Computing artificial neural network and genetic algorithm for the feature optimization of basal salts and cytokinin-auxin for in vitro organogenesis of royal purple (Cotinus coggygria Scop)

Abstract

This study presents the in vitro regneration protocol for Royal purple [(Cotinus coggygria Scop. (syn.: Rhus cotinus L.)] from nodal segment explants followed by optimizing the input variable combinations with the aid of PyTorch ANN and Genetic Algorithm (GA). The Murashige and Skoog (MS) culture medium yielded relatively higher regeneration frequency (91.52 %) and shoot count (1.96) as compared to woody plant medium (WPM), which yielded 84.58 % regeneration and shoot count (1.61) per explant. The supplementation of plant growth regulators (PGRs) + MS medium yielded 80.0–100.0 % shoot regeneration and 1.48–3.25 shoot counts compared to 60.0–100.0 % shoot regeneration and 1.00–2.37 shoots from the combination of PGRs + WPM. In order to predict the shoot count and regeneration with the aid of a mathematical model, the machine learning algorithms of Multilayer Perceptron (MLP), Support Vector Regression (SVR), Extreme Gradient Boosting (XGB), and Random Forest (RF) models were utilized. The highest R2 values for both output variables were acquired using MLP model in PyTorch platform. The R2 scores for regeneration and shoot counting were recorded as 0.69 and 0.71 respectively. NSGA-II algorithm revealed the 1.25 mg/L BAP (6-Benzylaminopurine), 0.02 mg/L NAA (Naphthalene acetic acid), and 0.03 mg/L IBA (Indole butyric acid) in WPM medium as an optimum combination for 100 % regeneration. On the other hand, the algorithm suggested multiple combination in MS medium for maximum shoot counting.