Related Experiment Video
Updated: Jul 6, 2025
A Simple Method to Identify Kinases That Regulate Embryonic Stem Cell Pluripotency by High-throughput Inhibitor Screening
Published on: May 12, 2017
Discovery of hematopoietic progenitor kinase 1 inhibitors using machine learning-based screening and free energy
Dazhi Feng1,2, Bo Liu3, Zhiwei Chen1,4
1Department of Medicinal Chemistry, Shanghai Institute of Materia Medica (SIMM), Chinese Academy of Sciences, Shanghai, China.
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.
Insights
Novel machine learning and computational methods identified potent inhibitors for Hematopoietic progenitor kinase 1 (HPK1), a key target in cancer immunotherapy. One compound, DW21302-A, significantly enhanced T-cell function, offering new therapeutic strategies.
Area of Science:
- Medicinal Chemistry
- Computational Chemistry
- Immunology
Background:
- Hematopoietic progenitor kinase 1 (HPK1) negatively regulates T-cell receptor (TCR) signaling.
- HPK1 is a promising target for developing novel cancer immunotherapies.
- Developing effective HPK1 inhibitors presents significant challenges.
Purpose of the Study:
- To identify novel HPK1 inhibitors using a combination of machine learning and free energy perturbation (FEP) calculations.
- To explore structure-activity relationships and optimize lead compounds for enhanced potency and efficacy.
- To validate potential drug candidates through in vitro and in silico methods.
Main Methods:
- Machine learning (ML)-based virtual screening was employed to identify initial hits.
- Free energy perturbation (FEP) calculations guided the modification of a false-positive hit (DW21302).
- Molecular dynamics (MD) simulations and ADME predictions were used for compound validation.
Main Results:
- ML screening identified 10 potent HPK1 inhibitors with IC50 < 1 μM.
- FEP-guided optimization led to DW21302-A, a highly potent HPK1 inhibitor (IC50 = 2.1 nM).
- DW21302-A demonstrated potent inhibition of cellular HPK1 signaling and enhanced T-cell function.
Conclusions:
- This study presents a successful strategy combining ML and FEP for discovering potent HPK1 inhibitors.
- DW21302-A emerged as a promising candidate compound for cancer immunotherapy.
- New chemical scaffolds and strategies for HPK1 inhibitor development were established.
