We developed a knowledge-based statistical energy function for protein-ligand, protein-protein, and protein-DNA complexes by using 19 atom types and a distance-scale finite ideal-gas reference (DFIRE) state. The correlation coefficients between experimentally measured protein-ligand binding affinities and those predicted by the DFIRE energy function are around 0.63 for one training set and two testing sets. The energy function also makes highly accurate predictions of binding affinities of protein-protein and protein-DNA complexes. Correlation coefficients between theoretical and experimental results are 0.73 for 82 protein-protein (peptide) complexes and 0.83 for 45 protein-DNA complexes, despite the fact that the structures of protein-protein (peptide) and protein-DNA complexes were not used in training the energy function. The results of the DFIRE energy function on protein-ligand complexes are compared to the published results of 12 other scoring functions generated from either physical-based, knowledge-based, or empirical methods. They include AutoDock, X-Score, DrugScore, four scoring functions in Cerius 2 (LigScore, PLP, PMF, and LUDI), four scoring functions in SYBYL (F-Score, G-Score, D-Score, and ChemScore), and BLEEP. While the DFIRE energy function is only moderately successful in ranking native or near native conformations, it yields the strongest correlation between theoretical and experimental binding affinities of the testing sets and between rmsd values and energy scores of docking decoys in a benchmark of 100 protein-ligand complexes. The parameters and the program of the all-atom DFIRE energy function are freely available for academic users at http://theory.med.buffalo.edu.

Most biological processes are mediated by interactions between proteins and their interacting partners including proteins, nucleic acids and small molecules. This work establishes a method called PINUP for binding site prediction of monomeric proteins. With only two weight parameters to optimize, PINUP produces not only 42.2% coverage of actual interfaces (percentage of correctly predicted interface residues in actual interface residues) but also 44.5% accuracy in predicted interfaces (percentage of correctly predicted interface residues in the predicted interface residues) in a cross validation using a 57-protein dataset. By comparison, the expected accuracy via random prediction (percentage of actual interface residues in surface residues) is only 15%. The binding sites of the 57-protein set are found to be easier to predict than that of an independent test set of 68 proteins. The average coverage and accuracy for this independent test set are 30.5 and 29.4%, respectively. The significant gain of PINUP over expected random prediction is attributed to (i) effective residue-energy score and accessible-surface-area-dependent interface-propensity, (ii) isolation of functional constraints contained in the conservation score from the structural constraints through the combination of residue-energy score (for structural constraints) and conservation score and (iii) a consensus region built on top-ranked initial patches.