Figure 2
From: Constructing patch-based ligand-binding pocket database for predicting function of proteins
Effect of the sequence similarity in retrieval performance. The sequence identity against the enrichment factor is plotted for all 75 test pockets. The dots in the center of bars show the average sequence identity between a query protein and the proteins that bind the same ligand molecule as the query protein. The boundary of the bars shows the standard deviation of the sequence identity for each query protein.