Machine Learning-Based Virtual Screening for the Identification of Cdk5 Inhibitors

Abstract

Cyclin-dependent kinase 5 (Cdk5) is an atypical proline-directed serine/threonine protein kinase well-characterized for its role in the central nervous system rather than in the cell cycle. Indeed, its dysregulation has been strongly implicated in the progression of synaptic dysfunction and neurodegenerative diseases, such as Alzheimer's disease (AD) and Parkinson's disease (PD), and also in the development and progression of a variety of cancers. For this reason, Cdk5 is considered as a promising target for drug design, and the discovery of novel small-molecule Cdk5 inhibitors is of great interest in the medicinal chemistry field. In this context, we employed a machine learning-based virtual screening protocol with subsequent molecular docking, molecular dynamics simulations and binding free energy evaluations. Our virtual screening studies resulted in the identification of two novel Cdk5 inhibitors, highlighting an experimental hit rate of 50% and thus validating the reliability of the in silico workflow. Both identified ligands, compounds CPD1 and CPD4, showed a promising enzyme inhibitory activity and CPD1 also demonstrated a remarkable antiproliferative activity in ovarian and colon cancer cells. These ligands represent a valuable starting point for structure-based hit-optimization studies aimed at identifying new potent Cdk5 inhibitors.

Keywords: CDK5; kinase; machine learning; virtual screening.

Figure 1

Performance evaluation of RF model with different classification thresholds, based on test set prediction. The test set consists of 314 instances of which 98 active.

Figure 2

Analysis of the MD simulations of the different Cdk5-CPD1 (A) and Cdk5-CPD4 (B) complexes.

Figure 3

Minimized average structures of CPD1 (orange) in complex with Cdk5. The two different binding modes represented by (A) cluster 1 and (B) cluster 2 are shown. The protein residues surrounding the ligand, constituting the binding site, are shown as grey sticks, whereas hydrogen bonds are shown as black dashed lines.

Figure 4

Minimized average structures of CPD4 (green) in complex with Cdk5. The protein residues surrounding the ligand, constituting the binding site, are shown as grey sticks, whereas hydrogen bonds are shown as black dashed lines.