From Multi-Omics to Transferable Prediction: Artificial Intelligence for Next-Generation Plant Breeding

Plant breeding is being transformed by rapid advances in genomics, pangenomics, transcriptomics, epigenomics, proteomics, metabolomics, high-throughput phenotyping, and environmental characterization. Across field crops, horticultural crops, fruit and forest trees, forage species, medicinal plants, and other economically important species, these technologies generate unprecedented volumes of biological data, while artificial intelligence and machine learning offer new ways to extract predictive information from complex and heterogeneous datasets. The major challenge has therefore shifted from data generation to integration and translation. One largely unresolved dimension of that challenge is transferability: models trained in one environment, population, or species often lose accuracy when applied elsewhere. Understanding when and why predictions generalize, and when added omics complexity genuinely improves them, is now central to making multi-omics and computational approaches useful for routine breeding decisions.This Research Topic aims to showcase recent advances that integrate multi-omics, quantitative genetics, bioinformatics, and artificial intelligence to accelerate plant genetic improvement, with a deliberate emphasis on predictions that transfer beyond the dataset in which they were built. Key challenges include identifying causal genetic and regulatory variation, integrating heterogeneous omics layers, predicting complex traits across populations and environments, understanding genotype-by-environment interactions, and translating predictions into actionable breeding decisions. Recent developments in long-read sequencing, pangenomics, structural variation analysis, high-throughput phenotyping, environmental modelling, genomic prediction, and machine learning now provide new opportunities to address these challenges. We therefore invite work that connects genotype, molecular regulation, phenotype, and environment, and that demonstrates how such information can improve parental selection, genomic prediction, adaptation breeding, population improvement, and the design of superior plant varieties. We equally welcome critical Perspectives and Opinions on a question the field has not settled: under what circumstances does adding omics layers measurably improve prediction over well-specified genomic models, and when does it not?We especially welcome contributions from annual crop breeding programs, perennial and forest-tree breeding, and genebank and germplasm-diversity research, alongside horticultural, forage, medicinal, and other breeding-relevant plant species.Topics of interest include, but are not limited to:· integration of genomics, transcriptomics, epigenomics, proteomics, metabolomics, phenomics, and environmental data to dissect complex traits; · genomic prediction and selection, including multi-trait, multi-environment, and cross-population models; · transferability and generalization of predictive models across environments, populations, and species; · genotype-by-environment interaction, phenotypic plasticity, climate adaptation, and yield stability; · pangenomics, structural variation, haplotypes, and novel sources of breeding variation;· artificial intelligence, machine learning, and deep learning for breeding decision support; · identification of causal genes, regulatory elements, molecular networks, and favorable alleles; · high-throughput phenotyping, environmental characterization, and bioinformatics platforms; · parent selection, hybrid prediction, population improvement, and precision breeding.We welcome Original Research, Reviews, Methods, Perspectives, and other relevant article types.-------We welcome contributions from researchers across the field, and we are glad to support you as you prepare your submission. If you would like early feedback on whether your planned manuscript fits the scope of this Research Topic, please write to us at plantscience@frontiersin.org before submitting. A quick check at this stage helps confirm your work is a strong fit and can save you time later in the process.To take part, click “Participate in this topic” at the top right of this page, then confirm through the “Participate” link in the follow-up email. This lets us know to expect your contribution, keeps you informed of key deadlines, and gives you access to resources that guide you through submission. We would also be glad to talk with you about possible routes for support with the Article Processing Charge (APC).We look forward to your participation and to building a vibrant, cohesive Research Topic together. Topic editors: Yanjun Zan, Wei Zhao Source: https://www.frontiersin.org/research-topics/85217/from-multi-omics-to-transferable-prediction-artificial-intelligence-for-next-generation-plant-breeding