NNScore: A Neural-Network-Based Scoring Function for the Characterization of Protein−Ligand Complexes

TLDR

Virtual screening is employed to identify potential ligands, yet current scoring functions frequently generate many false positives and negatives, limiting their reliability compared to human visual assessment. This study introduces a neural‑network‑based scoring function designed to emulate the brain’s microscopic organization for protein–ligand complex evaluation. The scoring function is implemented as a neural network that models the brain’s microscopic organization to evaluate ligand binding. Initial results suggest that this function, alone or combined with traditional scoring methods, may enhance future drug‑discovery efforts.

Abstract

As high-throughput biochemical screens are both expensive and labor intensive, researchers in academia and industry are turning increasingly to virtual-screening methodologies. Virtual screening relies on scoring functions to quickly assess ligand potency. Although useful for in silico ligand identification, these scoring functions generally give many false positives and negatives; indeed, a properly trained human being can often assess ligand potency by visual inspection with greater accuracy. Given the success of the human mind at protein−ligand complex characterization, we present here a scoring function based on a neural network, a computational model that attempts to simulate, albeit inadequately, the microscopic organization of the brain. Computer-aided drug design depends on fast and accurate scoring functions to aid in the identification of small-molecule ligands. The scoring function presented here, used either on its own or in conjunction with other more traditional functions, could prove useful in future drug-discovery efforts.