A Digital PCR Assay to Quantify the Percentages of Hulled vs. Hulless Wheat in Flours and Flour-Based Products

Several food products, made from hulled wheats, are now offered by the market, ranging from grains and pasta to flour and bakery products. The possibility of verifying the authenticity of wheat species used at any point in the production chain is relevant, in defense of both producers and consumers. A chip digital PCR assay has been developed to detect and quantify percentages of hulless (i.e., common and durum wheat) and hulled (i.e., einkorn, emmer and spelt) wheats in grains, flours and food products. The assay has been designed on a polymorphism in the miRNA172 target site of the AP2-5 transcription factor localized on chromosome 5A and involved in wheat spike morphogenesis and grain threshability. The assay has been evaluated even in a real-time PCR system to assess its applicability and to compare the analytical costs between dPCR and real-time PCR approaches.

A Wheat Spike Detection Method in UAV Images Based on Improved YOLOv5

Deep-learning-based object detection algorithms have significantly improved the performance of wheat spike detection. However, UAV images crowned with small-sized, highly dense, and overlapping spikes cause the accuracy to decrease for detection. This paper proposes an improved YOLOv5 (You Look Only Once)-based method to detect wheat spikes accurately in UAV images and solve spike error detection and miss detection caused by occlusion conditions. The proposed method introduces data cleaning and data augmentation to improve the generalization ability of the detection network. The network is rebuilt by adding a microscale detection layer, setting prior anchor boxes, and adapting the confidence loss function of the detection layer based on the IoU (Intersection over Union). These refinements improve the feature extraction for small-sized wheat spikes and lead to better detection accuracy. With the confidence weights, the detection boxes in multiresolution images are fused to increase the accuracy under occlusion conditions. The result shows that the proposed method is better than the existing object detection algorithms, such as Faster RCNN, Single Shot MultiBox Detector (SSD), RetinaNet, and standard YOLOv5. The average accuracy (AP) of wheat spike detection in UAV images is 94.1%, which is 10.8% higher than the standard YOLOv5. Thus, the proposed method is a practical way to handle the spike detection in complex field scenarios and provide technical references for field-level wheat phenotype monitoring.

Genome-wide profiling of long noncoding RNAs involved in wheat spike development

Background Long noncoding RNAs (lncRNAs) have been shown to play important roles in the regulation of plant growth and development. Recent transcriptomic analyses have revealed the gene expression profiling in wheat spike development, however, the possible regulatory roles of lncRNAs in wheat spike morphogenesis remain largely unclear. Results Here, we analyzed the genome-wide profiling of lncRNAs during wheat spike development at six stages, and identified a total of 8,889 expressed lncRNAs, among which 2,753 were differentially expressed lncRNAs (DE lncRNAs) at various developmental stages. Three hundred fifteen differentially expressed cis- and trans-regulatory lncRNA-mRNA pairs comprised of 205 lncRNAs and 279 genes were predicted, which were found to be mainly involved in the stress responses, transcriptional and enzymatic regulations. Moreover, the 145 DE lncRNAs were predicted as putative precursors or target mimics of miRNAs. Finally, we identified the important lncRNAs that participate in spike development by potentially targeting stress response genes, TF genes or miRNAs. Conclusions This study outlines an overall view of lncRNAs and their possible regulatory networks during wheat spike development, which also provides an alternative resource for genetic manipulation of wheat spike architecture and thus yield.

Parts-per-Object Count in Agricultural Images: Solving Phenotyping Problems via a Single Deep Neural Network

Solving many phenotyping problems involves not only automatic detection of objects in an image, but also counting the number of parts per object. We propose a solution in the form of a single deep network, tested for three agricultural datasets pertaining to bananas-per-bunch, spikelets-per-wheat-spike, and berries-per-grape-cluster. The suggested network incorporates object detection, object resizing, and part counting as modules in a single deep network, with several variants tested. The detection module is based on a Retina-Net architecture, whereas for the counting modules, two different architectures are examined: the first based on direct regression of the predicted count, and the other on explicit parts detection and counting. The results are promising, with the mean relative deviation between estimated and visible part count in the range of 9.2% to 11.5%. Further inference of count-based yield related statistics is considered. For banana bunches, the actual banana count (including occluded bananas) is inferred from the count of visible bananas. For spikelets-per-wheat-spike, robust estimation methods are employed to get the average spikelet count across the field, which is an effective yield estimator.

Wheat Spike Blast Image Classification Using Deep Convolutional Neural Networks

Wheat blast is a threat to global wheat production, and limited blast-resistant cultivars are available. The current estimations of wheat spike blast severity rely on human assessments, but this technique could have limitations. Reliable visual disease estimations paired with Red Green Blue (RGB) images of wheat spike blast can be used to train deep convolutional neural networks (CNN) for disease severity (DS) classification. Inter-rater agreement analysis was used to measure the reliability of who collected and classified data obtained under controlled conditions. We then trained CNN models to classify wheat spike blast severity. Inter-rater agreement analysis showed high accuracy and low bias before model training. Results showed that the CNN models trained provide a promising approach to classify images in the three wheat blast severity categories. However, the models trained on non-matured and matured spikes images showing the highest precision, recall, and F1 score when classifying the images. The high classification accuracy could serve as a basis to facilitate wheat spike blast phenotyping in the future.

First report of blast of durum wheat in Bangladesh, caused by Magnaporthe oryzae pathotype Triticum

Durum wheat (Triticum turgidum var. durum Desf.) is an important cereal crop in many regions of the world. In March of 2018 and 2019, symptoms typical of blast were frequently observed on durum wheat plants under field conditions in Jashore, Bangladesh. The putative causal pathogen was isolated from infected wheat spike specimens onto potato dextrose agar and oatmeal agar, and was identified from mono-conidium cultures as Magnaporthe oryzae, based on morphological features. The pathotype of the fungus was identified as Triticum, based on comparative molecular analyses of ITS sequences and MoT3 specific markers. BLAST analysis revealed >99.8% similarity with M. oryzae/P. oryzae, retrieved from the NCBI Genebank. This was confirmed through amplification of the predicted products with MoT3 primers in PCR analysis. Pathogenicity was confirmed by inoculating healthy durum wheat seedling leaves and spikes with a conidium suspensions of M. oryzae isolate DuBWMRI1901.2A. The fungus produced similar symptoms on inoculated leaves and spikes as those observed in the field, and was subsequently re-isolated, fulfilling Koch’s postulates. This is the first report of blast of durum wheat caused by Magnaporthe oryzae pathotype Triticum in Bangladesh.