مدل‌سازی راندمان انکپسولاسیون و پایداری کورکومین موجود در پیکرینگ امولسیون سلولز با استفاده از الگوریتم‌های شبکه عصبی مصنوعی (ANN) و درخت طبقه بندی و رگرسیون (CART)

نویسندگان
هدا فهیم 1
علی معتمدزادگان 2
رضا فرهمندفر 3
نادر غفاری خلیق 4
1 دانشجوی دکتری دانشگاه کشاورزی و منابع طبیعی ساری
2 استاد، گروه علوم و صنایع غذایی، دانشگاه کشاورزی و منابع طبیعی ساری، ایران
3 دانشیار، گروه علوم و صنایع غذایی، دانشگاه کشاورزی و منابع طبیعی ساری، ایران
4 دانشیار، مرکز تحقیقات نانوتکنولوژی و کاتالیست، انستیتوی مطالعات تحصیلات تکمیلی، دانشگاه مالایا، کوالالامپور، مالزی
10.22034/FSCT.20.136.38
چکیده
پایداری کورکومین و راندمان انکپسولاسیون آن در امولسیون از جمله مهمترین فاکتورهای تعیین کننده زیست‌دسترس‌پذیری و جذب آن در بدن است. به این منظور در پژوهش حاضر پارامترهای موثر بر این دو فاکتور شامل زمان، pH و غلظت سلولز به‌عنوان متغیرهای ورودی و پایداری کورکومین و راندمان انکپسولاسیون به‌عنوان متغیر پاسخ در شبکه عصبی مصنوعی و الگوریتم درخت تصمیم استفاده شد. در این راستا نانوکریستال سلولز حاصل از هیدرولیز اسیدی برای تهیه پیکرینگ امولسیون کورکومین با نسبت روغن:آب 95:5 و غلظت سلولز 1، 5/1، 2، 5/2، و 3 درصد وزنی/حجمی استفاده شد و راندمان انکپسولاسیون روغن حاوی کورکومین و پایداری آن در طول 8 روز اندازه‌گیری شد. نتایج نشان داد که با افزایش غلظت سلولز راندمان انکپسولاسیون به صورت معنی‌داری افزایش یافته و همچنین راندمان انکپسولاسیون در pH 7 بالاتر از pH 2 بود (05/0p≤). کورکومین موجود در امولسیون‌های تهیه شده در pH 2 در طول نگهداری به شدت کاهش یافت این درحالی بود که میزان کورکومین موجود در امولسیون‌های با pH 7 در طول 8 روز نگهداری به‌خوبی پایدار بود. مدل‌سازی برای دو پارامتر پایداری کورکومین و راندمان انکپسولاسیون با آماره‌های R2 و RMSE% به‌ترتیب نشان داد 1-6- 3 MLP (00/10RMSE%= و 99/0 R2=) و 1-6-2 RBF (99/9RMSE%= و 99/0 R2=) دارای دقت بالاتری است. در نهایت نتایج نشان داد استفاده از الگوریتم شبکه عصبی مصنوعی نسبت به درخت تصمیم برای پیشبینی این دو پارامتر عملکرد بهتری داشت.
کلیدواژه‌ها
پیکرینگ امولسیون
درخت تصمیم
سلولز
شبکه عصبی مصنوعی
کورکومین

موضوعات

عنوان مقاله English

Modeling the encapsulation efficiency and stability of curcumin in cellulose Pickering emulsions using artificial neural network (ANN) and classification and regression tree (CART) algorithms

نویسندگان English

hoda fahim 1
Ali Motamedzadegan 2
Reza Farahmandfara 3
Nader Ghaffari Khaligh 4
1 PhD student, Department of Food Science and Technology, Sari Agricultural Sciences and Natural Resources University, Sari, Mazandaran, Iran
2 professor, department of Food Science and Technology, Sari Agricultural Sciences and Natural Resources University
3 Department of Food Science and Technology, Sari Agricultural Sciences and Natural Resources University, Sari, Mazandaran
4 Nanotechnology and Catalysis Research Center, Institute for Advanced Studies (IAS), University of Malaya, Kuala Lumpur, Malaysia
چکیده English

The stability of curcumin and its encapsulation efficiency in emulsion are among the most important factors determining its bioavailability and absorption in the body. For this purpose, parameters affecting these two factors, including time, pH, and cellulose concentration, were used as input variables in the present study. Curcumin stability and encapsulation efficiency were used as response variables in artificial neural networks and decision tree algorithms. In this regard, cellulose nanocrystal obtained from acid hydrolysis was used to prepare curcumin Pickering emulsion with oil:water ratio of 5:95 and cellulose concentration 1, 1.5, 2, 2.5, and 3% (w/v) and the encapsulation efficiency and stability of curcumin were measured during 8 days. The results showed that the encapsulation efficiency significantly increased as cellulose concentration increased. Encapsulation efficiency at pH 7 was higher than at pH 2 (p≤0.05). The curcumin content in the emulsions prepared at pH 2 drastically decreased during storage, while it was less degraded in emulsions at pH 7 after 8 days of storage. The modelling results for curcumin stability and encapsulation efficiency based on R2 and RMSE% statistics showed that MLP 3-6-1 (R2=0.99; RMSE%=10.00) and RBF 2-6-1 (R2=0.99; RMSE %=9.99) were had more accuracy than other models. Finally, the results showed that the artificial neural network algorithm performed better than the decision tree in predicting cellulose Pickering emulsions' encapsulation efficiency and curcumin stability.

کلیدواژه‌ها English

Artificial neural network (ANN)
Cellulose
Classification and regression tree (CART)
Curcumin
Decision Tree
Pickering emulsion
1. Berton-Carabin, C.C. and K. Schroën, Pickering emulsions for food applications: background, trends, and challenges. Annual review of food science and technology, 2015. 6: p. 263-297.
2. Yu, J., M. Ahmedna, and I. Goktepe, Peanut protein concentrate: Production and functional properties as affected by processing. Food chemistry, 2007. 103(1): p. 121-129.
3. Capron, I. and B. Cathala, Surfactant-free high internal phase emulsions stabilized by cellulose nanocrystals. Biomacromolecules, 2013. 14(2): p. 29-296-1.
4. Miao, C., M.-N. Mirvakili, and W.Y. Hamad, A rheological investigation of oil-in-water Pickering emulsions stabilized by cellulose nanocrystals. Journal of Colloid and Interface Science, 2022. 608: p. 2820-2829.
5. Torlopov, M.A., et al., Pickering emulsions stabilized by partially acetylated cellulose nanocrystals for oral administration: oils effect and in vivo toxicity. Cellulose, 2021. 28(4): p. 2365-2385.
6. Tagde, P., et al., The multifaceted role of curcumin in advanced nanocurcumin form in the treatment and management of chronic disorders. Molecules, 2021. 26(23): p. 7109.
7. Saffarionpour, S. and L.L. Diosady, Curcumin, a potent therapeutic nutraceutical and its enhanced delivery and bioaccessibility by pickering emulsions. Drug Delivery and Translational Research, 2022. 12(1): p. 124-157.
8. Li, Z., et al., The use of bacterial cellulose from kombucha to produce curcumin loaded Pickering emulsion with improved stability and antioxidant properties. Food Science and Human Wellness, 2023. 12 (2): p. 669-679.
9. Fallah, A., et al., Modeling the commercial volume of pure and mixed stands of beech trees using non-parametric algorithms in the educational-research Forest of Darabkola, Sari, Iran. Iranian Journal of Forest and Poplar Research, 2022. 30(2): p. 180-192.
10. Alehosseini, E., S.M. Jafari, and H. Shahiri Tabarestani, Evaluating the performance of artificial neural networks (ANNs) for predicting the physical, rheological, and colorimetric properties of chitosan nanoparticles (CSNPs). Journal of food science and technology(Iran), 2021. 18(113): p. 77-90.
11. Mohebbi, M., M. Fathi, and F. Shahidi, Genetic algorithm–artificial neural network modeling of moisture and oil content of pretreated fried mushroom. Food and Bioprocess Technology, 2011 .4(4): p. 603-609.
12. Cardoso-Daodu, I.M., et al., Artificial neural network for optimizing the formulation of curcumin-loaded liposomes from statistically designed experiments. Progress in Biomaterials, 2022. 11(1): p. 55-65.
13. Pirich, C.L., et al., Influence of mechanical pretreatment to isolate cellulose nanocrystals by sulfuric acid hydrolysis. International journal of biological macromolecules, 2019. 130: p. 622-626.
14. Ngwabebhoh, F.A., S.I. Erdagi, and U. Yildiz, Pickering emulsions stabilized nanocellulosic-based nanoparticles for coumarin and curcumin nanoencapsulations: In vitro release, anticancer and antimicrobial activities. Carbohydrate polymers, 2018. 201: p. 317-328.
15. Kadam, P.V., et al., Standardization and quantification of curcumin from Curcuma longa extract using UV visible spectroscopy and HPLC. Journal of Pharmacognosy and Phytochemistry, 2018. 7(5): p. 1913-1918.
16. Tooke, T.R., et al., Extracting urban vegetation characteristics using spectral mixture analysis and decision tree classifications. Remote Sensing of Environment, 2009. 113(2): p. 398-407.
17. Lawrence, R.L. and A. Wright, Rule-based classification systems using classification and regression tree (CART) analysis. Photogrammetric engineering and remote sensing, 2001. 67(10): p. 1137-1142.
18. Tiryaki, S. and A. Aydın, An artificial neural network model for predicting compression strength of heat treated woods and comparison with a multiple linear regression model. Construction and Building Materials, 2014 (62): p. 102-108.
19. Zheng, B., et al., Impact of delivery system type on curcumin stability: Comparison of curcumin degradation in aqueous solutions, emulsions, and hydrogel beads. Food Hydrocolloids, 2017. 71: p. 187-197.
20. Lu, X. and Q. Huang, Stability and in vitro digestion study of curcumin-encapsulated in different milled cellulose particle stabilized Pickering emulsions. Food & function, 2020. 11(1): p. 606-616.
21. Tikekar, R.V., Y. Pan, and N. Nitin, Fate of curcumin encapsulated in silica nanoparticle stabilized Pickering emulsion during storage and simulated digestion. Food Research International, 2013. 51(1): p. 370-377.
22. Shahkol, F., H. Abbasi, and M. Norouzi Mobarakeh, Modeling the Encapsulation of Thymus Essential Oil (Thymus vulgaris) in Sodium Caseinate, Maltodextrin and Modified Starch Using Response Surface (RSM) and Artificial Neural Network (ANN). Journal of food science and technology(Iran), 2022. 19(125): p. 225-241.
23. Liu, H., et al., Study of Pickering emulsion stabilized by sulfonated cellulose nanowhiskers extracted from sisal fiber. Colloid and Polymer Science, 2015. 293: p. 963-974.
24. Espinosa-Sandoval, L., et al., Phenolic compound–loaded nanosystems: artificial neural network modeling to predict particle size, polydispersity index, and encapsulation efficiency. Food and Bioprocess Technology, 2019. 12(8): p. 1395-1408.
25. Tao, Y., et al., Combining various wall materials for encapsulation of blueberry anthocyanin extracts: Optimization by artificial neural network and genetic algorithm and a comprehensive analysis of anthocyanin powder properties. Powder technology, 2017. 311: p. 77-87.