Development of image-based wheat spike counter through a Faster R-CNN algorithm and application for genetic studies

Spike number(SN) per unit area is one of the major determinants of grain yield in wheat. Development of high-throughput techniques to count SN from large populations enables rapid and cost-effective selection and facilitates genetic studies. In the present study, we used a deep-learning algorithm, i.e., Faster Region-based Convolutional Neural Networks(Faster R-CNN) on Red-Green-Blue(RGB) images to explore the possibility of image-based detection of SN and its application to identify the loci underlying SN. A doubled haploid population of 101 lines derived from the Yangmai 16/Zhongmai 895 cross was grown at two sites for SN phenotyping and genotyped using the high-density wheat 660 K SNP array.Analysis of manual spike number(MSN) in the field, image-based spike number(ISN), and verification of spike number(VSN) by Faster R-CNN revealed significant variation(P < 0.001) among genotypes, with high heritability ranged from 0.71 to 0.96. The coefficients of determination(R^(2)) between ISN and VSN was 0.83, which was higher than that between ISN and MSN(R^(2)= 0.51), and between VSN and MSN(R^(2)= 0.50). Results showed that VSN data can effectively predict wheat spikes with an average accuracy of 86.7% when validated using MSN data. Three QTL Qsnyz.caas-4 DS, Qsnyz.caas-7 DS, and QSnyz.caas-7 DL were identified based on MSN, ISN and VSN data, while QSnyz.caas-7 DS was detected in all the three data sets. These results indicate that using Faster R-CNN model for image-based identification of SN per unit area is a precise and rapid phenotyping method, which can be used for genetic studies of SN in wheat.

QTL mapping of seedling biomass and root traits under different nitrogen conditions in bread wheat(Triticum aestivum L.)

Plant nitrogen assimilation and use efficiency in the seedling's root system are beneficial for adult plants in field condition for yield enhancement.Identification of the genetic basis between root traits and N uptake plays a crucial role in wheat breeding.In the present study,198 doubled haploid lines from the cross of Yangmai 16/Zhongmai 895 were used to identify quantitative trait loci(QTLs)underpinning four seedling biomass traits and five root system architecture(RSA)related traits.The plants were grown under hydroponic conditions with control,low and high N treatments(Ca(NO_(3))_(2)·4H_(2)O at 0,0.05 and 2.0 mmol L^(-1),respectively).Significant variations among the treatments and genotypes,and positive correlations between seedling biomass and RSA traits(r=0.20 to 0.98)were observed.Inclusive composite interval mapping based on a high-density map from the Wheat 660 K single nucleotide polymorphisms(SNP)array identified 51 QTLs from the three N treatments.Twelve new QTLs detected on chromosomes 1 AL(1)in the control,1 DS(2)in high N treatment,4 BL(5)in low and high N treatments,and 7 DS(3)and 7 DL(1)in low N treatments,are first reported in influencing the root and biomass related traits for N uptake.The most stable QTLs(RRS.caas-4 DS)on chromosome 4 DS,which were related to ratio of root to shoot dry weight trait,was in close proximity of the Rht-D1 gene,and it showed high phenotypic effects,explaining 13.1%of the phenotypic variance.Twenty-eight QTLs were clustered in 12 genetic regions.SNP markers tightly linked to two important QTLs clusters C10 and C11 on chromosomes 6 BL and 7 BL were converted to kompetitive allele-specific PCR(KASP)assays that underpin important traits in root development,including root dry weight,root surface area and shoot dry weight.These QTLs,clusters and KASP assays can greatly improve the efficiency of selection for root traits in wheat breeding programmes.