Last updated: 2026-07-13

Checks: 2 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! 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 6f375a8. 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
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

Overview

This website presents a reproducible tutorial for modeling genotype-by-environment interaction using tree-based learning algorithms and Shapley decomposition.

The analytical workflow integrates machine learning interpretability with traditional biometric methods for evaluating genotype performance, adaptability, and stability in multi-environment trials.

Tutorial scope

The tutorial covers the complete sequence used in the associated analysis:

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

All analytical code will be displayed directly in a single R Markdown page so that the complete pipeline can be inspected and reproduced in its execution order.

Data set

The tutorial uses a maize multi-environment trial data set with nine genotypes evaluated across twenty environments.

Each genotype-by-environment combination contains four replicates, and the analyzed trait is grain yield measured in kilograms per hectare.

Analytical frameworks

The project includes the following analytical components:

  • Random Forest;
  • Shapley Additive Explanations;
  • AMMI analysis;
  • AMMI Stability Value;
  • Simultaneous Selection Index;
  • genotype ranking;
  • rank concordance;
  • Spearman correlation.

Website structure

The website currently contains the following pages:

  • Home — general project overview;
  • About — methodological context and tutorial organization;
  • License — terms of use and redistribution.

The complete reproducible analysis will be added after the initial website structure is finalized.

Reproducibility

The repository is managed with workflowr, combining R Markdown, Git version control, reproducibility checks, and a versioned research website.

The source code and the rendered results are maintained in the same version-controlled project.