AA-Score: a New Scoring Function Based on Amino Acid-Specific Interaction for Molecular Docking

Abstract

The protein−ligand scoring function plays an important role in computer-aided drug discovery and is heavily used in virtual screening and lead optimization. In this study, we developed a new empirical protein−ligand scoring function with amino acid-specific interaction components for hydrogen bond, van der Waals, and electrostatic interactions. In addition, hydrophobic, πstacking, π-cation, and metal−ligand interactions are also included in the new scoring function. To better evaluate the performance of the AA-Score, we generated several new test sets for evaluation of scoring, ranking, and docking performances, respectively. Extensive tests show that AA-Score performs well on scoring, docking, and ranking as compared to other widely used traditional scoring functions. The performance improvement of AA-Score benefits from the decomposition of individual interaction into amino acid-specific types. To facilitate applications, we developed an easy-to-use tool to analyze protein−ligand interaction fingerprint and predict binding affinity using the AA-Score. The source code and associated running examples can be found at https://github.com/ xundrug/AA-Score-Tool.

Conserved Sites and Recognition Mechanisms of T1R1 and T2R14 Receptors Revealed by Ensemble Docking and Molecular Descriptors and Fingerprints Combined with Machine Learning

“…Based on specialized Vina 48 features (including polar–polar, polar–nonpolar, nonpolar–nonpolar, hydrogen bond, and metal–ligand interactions), Δ Lin _F9XGB improved redock-RMSD to 0.85351 using XGBT . AA-Score calculates two additional indicators (π-stacking and π-cation), which improve the performance of the model . OnionNet-SCT incorporated protein–ligands and multilayer contacts and also further used the ABT model training to generate scoring function correction terms .…”

“…34 AA-Score calculates two additional indicators (π-stacking and π-cation), which improve the performance of the model. 35 OnionNet-SCT incorporated protein−ligands and multilayer contacts and also further used the ABT model training to generate scoring function correction terms. 36 In addition to the training based on cocrystal structures, the machine learning-based protein− ligand scoring proved that a classification task was constructed to make the learning features more robust.…”

Estudo in silico de fitoquímicos na região Receptor-Binding Domain (RBD) da proteína spike do SARS-CoV-2 (variante Ômicron, B.1.1.529)

“…Observou-se que apenas duas simulações apresentaram dados de afinidade aceitáveis, abaixo de -6,0 kcal/mol, as estruturas de glicirrizina e quercetina. Em simulações computacionais de docking, moléculas que apresentam energia mais negativa são capazes de se ligar firmemente com macromoléculas-alvo (Pan et al, 2022). As interações entre as glicirrizina e quercetina e a estrutura-alvo RBD da proteína S em formato 3D são vistas respectivamente nas Figuras 3A e 3C.…”

Scoring Functions for Protein-Ligand Binding Affinity Prediction Using Structure-based Deep Learning: A Review

“…One of the first empirical scoring functions was introduced by Böhm (1994) and notable examples include ChemScore (Eldridge et al, 1997;Verdonk et al, 2003), X-Score (Wang et al, 2002), Glide (Friesner et al, 2004) DockThor (de Magalhães et al, 2014, SFCscore (Sotriffer et al, 2008). More recent scoring functions are Vinardo (Quiroga and Villarreal 2016), Lin_F9 (Yang and Zhang 2021), DockTScore (Guedes et al, 2021a) (combined with ML), and AA-Score (Pan et al, 2022).…”