Discovery of novel JAK1 inhibitors through combining machine learning, structure-based pharmacophore modeling and bio-evaluation

Abstract

Background: Janus kinase 1 (JAK1) plays a critical role in most cytokine-mediated inflammatory, autoimmune responses and various cancers via the JAK/STAT signaling pathway. Inhibition of JAK1 is therefore an attractive therapeutic strategy for several diseases. Recently, high-performance machine learning techniques have been increasingly applied in virtual screening to develop new kinase inhibitors. Our study aimed to develop a novel layered virtual screening method based on machine learning (ML) and pharmacophore models to identify the potential JAK1 inhibitors.

Methods: Firstly, we constructed a high-quality dataset comprising 3834 JAK1 inhibitors and 12,230 decoys, followed by establishing a series of classification models based on a combination of three molecular descriptors and six ML algorithms. To further screen potential compounds, we constructed several pharmacophore models based on Hiphop and receptor-ligand algorithms. We then used molecular docking to filter the recognized compounds. Finally, the binding stability and enzyme inhibition activity of the identified compounds were assessed by molecular dynamics (MD) simulations and in vitro enzyme activity tests.

Results: The best performance ML model DNN-ECFP4 and two pharmacophore models Hiphop3 and 6TPF 08 were utilized to screen the ZINC database. A total of 13 potentially active compounds were screened and the MD results demonstrated that all of the above molecules could bind with JAK1 stably in dynamic conditions. Among the shortlisted compounds, the four purchasable compounds demonstrated significant kinase inhibition activity, with Z-10 being the most active (IC₅₀ = 194.9 nM).

Conclusion: The current study provides an efficient and accurate integrated model. The hit compounds were promising candidates for the further development of novel JAK1 inhibitors.

Keywords: Janus kinase 1; Machine learning; Molecular dynamics simulations; Pharmacophore; Virtual screening.

Fig. 1

Crystal structure and active pocket of JAK1 (PDB ID: 3EYG)

Fig. 2

The flowchart for ML model construction

Fig. 3

Chemical structures of the training set and their IC₅₀ values (Hiphop)

Fig. 4

A Applicability domain plot based on ECFP4, RDK, and MACCS. B Comparison of the F1 Score, Mcc, and AUC of the different models. C The accuracy and AUC of Y-randomization models

Fig. 5

A The Hiphop3 pharmacophore model and it mapping with the compound 4. B The 6TPF 08 pharmacophore model was identified based on the 6TPF complex. Green color indicates A; Cyan and magenta indicate H and D, respectively; Gray color indicates excluded volume

Fig. 6

A–N Binding mode of the Tofacitinib and top 13 compounds in the active site of JAK1 (PDB ID: 3EYG)

Fig. 7

A–C RMSD plots of the Tofacitinib and top 13 compounds bound to the JAK1 protein. D–G RMSF plots of the proteins in the 14 systems

Fig. 8

A–F H-bond plots of the Tofacitinib and top 13 compounds in the MD simulations

Fig. 9

A–E IC₅₀ of Z-05, Z-08, Z-10, Z-12, and Tofacitinib toward the JAK1