Fig. 2
From: String kernels for protein sequence comparisons: improved fold recognition
ROC analyses of three measures of protein similarity. We compare the efficiency of two sequence comparison methods, pairwise sequence alignment using SSEARCH from FASTA (red), the SeqKernel alignment free method introduced in this paper with two sets of parameters, (k max =2, β=0.0001) (green), (k max =10, β=0.2) (cyan), and the 3D structure alignment program STRUCTAL (purple) to detect fold similarity in two different sets of proteins, CATH2883 (panel a), and CATH793 (panel b). “True” relationships are defined according to CATH topologies. Curves close to the first diagonal (such as the ROC curve for FASTA) indicate poor performance, while the upper most curves (such as the 3D structure-based curve) indicate good performance