{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T17:37:17Z","timestamp":1793381837910,"version":"4.5.0"},"reference-count":19,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32341036"],"award-info":[{"award-number":["32341036"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Plant Sci."],"abstract":"<jats:p>\n                    Breeding programs increasingly need prediction systems that support reliable candidate selection across heterogeneous environments, which makes cross-environment genomic prediction an important component of multienvironment crop improvement. However, model evaluation still relies heavily on Pearson\u2019s correlation coefficient (\n                    <jats:italic>r<\/jats:italic>\n                    ), a global summary that may not fully capture which top-ranked candidates would be advanced. Using maize and switchgrass datasets as focused case studies, we compared global predictive ability with phenotype-referenced candidate diagnostics across within-environment and directed cross-environment evaluations of rrBLUP\/ridge, Light Gradient Boosting Machine (LightGBM), a multilayer perceptron, and mixed-effect deep neural network (MeNet). Rather than proposing a new selection metric, we used a conditional comparison framework that distinguishes nominal metric reversal from strict decision-level discordance among models with similar Pearson\u2019s\n                    <jats:italic>r<\/jats:italic>\n                    . The\n                    <jats:italic>r<\/jats:italic>\n                    -best and candidate-metric-best models disagreed in 25%\u201355% of evaluation contexts, but large differences in candidate metrics among near-\n                    <jats:italic>r<\/jats:italic>\n                    models (|\u0394\n                    <jats:italic>r<\/jats:italic>\n                    | \u2264 0.02) were uncommon. Nevertheless, models with nearly identical\n                    <jats:italic>r<\/jats:italic>\n                    did not always prioritize the same candidates: LightGBM and rrBLUP\/ridge shared, on average, 72.9% of the top 5% candidates in maize and 68.8% in switchgrass. These results indicate that Pearson\u2019s\n                    <jats:italic>r<\/jats:italic>\n                    remains informative for broad model comparison but does not fully describe decision-level behavior. Phenotype-referenced candidate diagnostics are therefore best used as targeted complements when models have similar predictive ability, selection intensity is high, or candidate identity is consequential across environments.\n                  <\/jats:p>","DOI":"10.3389\/fpls.2026.1951182","type":"journal-article","created":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T04:48:01Z","timestamp":1790830081000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Selection-aware metrics provide complementary decision-level information in plant genomic prediction"],"prefix":"10.3389","volume":"17","author":[{"given":"Xueyang","family":"Wang","sequence":"first","affiliation":[{"name":"Frontiers Science Center for Molecular Design Breeding, State Key Laboratory of Maize Bio-Breeding, National Maize Improvement Center, College of Agronomy and Biotechnology, China Agricultural University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Yan","sequence":"additional","affiliation":[{"name":"Frontiers Science Center for Molecular Design Breeding, State Key Laboratory of Maize Bio-Breeding, National Maize Improvement Center, College of Agronomy and Biotechnology, China Agricultural University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"3691","DOI":"10.1534\/g3.119.400498","article-title":"Benchmarking parametric and machine learning models for genomic prediction of complex traits","volume":"9","author":"Azodi","year":"2019","journal-title":"G3: Genes|Genomes|Genetics."},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0128570","article-title":"A ranking approach to genomic selection","volume":"10","author":"Blondel","year":"2015","journal-title":"PloS One"},{"key":"B3","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1007\/s00122-024-04766-y","article-title":"Constructing training sets for genomic selection to identify superior genotypes in candidate populations","volume":"137","author":"Chen","year":"2024","journal-title":"Theor. Appl. Genet."},{"key":"B4","doi-asserted-by":"publisher","first-page":"756","DOI":"10.1016\/j.tplants.2024.12.009","article-title":"Expanding genomic prediction in plant breeding: harnessing big data, machine learning, and advanced software","volume":"30","author":"Crossa","year":"2025","journal-title":"Trends Plant Sci."},{"key":"B5","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1534\/genetics.112.143313","article-title":"Whole-genome regression and prediction methods applied to plant and animal breeding","volume":"193","author":"de los Campos","year":"2013","journal-title":"Genetics"},{"key":"B6","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1534\/g3.119.400759","article-title":"Novel Bayesian networks for genomic prediction of developmental traits in biomass sorghum","volume":"10","author":"dos Santos","year":"2020","journal-title":"G3: Genes|Genomes|Genetics."},{"key":"B7","doi-asserted-by":"publisher","first-page":"250","DOI":"10.3835\/plantgenome2011.08.0024","article-title":"Ridge regression and other kernels for genomic selection with R package rrBLUP","volume":"4","author":"Endelman","year":"2011","journal-title":"Plant Genome"},{"key":"B8","doi-asserted-by":"publisher","first-page":"170055","DOI":"10.3835\/plantgenome2017.06.0055","article-title":"Extensive genetic diversity is present within North American switchgrass germplasm","volume":"11","author":"Evans","year":"2018","journal-title":"Plant Genome"},{"key":"B9","doi-asserted-by":"publisher","first-page":"390","DOI":"10.1111\/jbg.12420","article-title":"Effect of selection and selective genotyping for creation of reference on bias and accuracy of genomic prediction","volume":"136","author":"Gowane","year":"2019","journal-title":"J. Anim. Breed. Genet."},{"key":"B10","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1186\/s12711-025-01022-9","article-title":"Normalized cumulative gain as an alternative evaluation measure for genomic selection models","volume":"57","author":"Heinrich","year":"2025","journal-title":"Genet. Sel. Evol."},{"key":"B11","first-page":"3146","article-title":"LightGBM: a highly efficient gradient boosting decision tree","volume":"30","author":"Ke","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"B12","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1186\/s12711-018-0426-6","article-title":"Semi-parametric estimates of population accuracy and bias of predictions of breeding values and future phenotypes using the LR method","volume":"50","author":"Legarra","year":"2018","journal-title":"Genet. Sel. Evol."},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.xplc.2025.101620","article-title":"MeNet: a mixed-effect deep neural network for multi-environment genomic prediction of agronomic traits","volume":"7","author":"Li","year":"2026","journal-title":"Plant Commun."},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0112227","article-title":"Accelerating the switchgrass (Panicum virgatum L.) breeding cycle using genomic selection approaches","volume":"9","author":"Lipka","year":"2014","journal-title":"PloS One"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1819","DOI":"10.1093\/genetics\/157.4.1819","article-title":"Prediction of total genetic value using genome-wide dense marker maps","volume":"157","author":"Meuwissen","year":"2001","journal-title":"Genetics"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.3390\/plants14030308","article-title":"Balancing sensitivity and specificity enhances top and bottom ranking in genomic prediction of cultivars","volume":"14","author":"Montesinos-Lopez","year":"2025","journal-title":"Plants"},{"key":"B17","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1038\/hdy.2013.144","article-title":"Genomic-enabled prediction with classification algorithms","volume":"112","author":"Ornella","year":"2014","journal-title":"Heredity"},{"key":"B18","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1186\/s13059-021-02370-7","article-title":"The genetic mechanism of heterosis utilization in maize improvement","volume":"22","author":"Xiao","year":"2021","journal-title":"Genome Biol."},{"key":"B19","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/j.tplants.2022.08.018","article-title":"Machine learning bridges omics sciences and plant breeding","volume":"28","author":"Yan","year":"2023","journal-title":"Trends Plant Sci."}],"container-title":["Frontiers in Plant Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1951182\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T04:48:03Z","timestamp":1790830083000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpls.2026.1951182\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,1]]},"references-count":19,"alternative-id":["10.3389\/fpls.2026.1951182"],"URL":"https:\/\/doi.org\/10.3389\/fpls.2026.1951182","relation":{},"ISSN":["1664-462X"],"issn-type":[{"value":"1664-462X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,1]]},"article-number":"1951182"}}