Agricultural Multi-Omics through Artificial Intelligence and Machine Learning

Agriculture is undergoing a profound transformation driven by advances in high-throughput sequencing technologies and artificial intelligence. The increased availability of genomic, transcriptomic, and other multi-omics data across numerous agriculturally important species is generating voluminous information that exceed the capabilities of conventional analytical approaches. Machine learning (ML) and AI-based methods are emerging as pivotal tools to decipher complex genotype–phenotype relationships, enabling the prediction of agronomic traits, the discovery of adaptive alleles, and the design of improved crop varieties suited for a changing climate. Despite recent achievements, challenges persist in integrating heterogeneous datasets, improving model interpretability, and translating computational discoveries into practical breeding outcomes. Current studies have demonstrated the potential of ML-based genomic prediction, deep learning for sequence annotation, and data-driven identification of regulatory elements, but further efforts are necessary to standardize methodologies and ensure biological robustness.This Research Topic aims to unite researchers working at the intersection of artificial intelligence and agricultural genetics involving plants, animals, microbes, fishes etc. to highlight emerging computational strategies that advance our understanding of genomes and accelerate improvement programs. The goal is to explore how AI-driven approaches can deepen insights into gene function, enhance genomic prediction accuracy, and facilitate the discovery of molecular signatures linked to yield, stress tolerance, and nutritional quality. Authors are encouraged to investigate algorithmic developments, interdisciplinary data integration frameworks, and case studies that demonstrate translational applications of AI in genomics and breeding pipelines. Through the compilation of these studies, the Research Topic seeks to foster collaboration between computational scientists, geneticists, and breeders and other stakeholders to deploy intelligent systems that improve food security and sustainability.To gather further insights into the application boundaries of AI and ML in agriculture and allied sectors, we welcome articles addressing, but not limited to, the following themes:o Deep learning architectures for genomic sequence and variant analysiso AI-based genotype–phenotype prediction and genomic selection approacheso Integration of multi-omics datasets using machine learning frameworkso Foundation models and large language models for plant and animal genomicso Explainable and interpretable AI for regulatory network inferenceo Predictive modelling of complex traits under environmental variabilityo Machine learning pipelines for detection of structural variants and pan-genome diversityo Application of AI to accelerate breeding programs for climate resilience Topic editors: TANMAYA KUMAR SAHU, Khurshid Ahmad, Kanaka K K, Tanuj Misra, Neetesh Pandey Source: https://www.frontiersin.org/research-topics/82782/agricultural-multi-omics-through-artificial-intelligence-and-machine-learning