Background: Optimizing the somatic embryogenesis protocol can be considered as the first and foremost step in successful gene transformation studies. However, it is usually difficult to achieve an optimized embryogenesis protocol due to the cost and time-consuming as well as the complexity of this process. Therefore, it is necessary to use a novel computational approach, such as machine learning algorithms for this aim. In the present study, two machine learning algorithms, including Multilayer Perceptron (MLP) as an artificial neural network (ANN) and support vector regression (SVR), were employed to model somatic embryogenesis of chrysanthemum, as a case study, and compare their prediction accuracy. Results: The results showed that SVR (R² > 0.92) had better performance accuracy than MLP (R² > 0.82). Moreover, the Non-dominated Sorting Genetic Algorithm-II (NSGA-II) was also applied for the optimization of the somatic embryogenesis and the results showed that the highest embryogenesis rate (99.09%) and the maximum number of somatic embryos per explant (56.24) can be obtained from a medium containing 9.10 μM 2,4-dichlorophenoxyacetic acid (2,4-D), 4.70 μM kinetin (KIN), and 18.73 μM sodium nitroprusside (SNP). According to our results, SVR-NSGA-II was able to optimize the chrysanthemum’s somatic embryogenesis accurately. Conclusions: SVR-NSGA-II can be employed as a reliable and applicable computational methodology in future plant tissue culture studies.

Abiotic stresses limit the quantity and quality of rice grain production, which is considered a strategic crop in many countries. In this study, a meta-analysis of different microarray data at seedling stage was performed to investigate the effects of multiple abiotic stresses (drought, salinity, cold situation, high temperature, alkali condition, iron, aluminum, and heavy metal toxicity, nitrogen, phosphorus, and potassium deficiency) on rice. Comparative analysis between multiple abiotic stress groups and their control groups indicated 561 differentially expressed genes (DEGs), among which 422 and 139 genes were up-regulated and down-regulated, respectively. Gene Ontology analysis showed that the process of responding to stresses and stimuli was significantly enriched. In addition, pathways such as metabolic process and biosynthesis of secondary metabolites were identified by KEGG pathway analysis. Weighted correlation network analysis (WGCNA) uncovered 17 distinct co-expression modules. Six modules were significantly associated with genes involved in response to abiotic stresses. Finally, to validate the results of the meta-analysis, five genes, including TIFY9 (JAZ5), RAB16B, ADF3, Os01g0124650, and Os05g0142900 selected for qRT-PCR analysis. Expression patterns of selected genes confirmed the results of the meta-analysis. The outcome of this study could help introduce candidate genes that may be beneficial for use in genetic engineering programs to produce more tolerant crops or as markers for selection.

Fusarium head blight (FHB) is a devastating fungal disease affecting different cereals, particularly wheat, and poses a serious threat to global wheat production. Chitinases and β-glucanases are two important proteins involved in lysing fungal cell walls by targeting essential macromolecular components, including chitin and β-glucan micro fibrils. In our experiment, a transgenic wheat (Triticum aestivum) was generated by introducing chitinase and glucanase genes using Biolistic technique and Recombinant pBI121 plasmid (pBI-ChiGlu (-)). This plasmid contained chitinase and glucanase genes as well as nptII gene as a selectable marker. The expression of chitinase and glucanase was individually controlled by CaMV35S promoter and Nos terminator. Immature embryo explants from five Iranian cultivars (Arta, Moghan, Sisun, Gascogen and A-Line) were excised from seeds and cultured on callus induction medium to generate embryonic calluses. Embryogenic calluses with light cream color and brittle texture were selected and bombarded using gold nanoparticles coated with the recombinant pBI-ChiGlu plasmid. Bombarded calluses initially were transferred to selective callus induction medium, and later, they were transfferd to selective regeneration medium. The selective agent was kanamycin at a concentration of 25 mg/l in both media. Among five studied cultivars, A-Line showed the highest transformation percentage (4.8%), followed by the Sisun, Gascogen and Arta in descending order. PCR and Southern blot analysis confirmed the integration of genes into the genome of wheat cultivars. Furthermore, in an in-vitro assay, the growth of Fusarium graminearum was significantly inhibited by using 200 μg of leaf protein extract from transgenic plants. According to our results, the transgenic plants (T₁) showed the resistance against Fusarium when were compared to the non-transgenic plants. All transgenic plants showed normal fertility and no abnormal response was observed in their growth and development.