FIGURE 3.

(A) Projection along the first two principal components of the residues in the Protein dataset as obtained by a PCA analysis using $P\left(R\right)$, $P_c\left({\theta }_1\right)$, and $P_c\left({\theta }_2\right)$ as descriptors for each residue. Each dot in the plane represents a residue, with different colors corresponding to different amino acids (B) Cluster of the residue forming the Protein dataset using the $P_c\left({\theta }_1\right)$ (top) or $P_c\left({\theta }_2\right)$ (bottom) as descriptors for each residue (C) Average silhouette score as a function of the number of clusters considered in (B).