Fig. 4 | Scientific Reports

Fig. 4

From: Label-free estimation of regulatory T cell activation markers using Raman spectroscopy with machine learning

Fig. 4

Comparison of testing scores for five machine learning models. The models Ordinary Least-Squares (OLS), Lasso, Ridge, Partial Least-Squares (PLS), and Linear Support Vector Regression (LSVR) were investigated. Boxplots for the (A) testing \({R}^{2}\) and (B) testing RMSE are shown for 50 repeated 8-fold cross validation with donors 1-8, which was performed with the optimal hyperparameters for each of the four biomarkers with each of the regularized models. For subplot B1, the RMSE of the percent positive (%) and MFI values are plotted on separate y-axes and are not intended to be compared. The dashed lines connecting plots A2 and B2 to plots A1 and B1, respectively, are for illustrative purposes only. The plot B2 is not an exact inset of B1, but rather it is the same plot zoomed in with different relative y-axis positions for the left and right y-axes. The plot B1 does not have the same relative y-axes positions as B2.

Back to article page