Converging a Knowledge-Based Scoring Function: DrugScore(2018)

We present DrugScore(2018), a new version of the knowledge-based scoring function DrugScore, which builds upon the same formalism used to derive DrugScore but exploits a training data set of nearly 40 000 X-ray complex structures, a highly diverse and the, by far, largest data set ever used for such an endeavor. About 2.5 times as many pair potentials than before now have a data basis required to yield smooth potentials, and pair potentials could now be derived for eight more atom types, including interactions involving halogen atoms and metal ions highly relevant for medicinal chemistry. Probing for dependence on training data set size and quality, we show that DrugScore(2018) potentials are converged. We evaluated DrugScore(2018) in comprehensive scoring, ranking, docking, and screening tests on the CASF-2013 data set, allowing for a comparison with >30 other scoring functions. There, DnigScore(2018) showed similar or improved performance in all aspects when compared to either DrugScore, DrugScorecs(CSD), or DSX and was, overall, the scoring function showing the most consistently good performance in scoring, ranking, and docking tests. Applying DrugScore(2018) as objective function in AutoDock3 in a large-scale docking trial, using 4056 protein ligand complexes from PDBbind 2016, reproduced a docked pose to within 2 angstrom RMSD to the crystal structure in >75% of all dockings. These results are remarkable as the DrugScore(2018) potentials were derived from crystallographic information only, without any further adaptation using binding affinity or docking decoy data. DrugScore(2018) should thus be a competitive scoring and objective function for structure-based ligand design purposes.