Biology subjects

Carter, A. H.

Publications and source records attributed to Carter, A. H..

10 recordsLinked to original sources

bioRxiv2026

AGIcam: An open-source IoT-based camera system for automated in-field phenotyping and yield prediction

Continuous, high-frequency monitoring is essential to capture rapid phenological transitions and dynamic crop responses to the environment. However, most phenotyping platforms lack the temporal resolution and automation required for consistent, season-long trait assessment. This study introduces AGIcam, an open-source IoT camera system for automated and continuous in-field plant phenotyping and yield prediction. The platform integrates solar-powered Raspberry Pi units with a modular software stack, comprising Node-RED, InfluxDB, Grafana, and Microsoft Azure, for automated data acquisition, transfer, and visualization. In the 2022 growing season, 18 AGIcam systems were deployed in spring and winter wheat breeding trials, maintaining an uptime of over 85% while capturing frequent RGB and NoIR imagery. Time-series vegetation indices derived from these images were used to predict yield using random forest and Long Short-Term Memory (LSTM) models. The LSTM approach achieved the highest accuracy approximately one week after heading, with mean prediction errors of 3.41% for spring wheat and 1.62% for winter wheat. These results highlight the potential of IoT-based platforms such as AGIcam to enable real-time, scalable, and effective phenotyping solutions for data-driven crop improvement.

plant biology↗

bioRxiv2021

Classification and Regression Models for Genomic Selection of Skewed Phenotypes: A Case for Disease Resistance in Winter Wheat (Triticum aestivum L.)

Most genomic prediction models are linear regression models that assume continuous and normally distributed phenotypes, but responses to diseases such as stripe rust (caused by Puccinia striiformis f. sp. tritici) are commonly recorded in ordinal scales and percentages. Disease severity (SEV) and infection type (IT) data in germplasm screening nurseries generally do not follow these assumptions. On this regard, researchers may ignore the lack of normality, transform the phenotypes, use generalized linear models, or use supervised learning algorithms and classification models with no restriction on the distribution of response variables, which are less sensitive when modeling ordinal scores. The goal of this research was to compare classification and regression genomic selection models for skewed phenotypes using stripe rust SEV and IT in winter wheat. We extensively compared both regression and classification prediction models using two training populations composed of breeding lines phenotyped in four years (2016-2018, and 2020) and a diversity panel phenotyped in four years (2013-2016). The prediction models used 19,861 genotyping-by-sequencing single-nucleotide polymorphism markers. Overall, square root transformed phenotypes using rrBLUP and support vector machine regression models displayed the highest combination of accuracy and relative efficiency across the regression and classification models. Further, a classification system based on support vector machine and ordinal Bayesian models with a 2-Class scale for SEV reached the highest class accuracy of 0.99. This study showed that breeders can use linear and non-parametric regression models within their own breeding lines over combined years to accurately predict skewed phenotypes.

genetics↗

bioRxiv2021

Comparison of Single-Trait and Multi-Trait Genome-Wide Association Models and Inclusion of Correlated Traits in the Dissection of the Genetic Architecture of a Complex Trait in a Breeding Program

Traits with an unknown genetic architecture make it difficult to create a useful bi-parental mapping population to characterize the genetic basis of the trait due to a combination of complex and pleiotropic effects. Seedling emergence of wheat (Triticum aestivum L.) from deep planting is a vital factor affecting stand establishment and grain yield, has a poorly understood genetic architecture, and is historically correlated with coleoptile length. The creation of bi-parental mapping populations can be overcome by using genome-wide association studies (GWAS). This study aimed to dissect the genetic architecture of seedling emergence while accounting for correlated traits using one multi-trait GWAS model (MT-GWAS) and three single-trait GWAS models (ST-GWAS) with the inclusion of covariates for correlated traits. The ST-GWAS models included one single locus model (MLM), and two multiple loci models (FarmCPU and BLINK). We conducted the GWAS using two populations, the first consisting of 473 varieties from a diverse association mapping panel (DP) phenotyped from 2015-2019, and the other population used as a validation population consisting of 279 breeding lines (BL) phenotyped in 2015 in Lind, WA, with 40,368 markers. We also compared the inclusion of coleoptile length and markers associated with reduced height as covariates in our ST-GWAS models for the DP. ST-GWAS found 107 significant markers across 19 chromosomes, while MT-GWAS found 82 significant markers across 14 chromosomes. MT-GWAS models were able to identify large-effect markers on chromosome 5A. FarmCPU and BLINK models were able to identify many small effect markers, and the inclusion of covariates helped to identify the large effect markers on chromosome 5A. Therefore, by using multi-locus models combined with pleiotropic covariates, breeding programs can uncover the complex nature of traits to help identify candidate genes and the underlying architecture of a trait, such as seedling emergence of deep-sown winter wheat.

genetics↗

bioRxiv2021

Development of the Wheat Practical Haplotype Graph Database as a Resource for Genotyping Data Storage and Genotype Imputation

To improve the efficiency of high-density genotype data storage and imputation in bread wheat (Triticum aestivum L.), we applied the Practical Haplotype Graph (PHG) tool. The wheat PHG database was built using whole-exome capture sequencing data from a diverse set of 65 wheat accessions. Population haplotypes were inferred for the reference genome intervals defined by the boundaries of the high-quality gene models. Missing genotypes in the inference panels, composed of wheat cultivars or recombinant inbred lines genotyped by exome capture, genotyping-by-sequencing (GBS), or whole-genome skim-seq sequencing approaches, were imputed using the wheat PHG database. Though imputation accuracy varied depending on the method of sequencing and coverage depth, we found 93% imputation accuracy with 0.01x sequence coverage, which was only slightly lower than the accuracy obtained using the 0.5x sequence coverage (96.9%). Compared to Beagle, on average, PHG imputation was ~4% (p-value = 0.00027) more accurate, and showed 27% higher accuracy at imputing a rare haplotype introgressed from a wild relative into wheat. The reduced accuracy of imputation with GBS data (90.4%) is likely associated with the small overlap between GBS markers and the exome capture dataset, which was used for constructing PHG. The highest imputation accuracy was obtained with exome capture for the wheat D genome, which also showed the highest levels of linkage disequlibrium and proportion of identity-by-descent regions among accessions in our reference panel. We demonstrate that genetic mapping based on genotypes imputed using PHG identifies SNPs with a broader range of effect sizes that together explain a higher proportion of genetic variance for heading date and meiotic crossover rate compared to previous studies.

genomics↗

bioRxiv2021

Genomic Selection for End-Use Quality and Processing Traits in Soft White Winter Wheat Breeding Program with Machine and Deep Learning Models

Breeding for grain yield, biotic and abiotic stress resistance, and end-use quality are important goals of wheat breeding programs. Screening for end-use quality traits is usually secondary to grain yield due to high labor needs, cost of testing, and large seed requirements for phenotyping. Hence, testing is delayed until later stages in the breeding program. Delayed phenotyping results in advancement of inferior end-use quality lines into the program. Genomic selection provides an alternative to predict performance using genome-wide markers. Due to large datasets in breeding programs, we explored the potential of the machine and deep learning models to predict fourteen end-use quality traits in a winter wheat breeding program. The population used consisted of 666 wheat genotypes screened for five years (2015-19) at two locations (Pullman and Lind, WA, USA). Nine different models, including two machine learning (random forest and support vector machine) and two deep learning models (convolutional neural network and multilayer perceptron), were explored for cross-validation, forward, and across locations predictions. The prediction accuracies for different traits varied from 0.45-0.81, 0.29-0.55, and 0.27-0.50 under cross-validation, forward, and across location predictions. In general, forward prediction accuracies kept increasing over time due to increments in training data size and was more evident for machine and deep learning models. Deep learning models performed superior over the traditional ridge regression best linear unbiased prediction (RRBLUP) and Bayesian models under all prediction scenarios. The high accuracy observed for end-use quality traits in this study support predicting them in early generations, leading to the advancement of superior genotypes to more extensive grain yield trailing. Furthermore, the superior performance of machine and deep learning models strengthen the idea to include them in large scale breeding programs for predicting complex traits.

genetics↗

bioRxiv2021

Breeding with Major and Minor Genes: Genomic Selection for Quantitative Disease Resistance

Most disease resistance in plants is quantitative, with both major and minor genes controlling resistance. This research aimed to optimize genomic selection (GS) models for use in breeding programs needing to select both major and minor genes for resistance. In this experiment, stripe rust (Puccinia striiformis Westend. f. sp. tritici Erikss.) of wheat (Triticum aestivum L.) was used as a model for quantitative disease resistance. The quantitative nature of stripe rust is usually phenotyped with two disease traits, infection type and disease severity. We compared two types of training populations composed of 2,630 breeding lines phenotyped in single plot trials from four years (2016-2020) and 475 diversity panel lines from four years (2013-2016), both across two locations. We also compared the accuracy of models with four different major gene markers and genome-wide association (GWAS) markers as fixed effects. The prediction models used 31,975 markers replicated 50 times using 5-fold cross-validation. We then compared the GS models with marker-assisted selection to compare the prediction accuracy of the markers alone and in combination. The GS models had higher accuracies than marker-assisted selection and reached an accuracy of 0.72 for disease severity. The major gene and GWAS markers had only a small to zero increase in prediction accuracy over the base GS model, with the highest accuracy increase of 0.03 for major markers and 0.06 for GWAS markers. There was a statistical increase in accuracy by using the disease severity trait, the breeding lines, population type, and by combing years. There was also a statistical increase in accuracy using major markers within the validation sets as the mean accuracy decreased. The inclusion of fixed effects in low prediction scenarios increased accuracy up to 0.06 for GS models using significant GWAS markers. Our results indicate that GS can accurately predict quantitative disease resistance in the presence of major and minor genes.

genetics↗

bioRxiv2021

Genome-Wide Association Studies and Genomic Selection for Grain Protein Content Stability in a Nested Association Mapping Population of Spring Wheat

Grain protein content (GPC) is controlled by complex genetic systems and their interactions, and is an important quality determinant for hard spring wheat as it has a positive effect on bread and pasta quality. GPC is variable among genotypes and strongly influenced by environment. Thus, understanding the genetic control of wheat GPC and identifying genotypes with improved stability is an important breeding goal. The objectives of this research were to identify genetic backgrounds with less variation for GPC across environments and identify quantitative trait loci (QTLs) controlling the stability of GPC. A spring wheat nested association mapping (NAM) population of 650 recombinant inbred lines (RIL) derived from 26 diverse founder parents crossed to one common parent, Berkut, was phenotyped over three years of field trials (2014-2016). Genomic selection models were developed and compared based on prediction of GPC and GPC stability. After observing variable genetic control of GPC within the NAM population, seven RIL families displaying reduced marker-by-environment interaction were selected based on a stability index derived from Finlay-Wilkinson regression. A genome-wide association study identified seven significant QTLs for GPC stability with a Bonferroni-adjusted P value <0.05. This study also demonstrated that genome-wide prediction of GPC with ridge regression best linear unbiased estimates reached up to r = 0.69. Genomic selection can be used to apply selection pressure for GPC and improve genetic gain for GPC.

genomics↗

bioRxiv2021

Comparison of Genomic Selection Models for Exploring Predictive Ability of Complex Traits in Breeding Programs

Traits with a complex unknown genetic architecture are common in breeding programs. However, they pose a challenge for selection due to a combination of complex environmental and pleiotropic effects that impede the ability to create mapping populations to characterize the traits genetic basis. One such trait, seedling emergence of wheat (Triticum aestivum L.) from deep planting, presents a unique opportunity to explore the best method to use and implement GS models to predict a complex trait. 17 GS models were compared using two training populations, consisting of 473 genotypes from a diverse association mapping panel (DP) phenotyped from 2015-2019 and the other training population consisting of 643 breeding lines phenotyped in 2015 and 2020 in Lind, WA with 40,368 markers. There were only a few significant differences between GS models, with support vector machines reaching the highest accuracy of 0.56 in a single breeding line trial using cross-validations. However, the consistent moderate accuracy of cBLUP and other parametric models indicates no need to implement computationally demanding non-parametric models for complex traits. There was an increase in accuracy using cross-validations from 0.40 to 0.41 and independent validations from 0.10 to 0.17 using diversity panels lines to breeding lines. The environmental effects of complex traits can be overcome by combining years of the same populations. Overall, our study showed that breeders can accurately predict and implement GS for a complex trait by using parametric models within their own breeding programs with increased accuracy as they combine training populations over the years.

genetics↗

bioRxiv2021

Multi-Trait Machine and Deep Learning Models for Genomic Selection using Spectral Information in a Wheat Breeding Program

Prediction of breeding values and phenotypes is central to plant breeding and has been revolutionized by the adoption of genomic selection (GS). Use of machine and deep learning algorithms applied to complex traits in plants can improve prediction accuracies in the context of GS. Spectral reflectance indices further provide information about various physiological parameters previously undetectable in plants. This research explores the potential of multi-trait (MT) machine and deep learning models for predicting grain yield and grain protein content in wheat using spectral information in GS models. This study compares the performance of four machine and deep learning-based uni-trait (UT) and MT models with traditional GBLUP and Bayesian models. The dataset consisted of 650 recombinant inbred lines from a spring wheat breeding program, grown for three years (2014-2016), and spectral data were collected at heading and grain filling stages. MT-GS models performed 0-28.5% and -0.04-15% superior to the UT-GS models for predicting grain yield and grain protein content. Random forest and multilayer perceptron were the best performing machine and deep learning models to predict both traits. These two models performed similarly under UT and MT-GS models. Four explored Bayesian models gave similar accuracies, which were less than machine and deep learning-based models, and required increased computational time. Green normalized difference vegetation index best predicted grain protein content in seven out of the nine MT-GS models. Overall, this study concluded that machine and deep learning-based MT-GS models increased prediction accuracy and should be employed in large-scale breeding programs. Core IdeasO_LIPotential for combining high throughput phenotyping, machine and deep learning in breeding. C_LIO_LIMulti-trait models exploit information from secondary correlated traits efficiently. C_LIO_LISpectral information improves genomic selection models. C_LIO_LIDeep learning can aid plant breeders owing to increased data generated in breeding programs C_LI

genetics↗

bioRxiv2019

Gains through selection for grain yield in a winter wheat breeding program

Increased genetic gains for complex traits in plant breeding programs can be achieved through different selection strategies. The objective of this study was to compare potential gains for grain yield in a winter wheat breeding program through estimating response to selection R values across several selection approaches including phenotypic (PS), marker-based (MS), genomic (GS), and a combination of PS and GS. Five populations of Washington State University (WSU) winter wheat breeding lines evaluated from 2015 to 2018 in Lind and Pullman, WA, USA were used in the study. Selection was conducted by selecting the top 20% of lines based on observed yield (PS strategy), genomic estimated breeding values (GS), presence of yield \"enhancing\" alleles of the most significant single nucleotide polymorphism (SNP) markers identified from genome-wide association mapping (MS), and high observed yield and estimated breeding values (PS+GS). Overall, PS compared to other individual strategies showed the highest response. However, when combined with GS, a 23% improvement in R for yield was observed, indicating that gains could be improved by complementing traditional PS with GS. Using GS alone as a selection strategy for grain yield should be taken with caution. MS was not that successful in terms of R relative to the other selection approaches. Altogether, we demonstrated that gains through increased response to selection for yield could be achieved in the WSU winter wheat breeding program by implementing different selection strategies either exclusively or in combination.

genetics↗