“…In the second example, we apply our method to analyze a data set consisting of 36 protein sequences of 5 different families: Globin (1eca, 5mbn, 1hlb, 1hlm, 1babA, 1babB, 1ithA, 1mba, 2hbg, 2lhb, 3sdhA, 1ash, 1flp, 1myt, 1lh2, 2vhbA, 2vhb), Alpha-Beta (1aa9, 1gnp, 6q21A, 1ct9A, 1qraA, 5p21), Tim-Barrel (6xia, 2mnr, 1chrA, 4enl), Beta (1 cd8, 1ci5, 1qa9, 1cdb, 1neu, 1qfoA, 1hnf ), and Alpha (1cnp, 1jhg) [20,[43][44][45][46][47][48]. After extracting features by the method DCGR and reducing the dimensionality using PCA, the Manhattan distance was used to calculate the distance matrix of the 36 protein sequences.…”