Author(s)

Marie Liliane Mouto Kalla^1,2*, Guifo Joseph Kayem¹, Emmanuel Jong Nso¹, Bineesh Prakasan Nisha²

¹Department of Process Engineering, National School of Agro-Industrial Sciences (NSAIS), University of Ngaoundéré, Ngaoundéré, Cameroon.
²Department of Agro-Processing and Natural Product, National Institute for Interdisciplinary Science and Technology (NIIST), Trivandrum, India.

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.

Hibiscus Sabdariffa, Anthocyanins, Optimum Transesterification Conditions, RSM, VAE-ANN

Kalla, M. , Kayem, G. , Nso, E. and Nisha, B. (2026) Ensuring Optimum Conditions for the Enzymatic Transesterification of Anthocyanin Mixture from Roselle (Hibiscus sabdariffa L.) Calyx Using RSM and ANN. Advances in Bioscience and Biotechnology, 17, 62-79. doi: 10.4236/abb.2026.172005.