The sugar moieties of anthocyanins can be acylated via enzymatic transesterification, which improves their solubility in lipids and enhances their stability to external factors such as light, pH, and high temperatures by inducing structural changes. Process parameters, such as reaction time, temperature, and initial reaction conditions, define the reaction yield. Optimal conditions for the highest conversion yield were investigated during the enzymatic transesterification of a mixture of anthocyanins from Roselle calyx extract, using CAL-B as the catalyst and two acyl donors (methyl palmitate, MP, and vinyl laurate, VL). To model and optimise the reaction conditions, Response Surface Methodology (RSM) and a Variational Autoencoder coupled with an Artificial Neural Network (VAE-ANN) were applied to 15 data points generated using a Circumscribed Centred Composite (CCC) design. ANN was trained on 265 data points (15 experimental and 250 artificially generated using a VAE) and demonstrated better fit and predictive performance than RSM. Experimentally, the maximum conversion yields were 85.69% and 96.73% for VL and MP, respectively, whereas the predicted maximum values were 78.87% and 93.85%, respectively. Optimal conditions were found to be the same experimentally and by prediction for VL, using both RSM and VAE-ANN, whereas for MP, VAE-ANN yielded different conditions. The developed ANN exhibited Root Mean Square Error (RMSE) and Coefficient of Determination (R2) values of 1.60 and 0.98 for MP, and 3.27 and 0.96 for VL, while RSM gave 6.82, 0.93 and 4.10, 0.96, respectively. The optimal conditions for the transesterification of Roselle anthocyanins with VL (RSM, VAE-ANN) and MP (RSM) were 66？C for 54 h 24 min and a substrate-to-enzyme ratio of 6.01. Both optimisation techniques could therefore be used to ensure optimal conditions for achieving the highest reaction yield, but VAE-ANN showed relative superiority to RSM.
References
[1]
Dulęba, J., Czirson, K., Siódmiak, T. and Marszałł, M.P. (2019) Lipase B from Candida Antarctica—The Wide Applicable Biocatalyst in Obtaining Pharmaceutical Compounds. Medical Research Journal, 4, 174-177. https://doi.org/10.5603/mrj.a2019.0030
[2]
Luo, X., Wang, R., Wang, J., Li, Y., Luo, H., Chen, S., et al. (2022) Acylation of Anthocyanins and Their Applications in the Food Industry: Mechanisms and Recent Research Advances. Foods, 11, Article 2166. https://doi.org/10.3390/foods11142166
[3]
Stevenson, D.E., Wibisono, R., Jensen, D.J., Stanley, R.A. and Cooney, J.M. (2006) Direct Acylation of Flavonoid Glycosides with Phenolic Acids Catalysed by Candida Antarctica Lipase B (Novozym 435). Enzyme and Microbial Technology, 39, 1236-1241. https://doi.org/10.1016/j.enzmictec.2006.03.006
[4]
Zeng, S., Lin, S., Jiang, R., Wei, J. and Wang, Y. (2025) Biotechnology Advances in Natural Food Colorant Acylated Anthocyanin Production. Food Frontiers, 6, 698-715. https://doi.org/10.1002/fft2.527
[5]
Mokhtar, N.F., Abd. Rahman, R.N.Z.R., Muhd Noor, N.D., Mohd Shariff, F. and Mohamad Ali, M.S. (2020) The Immobilization of Lipases on Porous Support by Adsorption and Hydrophobic Interaction Method. Catalysts, 10, Article 744. https://doi.org/10.3390/catal10070744
[6]
Ortiz, C., Ferreira, M.L., Barbosa, O., dos Santos, J.C.S., Rodrigues, R.C., Berenguer-Murcia, Á., et al. (2019) Novozym 435: The “Perfect” Lipase Immobilized Biocatalyst? Catalysis Science & Technology, 9, 2380-2420. https://doi.org/10.1039/c9cy00415g
[7]
Saik, A.Y.H., Lim, Y.Y., Stanslas, J. and Choo, W.S. (2017) Enzymatic Synthesis of Quercetin Oleate Esters Using Candida Antarctica Lipase B. Biotechnology Letters, 39, 297-304. https://doi.org/10.1007/s10529-016-2246-5
[8]
Thangaraj, B., Solomon, P.R., Muniyandi, B., Ranganathan, S. and Lin, L. (2019) Catalysis in Biodiesel Production—A Review. Clean Energy, 3, 2-23. https://doi.org/10.1093/ce/zky020
[9]
Uppenberg, J., Hansen, M.T., Patkar, S., and Jones, T.A. (1994) The Sequence, Crystal Structure Determination and Refinement of Two Crystal from Candida antarctica. Structure, 2, 293-308. https://doi.org/10.1016/S0969-2126(00)00031-9
[10]
Chavan, A.S., Kharat, A.S., Bhosle, M.R., Dhumal, S.T. and Mane, R.A. (2022) Novel CAL-B Catalyzed Synthetic Protocols for Pyridodipyrimidines and Mercapto Oxadiazoles. Journal of Chemical Sciences, 134, Article No. 120. https://doi.org/10.1007/s12039-022-02116-3
[11]
Elliot, S.G., Andersen, C., Tolborg, S., Meier, S., Sádaba, I., Daugaard, A.E., et al. (2017) Synthesis of a Novel Polyester Building Block from Pentoses by Tin-Containing Silicates. RSC Advances, 7, 985-996. https://doi.org/10.1039/c6ra26708d
[12]
Passicos, E., Santarelli, X. and Coulon, D. (2004) Regioselective Acylation of Flavonoids Catalyzed by Immobilized Candida Antarctica Lipase under Reduced Pressure. Biotechnology Letters, 26, 1073-1076. https://doi.org/10.1023/b:bile.0000032967.23282.15
[13]
Hedfors, C., Hult, K. and Martinelle, M. (2010) Lipase Chemoselectivity towards Alcohol and Thiol Acyl Acceptors in a Transacylation Reaction. Journal of Molecular Catalysis B: Enzymatic, 66, 120-123. https://doi.org/10.1016/j.molcatb.2010.04.005
[14]
Tindal, R.A., Jeffery, D.W. and Muhlack, R.A. (2024) Nonlinearity and Anthocyanin Colour Expression: A Mathematical Analysis of Anthocyanin Association Kinetics and Equilibria. Food Research International, 183, Article 114195. https://doi.org/10.1016/j.foodres.2024.114195
[15]
Ware, K., Kashyap, P., Gorde, P.M., Yadav, R. and Sharma, V. (2025) Comparative Analysis of RSM and ANN-GA Based Modeling for Protein Extraction from Cotton Seed Meal: Effect of Extraction Parameters on Amino Acid Profile and Nutritional Characteristics. Food and Bioproducts Processing, 150, 63-77. https://doi.org/10.1016/j.fbp.2024.12.016
[16]
Yang, T., Lai, H., Cao, Z., Niu, Y., Xiang, J., Zhang, C., et al. (2022) Comparison of an Artificial Neural Network and a Response Surface Model during the Extraction of Selenium-Containing Protein from Selenium-Enriched Brassica napus L. Foods, 11, Article 3823. https://doi.org/10.3390/foods11233823
[17]
Baş, D. and Boyacı, İ.H. (2007) Modeling and Optimization II: Comparison of Estimation Capabilities of Response Surface Methodology with Artificial Neural Networks in a Biochemical Reaction. Journal of Food Engineering, 78, 846-854. https://doi.org/10.1016/j.jfoodeng.2005.11.025
[18]
Blanco, M., Coello, J., Iturriaga, H., Maspoch, S. and Porcel, M. (1999) Simultaneous Enzymatic Spectrophotometric Determination of Ethanol and Methanol by Use of Artificial Neural Networks for Calibration. Analytica Chimica Acta, 398, 83-92. https://doi.org/10.1016/s0003-2670(99)00373-6
[19]
Bryjak, J., Murlikiewicz, K., Zbiciński, I. and Stawczyk, J. (2000) Application of Artificial Neural Networks to Modelling of Starch Hydrolysis by Glucoamylase. Bioprocess Engineering, 23, 351-357. https://doi.org/10.1007/s004499900170
[20]
Geeraerd, A.H., Herremans, C.H., Ludikhuyze, L.R., Hendrickx, M.E. and Van Impe, J.F. (1998) Modeling the Kinetics of Isobaric-Isothermal Inactivation of Bacillus Subtilis α-Amylase with Artificial Neural Networks. Journal of Food Engineering, 36, 263-279. https://doi.org/10.1016/s0260-8774(98)00064-8
[21]
Manohar, B. and Divakar, S. (2005) An Artificial Neural Network Analysis of Porcine Pancreas Lipase Catalysed Esterification of Anthranilic Acid with Methanol. Process Biochemistry, 40, 3372-3376. https://doi.org/10.1016/j.procbio.2005.03.045
[22]
Talebian-Kiakalaieh, A., Amin, N.A.S., Zarei, A. and Noshadi, I. (2013) Transesterification of Waste Cooking Oil by Heteropoly Acid (HPA) Catalyst: Optimization and Kinetic Model. Applied Energy, 102, 283-292. https://doi.org/10.1016/j.apenergy.2012.07.018
[23]
Wang, Z., Duan, H. and Hu, C. (2009) Modelling the Respiration Rate of Guava (Psidium guajava L.) Fruit Using Enzyme Kinetics, Chemical Kinetics and Artificial Neural Network. European Food Research and Technology, 229, 495-503. https://doi.org/10.1007/s00217-009-1079-z
[24]
Wei, S., Chen, Z., Arumugasamy, S.K. and Chew, I.M.L. (2022) Data Augmentation and Machine Learning Techniques for Control Strategy Development in Bio-Polymerization Process. Environmental Science and Ecotechnology, 11, Article 100172. https://doi.org/10.1016/j.ese.2022.100172
[25]
Moreno-Barea, F.J., Jerez, J.M. and Franco, L. (2020) Improving Classification Accuracy Using Data Augmentation on Small Data Sets. Expert Systems with Applications, 161, Article 113696. https://doi.org/10.1016/j.eswa.2020.113696
[26]
Shorten, C. and Khoshgoftaar, T.M. (2019) A Survey on Image Data Augmentation for Deep Learning. Journal of Big Data, 6, Article No. 60. https://doi.org/10.1186/s40537-019-0197-0
[27]
Ohno, H. (2020) Auto-Encoder-Based Generative Models for Data Augmentation on Regression Problems. Soft Computing, 24, 7999-8009. https://doi.org/10.1007/s00500-019-04094-0
[28]
Rezagholiradeh, M. and Haidar, M.A. (2018) Reg-Gan: Semi-Supervised Learning Based on Generative Adversarial Networks for Regression. 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, 15-20 April 2018, 2806-2810. https://doi.org/10.1109/icassp.2018.8462534
[29]
Segura-Carretero, A., Puertas-Mejía, M.A., Cortacero-Ramírez, S., Beltrán, R., Alonso-Villaverde, C., Joven, J., et al. (2008) Selective Extraction, Separation, and Identification of Anthocyanins from Hibiscus sabdariffa L. Using Solid Phase Extraction-Capillary Electrophoresis-Mass Spectrometry (Time-of-Flight/Ion Trap). Electrophoresis, 29, 2852-2861. https://doi.org/10.1002/elps.200700819
[30]
Rodríguez-Medina, I.C., Beltrán-Debón, R., Molina, V.M., Alonso-Villaverde, C., Joven, J., Menéndez, J.A., et al. (2009) Direct Characterization of Aqueous Extract of Hibiscus sabdariffa Using HPLC with Diode Array Detection Coupled to ESI and Ion Trap MS. Journal of Separation Science, 32, 3441-3448. https://doi.org/10.1002/jssc.200900298
[31]
Omotuyi, I.O., Elekofehinti, O.O., Ejelonu, O.C. and Obi, F.O. (2013) Mass Spectra Analysis of H. sabdariffa L. Anthocyanidins and Their In-Silico Corticosteroid-Binding Globulin Interactions. Pharmacology Online. Archives, 1, 206-217.
[32]
Yang, W., Kortesniemi, M., Ma, X., Zheng, J. and Yang, B. (2019) Enzymatic Acylation of Blackcurrant (Ribes nigrum) Anthocyanins and Evaluation of Lipophilic Properties and Antioxidant Capacity of Derivatives. Food Chemistry, 281, 189-196. https://doi.org/10.1016/j.foodchem.2018.12.111
[33]
Chebil, L., Humeau, C., Falcimaigne, A., Engasser, J. and Ghoul, M. (2006) Enzymatic Acylation of Flavonoids. Process Biochemistry, 41, 2237-2251. https://doi.org/10.1016/j.procbio.2006.05.027
[34]
Martinelle, M., Holmquist, M. and Hult, K. (1995) On the Interfacial Activation of Candida Antarctica Lipase A and B as Compared with Humicola Lanuginosa Lipase. Biochimica et Biophysica Acta—Lipids and Lipid Metabolism, 1258, 272-276. https://doi.org/10.1016/0005-2760(95)00131-u
[35]
Enaud, E., Humeau, C., Piffaut, B. and Girardin, M. (2004) Enzymatic Synthesis of New Aromatic Esters of Phloridzin. Journal of Molecular Catalysis B: Enzymatic, 27, 1-6. https://doi.org/10.1016/j.molcatb.2003.08.002
[36]
Turner, N.A. and Vulfson, E.N. (2000) At What Temperature Can Enzymes Maintain Their Catalytic Activity? Enzyme and Microbial Technology, 27, 108-113. https://doi.org/10.1016/s0141-0229(00)00184-8
[37]
Coulon, D., Girardin, M., Engasser, J.M. and Ghoul, M. (1997) Investigation of Keys Parameters of Fructose Oleate Enzymatic Synthesis Catalyzed by an Immobilized Lipase. Industrial Crops and Products, 6, 375-381. https://doi.org/10.1016/s0926-6690(97)00028-9
[38]
Cao, L., Bornscheuer, U.T. and Schmid, R.D. (1999) Lipase-Catalyzed Solid-Phase Synthesis of Sugar Esters. Influence of Immobilization on Productivity and Stability of the Enzyme. Journal of Molecular Catalysis B: Enzymatic, 6, 279-285. https://doi.org/10.1016/s1381-1177(98)00083-6
[39]
Chamouleau, F., Coulon, D., Girardin, M. and Ghoul, M. (2001) Influence of Water Activity and Water Content on Sugar Esters Lipase-Catalyzed Synthesis in Organic Media. Journal of Molecular Catalysis B: Enzymatic, 11, 949-954. https://doi.org/10.1016/s1381-1177(00)00166-1
[40]
Awolusi, T.F., Oke, O.L., Akinkurolere, O.O. and Atoyebi, O.D. (2019) Comparison of Response Surface Methodology and Hybrid-Training Approach of Artificial Neural Network in Modelling the Properties of Concrete Containing Steel Fibre Extracted from Waste Tyres. Cogent Engineering, 6, 1-18. https://doi.org/10.1080/23311916.2019.1649852
[41]
Nazerian, M., Kamyabb, M., Shamsianb, M., Dahmardehb, M. and Kooshaa, M. (2018) Comparison of Response Surface Methodology (RSM) and Artificial Neural Networks (ANN) towards Efficient Optimization of Flexural Properties of Gypsum-Bonded Fiberboards. CERNE, 24, 35-47. https://doi.org/10.1590/01047760201824012484
[42]
Optimization of Fermentation Medium Components by Response Surface Methodology (RSM) and Artificial Neural Network Hybrid with Genetic Algorithm (ANN-GA) for Lipase Production by Burkholderia Cenocepacia ST8 Using Used Automotive Engine Oil as Substrate. Biocatalysis and Agricultural Biotechnology, 50, Article 102696. https://doi.org/10.1016/j.bcab.2023.102696
