This review discusses the potential of artificial intelligence (AI), particularly machine learning (ML) and its subset, deep learning (DL), in advancing the genetic improvement of Solanaceous crops. AI has emerged as a powerful solution to overcome the limitations of traditional breeding techniques, which often involve time-consuming, resource-intensive processes with limited predictive accuracy. Through advanced algorithms and predictive models, ML and DL facilitate the identification and optimization of key traits, including higher yield, improved quality, pest resistance, and tolerance to extreme climatic conditions. By integrating big data analytics and omics, these methods enhance genomic selection (GS), support gene-editing technologies like CRISPR-Cas9, and accelerate crop breeding, thus enabling the development of resilient and adaptable crops. This review highlights the role of ML and DL in improving Solanaceae crops, such as tomato, potato, eggplant, and pepper, with the aim of developing novel varieties with superior agronomic and quality traits. Additionally, this study examines the advantages and limitations of AI-driven breeding compared to traditional methods in Solanaceae, emphasizing its contribution to agricultural resilience, food security, and environmental sustainability.

Within the framework of preserving and valorizing the rich grapevine germplasm of the Epirus region of Greece, indigenous grapevine (Vitis vinifera L.) cultivars were characterized and assessed for their resilience to abiotic stresses in the context of climate change. The cultivars ‘Debina’ and ‘Dichali’ displayed significant differences in their response to drought stress as judged by morpho-physiological analysis, indicating higher drought tolerance for Dichali. Hence, they were selected for further study aiming to identify genetic and epigenetic mechanisms possibly regulating drought adaptability. Specifically, self-rooted and heterografted on ‘Richter 110’ rootstock plants were subjected to two phases of drought with a recovery period in between. Gene expression analysis was performed for two stress-related miRNAs and their target genes: (a) miRNA159 and putative targets, VvMYB101, VvGATA-26-like, VvTOPLESS-4-like and (b) miRNA156 and putative target gene VvCONSTANS-5. Overall, grafted plants exhibited a higher drought tolerance than self-rooted plants, suggesting beneficial rootstock–scion interactions. Comparative analysis revealed differential gene expression under repetitive drought stresses between the two cultivars as well as between the self-rooted and grafted plants. ‘Dichali’ exhibited an up-regulation of most of the genes examined, which may be associated with increased tolerance. Nevertheless, the profound down-regulation of VvTOPLESS-4-like (a transcriptional co-repressor of transcription factors) upon drought and the concomitant up-regulation of miRNA159 highlights the importance of this ‘miRNA-target’ module in drought responsiveness. DNA methylation profiling using MSAP analysis revealed differential methylation patterns between the two genotypes in response to drought. Further investigations of gene expression and DNA methylation will contribute to our understanding of the epigenetic mechanisms underlying grapevine tolerance to drought stress.

Anastasios Katsileros, Nikolaos Antonetsis, Paschalis Mouzaidis, Eleni Tani, Penelope J. Bebeli, Alex Karagrigoriou. CSAM 2024;31:1-35. https://doi.org/10.29220/CSAM.2024.31.1.001

Wood-boring insect pests pose a significant threat to orchards, potentially leading to tree mortality. In the initial stages of infestation, no visible symptoms are apparent, but as infestations progress, rapid and widespread symptoms emerge, resulting in accelerated tree decline. Therefore, the timely detection of early wood-boring insect symptoms is critical for effective pest control, necessitating advanced methods such as remote sensing. In this study, remote sensing is utilized to identify the early symptoms of peach flatheaded root borer (PFRB) infestation in trees. A multispectral sensor attached to a UAV captures aerial imagery data from stone fruit and pome fruit orchards. These data undergo processing in photogrammetric and GIS programs, where NDVI, NDRE, and the tree crown area are computed. On-site observations confirm PFRB infestations. Various machine-learning models, including logistic regression (LR), artificial neural network (NN), random forest (RF), and extreme gradient boosting (XGBoost), are compared using mean NDVI values, mean NDRE values, crown area, mean temperature, and mean relative humidity. Mean NDVI values emerge as the most crucial factor for predicting PFRB infestation across all machine-learning models. The XGBoost model proves the most effective, achieving an accuracy of 0.85, with marginal variations from the other tested models.

In this study, three pea varieties (Pisum sativum), including one field pea variety ‘Dodoni’, and two varieties of garden peas ‘Early Onward’ and ‘Rondo’, were irradiated with 100 Gy gamma rays. The irradiated seeds were then cultivated in the experimental field of the Plant Breeding and Agricultural Experimentation Laboratory of the Agricultural University of Athens, in the period of 2021–2022, affording them the chance to reveal their full potential under natural environmental conditions. The M1 generation plants were compared to non-irradiated plants in terms of their agro-morphological traits. The results indicate a statistically significant difference on several traits: plant height, plant weight, dry biomass, pod length, and the number of seeds per pod. On the other hand, no significant difference was detected in: plant growth rate, the number of shoots and leaves per plant, pods and seed yield per plant, and 1000-seed weight. However, the three pea varieties did not seem to respond in the same way. The M1 generation plants of the two garden pea varieties (‘Early Onward’ and ‘Rondo’) showed a shorter plant height and pod length than their corresponding non-irradiated plants. Likewise, the number of seeds per pod for both ‘Early Onward’ and ‘Dodoni’ was lower for the mutant plants than it was for the plants used as the control. In contrast, mutant plants of the ‘Dodoni’ variety indicated a greater plant weight and dry biomass per plant compared to non-irradiated plants. Finally, the correlation found between agronomic traits was the same regardless of the treatment (control and mutant plants). The number of seeds per plant indicated a positive correlation with the pods per plant and plant weight. Similarly, the dry biomass was positively correlated with plant weight, while being negatively correlated with pod length. Thus, the results obtained in the present study clearly indicate that there were differences between seeds irradiated with gamma rays and non-irradiated seeds in terms of their overall performance and various quantitative pea traits, which should to be further investigated in M2 and the following generations. Peas have gathered a significant market interest and demand. Given their narrow genetic base, we employed gamma irradiation technology, which can be effectively integrated with omics technologies in future generations. This study underscores the necessity to explore performance characteristics and integrate them with quality traits. Our findings reveal that each generation exhibits unique attributes, and specifically, provide a valuable foundation for identifying valuable characteristics for future breeding programs.