Discovery of hematopoietic progenitor kinase 1 inhibitors using machine learning-based screening and free energy perturbation

Abstract

Hematopoietic progenitor kinase 1 (HPK1) is a key negative regulator of T-cell receptor (TCR) signaling and a promising target for cancer immunotherapy. The development of novel HPK1 inhibitors is challenging yet promising. In this study, we used a combination of machine learning (ML)-based virtual screening and free energy perturbation (FEP) calculations to identify novel HPK1 inhibitors. ML-based screening yielded 10 potent HPK1 inhibitors (IC₅₀ < 1 μM). The FEP-guided modification of the in-house false-positive hit, DW21302, revealed that a single key atom change could trigger activity cliffs. The resulting DW21302-A was a potent HPK1 inhibitor (IC₅₀ = 2.1 nM) and potently inhibited cellular HPK1 signaling and enhanced T-cell function. Molecular dynamics (MD) simulations and ADME predictions confirmed DW21302-A as candidate compound. This study provides new strategies and chemical scaffolds for HPK1 inhibitor development.

Communicated by Ramaswamy H. Sarma

Keywords:

• HPK1 inhibitor
• machine learning
• virtual screening
• free energy perturbation
• structural modification

Disclosure statement

No potential conflict of interest was reported by the authors.

Data availability statement

All data is provided in the manuscript and supplemental information.

Additional information

Funding

This study was supported by the Natural Science Foundation of China for Innovation Research Group (No.81821005), the National Natural Science Foundation of China (Grants 82173834), Institutes for Drug Discovery and Development, Chinese Academy of Sciences (No.CASIMM0120215010, No.CASIMM0120225002), the China Postdoctoral Science Foundation (Certificate Number: 2023T160663), the Shandong Laboratory Program (SYS202205).