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 accessAbstract
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
Cites
Statistics
Figures



Verification
Claims the paper makes
20 Valid · 3 Not valid · 6 Not checked · 125 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Some of the statistical complexities can be addressed by using semiparametric genomic regression methods to account for nonadditive variation (Gianola et al. 2006, 2011; Gianola and Van Kaam 2008; Morota and Gianola 2014).”
§ Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials > Introduction
What the sources say
- Not matchedcites Gianola et al. 2006, 2011
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites Gianola and Van Kaam 2008 source
The section headed “2. A second specification is the additive regression model” says that parametric treatment of nonadditive gene action requires strong assumptions and presents a model combining additive effects with a nonparametric genomic function. The Discussion and Extensions says the methods aim to capture interactions between loci that parametric models cannot adequately explore. Page numbers are unavailable in our copy. (LLM, conf=0.91)
- Supportedcites Morota and Gianola 2014 source
The Introduction describes semiparametric kernel methods as an approach to whole-genome prediction where additive assumptions can fail. Section 3.2 says non-parametric kernels are expected to capture genomic complexity, including non-additive effects; the Conclusions say combinations of kernels may capture non-additive variation. No page numbers are available in our copy. (LLM, conf=0.90)
plainstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Cuevas et al. (2016, 2018) and Souza et al. (2017) showed that using the GK within the multi-environment genomic GE model of Jarquín et al. (2014) led to higher prediction accuracy than the same method with the linear kernel GB.”
§ Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials > Introduction
What the sources say
- Not matchedcites Cuevas et al. 2016, 2018
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Not matchedcites Souza et al. 2017
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites Jarquín et al. 2014 source
The citation to Jarquín et al. identifies the multi-environment genomic G × E model, not the reported GK-versus-GB accuracy comparison, which the sentence attributes to Cuevas et al. and Souza et al. The Materials and methods section describes Jarquín et al.’s model with marker, environment, and marker-by-environment effects. Our copy does not establish the GK-versus-GB comparison, but that comparison is not attributed to this source. (LLM, conf=0.92)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Not matched
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“WGP models including the so-called envirotyping (Xu 2016) analysis can be used to mimic the linear response of the phenotypic performance of genotypes over a certain type of environmental gradient (envirotype), i.e., the reaction norm (Jarquín et al. 2014; Crossa et al. 2017), in which the GE effects are studied as an extension of the GBLUP.”
§ Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials > Introduction
What the sources say
- Not matchedcites Xu 2016
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites Jarquín et al. 2014 source
Split into 2 atoms — 2 confirmed, 0 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
- Partly supportedcites Crossa et al. 2017 sourceExperimental — accuracy not yet measured
Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Rests on an assumption not shown here.
- Not matched
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“The assessment and prediction of hybrid performance have two main sources of variation: the estimated additive (A) effects among lines based on the variance of the general combining ability of the two parents, and the dominance (D) (and/or epistatic) effects among lines based on the variance of the specific combining ability of the cross between parents (Alves et al. 2019).”
§ Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials > Introduction
What the sources say
- Partly supportedcites Alves et al. 2019 sourceExperimental — accuracy not yet measured
Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
hedgedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“On the other hand, the use of data derived from environmental typing analysis (e.g., environmental covariable, W) can be an important source to bridge the gap between phenotypic and genomic correlations across MET (Cooper et al. 2014).”
§ Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials > Introduction
What the sources say
- Partly supportedcites Cooper et al. 2014 sourceExperimental — accuracy not yet measured
The ‘Improved phenotyping methodology: managed environments’ section (page unavailable) describes envirotyping as characterising environments in multi-environment trials and as a complement to genotyping and phenotyping. The ‘experimental design and analysis’ section discusses genetic correlations between environments, but the copy does not say that envirotyping data bridge a gap between phenotypic and genomic correlations. (LLM, conf=0.82)
plainstates a possible cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
73 more claims · 3 with their cited sources checked
Create a free account to see all 154 claims and every source verdict.
- Probably not a substantial claim. 38
- It may state two separate claims as one. 43
- The quote only partly states this claim. 3
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The linear kernel K E is thus a correlation matrix, meaning that the implicit mapping underlying the kernel is the identity map (Costa-Neto et al. , 2021a).”
From REML implementations of kernel-based genomic prediction models for genotype x environment x management interactions (2025) · cites this paper as Costa-Neto et al. , 2021a
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“A commonly used example of such nonlinear kernels is the Gaussian or radial basis function (RBF) kernel which introduces nonlinearity and flexibility through a single parameter often referred to as the bandwidth or scale parameter (Costa-Neto et al. , 2021a; Montesinos-L´ opez et al. , 2021).”
From REML implementations of kernel-based genomic prediction models for genotype x environment x management interactions (2025) · cites this paper as Costa-Neto et al. , 2021a
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.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials > Abstract
“GK and DK outperformed GB in prediction accuracy and reduction of computation time (~up to 20%) under all model–kernel scenarios.”
§ Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials > Results > Computational efficiency
“| HEL | EA | 47 | 58 (+19%) | 54 (+13%) |”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials > Results > Differences in explaining the sources of variation
“In models involving the reaction norm for the effects of GW = AW + DW (model 4, EADW + GW)”
§ Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials > Materials and methods > Model 5: main-effect EADW plus reaction norm for GE (EADW+GW)
“### Model 5: main-effect EADW plus reaction norm for GE (EADW+GW)”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials > Results > Accuracy in the HEL set
“As expected, the PA values were higher than CV1 and CV2 because this scheme uses much more phenotypic information than the other schemes.”
§ Nonlinear kernels, dominance, and envirotyping data increase the accuracy of genome-based prediction in multi-environment trials > Results > Accuracy in the HEL set
“| CV2 | GK | 0.240 | 0.197 | 0.892 | 0.838 | 0.835 |”
Citations
Cites
Advances in neural information processing systems 7
Cios, K., & Shields, M. (1997) · Neurocomputing · doi:10.1016/s0925-2312(97)90018-7 · Cited by 22,059
Prediction of Total Genetic Value Using Genome-Wide Dense Marker Maps
Meuwissen, T. H. E., Hayes, B. J., & Goddard, M. E. (2001) · Genetics · doi:10.1093/genetics/157.4.1819 · Cited by 7,917
Efficient Methods to Compute Genomic Predictions
VanRaden, P. M. (2008) · Journal of Dairy Science · doi:10.3168/jds.2007-0980 · Cited by 6,050
Bayesian Learning for Neural Networks
Neal, R. M. (1996) · Lecture Notes in Statistics · doi:10.1007/978-1-4612-0745-0 · Cited by 4,276
Genomic Selection in Plant Breeding: Methods, Models, and Perspectives
Crossa, J., Pérez-Rodríguez, P., Cuevas, J., Montesinos-López, O., Jarquín, D., de los Campos, G., Burgueño, J., González-Camacho, J. M., Pérez-Elizalde, S., Beyene, Y., et al. (2017) · Trends in Plant Science · doi:10.1016/j.tplants.2017.08.011 · Cited by 1,839
Self-citationBrowning, B. L., & Browning, S. R. (2009) · The American Journal of Human Genetics · doi:10.1016/j.ajhg.2009.01.005 · Cited by 1,640
Cytoplasmic 5′-3′ exonuclease Xrn1p is also a genome-wide transcription factor in yeast
Medina, D. A., Jordán-Pla, A., Millán-Zambrano, G., Chávez, S., Choder, M., & Pérez-Ortín, J. E. (2014) · Frontiers in Genetics · doi:10.3389/fgene.2014.00001 · Cited by 757
Kernel Methods for Deep Learning
Cho, Y., & Saul, L. K. (2009) · eScholarship (California Digital Library) · Cited by 722
A reaction norm model for genomic selection using high-dimensional genomic and environmental data
Jarquín, D., Crossa, J., Lacaze, X., Du Cheyron, P., Daucourt, J., Lorgeou, J., Piraux, F., Guerreiro, L., Pérez, P., Calus, M., et al. (2014) · Theoretical and Applied Genetics · doi:10.1007/s00122-013-2243-1 · Cited by 687
Self-citationGianola, D., & van Kaam, J. B. C. H. M. (2008) · Genetics · doi:10.1534/genetics.107.084285 · Cited by 457
Research works printed but not linked: 2
- 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
- R Core Team (2019) A language and environment for statistical computing. R Found Stat Comput Austria, Vienna, Au
Cited by
Xu, Y., Zhang, X., Li, H., Zheng, H., Zhang, J., Olsen, M. S., Varshney, R. K., Prasanna, B. M., & Qian, Q. (2022) · Molecular Plant · doi:10.1016/j.molp.2022.09.001 · Cited by 363
The Modern Plant Breeding Triangle: Optimizing the Use of Genomics, Phenomics, and Enviromics Data
Crossa, J., Fritsche-Neto, R., Montesinos-Lopez, O. A., Costa-Neto, G., Dreisigacker, S., Montesinos-Lopez, A., & Bentley, A. R. (2021) · Frontiers in Plant Science · doi:10.3389/fpls.2021.651480 · Cited by 266
Self-citationEnvRtype : a software to interplay enviromics and quantitative genomics in agriculture
Costa‐Neto, G., Galli, G., Carvalho, H. F., Crossa, J. L., & Fritsche‐Neto, R. (2021) · G3 Genes Genomes Genetics · doi:10.1093/g3journal/jkab040 · Cited by 181
Self-citationModern Strategies to Assess and Breed Forest Tree Adaptation to Changing Climate
Cortés, A. J., Restrepo-Montoya, M., & Bedoya-Canas, L. E. (2020) · Frontiers in Plant Science · doi:10.3389/fpls.2020.583323 · Cited by 155
Harnessing Crop Wild Diversity for Climate Change Adaptation
Cortés, A. J., & López-Hernández, F. (2021) · Genes · doi:10.3390/genes12050783 · Cited by 157
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
- PMC
- PMC7852533
- 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
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- 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.