Integrating Machine Learning-Based Virtual Screening With Multiple Protein Structures and Bio-Assay Evaluation for Discovery of Novel GSK3β Inhibitors

Abstract

Glycogen synthase kinase-3β (GSK3β) is associated with various key biological processes, and it has been considered as a critical therapeutic target for the treatment of many diseases. However, it is a big challenge to develop ATP-competition GSK3β inhibitors because of the high sequence homology with other kinases. In this work, a novel parallel virtual screening strategy based on multiple GSK3β protein structures, integrating molecular docking, complex-based pharmacophore, and naive Bayesian classification, was developed to screen a large chemical database, the 50 compounds with top-scores then underwent a luminescent kinase assay, which led to the discovery of two GSK3β inhibitor hits. The high screening enrichment rate indicates the reliability and practicability of the integrated protocol. Finally, molecular docking and molecular dynamics simulation were employed to investigate the binding modes of the GSK3β inhibitors, and some "hot residues" critical to GSK3β affinity were highlighted. The present study may provide some valuable guidance for the development of novel GSK3β inhibitors.

Keywords: GSK3β; glycogen synthase kinase-3 beta inhibitor; molecular docking; molecular dynamics simulation; naive Bayesian classification; pharmacophore; virtual screening.

Figure 1

The workflow of this study.

Figure 2

(A–H) Eight GSK3β complexes have better ability to distinguish known inhibitors and non-inhibitors under SP or XP docking accuracy; (I) AUC value of Bayesian model constructed based on docking score or integrating docking scores and pharmacophore fit values.

Figure 3

(A) Preliminary screening results of 50 compounds with enzyme experiments; (B) Cpd22 and Cpd49 concentration gradient results; (C, D) 2D structure diagram of Cpd22 and Cpd49.

Figure 4

2D presentations of the interactions between GSK3β and (A) Cpd22; (B) Cpd49; (C) LY2090314; (D) 2D presentations of the interactions between GSK3α and Cpd49 (H-bonds colored in magenta).

Figure 5

(A) the Cpd49-GSK3β residues interaction spectrum; (B) 2D presentations of the MD simulation interactions between GSK3β and Cpd49; (C) 3D presentations of the MD simulation interactions between GSK3β and Cpd49.

Figure 6

X-ray crystal structures of (A) GSK3β/AMP-PNP (PDB ID 1PYX); (B) GSK3β/AZD2858 (PDB ID 4ACD); (C) GSK3β/CHIR-99021 (PDB ID 5HLN); (D) GSK3β/Alsterpaullone (PDB ID 1Q3W).