marker_effect_per_env_EN: Compute marker effects per environment with Elastic Net

In cjubin/learnMET: Predictions with Machine Learning methods in Multi Environment Trials (MET)

Compute marker effects per environment with Elastic Net

Description

In each environment of the MET dataset, marker effects are computed separately.

Usage

marker_effect_per_env_EN(
  geno,
  pheno,
  environment,
  pheno_trait,
  nb_folds_cv = 4,
  reps = 2,
  ...
)

Arguments

geno	data.frame with markers in columns and inviduals in rows. Typical input is METData$geno from the create_METData() function.
pheno	data.frame with: First column: ID genotypes Second column: year Third column: location Subsequent columns: phenotypic traits with names indicated in colnames() Last column: IDenv (combination LocationxYear) Typical input is METData$pheno from the create_METData() function.
environment	character indicating the name of the environment for which marker effects should be computed
pheno_trait	character Name of the trait under study for which marker effects should be estimated
nb_folds_cv	numeric Number of folds in the CV process
reps	numeric Number of repeats of the k-folds CV

Value

all_coef_avg data.frame

1. First column character contains the marker names.

2. Second column numeric the marker effects in this environment calculated by cross-validation with Elastic Net.

3. Third column character contains the environment name (combination LocationxYear).

Author(s)

Cathy C. Westhues [e-mail]

cjubin/learnMET documentation built on Nov. 4, 2024, 6:23 p.m.