Enhancing genomic diversity for climate-resilient crops and their phytoecosystems, by engaging AI and genome editing

Advances in plant genomics are rapidly transforming the landscape of crop improvement. The emergence of pangenomics and progress in genotyping for genetic diversity analysis have revealed the full spectrum of variation within and across crop species, providing unprecedented insight into allelic and regulatory diversity. At the same time, artificial intelligence (AI) and machine learning (ML) tools enable data-driven prediction of complex genotype × environment interactions. Precision genome editing technologies, such as CRISPR-based methods, are redefining how breeders can manipulate key loci and regulatory networks. The convergence of these approaches presents a unique opportunity to design crops with enhanced resilience, productivity, and sustainability under changing climate conditions. We particularly encourage studies integrating plant genomic variation with symbiont and metagenomic data (e.g., rhizosphere/phyllosphere microbiomes, mycorrhizae, endophytes) to elucidate plant–microbe–environment interactions underpinning resilience and ecosystem services.This Research Topic aims to explore pangenomic diversity to accelerate the development of climate-resilient crops by engaging AI-driven analytics, and genome editing approaches. Despite major genomic advances, translating genetic variation into usable breeding outcomes remains a significant challenge. By exploiting the comprehensive allelic variation revealed by pangenomes and the genetic diversity captured through high-throughput genotyping, combined with predictive AI models, breeders might more effectively identify and prioritize genes and alleles associated with tolerance to heat, drought, and salinity, as well as improved yield stability and nutrient-use efficiency. In parallel, genome editing technologies such as CRISPR-based methods offer precise and efficient tools to fine-tune adaptive traits associated with environmental resilience. The overarching goal is to establish an integrated, breeding-by-design framework capable of predicting, selecting, and engineering crop genotypes with enhanced stability and adaptability to future climate scenarios, while accounting for phytoecosystem dynamics and plant–symbiont interactions where relevant.This Research Topic welcomes original research articles, reviews, and perspectives focusing on pangenomics, AI/machine learning, and genome editing for crop improvement. Areas of interest include (but are not limited to): pangenome construction and analysis; identification of adaptive alleles from wild relatives; AI-based genomic prediction and explainable models for genotype × environment interactions; CRISPR-based precision breeding; and multi-omics integration for trait dissection. We particularly welcome work that links genomic findings to mechanistic insights, including chromatin and epigenomic regulation of stress responses, structural variation and chromosome dynamics revealed by pangenomes, the roles of non-coding RNAs, and RNA processing in adaptation. Studies that integrate metagenomic or community-level data (e.g., plant-associated microbiomes and symbiont genomes) to analyze plant–microbe interactions within the phytoecosystem are encouraged.Contributions addressing methodological innovations, computational pipelines, or comparative and evolutionary analyses (e.g., selection scans, domestication trajectories, structural variant evolution) across taxa are encouraged, provided they include comprehensive analysis beyond single-species gene-family catalogs. Organellar genome analyses should be integrated with nuclear genomic responses and phytoecologic context to be considered. Studies focused solely on quality traits, nutritional aspects, or soil quality must include a fundamental plant genomics basis and integration with broader phytoecosystem dynamics.Rigor and reproducibility expectations:o AI/ML: Clearly describe data partitioning (train/validation/test), prevent information leakage, report performance with appropriate metrics, include external or cross-environment validation where possible, and provide model interpretability/explainability.o Experimental design: Use widely accepted standards for biological replication and statistical analysis; validate genotype–phenotype associations across environments or populations when feasible.This Topic advances SDG 2 (Zero Hunger) through resilient, productive crops; SDG 13 (Climate Action) by addressing adaptation to climatic stressors; and SDG 15 (Life on Land) by leveraging wild relatives, biodiversity, and plant–symbiont interactions that support ecosystem services. Topic editors: Nunzio D'Agostino, Francesca Taranto Source: https://www.frontiersin.org/research-topics/75823/enhancing-genomic-diversity-for-climate-resilient-crops-and-their-phytoecosystems-by-engaging-ai-and-genome-editing