learnMET (learn Multi-Environment Trials) provides a
pipeline for crop predictive breeding. In particular, learnMET (1)
facilitate environmental characterization via the retrieval and
aggregation of daily weather data; (2) allows the evaluation of various
types of state-of-the-art machine learning approaches based on relevant
cross-validation schemes for multi-environment trial datasets (3)
enables to implement predictions for unobserved configurations of
genotypic and environmental predictors that the user wants to test in
silico.
In the Reference section, the different functions implemented in the
package are listed. Only the so called main functions have to be run
by the user in a typical workflow.
Install the development version from GitHub with:
devtools::install_github("cjubin/learnMET")
# To build the HTML vignette use
devtools::install_github("cjubin/learnMET", build_vignettes = TRUE)Vignettes and documentation are available at:
https://cjubin.github.io/learnMET/
Vignettes are displayed under the Articles section.
A publication is available that describes the main features of the package and how to apply the different functions as a workflow. Results are provided for several Machine Learning state-of-the-art models tested with two breeding datasets:
- learnMET: an R package to apply machine learning methods for genomic prediction using multi-environment trial data Cathy C. Westhues, Henner Simianer, Timothy M. Beissinger. G3. doi: https://doi.org/10.1093/g3journal/jkac226
We are glad about any new user testing learnMET!
Please contact us if you encounter issues to use some functions of the
package (contact: [email protected]).
Please also do not hesitate to report errors, or additional features
that could be added to the package.