Abstract 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 ( R 2 = 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.
Wheat resistance to Fusarium head blight (FHB) has often been associated with some undesirable agronomic traits. To study the relationship between wheat FHB resistance and agronomic traits, we ...constructed a linkage map of single nucleotide polymorphisms (SNPs) using an F6:8 population from G97252W × G97380A. The two hard winter wheat parents showed contrasts in FHB resistance, plant height (HT), heading date (HD), spike length (SL), spike compactness (SC), kernel number per spike (KNS), spikelet number per spike (SNS), thousand-grain weight (TGW) and grain size (length and width). Quantitative trait locus (QTL) mapping identified one major QTL (QFhb.hwwg-2DS) on chromosome arm 2DS for the percentage of symptomatic spikelets (PSS) in the spike, deoxynivalenol (DON) content and Fusarium damaged kernel (FDK). This QTL explained up to 71.8% of the phenotypic variation for the three FHB-related traits and overlapped with the major QTL for HT, HD, SL, KNS, SNS, TGW, and grain size. QTL on chromosome arms 2AL, 2DS, 3AL and 4BS were significant for the spike and grain traits measured. G97252W contributed FHB resistance and high SNS alleles at QFhb.hwwg-2DS, high KNS alleles at the QTL on 2AL and 2DS, and high TGW and grain size alleles at QTL on 3AL; whereas G97380A contributed high TGW and grain size alleles at the QTL on 2AL and 2DS, respectively, and the high KNS allele at the 4BS QTL. Combining QFhb.hwwg-2DS with positive alleles for spike and grain traits from other chromosomes may simultaneously improve FHB resistance and grain yield in new cultivars.
A recently identified Wheat streak mosaic virus (WSMV) resistance gene Wsm2 confers a high level of resistance. Objective of this study was to identify closely linked DNA markers for Wsm2 for use in ...marker-assisted selection (MAS) in wheat (Triticum aestivum L.). Two segregating populations (CO960293-2 × ‘TAM 111’ and CO960293-2 × ‘Yuma’) of F2:3 families were evaluated for response to WSMV infection in growth chamber experiments. Forty-eight simple sequence repeat (SSR) or sequence-tagged site (STS) markers were screened for polymorphism between the parents of both populations. In the CO960293-2 × TAM 111 population, five markers were mapped to the region of Wsm2 with XSTS3B-55 being the closest marker (5.2 cM distal to Wsm2). In the CO960293-2 × Yuma population, eight markers were linked to Wsm2 with the closest marker Xbarc102 linked at 3.9 cM proximal to Wsm2. Results from consensus mapping of the two populations suggested that Xbarc102 was distal to Wsm2. The marker Xbarc102 was associated with Wsm2 in all 22 wheat lines derived from crosses between susceptible parents and either CO960293-2 or ‘RonL’ (also carrying Wsm2). The marker allele Xbarc102-219-bp present in CO960293-2 was amplified in polymerase chain reaction (PCR) from Wsm2-carrying genotypes CO960293-w133, RonL, and ‘Snowmass’ but not from the resistant line KS96HW10-3 (carrying Wsm1) or the susceptible genotypes ‘Karl 92’, ‘TAM 107’, and ‘N96L9970’. Therefore, this marker should be useful for MAS of Wsm2 in breeding programs.
Fusarium head blight (FHB), primarily caused by Fusarium graminearum Schw., is a destructive disease of wheat (Triticum aestivum L.). Although several genes related to FHB resistance have been ...reported, global analysis of gene expression in response to FHB infection remains to be explored. The expression patterns of transcriptomes from wheat spikes of FHB-resistant cultivar Ning 7840 and susceptible cultivar Clark were monitored during a period of 72 h after inoculation (hai) with F. graminearum. Microarray analysis, coupled with suppression subtractive hybridization technique, identified 44 significantly differentially expressed genes between cv. Ning 7840 and cv. Clark. More differentially expressed genes were identified from susceptible libraries than from resistance libraries. The up-regulation of defense-related genes in Ning 7840 relative to cultivar Clark occurred during early fungal stress (3-12 hai). Three genes, with unknown function that were up-regulated in cv. Ning 7840 at most time points investigated, might play an important role in enhancing FHB resistance.
Scope and method of study. The objective of this study was to identify and characterize differentially expressed ESTs in wheat spikes as a response to F. graminearum infection. Suppression ...subtraction hybridization coupled with microarray analysis of ca. 4800 cDNAs was conducted to identify differentially expressed ESTs between Fusarium head blight (FHB) resistant and susceptible varieties and also between fungal-and mock-inoculated plants. Microarray data were analyzed using GenePix Pro 5.0, GenePix Pro AutoProcessor, BLAST-X and Genesis software. Findings and conclusions. Microarray analysis revealed ca. 290 significantly differentially expressed ESTs after imposition of fungal-stress. The identification of a large number of differentially expressed ESTs suggests that plant defense in response to FHB infection is complex and involves a regulatory network of genes involved in photosynthesis, transcription, metabolism, energy generation, protein modification, cell rescue/defense as well as genes of still unknown function. F. graminearum appears to have an antagonistic effect on photosynthesis since up-regulation of defense-related ESTs in FHB resistant varieties (relative to susceptible control) coincided with down-regulation of photosynthesis-related ESTs. Up-regulation of defense-related ESTs can occur early at 3 hours after inoculation (hai) in the resistant variety while mostly occur at 36 hai or later in the susceptible control. This indicates a slower defense response in FHB susceptible compared to resistant variety. There were more differentially induced ESTs than repressed ESTs in the resistant variety during the first 24 hai with the pathogen, but more significantly down-regulated ESTs were observed from treatments of 36 hai and onward.