The CompScore Web Service implements an algorithm that searches for the combination of docking scoring functions components that maximizes any of the BEDROC or Enrichment Factor virtual screening metrics through a genetic algorithm search. It is also possible to rescore a dataset provided that a previous run of the CompScore algorithm has been performed. We also provide a python script ScoresDecomposer, that facilitates the summarizing of scores components from Dock, Gold and OEDocking output files in a table for CompScore input. For the details on how the Web Service works you are suggested to read our help pages.
Last updated: August 26, 2019For technical information about the algorithm, you can refer to:
Y. Perez-Castillo et al., “CompScore: Boosting Structure-Based Virtual Screening Performance by Incorporating Docking Scoring Function Components into Consensus Scoring,” J. Chem. Inf. Model., vol. 59, no. 9, pp. 3655–3666, 2019, DOI:10.1021/acs.jcim.9b00343.