@article{he_gage_rellan-alvarez_xiang_2024, title={Swin-Roleaf: A new method for characterizing leaf azimuth angle in large-scale maize plants}, volume={224}, ISSN={["1872-7107"]}, url={https://doi.org/10.1016/j.compag.2024.109120}, DOI={10.1016/j.compag.2024.109120}, journal={COMPUTERS AND ELECTRONICS IN AGRICULTURE}, author={He, Weilong and Gage, Joseph L. and Rellan-Alvarez, Ruben and Xiang, Lirong}, year={2024}, month={Sep} } @article{lima_aviles_alpers_mcfarland_kaeppler_ertl_romay_gage_holland_beissinger_et al._2023, title={2018-2019 field seasons of the Maize Genomes to Fields (G2F) G x E project}, volume={24}, ISSN={["2730-6844"]}, url={https://doi.org/10.1186/s12863-023-01129-2}, DOI={10.1186/s12863-023-01129-2}, abstractNote={Abstract Objectives This report provides information about the public release of the 2018–2019 Maize G X E project of the Genomes to Fields (G2F) Initiative datasets. G2F is an umbrella initiative that evaluates maize hybrids and inbred lines across multiple environments and makes available phenotypic, genotypic, environmental, and metadata information. The initiative understands the necessity to characterize and deploy public sources of genetic diversity to face the challenges for more sustainable agriculture in the context of variable environmental conditions. Data description Datasets include phenotypic, climatic, and soil measurements, metadata information, and inbred genotypic information for each combination of location and year. Collaborators in the G2F initiative collected data for each location and year; members of the group responsible for coordination and data processing combined all the collected information and removed obvious erroneous data. The collaborators received the data before the DOI release to verify and declare that the data generated in their own locations was accurate. ReadMe and description files are available for each dataset. Previous years of evaluation are already publicly available, with common hybrids present to connect across all locations and years evaluated since this project’s inception. }, number={1}, journal={BMC GENOMIC DATA}, author={Lima, Dayane Cristina and Aviles, Alejandro Castro and Alpers, Ryan Timothy and McFarland, Bridget A. and Kaeppler, Shawn and Ertl, David and Romay, Maria Cinta and Gage, Joseph L. and Holland, James and Beissinger, Timothy and et al.}, year={2023}, month={May} } @article{2018–2019 field seasons of the maize genomes to fields (g2f) g x e project_2023, DOI={10.60692/eaqkd-zeh53}, journal={OpenAlex}, year={2023}, month={May} } @article{2018–2019 field seasons of the maize genomes to fields (g2f) g x e project_2023, DOI={10.60692/qhfpr-sm790}, journal={OpenAlex}, year={2023}, month={May} } @article{lima_aviles_alpers_perkins_schoemaker_costa_michel_kaeppler_ertl_romay_et al._2023, title={2020-2021 field seasons of Maize GxE project within the Genomes to Fields Initiative}, volume={16}, ISSN={["1756-0500"]}, DOI={10.1186/s13104-023-06430-y}, abstractNote={Abstract Objectives This release note describes the Maize GxE project datasets within the Genomes to Fields (G2F) Initiative. The Maize GxE project aims to understand genotype by environment (GxE) interactions and use the information collected to improve resource allocation efficiency and increase genotype predictability and stability, particularly in scenarios of variable environmental patterns. Hybrids and inbreds are evaluated across multiple environments and phenotypic, genotypic, environmental, and metadata information are made publicly available. Data description The datasets include phenotypic data of the hybrids and inbreds evaluated in 30 locations across the US and one location in Germany in 2020 and 2021, soil and climatic measurements and metadata information for all environments (combination of year and location), ReadMe, and description files for each data type. A set of common hybrids is present in each environment to connect with previous evaluations. Each environment had a collaborator responsible for collecting and submitting the data, the GxE coordination team combined all the collected information and removed obvious erroneous data. Collaborators received the combined data to use, verify and declare that the data generated in their own environments was accurate. Combined data is released to the public with minimal filtering to maintain fidelity to the original data. }, number={1}, journal={BMC RESEARCH NOTES}, author={Lima, Dayane Cristina and Aviles, Alejandro Castro and Alpers, Ryan Timothy and Perkins, Alden and Schoemaker, Dylan L. and Costa, Martin and Michel, Kathryn J. and Kaeppler, Shawn and Ertl, David and Romay, Maria Cinta and et al.}, year={2023}, month={Sep} } @article{lima_washburn_varela_chen_gage_romay_holland_ertl_lopez-cruz_aguate_et al._2023, title={Genomes to Fields 2022 Maize genotype by Environment Prediction Competition}, volume={16}, ISSN={["1756-0500"]}, url={https://doi.org/10.1186/s13104-023-06421-z}, DOI={10.1186/s13104-023-06421-z}, abstractNote={Abstract Objectives The Genomes to Fields (G2F) 2022 Maize Genotype by Environment (GxE) Prediction Competition aimed to develop models for predicting grain yield for the 2022 Maize GxE project field trials, leveraging the datasets previously generated by this project and other publicly available data. Data description This resource used data from the Maize GxE project within the G2F Initiative [1]. The dataset included phenotypic and genotypic data of the hybrids evaluated in 45 locations from 2014 to 2022. Also, soil, weather, environmental covariates data and metadata information for all environments (combination of year and location). Competitors also had access to ReadMe files which described all the files provided. The Maize GxE is a collaborative project and all the data generated becomes publicly available [2]. The dataset used in the 2022 Prediction Competition was curated and lightly filtered for quality and to ensure naming uniformity across years. }, number={1}, journal={BMC RESEARCH NOTES}, author={Lima, Dayane Cristina and Washburn, Jacob D. and Varela, Jose Ignacio and Chen, Qiuyue and Gage, Joseph L. and Romay, Maria Cinta and Holland, James and Ertl, David and Lopez-Cruz, Marco and Aguate, Fernando M. and et al.}, year={2023}, month={Jul} } @article{kick_wallace_schnable_kolkman_alaca_beissinger_edwards_ertl_flint-garcia_gage_et al._2023, title={Yield prediction through integration of genetic, environment, and management data through deep learning}, volume={13}, ISSN={["2160-1836"]}, DOI={10.1093/g3journal/jkad006}, abstractNote={Abstract Accurate prediction of the phenotypic outcomes produced by different combinations of genotypes, environments, and management interventions remains a key goal in biology with direct applications to agriculture, research, and conservation. The past decades have seen an expansion of new methods applied toward this goal. Here we predict maize yield using deep neural networks, compare the efficacy of 2 model development methods, and contextualize model performance using conventional linear and machine learning models. We examine the usefulness of incorporating interactions between disparate data types. We find deep learning and best linear unbiased predictor (BLUP) models with interactions had the best overall performance. BLUP models achieved the lowest average error, but deep learning models performed more consistently with similar average error. Optimizing deep neural network submodules for each data type improved model performance relative to optimizing the whole model for all data types at once. Examining the effect of interactions in the best-performing model revealed that including interactions altered the model's sensitivity to weather and management features, including a reduction of the importance scores for timepoints expected to have a limited physiological basis for influencing yield—those at the extreme end of the season, nearly 200 days post planting. Based on these results, deep learning provides a promising avenue for the phenotypic prediction of complex traits in complex environments and a potential mechanism to better understand the influence of environmental and genetic factors.}, number={4}, journal={G3-GENES GENOMES GENETICS}, author={Kick, Daniel R. and Wallace, Jason G. and Schnable, James C. and Kolkman, Judith M. and Alaca, Baris and Beissinger, Timothy M. and Edwards, Jode and Ertl, David and Flint-Garcia, Sherry and Gage, Joseph L. and et al.}, year={2023}, month={Apr} } @article{gage_mali_mcloughlin_khaipho-burch_monier_bailey-serres_vierstra_buckler_2022, title={Variation in upstream open reading frames contributes to allelic diversity in maize protein abundance}, volume={119}, ISSN={["1091-6490"]}, DOI={10.1073/pnas.2112516119}, abstractNote={Significance Proteins are the machinery which execute essential cellular functions. However, measuring their abundance within an organism can be difficult and resource-intensive. Cells use a variety of mechanisms to control protein synthesis from mRNA, including short open reading frames (uORFs) that lie upstream of the main coding sequence. Ribosomes can preferentially translate uORFs instead of the main coding sequence, leading to reduced translation of the main protein. In this study, we show that uORF sequence variation between individuals can lead to different rates of protein translation and thus variable protein abundances. We also demonstrate that natural variation in uORFs occurs frequently and can be linked to whole-plant phenotypes, indicating that uORF sequence variation likely contributes to plant adaptation.}, number={14}, journal={PROCEEDINGS OF THE NATIONAL ACADEMY OF SCIENCES OF THE UNITED STATES OF AMERICA}, author={Gage, Joseph L. and Mali, Sujina and McLoughlin, Fionn and Khaipho-Burch, Merritt and Monier, Brandon and Bailey-Serres, Julia and Vierstra, Richard D. and Buckler, Edward S.}, year={2022}, month={Apr} } @article{yield prediction through integration of genetic, environment, and management data through deep learning_2022, volume={7}, url={http://dx.doi.org/10.1101/2022.07.29.502051}, DOI={10.1101/2022.07.29.502051}, abstractNote={AbstractAccurate prediction of the phenotypic outcomes produced by different combinations of genotypes, environments, and management interventions remains a key goal in biology with direct applications to agriculture, research, and conservation. The past decades have seen an expansion of new methods applied towards this goal. Here we predict maize yield using deep neural networks, compare the efficacy of two model development methods, and contextualize model performance using linear models, which are the conventional method for this task, and machine learning models We examine the usefulness of incorporating interactions between disparate data types. We find a deep learning model with interactions has the best average performance. Optimizing submodules for each datatype improved model performance relative to optimizing the whole model for all data types at once. Examining the effect of interactions in the best performing model revealed that including interactions altered the model’s sensitivity to weather and management features, including a reduction of the importance scores for timepoints expected to have limited physiological basis for influencing yield – those at the extreme end of the season, nearly 200 days post planting. Based on these results, deep learning provides a promising avenue for phenotypic prediction of complex traits in complex environments and a potential mechanism to better understand the influence of environmental and genetic factors.}, journal={[]}, publisher={Cold Spring Harbor Laboratory}, year={2022}, month={Jul} } @article{feldmann_gage_turner-hissong_ubbens_2021, title={Images carried before the fire: The power, promise, and responsibility of latent phenotyping in plants}, volume={4}, url={http://dx.doi.org/10.1002/ppj2.20023}, DOI={10.1002/ppj2.20023}, abstractNote={AbstractUnderstanding the genetic basis of plant traits requires comprehensive and quantitative descriptions of the phenotypic variation that exists within populations. Cameras and other sensors have made high‐throughput phenotyping possible, but image‐based phenotyping procedures involve a step where a researcher selects the traits to be measured. This feature selection step is inherently prone to human biases. Recently, a set of phenotyping approaches, which are referred to collectively as latent phenotyping techniques, have arisen in the literature. Latent phenotyping techniques isolate a latent source of variance in the data, such as stress or genotype, and then quantify the effect of this latent source of variance using latent variables without defining any conventional traits. In this review, we discuss the differences between, and challenges of, both traditional and latent phenotyping.}, number={1}, journal={The Plant Phenome Journal}, publisher={Wiley}, author={Feldmann, Mitchell J. and Gage, Joseph L. and Turner-Hissong, Sarah D. and Ubbens, Jordan R.}, year={2021}, month={Jan} } @article{franco_gage_bradbury_johnson_miller_buckler_romay_2020, title={A Maize Practical Haplotype Graph Leverages Diverse NAM Assemblies}, volume={8}, url={http://dx.doi.org/10.1101/2020.08.31.268425}, DOI={10.1101/2020.08.31.268425}, abstractNote={AbstractAs a result of millions of years of transposon activity, multiple rounds of ancient polyploidization, and large populations that preserve diversity, maize has an extremely structurally diverse genome, evidenced by high-quality genome assemblies that capture substantial levels of both tropical and temperate diversity. We generated a pangenome representation (the Practical Haplotype Graph, PHG) of these assemblies in a database, representing the pangenome haplotype diversity and providing an initial estimate of structural diversity. We leveraged the pangenome to accurately impute haplotypes and genotypes of taxa using various kinds of sequence data, ranging from WGS to extremely-low coverage GBS. We imputed the genotypes of the recombinant inbred lines of the NAM population with over 99% mean accuracy, while unrelated germplasm attained a mean imputation accuracy of 92 or 95% when using GBS or WGS data, respectively. Most of the imputation errors occur in haplotypes within European or tropical germplasm, which have yet to be represented in the maize PHG database. Also, the PHG stores the imputation data in a 30,000-fold more space-efficient manner than a standard genotype file, which is a key improvement when dealing with large scale data.}, journal={[]}, publisher={Cold Spring Harbor Laboratory}, author={Franco, Jose A. Valdes and Gage, Joseph L. and Bradbury, Peter J. and Johnson, Lynn C. and Miller, Zachary R. and Buckler, Edward S. and Romay, M. Cinta}, year={2020}, month={Aug} } @article{mcfarland_alkhalifah_bohn_bubert_buckler_ciampitti_edwards_ertl_gage_falcon_et al._2020, title={Maize genomes to fields (G2F): 2014–2017 field seasons: genotype, phenotype, climatic, soil, and inbred ear image datasets}, volume={13}, url={http://dx.doi.org/10.1186/s13104-020-4922-8}, DOI={10.1186/s13104-020-4922-8}, abstractNote={Abstract Objectives Advanced tools and resources are needed to efficiently and sustainably produce food for an increasing world population in the context of variable environmental conditions. The maize genomes to fields (G2F) initiative is a multi-institutional initiative effort that seeks to approach this challenge by developing a flexible and distributed infrastructure addressing emerging problems. G2F has generated large-scale phenotypic, genotypic, and environmental datasets using publicly available inbred lines and hybrids evaluated through a network of collaborators that are part of the G2F’s genotype-by-environment (G × E) project. This report covers the public release of datasets for 2014–2017. Data description Datasets include inbred genotypic information; phenotypic, climatic, and soil measurements and metadata information for each testing location across years. For a subset of inbreds in 2014 and 2015, yield component phenotypes were quantified by image analysis. Data released are accompanied by README descriptions. For genotypic and phenotypic data, both raw data and a version without outliers are reported. For climatic data, a version calibrated to the nearest airport weather station and a version without outliers are reported. The 2014 and 2015 datasets are updated versions from the previously released files [1] while 2016 and 2017 datasets are newly available to the public. }, number={1}, journal={BMC Research Notes}, publisher={Springer Science and Business Media LLC}, author={McFarland, Bridget A. and AlKhalifah, Naser and Bohn, Martin and Bubert, Jessica and Buckler, Edward S. and Ciampitti, Ignacio and Edwards, Jode and Ertl, David and Gage, Joseph L. and Falcon, Celeste M. and et al.}, year={2020}, month={Dec} } @article{gage_monier_giri_buckler_2020, title={Ten Years of the Maize Nested Association Mapping Population: Impact, Limitations, and Future Directions}, volume={32}, url={http://dx.doi.org/10.1105/tpc.19.00951}, DOI={10.1105/tpc.19.00951}, abstractNote={Abstract It has been just over a decade since the release of the maize (Zea mays) Nested Association Mapping (NAM) population. The NAM population has been and continues to be an invaluable resource for the maize genetics community and has yielded insights into the genetic architecture of complex traits. The parental lines have become some of the most well-characterized maize germplasm, and their de novo assemblies were recently made publicly available. As we enter an exciting new stage in maize genomics, this retrospective will summarize the design and intentions behind the NAM population; its application, the discoveries it has enabled, and its influence in other systems; and use the past decade of hindsight to consider whether and how it will remain useful in a new age of genomics.}, number={7}, journal={The Plant Cell}, publisher={Oxford University Press (OUP)}, author={Gage, Joseph L. and Monier, Brandon and Giri, Anju and Buckler, Edward S.}, year={2020}, month={Jul}, pages={2083–2093} } @article{genome-wide association analysis of stalk biomass and anatomical traits in maize._2019, url={http://europepmc.org/articles/PMC6357476}, DOI={10.1186/s12870-019-1653-x}, abstractNote={Maize stover is an important source of crop residues and a promising sustainable energy source in the United States. Stalk is the main component of stover, representing about half of stover dry weight. Characterization of genetic determinants of stalk traits provide a foundation to optimize maize stover as a biofuel feedstock. We investigated maize natural genetic variation in genome-wide association studies (GWAS) to detect candidate genes associated with traits related to stalk biomass (stalk diameter and plant height) and stalk anatomy (rind thickness, vascular bundle density and area). Using a panel of 942 diverse inbred lines, 899,784 RNA-Seq derived single nucleotide polymorphism (SNP) markers were identified. Stalk traits were measured on 800 members of the panel in replicated field trials across years. GWAS revealed 16 candidate genes associated with four stalk traits. Most of the detected candidate genes were involved in fundamental cellular functions, such as regulation of gene expression and cell cycle progression. Two of the regulatory genes (Zmm22 and an ortholog of Fpa) that were associated with plant height were previously shown to be involved in regulating the vegetative to floral transition. The association of Zmm22 with plant height was confirmed using a transgenic approach. Transgenic lines with increased expression of Zmm22 showed a significant decrease in plant height as well as tassel branch number, indicating a pleiotropic effect of Zmm22. Substantial heritable variation was observed in the association panel for stalk traits, indicating a large potential for improving useful stalk traits in breeding programs. Genome-wide association analyses detected several candidate genes associated with multiple traits, suggesting common regulatory elements underlie various stalk traits. Results of this study provide insights into the genetic control of maize stalk anatomy and biomass.}, journal={BMC plant biology}, year={2019}, month={Jan} } @article{gage_richards_lepak_kaczmar_soman_chowdhary_gore_buckler_2019, title={In‐Field Whole‐Plant Maize Architecture Characterized by Subcanopy Rovers and Latent Space Phenotyping}, volume={2}, url={http://dx.doi.org/10.2135/tppj2019.07.0011}, DOI={10.2135/tppj2019.07.0011}, abstractNote={ Core Ideas Subcanopy rovers enabled 3D characterization of thousands of hybrid maize plots. Machine learning produces heritable latent traits that describe plant architecture. Rover‐based phenotyping is far more efficient than manual phenotyping. Latent phenotypes from rovers are ready for application to plant biology and breeding. Collecting useful, interpretable, and biologically relevant phenotypes in a resource‐efficient manner is a bottleneck to plant breeding, genetic mapping, and genomic prediction. Autonomous and affordable subcanopy rovers are an efficient and scalable way to generate sensor‐based datasets of in‐field crop plants. Rovers equipped with lidar can produce three‐dimensional reconstructions of entire hybrid maize (Zea mays L.) fields. In this study, we collected 2103 lidar scans of hybrid maize field plots and extracted phenotypic data from them by latent space phenotyping. We performed latent space phenotyping by two methods, principal component analysis and a convolutional autoencoder, to extract meaningful, quantitative latent space phenotypes (LSPs) describing whole‐plant architecture and biomass distribution. The LSPs had heritabilities of up to 0.44, similar to some manually measured traits, indicating that they can be selected on or genetically mapped. Manually measured traits can be successfully predicted by using LSPs as explanatory variables in partial least squares regression, indicating that the LSPs contain biologically relevant information about plant architecture. These techniques can be used to assess crop architecture at a reduced cost and in an automated fashion for breeding, research, or extension purposes, as well as to create or inform crop growth models.}, number={1}, journal={The Plant Phenome Journal}, publisher={Wiley}, author={Gage, Joseph L. and Richards, Elliot and Lepak, Nicholas and Kaczmar, Nicholas and Soman, Chinmay and Chowdhary, Girish and Gore, Michael A. and Buckler, Edward S.}, year={2019}, month={Jan}, pages={1–11} } @misc{lidar point clouds of hybrid maize_2019, DOI={10.25739/zxp6-g188}, journal={CyVerse Data Commons}, year={2019} } @article{multiple maize reference genomes impact the identification of variants by genome-wide association study in a diverse inbred panel_2019, url={http://dx.doi.org/10.3835/plantgenome2018.09.0069}, DOI={10.3835/plantgenome2018.09.0069}, abstractNote={Use of a single reference genome for genome‐wide association studies (GWAS) limits the gene space represented to that of a single accession. This limitation can complicate identification and characterization of genes located within presence–absence variations (PAVs). In this study, we present the draft de novo genome assembly of ‘PHJ89’, an ‘Oh43’‐type inbred line of maize (Zea mays L.). From three separate reference genome assemblies (‘B73’, ‘PH207’, and PHJ89) that represent the predominant germplasm groups of maize, we generated three separate whole‐seedling gene expression profiles and single nucleotide polymorphism (SNP) matrices from a panel of 942 diverse inbred lines. We identified 34,447 (B73), 39,672 (PH207), and 37,436 (PHJ89) transcripts that are not present in the respective reference genome assemblies. Genome‐wide association studies were conducted in the 942 inbred panel with both the SNP and expression data values to map Sugarcane mosaic virus (SCMV) resistance. Highlighting the impact of alternative reference genomes in gene discovery, the GWAS results for SCMV resistance with expression values as a surrogate measure of PAV resulted in robust detection of the physical location of a known resistance gene when the B73 reference that contains the gene was used, but not the PH207 reference. This study provides the valuable resource of the Oh43‐type PHJ89 genome assembly as well as SNP and expression data for 942 individuals generated from three different reference genomes.}, journal={The Plant Genome}, year={2019} } @article{residual heterozygosity and epistatic interactions underlie the complex genetic architecture of yield in diploid potato._2019, url={https://doi.org/10.1534/genetics.119.302036}, DOI={10.1534/genetics.119.302036}, abstractNote={Abstract Marand et al. use a high-resolution recombination map to dissect the genetic components of yield in diploid potato. Regions of recalcitrant heterozygosity in the inbred parent co-localized with elevated recombination rates, signatures of selection, and tissue-specific gene expression... Deconvolution of the genetic architecture underlying yield is critical for understanding bases of genetic gain in species of agronomic importance. To dissect the genetic components of yield in potato, we adopted a reference-based recombination map composed of four segregating alleles from an interspecific pseudotestcross F1 potato population (n = 90). Approximately 1.5 million short nucleotide variants were utilized during map construction, resulting in unprecedented resolution for an F1 population, estimated by a median bin length of 146 kb and 11 genes per bin. Regression models uncovered 14 quantitative trait loci (QTL) underpinning yield, average tuber weight, and tubers produced per plant in a population exhibiting a striking 332% average midparent-value heterosis. Nearly 80% of yield-associated QTL were epistatic, and contained between 0 and 44 annotated genes. We found that approximately one-half of epistatic QTL overlap regions of residual heterozygosity identified in the inbred parental parent (M6). Genomic regions recalcitrant to inbreeding were associated with an increased density of genes, many of which demonstrated signatures of selection and floral tissue specificity. Dissection of the genome-wide additive and dominance values for yield and yield components indicated a widespread prevalence of dominance contributions in this population, enriched at QTL and regions of residual heterozygosity. Finally, the effects of short nucleotide variants and patterns of gene expression were determined for all genes underlying yield-associated QTL, exposing several promising candidate genes for future investigation.}, journal={Genetics}, year={2019}, month={Mar} } @article{gage_de_clayton_2018, title={Comparing Genome-Wide Association Study Results from Different Measurements of an Underlying Phenotype.}, volume={9}, url={http://europepmc.org/abstract/med/30262522}, DOI={10.1534/g3.118.200700}, abstractNote={Abstract Increasing popularity of high-throughput phenotyping technologies, such as image-based phenotyping, offer novel ways for quantifying plant growth and morphology. These new methods can be more or less accurate and precise than traditional, manual measurements. Many large-scale phenotyping efforts are conducted to enable genome-wide association studies (GWAS), but it is unclear exactly how alternative methods of phenotyping will affect GWAS results. In this study we simulate phenotypes that are controlled by the same set of causal loci but have differing heritability, similar to two different measurements of the same morphological character. We then perform GWAS with the simulated traits and create receiver operating characteristic (ROC) curves from the results. The areas under the ROC curves (AUCs) provide a metric that allows direct comparisons of GWAS results from different simulated traits. We use this framework to evaluate the effects of heritability and the number of causative loci on the AUCs of simulated traits; we also test the differences between AUCs of traits with differing heritability. We find that both increasing the number of causative loci and decreasing the heritability reduce a trait’s AUC. We also find that when two traits are controlled by a greater number of causative loci, they are more likely to have significantly different AUCs as the difference between their heritabilities increases. When simulation results are applied to measures of tassel morphology, we find no significant difference between AUCs from GWAS using manual and image-based measurements of typical maize tassel characters. This finding indicates that both measurement methods have similar ability to identify genetic associations. These results provide a framework for deciding between competing phenotyping strategies when the ultimate goal is to generate and use phenotype-genotype associations from GWAS.}, journal={G3 (Bethesda, Md.)}, author={Gage, JL and de, Leon N and Clayton, MK}, year={2018}, month={Sep} } @article{gage_white_edwards_kaeppler_de_2018, title={Selection Signatures Underlying Dramatic Male Inflorescence Transformation During Modern Hybrid Maize Breeding.}, volume={9}, url={http://europepmc.org/abstract/med/30257936}, DOI={10.1534/genetics.118.301487}, abstractNote={Abstract Inflorescence capacity plays a crucial role in reproductive fitness in plants, and in production of hybrid crops. Maize is a monoecious species bearing separate male and female flowers (tassel and ear, respectively). The switch from open-pollinated populations of maize to hybrid-based breeding schemes in the early 20th century was accompanied by a dramatic reduction in tassel size, and the trend has continued with modern breeding over the recent decades. The goal of this study was to identify selection signatures in genes that may underlie this dramatic transformation. Using a population of 942 diverse inbred maize accessions and a nested association mapping population comprising three 200-line biparental populations, we measured 15 tassel morphological characteristics by manual and image-based methods. Genome-wide association studies identified 242 single nucleotide polymorphisms significantly associated with measured traits. We compared 41 unselected lines from the Iowa Stiff Stalk Synthetic (BSSS) population to 21 highly selected lines developed by modern commercial breeding programs, and found that tassel size and weight were reduced significantly. We assayed genetic differences between the two groups using three selection statistics: cross population extended haplotype homozogysity, cross-population composite likelihood ratio, and fixation index. All three statistics show evidence of selection at genomic regions associated with tassel morphology relative to genome-wide null distributions. These results support the tremendous effect, both phenotypic and genotypic, that selection has had on maize male inflorescence morphology.}, journal={Genetics}, author={Gage, JL and White and Edwards, JW and Kaeppler, S and de, Leon N}, year={2018}, month={Sep} } @article{gage_miller_spalding_kaeppler_leon_2017, title={TIPS: a system for automated image-based phenotyping of maize tassels}, volume={13}, url={http://dx.doi.org/10.1186/s13007-017-0172-8}, DOI={10.1186/s13007-017-0172-8}, abstractNote={The maize male inflorescence (tassel) produces pollen necessary for reproduction and commercial grain production of maize. The size of the tassel has been linked to factors affecting grain yield, so understanding the genetic control of tassel architecture is an important goal. Tassels are fragile and deform easily after removal from the plant, necessitating rapid measurement of any shape characteristics that cannot be retained during storage. Some morphological characteristics of tassels such as curvature and compactness are difficult to quantify using traditional methods, but can be quantified by image-based phenotyping tools. These constraints necessitate the development of an efficient method for capturing natural-state tassel morphology and complementary automated analytical methods that can quickly and reproducibly quantify traits of interest such as height, spread, and branch number. This paper presents the Tassel Image-based Phenotyping System (TIPS), which provides a platform for imaging tassels in the field immediately following removal from the plant. TIPS consists of custom methods that can quantify morphological traits from profile images of freshly harvested tassels acquired with a standard digital camera in a field-deployable light shelter. Correlations between manually measured traits (tassel weight, tassel length, spike length, and branch number) and image-based measurements ranged from 0.66 to 0.89. Additional tassel characteristics quantified by image analysis included some that cannot be quantified manually, such as curvature, compactness, fractal dimension, skeleton length, and perimeter. TIPS was used to measure tassel phenotypes of 3530 individual tassels from 749 diverse inbred lines that represent the diversity of tassel morphology found in modern breeding and academic research programs. Repeatability ranged from 0.85 to 0.92 for manually measured phenotypes, from 0.77 to 0.83 for the same traits measured by image-based methods, and from 0.49 to 0.81 for traits that can only be measured by image analysis. TIPS allows morphological features of maize tassels to be quantified automatically, with minimal disturbance, at a scale that supports population-level studies. TIPS is expected to accelerate the discovery of associations between genetic loci and tassel morphology characteristics, and can be applied to maize breeding programs to increase productivity with lower resource commitment.}, number={1}, journal={Plant Methods}, author={Gage, Joseph L. and Miller, Nathan D. and Spalding, Edgar P. and Kaeppler, Shawn M. and Leon, Natalia}, year={2017}, pages={21} } @article{gage_jarquin_romay_lorenz_buckler_kaeppler_alkhalifah_bohn_campbell_edwards_et al._2017, title={The effect of artificial selection on phenotypic plasticity in maize}, volume={8}, ISSN={["2041-1723"]}, url={https://doi.org/10.1038/s41467-017-01450-2}, DOI={10.1038/s41467-017-01450-2}, abstractNote={AbstractRemarkable productivity has been achieved in crop species through artificial selection and adaptation to modern agronomic practices. Whether intensive selection has changed the ability of improved cultivars to maintain high productivity across variable environments is unknown. Understanding the genetic control of phenotypic plasticity and genotype by environment (G × E) interaction will enhance crop performance predictions across diverse environments. Here we use data generated from the Genomes to Fields (G2F) Maize G × E project to assess the effect of selection on G × E variation and characterize polymorphisms associated with plasticity. Genomic regions putatively selected during modern temperate maize breeding explain less variability for yield G × E than unselected regions, indicating that improvement by breeding may have reduced G × E of modern temperate cultivars. Trends in genomic position of variants associated with stability reveal fewer genic associations and enrichment of variants 0–5000 base pairs upstream of genes, hypothetically due to control of plasticity by short-range regulatory elements.}, number={1}, journal={NATURE COMMUNICATIONS}, publisher={Springer Nature}, author={Gage, Joseph L. and Jarquin, Diego and Romay, Cinta and Lorenz, Aaron and Buckler, Edward S. and Kaeppler, Shawn and Alkhalifah, Naser and Bohn, Martin and Campbell, Darwin A. and Edwards, Jode and et al.}, year={2017}, month={Nov} } @article{spindel_wright_chen_cobb_gage_harrington_lorieux_ahmadi_mccouch_2013, title={Bridging the genotyping gap: using genotyping by sequencing (GBS) to add high-density SNP markers and new value to traditional bi-parental mapping and breeding populations.}, volume={8}, url={http://www.ncbi.nlm.nih.gov/pubmed/23918062}, DOI={10.1007/s00122-013-2166-x}, abstractNote={Genotyping by sequencing (GBS) is the latest application of next-generation sequencing protocols for the purposes of discovering and genotyping SNPs in a variety of crop species and populations. Unlike other high-density genotyping technologies which have mainly been applied to general interest "reference" genomes, the low cost of GBS makes it an attractive means of saturating mapping and breeding populations with a high density of SNP markers. One barrier to the widespread use of GBS has been the difficulty of the bioinformatics analysis as the approach is accompanied by a high number of erroneous SNP calls which are not easily diagnosed or corrected. In this study, we use a 384-plex GBS protocol to add 30,984 markers to an indica (IR64) × japonica (Azucena) mapping population consisting of 176 recombinant inbred lines of rice (Oryza sativa) and we release our imputation and error correction pipeline to address initial GBS data sparsity and error, and streamline the process of adding SNPs to RIL populations. Using the final imputed and corrected dataset of 30,984 markers, we were able to map recombination hot and cold spots and regions of segregation distortion across the genome with a high degree of accuracy, thus identifying regions of the genome containing putative sterility loci. We mapped QTL for leaf width and aluminum tolerance, and were able to identify additional QTL for both phenotypes when using the full set of 30,984 SNPs that were not identified using a subset of only 1,464 SNPs, including a previously unreported QTL for aluminum tolerance located directly within a recombination hotspot on chromosome 1. These results suggest that adding a high density of SNP markers to a mapping or breeding population through GBS has a great value for numerous applications in rice breeding and genetics research.}, journal={TAG. Theoretical and applied genetics. Theoretische und angewandte Genetik}, author={Spindel, Jennifer and Wright, Mark and Chen, Charles and Cobb, Joshua and Gage, Joseph and Harrington, Sandra and Lorieux, Mathias and Ahmadi, Nourollah and McCouch, Susan}, year={2013}, month={Aug} }