Fig. 2From: Identification of residue pairing in interacting β-strands from a predicted residue contact mapThe cumulative distributions for training and test sets with the respect of N/L. N is the number of sequences in the MSA and L is the protein length. There are more proteins in the training set with limited numbers of homologous sequences (N/L < 1) than in the BetaSheet916 and BetaSheet1452 setsBack to article page