In this study, we developed two iterative knowledge-based scoring functions, ITScore_pdbbind(rigid) and ITScore_pdbbind(flex), using rigid decoy structures and flexible decoy structures, respectively, that were generated from the protein-ligand complexes in the refined set of PDBbind 2012. These two scoring functions were evaluated using the 2013 and 2014 CSAR benchmarks. The results were compared with the results of two other scoring functions, the Vina scoring function and ITScore, the scoring function that we previously developed from rigid decoy structures for a smaller set of protein-ligand complexes. A graph-based method was developed to evaluate the root-mean-square deviation between two conformations of the same ligand with different atom names and orders due to different file preparations, and the program is freely available. Our study showed that the two new scoring functions developed from the larger training set yielded significantly improved performance in binding mode predictions. For binding affinity predictions, all four scoring functions showed protein-dependent performance. We suggest the development of protein-family-dependent scoring functions for accurate binding affinity prediction.