Skip to main content

Table 5 Accuracy and mean squared error (MSE) of genomic prediction of TNB and NBA in younger individuals from seven methods

From: Using machine learning to improve the accuracy of genomic prediction of reproduction traits in pigs

Hyperparameters Method TNB1 NBA2
Accuracy3 MSE Optimal hyperparameters4 Accuracy3 MSE Optimal hyperparameters4
  GBLUP 0.355ab 11.598 0.264ab 10.203
  ssGBLUP 0.408b 11.221 0.288ab 9.974
  BayesHE 0.357ab 11.566 0.262ab 10.143
Tuning SVR 0.307a 11.488 kernel = ‘rbf’; gamma = 0.00005; C = 14 0.229a 10.235 kernel = ‘rbf’; gamma = 0.00005; C = 13
KRR 0.362ab 11.367 kernel = ‘rbf’; gamma = 0.000001; λ = 0.07 0.266ab 10.121 kernel = ‘rbf’; gamma = 0.000001; λ = 0.12
RF 0.385ab 11.337 n_estimators = 430; max_depth = None 0.285ab 10.116 n_estimators = 400; max_depth = None
Adaboost.R2_KRR 0.395b 11.254 n_estimators = 70; kernel = ‘rbf’, gamma = 0.00001, λ = 1 0.328b 9.794 n_estimators = 60; kernel = ‘rbf’, gamma = 0.00001, λ = 0.9
Default SVR 0.271 11.858 0.17 10.37
KRR 0.346 11.538 0.259 10.158
RF 0.26 11.867 0.179 10.335
Adaboost.R2_KRR 0.36 11.392 0.322 9.797
  1. 1 TNB: total number of piglets born
  2. 2 NBA: number of piglets born alive
  3. 3 Accuracy: the correlation between corrected phenotypes and predicted values of the validation population;
  4. 4Optimal hyperparameters: The optimal hyper-parameters of each machine learning method obtained by using grid search
  5. The different superscript of accuracy indicates the significant difference by the Hotelling-Williams test