We compare our algorithm with the SCPS algorithm [13], [14], a spectral method for clustering biological sequence data. The experiment is run using datasets 1–4 from Nepusz et al.,5 which contain pre-computed sequence similarities together with the ground-truth clusterings. Dataset D1 contains 669 sequencesand5ground-truthclusters,dataset D2 contains587 sequences and 6 clusters, dataset D3 contains 567 sequences and 5 clusters, and dataset D4 contains 654 sequences and 8 ground-truth clusters.