Skip to main content
Fig. 2 | BMC Bioinformatics

Fig. 2

From: A weighted string kernel for protein fold recognition

Fig. 2

Parameterizing the weighted string kernel WSeqKernel. The string kernel defined in this paper is defined by two parameters, β and k max , and a weighting scheme to combine the individual kernels for different k-mer sizes (see text for details). We varied the two parameters in the respective ranges [10−3,1] and [1,20]; for each corresponding pairs of values, we applied the corresponding kernel to compute the similarities of all pairs of proteins in CATH2833 and checked the rankings of these similarities with the CATH classification of the proteins, using a ROC analysis. The corresponding AUC values are reported in panels a, b, and c for the three weighting schemes that are compared, respectively. High values of AUC indicate better fold recognition

Back to article page