High-throughput phenotyping serves as a framework to reduce chronological costs and accelerate breeding cycles.In this study,we developed models to estimate the phenotypes of biomass-related traits in soybean(Glycine ...High-throughput phenotyping serves as a framework to reduce chronological costs and accelerate breeding cycles.In this study,we developed models to estimate the phenotypes of biomass-related traits in soybean(Glycine max)using unmanned aerial vehicle(UAV)remote sensing and deep learning models.In 2018,a field experiment was conducted using 198 soybean germplasm accessions with known whole-genome sequences under 2 irrigation conditions:drought and control.We used a convolutional neural network(CNN)as a model to estimate the phenotypic values of 5 conventional biomass-related traits:dry weight,main stem length,numbers of nodes and branches,and plant height.We utilized manually measured phenotypes of conventional traits along with RGB images and digital surface models from UAV remote sensing to train our CNN models.The accuracy of the developed models was assessed through 10-fold cross-validation,which demonstrated their ability to accurately estimate the phenotypes of all conventional traits simultaneously.Deep learning enabled us to extract features that exhibited strong correlations with the output(i.e.,phenotypes of the target traits)and accurately estimate the values of the features from the input data.We considered the extracted low-dimensional features as phenotypes in the latent space and attempted to annotate them based on the phenotypes of conventional traits.Furthermore,we validated whether these low-dimensional latent features were genetically controlled by assessing the accuracy of genomic predictions.The results revealed the potential utility of these low-dimensional latent features in actual breeding scenarios.展开更多
The change in appearance during the seasonal transitions in ornamental greening plants is an important characteristic.In particular,the early onset of green leaf color is a desirable trait for a cultivar.In this study...The change in appearance during the seasonal transitions in ornamental greening plants is an important characteristic.In particular,the early onset of green leaf color is a desirable trait for a cultivar.In this study,we established a method for phenotyping leaf color change by multispectral imaging and performed genetic analysis based on the phenotypes to clarify the potential of the approach in breeding greening plants.We performed multispectral phenotyping and quantitative trait locus(QTL)analysis of an F1 population derived from 2 parental lines of Phedimus takesimensis,known to be a drought and heat-tolerant rooftop plant species.The imaging was conducted in April of 2019 and 2020 when dormancy breakage occurs and growth extension begins.Principal component analysis of 9 different wavelength values showed a high contribution from the first principal component(PC1),which captured variation in the visible light range.The high interannual correlation in PC1 and in the intensity of visible light indicated that the multispectral phenotyping captured genetic variation in the color of leaves.We also performed restriction site-associated DNA sequencing and obtained the first genetic linkage map of Phedimus spp.QTL analysis revealed 2 QTLs related to early dormancy breakage.Based on the genotypes of the markers underlying these 2 QTLs,the F1 phenotypes with early(late)dormancy break,green(red or brown)leaves,and a high(low)degree of vegetative growth were classified.The results suggest the potential of multispectral phenotyping in the genetic dissection of seasonal leaf color changes in greening plants.展开更多
基金supported by the JST CREST[grant number:JPMJCR16O2]and MEXT KAKENHI[grant number:JP22H02306].The funders had no role in the study design,data collection and analysis,decision to publish,or manuscript preparation.
文摘High-throughput phenotyping serves as a framework to reduce chronological costs and accelerate breeding cycles.In this study,we developed models to estimate the phenotypes of biomass-related traits in soybean(Glycine max)using unmanned aerial vehicle(UAV)remote sensing and deep learning models.In 2018,a field experiment was conducted using 198 soybean germplasm accessions with known whole-genome sequences under 2 irrigation conditions:drought and control.We used a convolutional neural network(CNN)as a model to estimate the phenotypic values of 5 conventional biomass-related traits:dry weight,main stem length,numbers of nodes and branches,and plant height.We utilized manually measured phenotypes of conventional traits along with RGB images and digital surface models from UAV remote sensing to train our CNN models.The accuracy of the developed models was assessed through 10-fold cross-validation,which demonstrated their ability to accurately estimate the phenotypes of all conventional traits simultaneously.Deep learning enabled us to extract features that exhibited strong correlations with the output(i.e.,phenotypes of the target traits)and accurately estimate the values of the features from the input data.We considered the extracted low-dimensional features as phenotypes in the latent space and attempted to annotate them based on the phenotypes of conventional traits.Furthermore,we validated whether these low-dimensional latent features were genetically controlled by assessing the accuracy of genomic predictions.The results revealed the potential utility of these low-dimensional latent features in actual breeding scenarios.
基金partly funded by the Joint Research Program of Arid Land Research Center,Tottori University(No.29C2003)Japan Science and Technology Agency(JST)CREST,Japan(No.JPMJCR16O2)Tottori University President’s Discretionary Fund for FY 2019.
文摘The change in appearance during the seasonal transitions in ornamental greening plants is an important characteristic.In particular,the early onset of green leaf color is a desirable trait for a cultivar.In this study,we established a method for phenotyping leaf color change by multispectral imaging and performed genetic analysis based on the phenotypes to clarify the potential of the approach in breeding greening plants.We performed multispectral phenotyping and quantitative trait locus(QTL)analysis of an F1 population derived from 2 parental lines of Phedimus takesimensis,known to be a drought and heat-tolerant rooftop plant species.The imaging was conducted in April of 2019 and 2020 when dormancy breakage occurs and growth extension begins.Principal component analysis of 9 different wavelength values showed a high contribution from the first principal component(PC1),which captured variation in the visible light range.The high interannual correlation in PC1 and in the intensity of visible light indicated that the multispectral phenotyping captured genetic variation in the color of leaves.We also performed restriction site-associated DNA sequencing and obtained the first genetic linkage map of Phedimus spp.QTL analysis revealed 2 QTLs related to early dormancy breakage.Based on the genotypes of the markers underlying these 2 QTLs,the F1 phenotypes with early(late)dormancy break,green(red or brown)leaves,and a high(low)degree of vegetative growth were classified.The results suggest the potential of multispectral phenotyping in the genetic dissection of seasonal leaf color changes in greening plants.
