However, de novo prediction for quantitative phenotypes based on network topology is always a challenging task.
The purpose of this research was to investigate suitable procedures for generating multivariate prediction vectors for quantitative composition and density analysis of intact solid oral dosage forms using terahertz pulsed imaging (TPI) spectroscopy.
We propose that future practical breeding platforms should adopt automated genotyping technologies, either array or sequencing based, target functional polymorphisms underpinning economic traits, and provide desirable prediction accuracy for quantitative traits, with universal applications under wide genetic backgrounds in crops.
A number of studies have assessed how these factors affect prediction accuracy for quantitative traits (Kizilkaya et al. 2014); however, little has been done with categorical traits.
The prediction model for quantitative histology had 0.742 0.950 AUC, 0.688 1.000 sensitivity, 0.679 0.857 specificity, and 0.696 0.848 accuracy, depending on the binary classification threshold.
Thus, it appears that the Gaussian KRR is a robust prediction method for quantitative traits, able to handle nonlinear genetic architectures.
Best performance suitable for quantitative predictions was achieved for relative density, glycerol, and ergosterol contents.
Accordingly, we considered the obtained RPD values for fructose and glucose good enough for quantitative predictions.
Hence, the correlation can be used for quantitative predictions of the tensile properties of the scaffolds.
In these cases, there are no obvious conclusions, and simulations are necessary for quantitative predictions.
