Last updated: 2026-07-14

Checks: 7 0

Knit directory: nonlinear-ge-interaction-shap/

This reproducible R Markdown analysis was created with workflowr (version 1.7.2). The Checks tab describes the reproducibility checks that were applied when the results were created. The Past versions tab lists the development history.


Great! Since the R Markdown file has been committed to the Git repository, you know the exact version of the code that produced these results.

Great job! The global environment was empty. Objects defined in the global environment can affect the analysis in your R Markdown file in unknown ways. For reproduciblity it’s best to always run the code in an empty environment.

The command set.seed(20260713) was run prior to running the code in the R Markdown file. Setting a seed ensures that any results that rely on randomness, e.g. subsampling or permutations, are reproducible.

Great job! Recording the operating system, R version, and package versions is critical for reproducibility.

Nice! There were no cached chunks for this analysis, so you can be confident that you successfully produced the results during this run.

Great job! Using relative paths to the files within your workflowr project makes it easier to run your code on other machines.

Great! You are using Git for version control. Tracking code development and connecting the code version to the results is critical for reproducibility.

The results in this page were generated with repository version 20f6446. See the Past versions tab to see a history of the changes made to the R Markdown and HTML files.

Note that you need to be careful to ensure that all relevant files for the analysis have been committed to Git prior to generating the results (you can use wflow_publish or wflow_git_commit). workflowr only checks the R Markdown file, but you know if there are other scripts or data files that it depends on. Below is the status of the Git repository when the results were generated:


Ignored files:
    Ignored:    .Rproj.user/
    Ignored:    code/Codigo_SHAP_GE_10_07_23.txt
    Ignored:    data/Manuscript_MN_NE_ACCN.docx

Note that any generated files, e.g. HTML, png, CSS, etc., are not included in this status report because it is ok for generated content to have uncommitted changes.


These are the previous versions of the repository in which changes were made to the R Markdown (analysis/index.Rmd) and HTML (docs/index.html) files. If you’ve configured a remote Git repository (see ?wflow_git_remote), click on the hyperlinks in the table below to view the files as they were in that past version.

File Version Author Date Message
Rmd 20f6446 WevertonGomesCosta 2026-07-14 Update project pages, authorship, contacts, and citation
html 9f70394 WevertonGomesCosta 2026-07-13 Build site.
html 725c4e7 WevertonGomesCosta 2026-07-13 Build site.
Rmd a6fc1fc WevertonGomesCosta 2026-07-13 Configure initial website and project documentation
Rmd 037bf18 WevertonGomesCosta 2026-07-13 Start workflowr project.

Non-Linear Modeling of Genotype × Environment Interaction

This website documents the reproducible analytical workflow associated with the study “Non-Linear Modeling of Genotype × Environment Interaction via Tree-Based Learning Algorithms and Shapley Decomposition.”

The project integrates Random Forest modeling, Shapley Additive Explanations, AMMI decomposition, stability indices, simultaneous selection, and genotype-rank comparison in multi-environment trials.

Scientific scope

Genotype-by-environment interaction occurs when genotypes present different response patterns across environmental conditions. Its evaluation is central to identifying genotypes that combine grain-yield performance, adaptability, responsiveness, and stability.

Traditional biometric approaches such as AMMI describe interaction through linear and multiplicative components. Tree-based learning algorithms provide an additional framework for representing complex response patterns, while SHAP decomposition quantifies genotype- and environment-specific contributions to model predictions.

The project compares these complementary representations through a unified and reproducible workflow.

Analytical workflow

The complete analysis includes:

  1. import and preparation of multi-environment trial data;
  2. visualization of phenotypic performance;
  3. calculation of the environmental index;
  4. Random Forest fitting and leave-one-environment-out validation;
  5. SHAP decomposition of model predictions;
  6. AMMI decomposition of genotype-by-environment interaction;
  7. calculation of AMMI and SHAP stability measures;
  8. simultaneous selection and genotype ranking;
  9. visualization of rank dynamics;
  10. concordance between linear and non-linear stability rankings;
  11. Spearman rank correlation among selection criteria.

The full analytical code, outputs, tables, and figures are available on the Reproducible Analysis page.

Data set

The analysis uses a maize multi-environment trial data set containing:

  • nine genotypes;
  • twenty environments;
  • four replicates per genotype-by-environment combination;
  • 720 original observations;
  • grain yield measured in kilograms per hectare.

Website organization

The website contains four pages:

  1. Home — project overview and analytical scope;
  2. Analysis — complete reproducible analytical pipeline;
  3. About — scientific context, project organization, authorship, and institutional information;
  4. License — conditions for reuse, attribution, and citation.

Reproducibility

The repository is managed with workflowr, integrating R Markdown, Git version control, computational documentation, reproducibility checks, and website publication.

Each published page is connected to a specific Git commit, allowing the analytical source code and rendered results to be tracked together.

Project context

This work is developed in connection with the LICAE Laboratory and the Department of Statistics at the Federal University of Viçosa.

Contact

Moyses Nascimento
Associate Professor — Department of Statistics — Federal University of Viçosa
moysesnascim@ufv.br

Weverton Gomes da Costa
Postdoctoral Researcher — Department of Statistics — Federal University of Viçosa
weverton.costa@ufv.br


R version 4.5.1 (2025-06-13 ucrt)
Platform: x86_64-w64-mingw32/x64
Running under: Windows 11 x64 (build 26200)

Matrix products: default
  LAPACK version 3.12.1

locale:
[1] LC_COLLATE=Portuguese_Brazil.utf8  LC_CTYPE=Portuguese_Brazil.utf8   
[3] LC_MONETARY=Portuguese_Brazil.utf8 LC_NUMERIC=C                      
[5] LC_TIME=Portuguese_Brazil.utf8    

time zone: America/Sao_Paulo
tzcode source: internal

attached base packages:
[1] stats     graphics  grDevices utils     datasets  methods   base     

other attached packages:
[1] workflowr_1.7.2

loaded via a namespace (and not attached):
 [1] vctrs_0.7.1       httr_1.4.7        cli_3.6.5         knitr_1.50       
 [5] rlang_1.1.7       xfun_0.54         stringi_1.8.7     otel_0.2.0       
 [9] processx_3.8.6    promises_1.5.0    jsonlite_2.0.0    glue_1.8.0       
[13] rprojroot_2.1.1   git2r_0.36.2      htmltools_0.5.9   httpuv_1.6.16    
[17] ps_1.9.1          sass_0.4.10       rmarkdown_2.30    jquerylib_0.1.4  
[21] tibble_3.3.1      evaluate_1.0.5    fastmap_1.2.0     yaml_2.3.12      
[25] lifecycle_1.0.5   whisker_0.4.1     stringr_1.6.0     compiler_4.5.1   
[29] fs_1.6.6          pkgconfig_2.0.3   Rcpp_1.1.1        rstudioapi_0.17.1
[33] later_1.4.4       digest_0.6.39     R6_2.6.1          pillar_1.11.1    
[37] callr_3.7.6       magrittr_2.0.4    bslib_0.9.0       tools_4.5.1      
[41] cachem_1.1.0      getPass_0.2-4    

  1. Moyses Nascimento, Associate Professor, Department of Statistics - Federal University of Viçosa, ↩︎

  2. Weverton Gomes da Costa, Postdoctoral Researcher, Department of Statistics - Federal University of Viçosa, ↩︎