DEKOIS: demanding evaluation kits for objective in silico screening--a versatile tool for benchmarking docking...

Area of Science:

• Computational chemistry
• Drug discovery
• Bioinformatics

Background:

• In silico screening methods require careful selection for success.
• Objective validation of docking algorithms and scoring functions is crucial.
• Existing decoy sets may not cover all target spaces.

Purpose of the Study:

• To present a fast, versatile, and robust method for constructing demanding evaluation kits for objective in silico screening (DEKOIS).
• To enable tailor-made decoy set creation for any set of bioactives.
• To facilitate target-dependent validation of docking algorithms and scoring functions.

Main Methods:

• Developed an automated process for creating custom decoy sets.
• Established metrics for assessing and improving decoy set quality.
• Investigated the impact of decoy embedding on docking performance.

Main Results:

• Demonstrated that screening performance is target-dependent.
• Identified that latent actives in the decoy set (LADS) can impair performance.
• Showed that poor decoy embedding can enhance screening performance.
• The DEKOIS method allows for the extension of high-quality decoy sets.

Conclusions:

• DEKOIS provides a robust approach for creating objective evaluation kits for in silico screening.
• The method aids in validating computational tools, saving time and resources.
• DEKOIS facilitates the expansion of decoy set collections for novel target spaces.