Мultivariate analysis for rapid screening and prediction of solid-state compatibility in pharmaceutical preformulation studies-paving the road for machine learning
DOI:
https://doi.org/10.20450/mjcce.2024.2838Keywords:
interaction, binary mixtures, principal component analysis, partial least squares-discriminant analysis, machine learningAbstract
Multivariate analysis models were developed to evaluate the results obtained from a compatibility study designed for ibuprofen with a large group of different types of excipients, as a possible approach for rapid screening of the incompatibility between the active pharmaceutical ingredient (API) and excipients. The solid-state characterization of the binary mixtures was performed by Fourier transform infrared spectroscopy (FTIR) and differential scanning calorimetry (DSC). Principal component analysis (PCA) and partial least squares-discriminant analysis (PLS-DA) using SIMCA® software were applied for evaluation of the experimentally obtained results. The optimal PCA model for the FTIR spectra explains 96.2 % of the variations in the dataset with good statistical indicators (R2X = 0.960, Q2 = 0.900), which was also the case for the PCA model for the DSC curves (R2X = 0.981, Q2 = 0.866). The applied PLS-DA models have shown similar behaviour to the PCA. Moreover, the main spectral variations in the FTIR spectra and the thermal events in the DSC data were attributed the highest variable importance for the projection (VIP) scores in the corresponding VIP plots, confirming the model capability for predicting ibuprofen interactions. Furthermore, the prediction power of the optimal models for FTIR and DSC experimental data was evaluated by the root mean square error of prediction (RMSEP) of 0.10 and 0.16, respectively. The obtained results demonstrated the potential of multivariate statistical analysis as a machine learning-based technique for screening and prediction of ibuprofen-excipients solid-state compatibility in the preformulation phase of the pharmaceutical development of dosage forms.
References
(1) Gupta, K. R.; Pounikar, A. R.; Umekar, M. J., Drug ex-cipient compatibility testing protocols and characteriza-tion: a review. Asian J. Chem. Sci. 2019, 6 (3), 1‒22. https://doi.org/10.9734/AJOCS/2019/v6i319000
(2) Rebiere, H.; Martin, M.; Ghyselinck, C.; Bonnet, P. A.; Brenier, C., Raman chemical imaging for spectroscopic screening and direct quantification of falsified drugs. J. Pharm. Biomed. Anal. 2018, 148, 316–323.
https://doi.org/10.1016/j.jpba.2017.10.005
(3) Hossain, M. N.; Igne, B.; Anderson, C. A.; Drennen III, J. K., Influence of moisture variation on the performance of Raman spectroscopy in quantitative pharmaceutical analyses. J. Pharm. Biomed. Anal. 2019, 164, 528–535. https://doi.org/10.1016/j.jpba.2018.10.022
(4) Čapková, T.; Pekárek, T.; Hanulíková, B.; Matějka, P., Application of reverse engineering in the field of pharma-ceutical tablets using Raman mapping and chemometrics. J. Pharm. Biomed. Anal. 2022, 209, 114496. https://doi.org/10.1016/j.jpba.2021.114496
(5) Antovska, P.; Petruševski, G.; Makreski, P., Solid‒state compatibility screening of excipients suitable for devel-opment of indapamide sustained release solid‒dosage formulation. Pharm. Dev. Technol. 2013, 18 (2), 481–489. https://doi.org/10.3109/10837450.2012.717948
(6) Chadha, R.; Bhandari, S., Drug-excipient compatibility screening ‒ Role of thermoanalytical and spectroscopic techniques. J. Pharm. Biomed. Anal. 2014, 87, 82‒97. https://doi.org/10.1016/j.jpba.2013.06.016
(7) Selvaraj, C.; Chandra, I.; Singh, S. K., Artificial intelli-gence and machine learning approaches for drug design: challenges and opportunities for the pharmaceutical indus-tries. Mol. Diversity 2021, 23, 1‒21.
https://doi.org/10.1007/s11030-021-10326-z
(8) International Conference on Harmonisation of Technical Requirements for Registration of Pharmaceuticals for Human Use. ICH Harmonised Tripartite Guideline on Pharmaceutical Development Q8 (R2), European Medi-cines Agency, London, 2009.
(9) Mansuri, N.; Patel, K.; Mehta, M.; Vyas, G.; Reddy, J. P.; Shah, T.; Steinbach, D.; Desai, D., Quality by design (QbD) approach to match tablet glossiness. Pharm. Dev. Technol. 2020, 25 (8), 1010–1017.
https://doi.org/10.1080/10837450.2020.1772291
(10) Feng, H.; Mohan, S., Application of process analytical technology for pharmaceutical coating: challenges, pitfalls and trends. AAPS PharmSciTech. 2020, 21, 1–17. https://doi.org/10.1208/s12249-020-01727-8
(11) Guidance for industry: PAT – A framework for innova-tive pharmaceutical development, manufacturing and quality assurance, U.S. Department of Health and Hu-man Services, Food and Drug Administration, USA, 2004.
(12) Lou, H.; Lian, B.; Hageman, M. J., Applications of ma-chine learning in solid oral dosage form development. J. Pharm. Sci. 2021, 110 (9), 3150‒3165.
https://doi.org/10.1016/j.xphs.2021.04.013
(13) Patel, S.; Patel, M.; Kulkarni, M.; Patel, M. S., DE-INTERACT: A machine-learning-based predictive tool for the drug-excipient interaction study during product development – Validation through paracetamol and vanil-lin as a case study. Int. J. Pharm. 2023, 637, 122839. https://doi.org/10.1016/j.ijpharm.2023.122839
(14) Wesolowski, M.; Rojek, B., Thermogravimetric detection of incompatibilities between atenolol and excipients using multivariate techniques. J. Therm. Anal. Calorim. 2013, 113, 169–177.
https://doi.org/10.1007/s10973-013-3070-y
(15) Rojek, B.; Wesolowski, M., A combined differential scanning calorimetry and thermogravimetry approach for the effective assessment of drug substance-excipient compatibility. J. Therm. Anal. Calorim. 2023, 148 (3), 845–858. https://doi.org/10.1007/s10973-022-11849-9
(16) Siozou, E.; Sakkas, V.; Kourkoumelis, N., Quantification and classification of diclofenac sodium content in dis-persed commercially available tablets by attenuated total reflection infrared spectroscopy and multivariate data analysis. Pharmaceuticals 2021, 14 (5), 440.
https://doi.org/10.3390/ph14050440
(17) Stojanovska Pecova, M.; Geskovski, N.; Petrushevski, G.; Chachorovska, M.; Krsteska, L.; Ugarkovic, S.; Makreski, P., Solid‒state interaction of ibuprofen with magnesium stearate and product characterization thereof. Drug Dev. Ind. Pharm. 2020, 46 (8), 1308–1317. https://doi.org/10.1080/03639045.2020.1788067
(18) Talwar, S.; Pawar, P.; Wu, H.; Sowrirajan, K.; Wu, S.; Igne, B.; Friedman, R.; Muzzio, F. J.; Drennen III, J. K., NIR spectroscopy as an online PAT tool for a narrow therapeutic index drug: Toward a platform approach across lab and pilot scales for development of a powder blending monitoring method and endpoint determination. AAPS PharmSciTech. 2022, 24 (6), 103.
https://doi.org/10.1208/s12248-022-00748-4
(19) Stojanovska Pecova, M.; Geskovski, N.; Petrushevski, G.; Makreski, P., A novel method for rapid particle size analysis of ibuprofen using near-infrared spectroscopy. AAPS PharmSciTech. 2021, 22, 1–13.
https://doi.org/10.1208/s12249-021-02156-x
(20) Company, A. D.; Simonetti, S., DFT study of the chemi-cal reaction and physical properties of ibuprofen sodium. Tetrahedron 2022, 120, 132899.
https://doi.org/10.1016/j.tet.2022.132899
(21) Censi, R.; Martena, V.; Hoti, E.; Malaj, L.; Di Martino, P., Sodium ibuprofen dihydrate and anhydrous: study of the dehydration and hydration mechanisms. J. Therm. Anal. Calorim. 2013, 111, 2009–2018.
https://doi.org/10.1007/s10973-012-2194-9
(22) Rossi, P.; Macedi, E.; Paoli, P.; Bernazzani, L.; Carignani, E.; Borsacchi, S.; Geppi, M., Solid–solid tran-sition between hydrated racemic compound and anhy-drous conglomerate in Na-Ibuprofen: A combined X-ray diffraction, solid-state NMR, calorimetric, and computa-tional study. Cryst. Growth Des. 2014, 14 (5), 2441‒2452. https://doi.org/10.1021/cg500161e
(23) Chaiya, P. O.; Phaechamud, T. H., Differential scanning calorimetric analysis for incompatibility: sodium stea-rate/magnesium stearate and acidic compounds. Key Eng. Mater. 2020, 859, 307‒312.
https://doi.org/10.4028/www/scientific.net/KEM.859.307.
(24) Kararli, T. T; Needham, T. E.; Seul, C. J.; Finnegan, P. M., Solid‒state interaction of magnesium oxide and ibu-profen to form a salt. Pharm. Res. 1989, 6, 804–808. https://doi.org/10.1023/A:1015983732667.
(25) Ravichandran, V.; Lee, M.; Nguyen Cao, T.G.; Shim, M. S., Polysorbate-based drug formulations for brain-targeted drug delivery and anticancer therapy. Appl. Sci. 2021, 11 (19), 9336.
https://doi.org/10.3390/app11199336
(26) Lombardo, R.; Musumeci, T.; Carbone, C.; Pignatello, R., Nanotechnologies for intranasal drug delivery: an update of literature. Pharm. Dev. Technol. 2021, 26 (8), 824–845. https://doi.org/10.1080/10837450.2021.1950186
(27) Kriegel, C.; Festag, M.; Kishore, R. S.; Roethilsberger, D.; Schmitt, G., Pediatric safety of polysorbates in drug formulations. Children 2019, 7 (1), 1.
https://doi.org/10.3390/children7010001
(28) Garbacz, P.; Wesolowski, M., DSC, FTIR and Raman spectroscopy coupled with multivariate analysis in a study of co-crystals of pharmaceutical interest. Molecules 2018, 23 (9), 2136.
https://doi.org/10.3390/molecules23092136
(29) Gao, Y.; Zhang, Y.; Hong, Y.; Wu, F.; Shen, L.; Wang, Y.; Lin, X., Multifunctional role of silica in pharmaceuti-cal formulations. AAPS PharmSciTech. 2022, 23 (4), 90. https://doi.org/10.1208/s12249-022-02237-5
(30) Rojek, B.; Gazda, M.; Wesolowski, M., Quantification of compatibility between polymeric excipients and atenolol using principal component analysis and hierarchical clus-ter analysis. AAPS PharmSciTech. 2022, 23, 1‒16. https://doi.org/10.1208/s12249-021-02143-2
(31) Lasalvia, M.; Capozzi, V.; Perna, G., A comparison of PCA-LDA and PLS-DA techniques for classification of vibrational spectra. Appl. Sci. 2022, 12 (11), 5345. https://doi.org/10.3390/app12115345
Downloads
Additional Files
Published
Versions
- 2024-05-19 (4)
- 2024-04-23 (3)
- 2024-04-23 (2)
- 2024-04-22 (1)
How to Cite
Issue
Section
License
Copyright (c) 2024 Elena Cvetkovska Bogatinovska, Nikola Geshkovski, Gjorgji Petrushevski, Viktor Stefov
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.