Evaluation Results

Performance Score Table

Model	MSE	R.Squared
Pre-Trained PRS	1.492	0.402
AB-PRS	1.069	0.571

Performance Score Comparisons

This barplot compares the mean squared error (MSE) performance scores between different sets of PRSs derived from different models.

 
   plot <- ggplot(data=Scores, aes(x=reorder(Model, +Score), y=Score, fill=Model)) +
    geom_bar(stat="identity", width=0.5) +
    geom_text(aes(label=round(Score, 2)), size=3.5, vjust=-0.3) +
    scale_y_continuous(expand = expansion(mult = c(0, .1))) + 
    labs(x="Model", y=ylab, fill="Model") +
    theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(),
          panel.background = element_blank(), axis.line = element_line(colour = "black"))

Phenotype vs PRS Percentile

This figure plots the mean of the continuous phenotype and +/- 1 standard deviation in each polygenic risk score quantiles, for different PRS models. For each model, 10 quantiles are plotted in the graph. A model that performs better should have a higher mean in the higher risk score percentiles and a lower mean in the lower percentiles.

 
  plot <- ggplot(MeanData, aes(x = Percentile, y = Prevalence, color=Model)) +
    geom_point(size = 3) +
    geom_errorbar(aes(ymin=Mean-SD, ymax=Mean+SD), width=0, alpha=0.8) +
    labs(x = "Risk Score Percentile", y = "Mean of Phenotype",
         title = "Mean of Phenotype vs. Risk Score Percentile") +
    theme(panel.grid.major = element_blank(), panel.grid.minor = element_blank(), 
          panel.background = element_blank(), axis.line = element_line(colour = "black"))