High-dimensional and high throughput genomic, field performance, and environmental data are becoming increasingly available to crop breeding programs, and their integration can facilitate genomic prediction within and across environments and provide insights into the genetic architecture of complex traits and the nature of genotype-by-environment interactions. To partition trait variation into additive and dominance (main effect) genetic and corresponding genetic-by-environment variances, and to identify specific environmental factors that influence genotype-by-environment interactions, we curated and analyzed genotypic and phenotypic data on 1918 maize (Zea mays L.) hybrids and environmental data from 65 testing environments. For grain yield, dominance variance was similar in magnitude to additive variance, and genetic-by-environment variances were more important than genetic main effect variances. Models involving both additive and dominance relationships best fit the data and modeling unique genetic covariances among all environments provided the best characterization of the genotype-by-environment interaction patterns. Similarity of relative hybrid performance among environments was modeled as a function of underlying weather variables, permitting identification of weather covariates driving correlations of genetic effects across environments. The resulting models can be used for genomic prediction of mean hybrid performance across populations of environments tested or for environment-specific predictions. These results can also guide efforts to incorporate high-throughput environmental data into genomic prediction models and predict values in new environments characterized with the same environmental characteristics.

Technology advances have made possible the collection of a wealth of genomic, environmental, and phenotypic data for use in plant breeding. Incorporation of environmental data into environment-specific genomic prediction (GP) is hindered in part because of inherently high data dimensionality. Computationally efficient approaches to combining genomic and environmental information may facilitate extension of GP models to new environments and germplasm, and better understanding of genotype-by-environment (G × E) interactions. Using genomic, yield trial, and environmental data on 1,918 unique hybrids evaluated in 59 environments from the maize Genomes to Fields project, we determined that a set of 10,153 SNP dominance coefficients and a 5-day temporal window size for summarizing environmental variables were optimal for GP using only genetic and environmental main effects. Adding marker-by-environment variable interactions required dimension reduction, and we found that reducing dimensionality of the genetic data while keeping the full set of environmental covariates was best for environment-specific GP of grain yield, leading to an increase in prediction ability of 2.7% to achieve a prediction ability of 80% across environments when data were masked at random. We then measured how prediction ability within environments was affected under stratified training-testing sets to approximate scenarios commonly encountered by plant breeders, finding that incorporation of marker-by-environment effects improved prediction ability in cases where training and test sets shared environments, but did not improve prediction in new untested environments. The environmental similarity between training and testing sets had a greater impact on the efficacy of prediction than genetic similarity between training and test sets.

8543 Background: The current AJCC TNM staging system has poor specificity for predicting visceral metastatic risk in patients diagnosed with stage I or stage II cutaneous melanoma. We, therefore, developed a gene expression profile signature (GEP) following in silico investigation of previously published microarray analyses. Methods: 60 formalin fixed paraffin embedded primary cutaneous melanoma samples from patients with stage I or II cutaneous melanoma with at least a follow up period of at least 6 years were macrodissected and analyzed blindly. RNA was isolated, converted to cDNA and RT-PCR was performed to assess the expression of the gene set. Expression data and biostatistical analysis was performed using GeNorm and JMP Genomics (SAS) Predictive modeling included Radial Basis Machine (RBM) and Partition Tree Analysis (PTA) Metastasis-free survival (MFS) was assessed using Kaplan-Meier analysis. The following clinical data was retrieved from medical records: survival, metastases, types of metastases. 20 out of 60 patients had developed visceral metastases in the follow up period. Results: GEP was developed following multiple analytical approaches.Two types of signatures emerged: Low risk (Class 1) and High risk (Class 2). Without optimizing for sensitivity, the analyses of the 60 sample cohort by radial basis machine (RBM) resulted in 92% ROC (met. accuracy = 90%, non-met. accuracy = 85%), while partition tree analysis (PTA) yielded 99% ROC (met. accuracy = 100%, non-met. accuracy = 95%). RBM classification showed 6-year MFS rates of 97% for Class 1 and 19% for predicted Class 2 of metastasis (median MFS = NR and 5.6 yrs, resp., P<0.0001 Log-Rank respectively). PTA showed 6-year MFS rates of 100% for predicted Class 1 and 14% for Class 2 of metastasis (median MFS = NR and 5.4 yrs, resp., P<0.0001 Log-Rank respectively). Conclusions: This study shows that DecisionDx-Melanoma GEP signature can provide excellent accuracy in predicting metastatic risk in stage I and II cutaneous melanoma.To our knowledge, the GEP provides the most accurate predictor to date for development of visceral metastases in patients with Stage I and II cutaneous melanoma.

The Germplasm Enhancement of Maize (GEM) project was initiated in 1993 as a cooperative effort of public‐ and private‐sector maize (Zea mays L.) breeders to enhance the genetic diversity of the U.S. maize crop. The GEM project selects progeny lines with high topcross yield potential from crosses between elite temperate lines and exotic parents. The GEM project has released hundreds of useful breeding lines based on phenotypic selection within selfing generations and multienvironment yield evaluations of GEM line topcrosses to elite adapted testers. Developing genomic selection (GS) models for the GEM project may contribute to increases in the rate of genetic gain. Here we evaluated the prediction ability of GS models trained on 6 yr of topcross evaluations from the two GEM programs in Raleigh, NC, and Ames, IA, documenting prediction abilities ranging from 0.36 to 0.75 for grain yield and from 0.78 to 0.96 for grain moisture when models were cross‐validated within program and heterotic group. Predicted genetic gain from GS ranged from 0.95 to 2.58 times the gain from phenotypic selection. Prediction ability across program and heterotic group was generally poorer than within groups. Based on observed genomic relationships between GEM breeding lines and their tropical ancestors, GS for either yield or moisture would reduce recovery of exotic germplasm only slightly. Using GS models trained within program, the GEM programs should be able to more effectively deliver on its mission to broaden the genetic base of U.S. germplasm.