Skip to main content
Fig. 3 | BMC Bioinformatics

Fig. 3

From: A weighted string kernel for protein fold recognition

Fig. 3

Statistical differences for WSeqKernel on different data sets. The mean performance over 10 randomized sets of proteins similar to CATH2833 the weighted string kernel WSeqKernel with the Mean Weight scheme and k max set to 10, as measured by AUC, is plotted against the value of the β parameter. Error bars correspond to ± one standard deviation over these ten sets. Note the similarity with the corresponding curve for CATH2833 (see Fig. 2), with the same maxima around β=0.2

Back to article page