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.
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.
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.
During the last decade, the sorghum aphid (Melanaphis sorghi), previously identified as sugarcane aphid (Melanaphis sacchari), became a serious pest of sorghum, spreading to all sorghum‐producing regions in the United States, Mexico, and South America, where crop losses of 50%–100% have been reported. Developing sorghum cultivars with resistance to this insect is the most sustainable strategy for long‐term pest management. To design cultivars with aphid resistance, comprehensively understanding the mechanisms underlying aphid survival, host plant resistance, and aphid–sorghum interactions is critical. In this review, we summarize the comprehensive efforts to characterize the aphid populations as well as their interaction with sorghum plants via hormonal pathways that trigger various genes including leucine rich repeats, WRKY transcription factors, lipoxygenases, calmodulins, and others. We discuss efforts made during the last decade to identify specific genomic regions and candidate genes that confer aphid resistance, as well as describe recent successes and potential challenges in breeding for aphid resistance. Furthermore, we discuss the use of disruptive technologies like high‐throughput phenotyping, artificial intelligence, or machine learning for developing aphid resistant sorghum cultivars. Integration of these new technologies has the potential to accelerate the development and design of novel traits that confer durable aphid resistance in new sorghum cultivars to defend sorghum against new aphid genotype development.
1 January 2021 in Agrosystems, Geosciences & Environment
Energycane (Saccharum hybrid) could be a viable bioenergy crop for the Southeast United States. Five energycane cultivars were planted in 2008 at a northern (Watkinsville, GA) and a southern (Tifton, GA) site, and were grown for 7 yr to compare biomass yields. Plots were arranged in a four replicate randomized complete block design at each site. Energycane was grown under rainfed conditions with 90–112 kg ha–1 N applied annually. Plant height was recorded at least monthly, and stalks were sampled to determine juice volume and Brix (estimate of sugar concentration) at harvest. Whole plots were mechanically harvested each year after killing freeze and weighed to determine biomass yields. Biomass yield and mature plant height were strongly correlated at both Tifton (r = .746) and Watkinsville (r = .727). Biomass yields peaked in Year 4 at Tifton (39.8 Mg ha–1) and Year 5 at Watkinsville (30.5 Mg ha–1), but local weather conditions had a greater influence on yields than stand age. Day‐long freezes during the winter and late spring freezes after shoot emergence resulted in reduced growth rate and yields in subsequent growing seasons. These cold weather events were more common at Watkinsville than Tifton, resulting in yields being more variable at the northern location. The greatest yielding cultivars were Ho 06‐9001 (27.0 Mg ha–1) and Ho 06‐9002 (25.1 Mg ha–1). Stability analysis revealed that these two cultivars responded positively to favorable environments in terms of biomass yield and plant height.
Sorghum production is expanding to warmer and more humid regions where its production is being limited by multiple fungal pathogens. Anthracnose, caused by Colletotrichum sublineolum, is one of the major diseases in these regions, where it can cause yield losses of both grain and biomass. In this study, 114 recombinant inbred lines (RILs) derived from resistant sorghum line SC112-14 were evaluated at four distinct geographic locations in the United States for response to anthracnose. A genome scan using a high-density linkage map of 3,838 single nucleotide polymorphism (SNPs) detected two loci at 5.25 and 1.18 Mb on chromosomes 5 and 6, respectively, that explain up to 77% and 20% of the observed phenotypic variation. A bin-mapping approach using a subset of 31 highly informative RILs was employed to determine the disease response to inoculation with ten Anthracnose pathotypes in the greenhouse. A genome scan showed that the 5.25 Mb region on chromosome 5 is associated with a resistant response to nine pathotypes. Five SNP markers were developed and used to fine map the locus on chromosome 5 by evaluating 1,500 segregating F2:3 progenies. Based on the genotypic and phenotypic analyses of 11 recombinants, the locus was narrowed down to a 470-kb genomic region. Following a genome-wide association study based on 574 accessions previously phenotyped and genotyped, the resistance locus was delimited to a 34-kb genomic interval with five candidate genes. All five candidate genes encode proteins associated with plant immune systems, suggesting they may act in synergy in the resistance response.