DeepBioGS: a hybrid framework for integrating crop growth modelling with genomic prediction through neural networks

Abstract

Ensuring global food security under rapid climate change demands accelerated genetic gain and breeding strategies that address complex Genotype-by-Environment (G×E) interactions. Traditional genomic selection models often fail to account for novel or extreme climates.Furthermore, integrating mechanistic crop growth models (CGMs) using traditional Bayesian frameworks to solve this issue presents severe computational bottlenecks. Here, we introduce DeepBioGS, a novel hybrid framework that integrates genomic selection with biophysical growth modelling via a fully differentiable deep learning architecture. DeepBioGS utilises a parameter-prediction multi-layer perceptron to map high-dimensional genomic markers to latent, highly heritable physiological traits (Genotype-Specific Parameters; GSP). These parameters mechanistically predict crop phenology across diverse environments. Using two multi-environment wheat datasets comprising over 6,000 genotypes, DeepBioGS extracted latent traits with near-perfect SNP-based heritability values (0.95-1.00). Crucially, the framework demonstrated superior or comparable predictive accuracy (up to r 2 = 0.77) against standard genomic best linear unbiased prediction (GBLUP) and traditional Bayesian CGM-WGP models. Its architecture drastically improved computational scalability by enabling standard backpropagation, effectively bypassing the stochastic sampling limitations of approximate Bayesian methods. Most importantly for climate adaptation, DeepBioGS allowed accurate forecasting of genotype performance in entirely unobserved environmental conditions. By merging the representational power of deep learning with the structural constraints of biophysics, DeepBioGS provides a highly scalable, interpretable tool to navigate G×E interactions, enabling the assessment of cultivars under future climate scenarios, thus optimising crop breeding for a changing global environment.

Plant phenotyping relevance

ゲノム情報から生理形質・作物フェノロジーを推定し、環境別の性能を予測する新規計算フレームワークが研究の中心であり、植物形質推定法の開発に該当する。

Code and data availability

The supplied blocks describe two wheat phenology datasets (from Jighly et al. 2023b and Joukhadar et al. 2021) and a TensorFlow-based DeepBioGS framework, but contain no data or code availability statement, no public repository URL, and no author-provided access point for the datasets, trained models, or analysis code.

No evidence-backed public reproduction asset is currently recorded.