Journal Article

Integrating genomics, phenomics, and deep learning improves the predictive ability for Fusarium head blight–related traits in winter wheat

St. Amand, Paul, Bernardo, Amy, Thapa, Subash, Gill, Harsimardeep S., Gill, Upinder, Bai, Guihua, Halder, Jyotirmoy, Rana, Anshul, Ali, Shaukat, Sehgal, Sunish K., Maimaitijiang, Maitiniyazi

2024

Overview

Fusarium head blight (FHB) remains one of the most destructive diseases of wheat (Triticum aestivum L.), causing considerable losses in yield and end‐use quality. Phenotyping of FHB resistance traits, Fusarium‐damaged kernels (FDK), and deoxynivalenol (DON), is either prone to human biases or resource expensive, hindering the progress in breeding for FHB‐resistant cultivars. Though genomic selection (GS) can be an effective way to select these traits, inaccurate phenotyping remains a hurdle in exploiting this approach. Here, we used an artificial intelligence (AI)‐based precise FDK estimation that exhibits high heritability and correlation with DON. Further, GS using AI‐based FDK (FDK_QVIS/FDK_QNIR) showed a two‐fold increase in predictive ability (PA) compared to GS for traditionally estimated FDK (FDK_V). Next, the AI‐based FDK was evaluated along with other traits in multi‐trait (MT) GS models to predict DON. The inclusion of FDK_QNIR and FDK_QVIS with days to heading as covariates improved the PA for DON by 58% over the baseline single‐trait GS model. We next used hyperspectral imaging of FHB‐infected wheat kernels as a novel avenue to improve the MT GS for DON. The PA for DON using selected wavebands derived from hyperspectral imaging in MT GS models surpassed the single‐trait GS model by around 40%. Finally, we evaluated phenomic prediction for DON by integrating hyperspectral imaging with deep learning to directly predict DON in FHB‐infected wheat kernels and observed an accuracy (R2 = 0.45) comparable to best‐performing MT GS models. This study demonstrates the potential application of AI and vision‐based platforms to improve PA for FHB‐related traits using genomic and phenomic selection. Core Ideas Vision and artificial intelligence (AI)‐based technology provide an effective way to phenotype Fusarium‐damaged kernels (FDK) in wheat. Inclusion of AI‐based FDK as a covariate in multi‐trait genomic prediction models yields high predictive ability for deoxynivalenol (DON). Hyperspectral imaging can be leveraged to improve the predictive ability of DON using genomic prediction as well as for direct phenomic prediction. Plain Language Summary Fusarium head blight (FHB) is a devastating disease of wheat and breeding for resistant cultivars is the best approach to counter this disease. However, complex phenotyping of various FHB traits makes it harder for breeders to select resistant cultivars. Our study investigates the usefulness of artificial intelligence (AI)‐based phenotyping in improving the prediction accuracy (PA) of FHB traits in wheat. We demonstrate that AI‐derived Fusarium‐damaged kernels phenotype can improve the prediction of FHB traits using genomic selection. Furthermore, we explored novel tools like hyperspectral imaging and deep learning for improved prediction of FHB resistance in wheat. Our results suggest that the application of novel technologies can be very useful in improving the prediction of FHB traits and can assist wheat breeders in developing FHB‐resistant cultivars.

• Publisher: John Wiley & Sons, Inc,Wiley
• Subject: Artificial intelligence / Automation / Cultivars / Deep Learning / Deoxynivalenol / Disease Resistance - genetics / Estimates / Fungicides / Fusarium / Fusarium - pathogenicity / Fusarium - physiology / Fusarium head blight / genome / Genomes / Genomics / Genomics - methods / head / Heritability / humans / Kernels / Machine learning / marker-assisted selection / Mass spectrometry / Observational learning / Pesticides / Phenomics / Phenotype / Phenotyping / Plant Breeding / Plant Diseases - genetics / Plant Diseases - microbiology / prediction / Scientific imaging / Triticum - genetics / Triticum - microbiology / Triticum aestivum / Wheat / winter wheat