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

• Published in: Journal of chemical information and modeling Vol. 50; no. 10; pp. 1865 - 1871
• Main Authors: Durrant, Jacob D, McCammon, J. Andrew
• Format: Journal Article
• Language: English
• Published: Washington, DC American Chemical Society 25-10-2010
• Subjects: Accuracy; Applied sciences; Artificial intelligence; Biochemistry; Biological and medical sciences; Brain; Chemistry; Computer science; control theory; systems; Computer simulation; Connectionism. Neural networks; Drug Design; Drugs; Exact sciences and technology; Fundamental and applied biological sciences. Psychology; General and physical chemistry; General pharmacology; General. Nomenclature, chemical documentation, computer chemistry; Humans; Interactions. Associations; Intermolecular phenomena; Ligands; Mathematical analysis; Mathematical models; Medical sciences; Molecular biophysics; Molecules; Neural networks; Neural Networks, Computer; Pharmaceutical Modeling; Pharmaceutical technology. Pharmaceutical industry; Pharmacology. Drug treatments; Protein Binding; Proteins; Proteins - metabolism; Scoring; Theory of reactions, general kinetics. Catalysis. Nomenclature, chemical documentation, computer chemistry; Visual inspection; Human; Brain; Ligand binding; Machining; Virtual screening; Molecular interaction; Turning; Biochemistry; Neural network; Encephalon; Computational chemistry; Scoring credit; Computer aided design; Visual control
• ISSN: 1549-9596; 1549-960X
• DOI: 10.1021/ci100244v

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.