Modeling and Optimizing Medium Composition for Shoot Regeneration of Chrysanthemum via Radial Basis Function-Non-dominated Sorting Genetic Algorithm-II (RBF-NSGAII)

Abstract

The aim of the current study was modeling and optimizing medium compositions for shoot proliferation of chrysanthemum, as a case study, through radial basis function- non-dominated sorting genetic algorithm-II (RBF-NSGAII). RBF as one of the artificial neural networks (ANNs) was used for modeling four outputs including proliferation rate (PR), shoot number (SN), shoot length (SL), and basal callus weight (BCW) based on four variables including 6-benzylaminopurine (BAP), indole-3-butyric acid (IBA), phloroglucinol (PG), and sucrose. Afterward, models were linked to the optimization algorithm. Also, sensitivity analysis was applied for evaluating the importance of each input. The R2 correlation values of 0.88, 0.91, 0.97, and 0.76 between observed and predicted data were obtained for PR, SN, SL, and BCW, respectively. According to RBF-NSGAII, optimal PR (98.85%), SN (13.32), SL (4.83 cm), and BCW (0.08 g) can be obtained from a medium containing 2.16 µM BAP, 0.14 µM IBA, 0.29 mM PG, and 87.63 mM sucrose. The results of sensitivity analysis indicated that PR, SN, and SL were more sensitive to BAP, followed by sucrose, PG, and IBA. Finally, the performance of predicted and optimized medium compositions were tested, and results showed that the difference between the validation data and RBF-NSGAII predicted and optimized data were negligible. Generally, RBF-NSGAII can be considered as an efficient computational strategy for modeling and optimizing in vitro organogenesis.

Mathematical Modeling of Growth and Paclitaxel Biosynthesis in Corylus avellana Cell Culture Responding to Fungal Elicitors Using Multilayer Perceptron-Genetic Algorithm

“…It processes information and makes decision in systems involving vagueness and uncertainty ( Patnaik, 1999 ; Gago et al, 2010 ). This technology has been widely used as a predictive instrument in a broad range of fields including ecology, food science, agriculture, environmental sciences, plant biology, pharmaceutical research, and biotechnology ( Hilbert and Ostendorf, 2001 ; Daniel et al, 2008 ; Huang, 2009 ; Arab et al, 2018 ; Hesami et al, 2019a ; Hesami et al, 2019b ; Hesami et al, 2019c ; Sheikhi et al, 2020 ). Multilayer perceptron (MLP), one of the most popular types of ANN, exhibits superior predictive ability as compared to traditional statistical methods to approximate the mathematical functions for analyzing and interpreting different unforeseeable data sets ( Ahmadi and Golian, 2011 ; Jamshidi et al, 2016 ).…”

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

“…Mathematical optimization has been successfully used in plant science [ 19 , 49 , 51 – 53 ]. Genetic algorithm (GA) as a robust optimizing tool has been successfully used to optimize culture medium composition for pear rootstock proliferation [ 37 , 38 ], in vitro rooting of Prunus rootstock [ 54 ] and melon differentiation [ 55 ].…”

Natural Variation in Plant Pluripotency and Regeneration

“…Machine learning algorithms provide a complementary prospect for fine-tuning protocol development, as they allow to predict optimal requirements in terms of incubation conditions, plant growth regulators, explant source, and genotype, without the need for large-scale, time-consuming, and costly experimental trials. The potential of this approach is illustrated by recent reports on the application of artificial neural networks to model and augment somatic embryogenesis and shoot proliferation in Chrysanthemum and shoot regeneration in wheat by altering medium composition [ 177 , 178 , 179 ]. Similar strategies have been used to increase the production of therapeutic metabolites from in vitro cultures of Swertia paniculata and Bryophyllum [ 180 , 181 ].…”