Table 2. Target dataset consists of 12 protein fold with structurally similar sequence dissimilar protein sequences.

		β-Strands		α-Helix
Fold Class and Fold Type	Sequence Length	#Strand	#res	#Helix	#res	#Loop res	Min SEQ ID
All beta Proteins
GFP-like protein	212 ~ 238	11	125	5	24	89	10
Cupredoxin-like proteins	102 ~ 108	6	37	1	3	65	15
Acid Proteases	99 ~ 113	5	45	1	4	50	27
Ribosomal Protein L14	122 ~ 138	5	35	2	10	76	35
Alpha and beta (α + β) Proteins
β-Grasp (Ubiquitin-like) protein	72 ~ 79	4	22	2	14	39	10
Nucleoside Triphosphate Hydrolase	165 ~ 180	6	46	6	49	84	16
RNAase A-like proteins	101 ~ 133	7	41	3	25	58	28
Cysteine Proteinases	201 ~ 218	6	36	6	55	129	33
Alpha and beta (α/β) Proteins
50 S Ribosomal Protein L25	94 ~ 98	6	43	3	20	31	16
50 S Ribosomal Protein L6P	164 ~ 191	13	70	3	36	71	23
Difydrofolate reductase-like proteins	159 ~ 186	10	49	4	34	76	27
Pyruvate kinase N-terminal domain	97 ~ 101	8	35	2	7	80	30

Here, table lists the 12 protein folds with structurally similar sequence dissimilar protein sequences which are used as target dataset. Fold class and title is listed in first column, second column shows the sequence length of representative structures of each fold. For each fold, secondary structure elements information, i.e. total number of residues involved in strand, helix and loop, are listed. Here, Min SEQ ID indicates the minimum sequence identity among the sequences representing the particular fold.