Student or educator? Sign up with your school email and get 6 months of Pro free.
CoChat

The DOI matches its Crossref record; 67 of the 67 references it cites were found in a registry or an index; 28 of the 40 sources its claims cite were checked for support.

Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials

Open access
Costa-Neto, Germano, Fritsche-Neto, Roberto, Crossa, José · 2021 · Heredity

Abstract

Modern whole-genome prediction (WGP) frameworks that focus on multi-environment trials (MET) integrate large-scale genomics, phenomics, and envirotyping data. However, the more complex the statistical model, the longer the computational processing times, which do not always result in accuracy gains. We investigated the use of new kernel methods and modeling structures involving genomics and nongenomic sources of variation in two MET maize data sets. Five WGP models were considered, advancing in complexity from a main-effect additive model (A) to more complex structures, including dominance deviations (D), genotype × environment interaction (AE and DE), and the reaction-norm model using environmental covariables (W) and their interaction with A and D (AW + DW). A combination of those models built with three different kernel methods, Gaussian kernel (GK), Deep kernel (DK), and the benchmark genomic best linear-unbiased predictor (GBLUP/GB), was tested under three prediction scenarios: newly developed hybrids (CV1), sparse MET conditions (CV2), and new environments (CV0). GK and DK outperformed GB in prediction accuracy and reduction of computation time (~up to 20%) under all model–kernel scenarios. GK was more efficient in capturing the variation due to A + AE and D + DE effects and translated it into accuracy gains (~up to 85% compared with GB). DK provided more consistent predictions, even for more complex structures such as W + AW + DW. Our results suggest that DK and GK are more efficient in translating model complexity into accuracy, and more suitable for including dominance and reaction-norm effects in a biologically accurate and faster way.

Overview

CoChat Summary

TL;DR

This study tested five whole-genome prediction models with three kernel methods (GB, GK, DK) in two tropical maize multi-environment trial datasets, integrating additive, dominance, GE, and envirotyping effects. GK and DK generally outperformed GBLUP in accuracy and computational efficiency, with dominance and reaction-norm/envirotyping data providing the largest gains.

Key findings

  • GK and DK outperformed GB in prediction accuracy and reduced computation time (~up to 20% in the abstract; e.g., HEL EADW DK 126 s vs GB 175 s).
  • In HEL, CV1 EAD+GE: GK r = 0.871 vs GB r = 0.220; CV2: GK r = 0.892 vs GB r = 0.132. In USP, CV2 EAD+GE: DK r = 0.891 vs GB r = 0.316.
  • Dominance effects improved CV0 accuracy: HEL GB EA 0.402 to EAD 0.558 (+39%); USP GB EA 0.335 to EAD 0.425 (+27%).
  • Envirotyping/reaction-norm models increased accuracy: HEL CV1 EADW GB r = 0.832 vs EA 0.247; USP CV1 EADW+GW GB r = 0.669 vs EA 0.306.

Methods

  • Two tropical maize hybrid datasets: HEL (247 hybrids, 5 environments, 52,811 SNPs) and USP (570 hybrids, 8 environments, 54,113 SNPs); 16 environmental factors yielded 243 and 248 envirotype covariables, respectively.
  • Five WGP models (EA, EAD, EAD+GE, EADW, EADW+GW) built with three kernels (GB, GK, DK), fitted via Bayesian BGGE with 10,000 MCMC iterations, 1000 burn-in, thinning 2.
  • Three cross-validation schemes: CV1 (new hybrids, 50 reps, 70% training), CV2 (sparse testing, 50 reps, 70% training), and CV0 (new environments, leave-one-environment-out); accuracy assessed by Pearson correlations.

Limitations

  • The paper has no formal limitations section; stated caveats include possible DK overfitting for the smaller HEL set, difficulty determining the best models in the less predictable environment S4 (HEL), and high computational cost of complex models.
  • Evident from the text: only two tropical maize datasets and one trait (grain yield) were evaluated, with no external validation beyond cross-validation, so generalization to other crops, traits, or environments is uncertain.
  • Evident from the text: GK bandwidth and DK hidden-layer number were tuned within cross-validation folds, which may affect reproducibility and comparability across settings.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1038/s41437-020-00353-1

Cites

67 of 67 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Fig. 1 Partition of the variance components related to the different genetics, environmental, and residual sources of variation. Each panel is based on the combination of the five WGP models (vertical titles) built with the three different kernel methods (x axis) over HEL and USP data sets (horizontal titles).
Fig. 1 Partition of the variance components related to the different genetics, environmental, and residual sources of variation. Each panel is based on the combination of the five WGP models (vertical titles) built with the three different kernel methods (x axis) over HEL and USP data sets (horizontal titles).CC BY · PubMed Central
Fig. 2 Resolution of the genomic-enabled models and kernel methods in predicting genotypes in novel environments. a Predictive ability of specific hybrids (each row) involving (q − 1) tested environments plus a one novel environment for sets HEL and USP, respectively; b typology of predictive abilities for sets HEL and USP, respectively. Predictive ability values are represented from warm colors (red, worst results) to cold colors (blue and purple, better results).
Fig. 2 Resolution of the genomic-enabled models and kernel methods in predicting genotypes in novel environments. a Predictive ability of specific hybrids (each row) involving (q − 1) tested environments plus a one novel environment for sets HEL and USP, respectively; b typology of predictive abilities for sets HEL and USP, respectively. Predictive ability values are represented from warm colors (red, worst results) to cold colors (blue and purple, better results).CC BY · PubMed Central
Fig. 3 Joint accuracy trends of best combinations of kernel method and model in predicting novel environments (CV0) for both maize data sets (HEL and USP). On the X axis, the environments were ordered from less predictable (S4) to higher predictable (S3). Environments with the acronym S denote sites (from 1 to 5, in the HEL set) and with E denoting environments (from 1 to 8, in the USP set).
Fig. 3 Joint accuracy trends of best combinations of kernel method and model in predicting novel environments (CV0) for both maize data sets (HEL and USP). On the X axis, the environments were ordered from less predictable (S4) to higher predictable (S3). Environments with the acronym S denote sites (from 1 to 5, in the HEL set) and with E denoting environments (from 1 to 8, in the USP set).CC BY · PubMed Central

Verification

Claims the paper makes

20 Valid · 3 Not valid · 6 Not checked · 125 Own results and interpretations

73 more claims · 3 with their cited sources checked

Create a free account to see all 154 claims and every source verdict.

See all claims — free account
  • Probably not a substantial claim. 38
  • It may state two separate claims as one. 43
  • The quote only partly states this claim. 3

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

3 of 3

Citations

Cites

Show all 66 references

Research works printed but not linked: 2

  1. Allen RG, Pereira LS, Raes D, Smith M (1998) Crop Evapotranspiration – guidelines for computing crop water requirements. 56th edn. (Food and Agriculture Organization, Ed.). FAO Irrigation and Drainage Paper No 56, Rome. http://www.fao.org/3/x0490e/x0490e00.htm
  2. R Core Team (2019) A language and environment for statistical computing. R Found Stat Comput Austria, Vienna, Au

Cited by

See all 153

Metadata

Authors
Costa-Neto, G., Fritsche-Neto, R., & Crossa, J.
Affiliations
Centro Internacional de Mejoramiento de Maíz Y Trigo (MX)
Corresponding author
Crossa, José
Venue
Heredity
Published
2020-08-27
Volume
126
Issue
1
Pages
92-106
ISSN
  • 0018-067X (ISSN-L)
  • 1365-2540
OpenAlex
W3080096554
Cited by
153
References
66
Citations by year
2026: 29 · 2025: 23 · 2024: 27 · 2023: 25 · 2022: 25 · 2021: 21 · 2020: 3
FWCI
10.84
Type
journal article
Language
en
Open access
Licence
Locations
  • Heredity (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, other-oa)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Civil War Book Review (submittedVersion)
  • LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) (submittedVersion, cc-by)
Funders
  • United States Agency for International Development
  • Bill and Melinda Gates Foundation (267806)
  • Fundação de Amparo à Pesquisa do Estado de São Paulo (17/24327-0)
  • Coordenação de Aperfeiçoamento de Pessoal de Nível Superior ((Code 001))
  • Conselho Nacional de Desenvolvimento Científico e Tecnológico
  • Foundation for Research Levy on Agricultural Products (267806)
Topics
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genetic and phenotypic traits in livestock
  • Life Sciences › Agricultural and Biological Sciences › Plant Science › Genetics and Plant Breeding
  • Life Sciences › Biochemistry, Genetics and Molecular Biology › Genetics › Genetic Mapping and Diversity in Plants and Animals
Keywords
whole-genome prediction, multi-environment trials, nonlinear kernels, deep kernel learning, Gaussian kernel, dominance effects, gene-environment interaction, reaction norms, envirotyping, maize, genomic best linear unbiased prediction, prediction accuracy, computational efficiency
MeSH terms
Models, Genetic, Genomics, Gene-Environment Interaction

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-01, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-01 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials. https://app.cochat.ai/papers/10.1038/s41437-020-00353-1
The paper
Costa-Neto, G., Fritsche-Neto, R., & Crossa, J. (2021). Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials. Heredity. https://doi.org/10.1038/s41437-020-00353-1

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.