Related Experiment Video
Updated: Aug 16, 2026
Kinase Inhibitor Screening In Self-assembled Human Protein Microarrays
Published on: October 23, 2019
Targeting WEE1 kinase: an integrated machine learning-cheminformatics framework for ultra-large-scale virtual
Rajesh Muthuraj1, Manasa Pacharla1, Nehal Arvind Kumar1
1Department of Pharmacology, Sri Ramachandra Faculty of Pharmacy, Sri Ramachandra Institute of Higher Education and Research (Deemed to Be University), Chennai, Tamil Nadu, 600116, India.
Abstract:
WEE1 kinase, a critical regulator of the G2/M checkpoint, represents a validated therapeutic target in tumors harboring defects in DNA damage response (DDR) pathways. Although clinical inhibitors such as adavosertib have demonstrated therapeutic potential, challenges, including selectivity constraints, dose-limiting toxicities, and emerging resistance, highlight the need to expand the structural diversity of WEE1-targeting chemotypes. Here, we report a scalable, machine-learning-integrated virtual screening framework designed to explore ultra-large chemical space spanning an input search space of approximately 884 million compounds from ZINC20 and 199,854 purchasable compounds from the SPECS database. Molecular representations using ECFP4 fingerprints combined with UMAP-based dimensionality reduction and K-means clustering enabled diversity-guided prioritization across distinct regions of chemical space. Multi-stage structure-based computational evaluation, including pharmacophore modelling, molecular docking, MM/GBSA rescoring, and 200-ns molecular dynamics simulations, yielded 18 high-confidence candidates, from which three structurally novel scaffolds were selected for detailed analysis. One ZINC-derived and two SPECS-derived compounds demonstrated predicted stable binding modes involving key WEE1 active-site residues and favourable estimated developability profiles. Critically, in silico selectivity profiling against the off-target PLK1 revealed structurally grounded differential binding, providing a computational basis for selectivity. Preliminary in vitro evaluation of one SPECS-derived compound (AJ-292/13095349) demonstrated antiproliferative activity in triple-negative breast cancer (TNBC) models. Collectively, this study establishes an efficient computational hit identification framework for ultra-large screening and reports structurally distinct starting points for WEE1-targeted oncology drug discovery.
Insights
This study developed a machine learning framework to screen millions of compounds for new WEE1 kinase inhibitors. The approach identified novel drug candidates with potential for treating cancers, including triple-negative breast cancer.
Area of Science:
- Oncology
- Medicinal Chemistry
- Computational Drug Discovery
Background:
- WEE1 kinase is a therapeutic target in cancers with DNA damage response (DDR) defects.
- Existing WEE1 inhibitors face challenges like toxicity and resistance, necessitating new chemotypes.
- Expanding structural diversity is crucial for developing effective WEE1-targeting drugs.
Purpose of the Study:
- To establish a scalable, machine learning-integrated virtual screening framework for ultra-large chemical spaces.
- To identify novel, structurally diverse WEE1 kinase inhibitors.
- To provide starting points for WEE1-targeted oncology drug discovery.
Main Methods:
- Employed a machine learning framework integrating ECFP4 fingerprints, UMAP, and K-means clustering for diversity-guided screening of ~884 million compounds.
- Utilized multi-stage structure-based computational evaluations: pharmacophore modeling, molecular docking, MM/GBSA rescoring, and molecular dynamics simulations.
- Conducted in silico selectivity profiling against PLK1 and preliminary in vitro testing of promising candidates.
Main Results:
- Identified 18 high-confidence WEE1 inhibitor candidates from ultra-large virtual screening.
- Selected three structurally novel scaffolds with predicted stable binding modes and favorable developability profiles.
- Demonstrated potential for selectivity against PLK1 and preliminary antiproliferative activity in triple-negative breast cancer (TNBC) models.
Conclusions:
- The developed computational framework enables efficient hit identification from ultra-large chemical libraries.
- Reported novel scaffolds represent promising starting points for WEE1-targeted cancer therapy.
- The study provides a computational basis for achieving WEE1 inhibitor selectivity.
Related Concept Videos
02:04Protein-protein Interfaces
01:26Drug Discovery: Overview