Predicting and optimizing reactive oxygen species metabolism in Punica granatum L. through machine learning: Role of exogenous GABA on antioxidant enzyme activity under drought and salinity stress

Drought and salinity stress have been proposed as the main environmental factors threatening food security, as they adversely affect crops' agricultural productivity. As a potential solution, the application of plant growth regulators to enhance drought and salinity tolerance has gained considerable attention. y-aminobutyric acid (GABA) is a four-carbon non-protein amino acid that accumulates in plants as a response to stressful conditions. This study focused on a comparative assessment of several machine learning (ML) regression models, including radial basis function, generalized regression neural network (GRNN), random forest (RF), and support vector regression (SVR) to develop predictive models for assessing the effect of different concentrations of GABA (۰, ۱۰, ۲۰, and ۴۰ mM) on various physio-biochemical traits during periods of drought, salinity, and combined stress conditions. The physio-biochemical traits included antioxidant enzyme activities (superoxide dismutase, SOD; peroxidase, POD; catalase, CAT; and ascorbate peroxidase, APX), protein content, malondialdehyde (MDA) levels, and hydrogen peroxide (H۲O۲) levels. The non-dominated sorting genetic algorithm-II (NSGA-II) was employed for optimizing the superior prediction model. The GRNN model outperformed the other ML algorithms and was therefore selected for optimization by NSGA-II. The GRNN-NSGA-II model revealed that treatment with GABA at concentrations of ۲۰.۹۰ mM and ۲۰.۵۴ mM, under combined drought and salinity stress conditions at ۲۰.۸۶ and ۲۰.۷۲ days post-treatment, respectively, could result in the maximum values for protein content (by ۰.۸۰ and ۰.۶۹), APX activity (by ۵۰.۶۳ and ۵۱.۵۱), SOD activity (by ۰.۵۴ and ۰.۵۳), POD activity (by ۱.۵۳ and ۱.۷۲), CAT activity (by ۴.۴۲ and ۵.۶۶), as well as lower MDA levels (by ۰.۱۲ and ۰.۱۵) and H۲O۲ levels (by ۰.۴۴ and ۰.۵۵), respectively, in the 'Atabaki' and 'Rabab' cultivars. This study demonstrates that the GRNN-NSGA-II model, as an advanced ML algorithm with a strong predictive ability for outcomes in combined stressful environmental conditions, provides valuable insights into the significant factors influencing such multifactorial processes.

کلیدواژه ها:

Hydrogen peroxide ، Machine learning ، Malondialdehyde ، Peroxidase ، Optimization tool