Dataset Information

Predicting biomass of rice with intermediate traits: Modeling method combining crop growth models and genomic prediction models.

ABSTRACT: Genomic prediction (GP) is expected to become a powerful technology for accelerating the genetic improvement of complex crop traits. Several GP models have been proposed to enhance their applications in plant breeding, including environmental effects and genotype-by-environment interactions (G×E). In this study, we proposed a two-step model for plant biomass prediction wherein environmental information and growth-related traits were considered. First, the growth-related traits were predicted by GP. Second, the biomass was predicted from the GP-predicted values and environmental data using machine learning or crop growth modeling. We applied the model to a 2-year-old field trial dataset of recombinant inbred lines of japonica rice and evaluated the prediction accuracy with training and testing data by cross-validation performed over two years. Therefore, the proposed model achieved an equivalent or a higher correlation between the observed and predicted values (0.53 and 0.65 for each year, respectively) than the model in which biomass was directly predicted by GP (0.40 and 0.65 for each year, respectively). This result indicated that including growth-related traits enhanced accuracy of biomass prediction. Our findings are expected to contribute to the spread of the use of GP in crop breeding by enabling more precise prediction of environmental effects on crop traits.

SUBMITTER: Toda Y

PROVIDER: S-EPMC7304626 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting biomass of rice with intermediate traits: Modeling method combining crop growth models and genomic prediction models.

Toda Yusuke Y Wakatsuki Hitomi H Aoike Toru T Kajiya-Kanegae Hiromi H Yamasaki Masanori M Yoshioka Takuma T Ebana Kaworu K Hayashi Takeshi T Nakagawa Hiroshi H Hasegawa Toshihiro T Iwata Hiroyoshi H

PloS one 20200619 6

Genomic prediction (GP) is expected to become a powerful technology for accelerating the genetic improvement of complex crop traits. Several GP models have been proposed to enhance their applications in plant breeding, including environmental effects and genotype-by-environment interactions (G×E). In this study, we proposed a two-step model for plant biomass prediction wherein environmental information and growth-related traits were considered. First, the growth-related traits were predicted by ...[more]

PMID: 32559220

Similar Datasets

Project description:Accurate prediction of heading date under various environmental conditions is expected to facilitate the decision-making process in cultivation management and the breeding process of new cultivars adaptable to the environment. Days to heading (DTH) is a complex trait known to be controlled by multiple genes and genotype-by-environment interactions. Crop growth models (CGMs) have been widely used to predict the phenological development of a plant in an environment; however, they usually require substantial experimental data to calibrate the parameters of the model. The parameters are mostly genotype-specific and are thus usually estimated separately for each cultivar. We propose an integrated approach that links genotype marker data with the developmental genotype-specific parameters of CGMs with a machine learning model, and allows heading date prediction of a new genotype in a new environment. To estimate the parameters, we implemented a Bayesian approach with the advanced Markov chain Monte-Carlo algorithm called the differential evolution adaptive metropolis and conducted the estimation using a large amount of data on heading date and environmental variables. The data comprised sowing and heading dates of 112 cultivars/lines tested at 7 locations for 14 years and the corresponding environmental variables (day length and daily temperature). We compared the predictive accuracy of DTH between the proposed approach, a CGM, and a single machine learning model. The results showed that the extreme learning machine (one of the implemented machine learning models) was superior to the CGM for the prediction of a tested genotype in a tested location. The proposed approach outperformed the machine learning method in the prediction of an untested genotype in an untested location. We also evaluated the potential of the proposed approach in the prediction of the distribution of DTH in 103 F2 segregation populations derived from crosses between a common parent, Koshihikari, and 103 cultivars/lines. The results showed a high correlation coefficient (ca. 0.8) of the 10, 50, and 90th percentiles of the observed and predicted distribution of DTH. In this study, the integration of a machine learning model and a CGM was better able to predict the heading date of a new rice cultivar in an untested potential environment.

Project description:Fusarium head blight (FHB) incited by Fusarium graminearum Schwabe is a devastating disease of barley and other cereal crops worldwide. Fusarium head blight is associated with trichothecene mycotoxins such as deoxynivalenol (DON), where contaminated grains are unfit for malting or animal feed industries. While genetically resistant cultivars offer the best economic and environmentally responsible means to mitigate disease, parent lines with adequate resistance are limited in barley. Resistancebreeding based upon quantitative genetic gains has been slow to date, due to intensive labour requirements of disease nurseries. The development of high throughput genome-wide molecular markers, allow application in genomic prediction models. A diverse genomic panel consisting of 400 two-row spring barley lines was assembled to focus on Canadian barley breeding programs. The panel was evaluated for FHB and DON content in three environments and over two years. Moreover, it was genotyped using an Illumina Infinium HTS iSelect custom beadchip array of single nucleotide polymorphic molecular markers (50K SNP), where over 23K molecular markers were polymorphic. Genomic prediction has been successfully demonstrated for reducing FHB and DON content in cereals using various statistically-based models of different underlying assumptions. Herein, we have studied an alternative method basedon machine learning and compare it with a statistical approach. Two encoding techniques were utilized (categorical or Hardy-Weinberg frequencies), followed by selecting essential genomic markers for phenotype prediction. Subsequently, we applied a transformer-based deep learning algorithm to predict FHB and DON. Apart from the transformer method, we also implemented a Residual Fully Connected Neural Network (RFCNN). Pearson correlation coefficients were calculated to compare true vs. predicted outputs. Under most model scenarios, the use of all markers vs. selected markers marginally improved prediction performance except for RFCNN method for FHB (27.6%). Hardy-Weinberg encoding generally improved correlation for FHB (6.9%) and DON (9.6%) for transformer. This study suggests the potential of the transformer based method for genomic prediction of complex traits such as FHB or DON, having performed better or equally compared with existing machine learning and statistical method. To genomic prediction in barley for Fusarium head blight and deoxynivalenol content using a custom Illumina Infinium array (BarleySNP50-JHI) (www.illumina.com). Sample types included leaves from 400 barley genotypes mostly of Canadian origin. This series includes 400 genotypes assayed on an Illumina infinium HTS platform 50K BeadChip.

Project description:Bioenergy sorghum is targeted for production in water-limited annual cropland therefore traits that improve plant water capture, water use efficiency, and resilience to water deficit are necessary to maximize productivity. A crop modeling framework, APSIM, was adapted to predict the growth and biomass yield of energy sorghum and to identify potentially useful traits for crop improvement. APSIM simulations of energy sorghum development and biomass accumulation replicated results from field experiments across multiple years, patterns of rainfall, and irrigation schemes. Modeling showed that energy sorghum's long duration of vegetative growth increased water capture and biomass yield by ~30% compared to short season crops in a water-limited production region. Additionally, APSIM was extended to enable modeling of VPD-limited transpiration traits that reduce crop water use under high vapor pressure deficits (VPDs). The response of transpiration rate to increasing VPD was modeled as a linear response until a VPD threshold was reached, at which the slope of the response decreases, representing a range of responses to VPD observed in sorghum germplasm. Simulation results indicated that the VPD-limited transpiration trait is most beneficial in hot and dry regions of production where crops are exposed to extended periods without rainfall during the season or to a terminal drought. In these environments, slower but more efficient transpiration increases biomass yield and prevents or delays the exhaustion of soil water and onset of leaf senescence. The VPD-limited transpiration responses observed in sorghum germplasm increased biomass accumulation by 20% in years with lower summer rainfall, and the ability to drastically reduce transpiration under high VPD conditions could increase biomass by 6% on average across all years. This work indicates that the productivity and resilience of bioenergy sorghum grown in water-limited environments could be further enhanced by development of genotypes with optimized VPD-limited transpiration traits and deployment of these crops in water limited growing environments. The energy sorghum model and VPD-limited transpiration trait implementation are made available to simulate performance in other target environments.

Dataset Information

Predicting biomass of rice with intermediate traits: Modeling method combining crop growth models and genomic prediction models.

Publications

Predicting biomass of rice with intermediate traits: Modeling method combining crop growth models and genomic prediction models.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets