Predicting In vitro Culture Medium Macro-Nutrients Composition for Pear Rootstocks Using Regression Analysis and...

Area of Science:

• Plant Biotechnology
• Agricultural Science
• Computational Biology

Background:

• In vitro propagation of pear rootstocks (OHF and Pyrodwarf) is crucial for horticulture.
• Optimizing media macronutrients is essential for successful plant tissue culture.
• Predictive modeling can enhance the efficiency of determining optimal culture conditions.

Purpose of the Study:

• To predict the impact of medium macronutrients on in vitro performance of pear rootstocks.
• To compare the predictive accuracy of artificial neural network-genetic algorithm (ANN-GA) and stepwise regression analysis.
• To identify optimal macronutrient concentrations for enhanced explant growth parameters.

Main Methods:

• Employed artificial neural network-genetic algorithm (ANN-GA) and stepwise regression analysis for modeling.
• Investigated eight macronutrients (nitrate, ammonium, calcium, potassium, magnesium, phosphate, sulfate, chloride) and their effect on explant growth.
• Assessed growth parameters including proliferation rate (PR), shoot length (SL), shoot tip necrosis (STN), chlorosis (Chl), and vitrification (Vitri).

Main Results:

• ANN-GA demonstrated substantially higher prediction accuracy compared to regression models.
• Identified key macronutrients influencing specific growth parameters for both OHF and Pyrodwarf rootstocks.
• Determined optimal media compositions (in mM) for achieving maximum PR in OHF (e.g., 62.5 NO3-, 5.7 NH4+) and Pyrodwarf (e.g., 25.6 NO3-, 13.1 NH4+).

Conclusions:

• ANN-GA is a powerful tool for optimizing plant tissue culture media.
• Specific macronutrient profiles are critical for maximizing in vitro performance of pear rootstocks.
• The study provides precise recommendations for media formulation to improve pear rootstock propagation.