GemAffinity: a scoring function for predicting binding affinity and virtual screening.

Area of Science:

• Computational chemistry
• Structural biology
• Drug discovery

Background:

• Protein-ligand binding affinity prediction is crucial for molecular recognition and virtual screening.
• Accurate scoring functions are needed to enhance the efficiency of drug discovery pipelines.

Purpose of the Study:

• To develop a novel scoring function, GemAffinity, for predicting protein-ligand binding affinities.
• To evaluate the performance of GemAffinity against existing methods in virtual screening tasks.

Main Methods:

• Developed GemAffinity using stepwise regression and 88 descriptors from 891 complex structures.
• Incorporated five key descriptors: van der Waals contacts, metal-ligand interactions, water effects, ligand deformation penalty, and conserved hydrogen-bonded residues.

Main Results:

• GemAffinity demonstrated superior performance compared to 13 other methods on a test set.
• The function significantly improved screening accuracies across four independent datasets.
• GemAffinity outperformed existing methods in predicting binding affinities.

Conclusions:

• GemAffinity is a highly effective tool for predicting protein-ligand binding affinities.
• The developed scoring function can enhance virtual screening and accelerate drug discovery efforts.
• GemAffinity offers a valuable addition to computational tools for molecular recognition.