Integrating docking scores and key interaction profiles to improve the accuracy of molecular docking: towards novel B-Raf^V600E inhibitors

Abstract

A set of ninety-eight B-Raf inhibitors was used for the development of a molecular docking based QSAR model using linear and non-linear regression models. The integration of docking scores and key interaction profiles significantly improved the accuracy of the QSAR models, providing reasonable statistical parameters ( = 0.935, = 0.728 and = 0.905). The established MD-SVR (molecular docking based SMV regression) model as well as model screening of a natural product database was carried out and two natural products (quercetin and myricetin) with good prediction activities were biologically evaluated. Both compounds exhibited promising B-Raf inhibitory activities (ICQuercetin50 = 7.59 μM and ICMyricetin50 = 1.56 μM), suggesting a high reliability and good applicability of the established MD-SVR model in the future development of B-Raf inhibitors with high efficacy.

Effect of Enterohepatic Circulation on the Accumulation of Per- and Polyfluoroalkyl Substances: Evidence from Experimental and Computational Studies

“…The introduction of molecular docking descriptors such as docking scores improved not only the internal robustness of prediction models but also provided the mechanistic implications of long half-lives of PFAS for human. The previous reports suggested that the integration of docking scores, key interaction profiles, and enthalpy contribution of binding free energy significantly improved the accuracy and interpretability of the QSAR models. ,− However, the available experimental data for the molecular properties of PFAS had relatively small size in most cases. These data limitations restrict the model development of QSAR based on machine learning.…”

Evaluation of Artificial Intelligence in Participating Structure-Based Virtual Screening for Identifying Novel Interleukin-1 Receptor Associated Kinase-1 Inhibitors

“…As a continuation of our virtual screening work which identified new inhibitors targeting NIK, CHK1, Akt, etc. (18)(19)(20)(21)(22)(23)(24). In this study, we performed a traditional VS procedure to identify potential inhibitors of IRAK1.…”

Identification of Novel Covalent XPO1 Inhibitors Based on a Hybrid Virtual Screening Strategy

“…In particular, covalent docking is known to be computationally intensive, and few research institutions have the computing power to support a high-performance virtual screening from a large library of covalent compounds [22][23][24][25][26][27]. Expanding on our previous research [28][29][30][31][32][33][34][35][36], we report in this study the development of a hybrid screening tool that combines non-covalent docking, covalent docking, and pose filters to improve the discovery efficiency for covalent molecules. While covalent virtual screening of 10,000 molecular libraries with the same 48-core computer configuration would take 416 days using traditional methods, the hybrid screening method required only 10 days.…”