Figure 5
From: A novel representation of RNA secondary structure based on element-contact graphs
Mapping results of ncRNA classification. The mapping results of ncRNA classification using K-means clustering algorithm for the three topological index families are shown. In this application case study, 25 sequences of each kind are randomly chosen from six kinds of ncRNAs (5S rRNA, riboswitch, miRNA, RNase P, Intron, and tRNA) listed in Table 1. Principal component analysis mapping method is employed here to visualize the clustering results for the three topological index families. The centroid of each kind of ncRNAs is marked with red '+'. (A) Mapping results of six kinds of ncRNAs in the Wiener indices space. (B) Mapping results of six kinds of ncRNAs in the Balaban indices space. (C) Mapping results of six kinds of ncRNAs in the Randić indices space.