Skip to main content

Table 9 Running time for kernel matrix computation (3860 × 3860), [s]

From: Efficient use of unlabeled data for protein sequence classification: a comparative study

Method mismatch(5,1) mismatch(5,2) triple(1,3)
full seq. 12,084 13,593 153
region 2,624 3,195 73
region+clustering 2,412 2,998 64