Diggrain: digital twin and knowledge graph platform for predicting cereal grain outcomes under environmental stress
DigGrain is a digital twin and knowledge graph platform that integrates multi-omics data with 3D imaging of rice panicles and grains to predict yield and quality outcomes under variable environmental and chemical conditions. Applicable to rice, wheat, and maize, it enables genotype-specific modeling of grain development under heat, drought, and hormonal treatments.
Overview
DigGrain is a computational platform that builds digital twins of developing cereal grains to predict yield and quality outcomes under changing environmental and chemical conditions. By combining large-scale transcriptomic, metabolomic, and phenomic datasets with high-resolution 3D imaging of rice panicles and individual grains, the platform models how specific genotypes respond to stress and treatment interventions.
The approach addresses a critical challenge in agriculture: predicting how crops will perform under variable field conditions before the growing season ends. By representing the Genotype-to-Environment-to-Chemical (G2E2C) system as a queryable knowledge graph, DigGrain enables researchers and breeders to simulate interventions and forecast grain morphology, quality, and nutritional content.
While initially developed for rice, the graph-based architecture is designed for broad applicability across cereal crops including wheat and maize, making it a scalable tool for crop improvement programs.
Technical specifications
Platform architecture:
- Knowledge graph with four interconnected compartments: Biological (whole plant, panicle or spike or cob, individual grain), Environment (heat stress, drought stress), Treatment (auxin, ABA, cytokinin), and Outcome (mature grain morphology, quality, nutritional content)
- Digital twins created from in-house 3D imaging of rice plants, panicles, and mature grains
- Integration of transcriptomics and metabolomics data from vegetative tissue and developing grains
- Hyperspectral characterization of mature grains for quality assessment
- Genotype-specific modeling leveraging high-density SNP information from diverse rice genotypes
Key capabilities:
- Predicts yield-associated parameters under environmental and chemical perturbation
- Queryable structure allows assessment of interventions at different biological nodes
- Scalable from individual grain to whole plant level
- Architecture transferable to wheat and maize with minimal modification
Technology readiness level
The platform builds on validated datasets already generated at the University of Nebraska, including multi-omics and phenomics data collected across diverse rice genotypes under temperature variation. The knowledge graph framework and digital twin methodology are currently in the development and validation phase. Future work will focus on generating the queryable knowledge graph, building digital twins from existing imaging resources, and validating predictions against experimental outcomes. The approach is immediately testable in wheat and maize, positioning it for staged expansion beyond rice.
About University of Nebraska, Lincoln
The University of Nebraska–Lincoln is a comprehensive public research university and the flagship campus of the University of Nebraska system, combining land-grant reach with a collaborative, industry-engaged culture. A research and technology park adjacent to campus provides modern wet and dry labs, greenhouses, offices, and conferencing, enabling companies to co-locate with faculty and access shared equipment and pilot environments. A statewide extension network links university expertise with producers and communities, creating rapid pathways for field trials, demonstrations, and workforce pipelines. Research is supported by competitive federal funding from NSF, USDA, DOE, and NIH. A dedicated technology transfer office manages IP, licensing, agreements, and startup formation with industry-friendly terms.
delivered to your inbox.