniakova S, Garcia G, Strong J, Helbling N, Bi D, Roy M, et al. Simultaneous Determination of N, N‐Diethyl‐M‐Toluamide and Permethrin by GC‐MS and Pyridostigmine Bromide by HPLC in Human Plasma. Application to Pharmacokinetic Studies. Clin Pharmacol Ther. 2003;73(2):27.

12. Chan K, Williams N, Baty J, Calvey T. A quantitative gas-liquid chromatographic method for the determination of neostigmine and pyridostigmine in human plasma. J Chromatogr A. 1976;120(2):349–358.

13. Cohan SL, Pohlmann JL, Mikszewski J, O'doherty DS. The pharmacokinetics of pyridostigmine. Neurology. 1976;26(6):536–539.

14. Davison S, Hyman N, Prentis R, Dehghan A, Chan K. The simultaneous monitoring of plasma levels of neostigmine and pyridostigmine in man. Methods Find Exp Clin Pharmacol. 1980;2(2):77–82. 7339332

15. Sorensen PS, Flachs H, Friis ML, Hvidberg EF, Paulson OB. Steady state kinetics of pyridostigmine in myasthenia gravis. Neurology. 1984;34(8):1020–1024 doi: 10.1212/wnl.34.8.1020 6540381

16. Altria K, Bestford J. Main component assay of pharmaceuticals by capillary electrophoresis: considerations regarding precision, accuracy, and linearity data. J Capillary Electrophor. 1996;3(1):13–23. 9384760

17. Hadley M, Gilges M, Senior J, Shah A, Camilleri P. Capillary electrophoresis in the pharmaceutical industry: applications in discovery and chemical development. J Chromatogr B Biomed Sci Appl.2000;745(1):177–188. doi: 10.1016/s0378-4347(00)00153-5 10997713

18. Havel J, Patocka J, Bocaz G. Determination of physostigmine and pyridostigmine in pharmaceutical formulations by capillary electrophoresis. J Capillary Electrophor Microchip Technol. 2002;7(5–6):107–112.

19. Ellin RI, Zvirblis P, Wilson MR. Method for isolation and determination of pyridostigmine and metabolites in urine and blood. J Chromatogr B Biomed Sci Appl. 1982;228:235–244.

20. Abu-Qare AW, Abou-Donia MB. Determination of depleted uranium, pyridostigmine bromide and its metabolite in plasma and urine following combined administration in rats. J Pharm Biomed Anal. 2001;26(2):281–289. doi: 10.1016/s0731-7085(01)00403-4 11470205

21. De Ruyter M-G, Cronnelly R, Castagnoli Jr N. Reversed-phase, ion-pair liquid chromatography of quaternary ammonium compounds: Determination of pyridostigmine, neostigmine and edrophonium in biological fluids. J Chromatogr B Biomed Sci Appl. 1980;183(2):193–201.

22. Abu-Qare AW, Abou-Donia MB. Chromatographic method for the determination of diazepam, pyridostigmine bromide, and their metabolites in rat plasma and urine. J Chromatogr B Biomed Sci Appl.2001;754(2):503–509. doi: 10.1016/s0378-4347(01)00040-8 11339294

23. Zhao B, Moochhala SM, Lu J, Tan D, Lai MH. Determination of pyridostigmine bromide and its metabolites in biological samples. J Pharm Sci. 2006;9(11):71–81.

24. Kornfeld P, Samuels AJ, Wolf RL, Osserman KE. Metabolism of 14C‐labeled pyridostigmine in myasthenia gravis: Evidence for multiple metabolites. Neurology. 1970;20(7):634–641. doi: 10.1212/wnl.20.7.634 5463535

25. Barber H, Bourne G, Calvey T, Muir K. The pharmacokinetics of pyridostigmine and 3-hydroxy-N-methylpyridinium in the rat: dose-dependent effects after portal vein administration. Br J Pharmacol. 1975;55(3):335–341. doi: 10.1111/j.1476-5381.1975.tb06936.x 173444

26. Birtley R, Roberts J-B, Thomas BH, Wilson A. Excretion and metabolism of [14C]-pyridostigmine in the rat. Br J Pharmacol Chemother. 1966;26(2):393–402. doi: 10.1111/j.1476-5381.1966.tb01919.x 5912686

27. Naguib IA, Abdelaleem EA, Emam AA, Abdallah FF. Green Simultaneous Chromatographic Separation of Pyridostigmine Bromide and Its Related Substances in Pure Form, Tablets and Spiked Human Plasma. J Chromatogr Sci. 2019. https://doi.org/10.1093/chromsci/bmz043.

28. Ali NW, Abdelaleem EA, Naguib IA, Abdallah FF. Development and validation of a stability-indicating high-performance thin-layer chromatographic method for determination of pyridostigmine bromide in the presence of its alkaline-induced degradation product. J Planar Chromatogr. 2015;28(4):316–322.

29. Ivanovic D, Medenica M, Jancic B, Knezevic N, Malenovic A, Milic J. Validation of an analytical procedure for simultaneous determination of hydrochlorothiazide, lisinopril, and their impurities. Acta chromatographica. 2007;18:143–156.

30. Naguib IA, Abdelaleem EA, Draz ME, Zaazaa HE. Linear support vector regression and partial least squares chemometric models for determination of Hydrochlorothiazide and Benazepril hydrochloride in presence of related impurities: a comparative study. Spectrochim Acta A Mol Biomol Spectrosc. 2014;130:350–356. doi: 10.1016/j.saa.2014.04.024 24802720

31. Bagtash M, Zolgharnein J. Removal of brilliant green and malachite green from aqueous solution by a viable magnetic polymeric nanocomposite: Simultaneous spectrophotometric determination of 2 dyes by PLS using original and first derivative spectra. J Chemom. 2018;32(7):e3014.

32. Naguib IA. Improved predictions of nonlinear support vector regression and artificial neural network models via preprocessing of data with orthogonal projection to latent structures: A case study. Bull Faculty Pharm, Cairo Univer. 2017;55(2):287–291.

33. Gasteiger J. Handbook of chemoinformatics: Wiley-VCH; 2003;3.

34. Wold S, Ruhe A, Wold H, Dunn I, WJ. The collinearity problem in linear regression. The partial least squares (PLS) approach to generalized inverses. SIAM J. Sci. Stat. Comput. 1984;5(3):735–743.

35. Efron B, Tibshirani R, An Introduction to the Bootstrap, Chapman & Hall, NewYork, 1993.

36. Hjorth JU. Computer intensive statistical methods: Validation, model selection, and bootstrap: Routledge; 1994.

37. Cristianini N, Shawe-Taylor J. An introduction to support vector machines and other kernel-based learning methods: Cambridge university press; 2000.

38. Suykens JA, Gestel TV, Brabanter JD, J. World Scientific, Least Squares Support Vector Machines, Singapore; 1999.

39. Xu Y, Zomer S, Brereton RG. Support vector machines: a recent method for classification in chemometrics. Crit. Rev. Anal. Chem. 2006;36(3–4):177–188.

40. Schölkopf B, Smola AJ, Learning with Kernels, MIT Press, Cambridge; 2002.

41. Gunn SR. Support vector machines for classification and regression. ISIS technical report. 1998;14(1):5–16.

42. Parrella F, Online Support Vector Regression, Thesis in Information Science, University of Genoa, Italy. <http://onlinesvr.altervista.org/> 2007.

43. Thissen U, Pepers M, Üstün B, Melssen W, Buydens L. Comparing support vector machines to PLS for spectral regression applications. Chemometr Intell Lab Syst. 2004;73(2):169–179.

44. Trygg J, Wold S. Orthogonal projections to latent structures (O‐PLS). J Chemom. 2002;16(3):119–128.

45. Tapp HS, Kemsley EK. Notes on the practical utility of OPLS. TrAC Trends Anal Chem. 2009;28(11):1322–1327.

Článek vyšel v časopise


2019 Číslo 9

Nejčtenější v tomto čísle

Tomuto tématu se dále věnují…

Kurzy Doporučená témata