Comparative analysis of different artificial neural networks for predicting and optimizing in vitro seed germination and sterilization of petunia

Abstract

The process of optimizing in vitro seed sterilization and germination is a complicated task since this process is influenced by interactions of many factors (e.g., genotype, disinfectants, pH of the media, temperature, light, immersion time). This study investigated the role of various types and concentrations of disinfectants (i.e., NaOCl, Ca(ClO)2, HgCl2, H2O2, NWCN-Fe, MWCNT) as well as immersion time in successful in vitro seed sterilization and germination of petunia. Also, the utility of three artificial neural networks (ANNs) (e.g., multilayer perceptron (MLP), radial basis function (RBF), and generalized regression neural network (GRNN)) as modeling tools were evaluated to analyze the effect of disinfectants and immersion time on in vitro seed sterilization and germination. Moreover, non‑dominated sorting genetic algorithm‑II (NSGA‑II) was employed for optimizing the selected prediction model. The GRNN algorithm displayed superior predictive accuracy in comparison to MLP and RBF models. Also, the results showed that NSGA‑II can be considered as a reliable multi-objective optimization algorithm for finding the optimal level of disinfectants and immersion time to simultaneously minimize contamination rate and maximize germination percentage. Generally, GRNN-NSGA-II as an up-to-date and reliable computational tool can be applied in future plant in vitro culture studies.

Machine learning-mediated Passiflora caerulea callogenesis optimization

“…Traditional approaches to optimizing tissue culture conditions are often time-consuming, resource-intensive, and limited by the complexity of the process [ 18 ]. However, the hybrid approach combines the strengths of MLP-based modeling and GA-driven optimization to streamline the optimization process significantly [ 42 , 58 ]. The hybrid MLP-GA approach presented in this study has proven to be a powerful tool in modeling, predicting, and optimizing the callogenesis process.…”

“…By combining these two approaches, researchers can create a powerful optimization framework to identify optimal combinations of PGRs, nutrient compositions, and other critical factors that influence in vitro culture efficiency [ 18 , 57 ]. The ANN-GA hybrid approach allows for a more systematic and automated exploration of the solution space, leading to improved tissue culture protocols and potentially accelerating the development of desirable plant traits with broader implications for agriculture, horticulture, and biotechnology [ 18 , 53 , 57 , 58 ].…”

Prediction and optimization of indirect shoot regeneration of Passiflora caerulea using machine learning and optimization algorithms

“…GA can significantly reduce reliance on time-consuming and expensive trial-and-error experiments [ 32 ]. The algorithm’s ability to intelligently evolve and refine solutions based on fitness evaluations not only expedites the optimization process but also ensures more consistent and reliable results [ 83 ]. Consequently, GA empowers researchers and plant tissue culture practitioners to efficiently design and implement effective protocols, leading to enhanced plant propagation techniques and expanded biotechnological applications [ 36 ].…”

Optimizing PGRs for in vitro shoot proliferation of pomegranate with bayesian-tuned ensemble stacking regression and NSGA-II: a comparative evaluation of machine learning models

“…ML approaches offer the advantage of autonomous learning and data transformation into useful information without being humanly programmed [17]. Recent studies have highlighted the superior predictive performance of MLs over traditional statistics in various in vitro culture systems, including optimizing culture conditions for shoot proliferation and rooting [10,18,19], androgenesis [20], seed germination [21], somatic embryogenesis [22], gene transformation [23], and enhancing of the secondary metabolite biosynthesis [24].…”

“…NSGA-II enables efficient solving and prediction of complex processes while providing a simplified interpretation of results, simultaneously [30]. In previous studies, the combining approach of ML with NSGA-II (ML-NSGA-II) has been acknowledged as a robust modeling technique for complex datasets, such as in optimizing the protocol of in vitro tissue culture on micropropagation phases [21,31,32] and in various plant science fields [30,33].…”