<p>We trained the models with equal training sample sizes (<i>N</i><sub>1</sub> = <i>N</i><sub>2</sub> = 28068, right panel) and unequal training sizes (<i>N</i><sub>1</sub> = 5000, <i>N</i><sub>2</sub> = 10000, left panel). Prediction accuracy was measured by correlation between simulated traits and predicted PRS.</p
<p>Simulation with 100 unknown QTL, 500 markers and 250 individuals in each training and testing set...
A: Number of true predictors that had a non-zero coefficient estimate (Oracle = 5). B: Number of fal...
<p>The figure shows the prediction accuracy on test sets TS1 (subplots A and B) and TS2 (subplots C ...
<p>We also compared here two combinations of training – candidate sets (i.e. the two figures on the ...
<p>Results are showed on simple and complex traits through the 10 replicates of the simulation. Figu...
<p>Mean prediction accuracy was calculated on all 10 replicates of the simulation using four methods...
Results of sensitivity analyses across different splits of the training and test sets. We created 1,...
<p>The experiment was conducted 10 times using 10-fold cross-validation performed on the training se...
<p>Prediction accuracies depending on marker number (<i>N</i><sub><i>M</i></sub>) and training popul...
<p>Comparison prediction accuracy of model with <i>p</i> = 1000 and <i>p</i> = 200.</p
<p>(A) The isolates predicted were not included in the training set, still performance is robust. Ba...
<p>Prediction accuracy based on different sampling strategies (k indicates the number of clusters). ...
<p>Accuracy is shown for classifiers based on recursive feature elimination (solid blue line), rando...
<p>Simulation with 100 unknown QTL, 500 markers and 250 individuals in each training and testing set...
<p>Accuracy of predictive models with respect to <i>K</i><sub><i>p</i>3</sub>.</p
<p>Simulation with 100 unknown QTL, 500 markers and 250 individuals in each training and testing set...
A: Number of true predictors that had a non-zero coefficient estimate (Oracle = 5). B: Number of fal...
<p>The figure shows the prediction accuracy on test sets TS1 (subplots A and B) and TS2 (subplots C ...
<p>We also compared here two combinations of training – candidate sets (i.e. the two figures on the ...
<p>Results are showed on simple and complex traits through the 10 replicates of the simulation. Figu...
<p>Mean prediction accuracy was calculated on all 10 replicates of the simulation using four methods...
Results of sensitivity analyses across different splits of the training and test sets. We created 1,...
<p>The experiment was conducted 10 times using 10-fold cross-validation performed on the training se...
<p>Prediction accuracies depending on marker number (<i>N</i><sub><i>M</i></sub>) and training popul...
<p>Comparison prediction accuracy of model with <i>p</i> = 1000 and <i>p</i> = 200.</p
<p>(A) The isolates predicted were not included in the training set, still performance is robust. Ba...
<p>Prediction accuracy based on different sampling strategies (k indicates the number of clusters). ...
<p>Accuracy is shown for classifiers based on recursive feature elimination (solid blue line), rando...
<p>Simulation with 100 unknown QTL, 500 markers and 250 individuals in each training and testing set...
<p>Accuracy of predictive models with respect to <i>K</i><sub><i>p</i>3</sub>.</p
<p>Simulation with 100 unknown QTL, 500 markers and 250 individuals in each training and testing set...
A: Number of true predictors that had a non-zero coefficient estimate (Oracle = 5). B: Number of fal...
<p>The figure shows the prediction accuracy on test sets TS1 (subplots A and B) and TS2 (subplots C ...