During the last two decades, human has increased his knowledge about the role of miRNAs and their target genes in plant stress response. Biotic and abiotic stresses result in simultaneous tissue-specific up/down-regulation of several miRNAs. In this study, for the first time, feature selection algorithms have been used to investigate the contribution of individual plant miRnAs in Arabidopsis thaliana response towards different levels of several abiotic stresses including drought, salinity, cold, and heat. Results of information theory-based feature selection revealed that miRNA-169, miRNA-159, miRNA-396, and miRNA-393 had the highest contributions to plant response towards drought, salinity, cold, and heat, respectively. Furthermore, regression models, i.e., decision tree (DT), support vector machines (SVMs), and Naïve Bayes (NB) were used to predict the plant stress by having the plant miRNAs' concentration. SVM with Gaussian kernel was capable of predicting plant stress (R 2 = 0.96) considering miRnA concentrations as input features. findings of this study prove the performance of machine learning as a promising tool to investigate some aspects of miRnAs' contribution to plant stress responses that have been undiscovered until today. microRNAs (miRNAs) are small single-stranded RNAs with low protein-coding potential 1. Although plant miR-NAs target only a small number of mRNAs (<1%) 2 , the role of miRNA-controlled gene regulation in plants cannot be neglected because most of the target mRNAs participate in most plant developmental processes 3,4. Furthermore, there are evidences showing the relationships between plant stress responses and changes in miR-NAs' expression 5,6. miRNAs are known as negative post-transcription regulators since they exert specific binding to their target mRNAs or repressing target mRNA translation 7-9. Among the major plant abiotic stress sources, drought, salinity, cold, heat, ultraviolet irradiation, carbon dioxide, and heavy metal pollution have significant effects on plant morphological, physiological, and biochemical characteristics 10,11. To adapt and survive under stress conditions, plants exert miRNA up/down-regulation which results in gene expression reprogramming to restore cellular homeostasis 12,13. Plant miRNA expression towards stress is generally spatial (plant tissue) and temporal (developmental/growth stage) specific 4,14. With the identification of stress-responsive miRNAs, useful information on their role in improving the stress tolerance mechanism of plants can be obtained. A search in bibliographic resources reveals that hundreds of research studies have been dedicated to the changes in plant miRNA expression in response to biotic and abiotic stresses. A large part of these studies has focused on Arabidopsis thaliana, Brachypodium distachyon, Glycine max, Hordeum vulgare, Medicago truncatula, Manihot esculenta, Phaseolus vulgaris, Populus euphratica, Populus trichocarpa, Populus tremula, Triticum turgidum, Oryza sativa, Vigna unguiculate, and Zea mays 15. Studies ...
