Modeling of paclitaxel biosynthesis elicitation in Corylus avellana cell culture using adaptive neuro-fuzzy inference system-genetic algorithm (ANFIS-GA) and multiple regression methods

Paclitaxel as a microtubule-stabilizing agent is widely used for the treatment of a vast range of cancers. Corylus avellana cell suspension culture (CSC) is a promising strategy for paclitaxel production. Elicitation of paclitaxel biosynthesis pathway is a key approach for improving its production in cell culture. However, optimization of this process is time-consuming and costly. Modeling of paclitaxel elicitation process can be helpful to predict the optimal condition for its high production in cell culture. The objective of this study was modeling and forecasting paclitaxel biosynthesis in C. avellana cell culture responding cell extract (CE), culture filtrate (CF) and cell wall (CW) derived from endophytic fungus, either individually or combined treatment with methyl-β-cyclodextrin (MBCD), based on four input variables including concentration levels of fungal elicitors and MBCD, elicitor adding day and CSC harvesting time, using adaptive neuro-fuzzy inference system (ANFIS) and multiple regression methods. The results displayed a higher accuracy of ANFIS models (0.94–0.97) as compared to regression models (0.16–0.54). The great accordance between the predicted and observed values of paclitaxel biosynthesis for both training and testing subsets support excellent performance of developed ANFIS models. Optimization process of developed ANFIS models with genetic algorithm (GA) showed that optimal MBCD (47.65 mM) and CW (2.77% (v/v)) concentration levels, elicitor adding day (16) and CSC harvesting time (139 h and 41 min after elicitation) can lead to highest paclitaxel biosynthesis (427.92 μg l(-1)). The validation experiment showed that ANFIS-GA method can be a promising tool for selecting the optimal conditions for maximum paclitaxel biosynthesis, as a case study.