Related Experiment Video
Updated: Jul 6, 2026
3D Microtissues for Injectable Regenerative Therapy and High-throughput Drug Screening
Published on: October 4, 2017
3D physiologically-informed deep learning for drug discovery of a novel vascular endothelial growth factor receptor-2
Mengyang Xu1, Xiaoyue Xiao1, Yinglu Chen1
1Faculty of Biology, Shenzhen MSU-BIT University, Shenzhen, 518172, Guangdong, China.
Abstract:
Angiogenesis is an essential process in tumorigenesis, tumor invasion, and metastasis, and is an intriguing pathway for drug discovery. Targeting vascular endothelial growth factor receptor 2 (VEGFR2) to inhibit tumor angiogenic pathways has been widely explored and adopted in clinical practice. However, most drugs, such as the Food and Drug Administration -approved drug axitinib (ATC code: L01EK01), have considerable side effects and limited tolerability. Therefore, there is an urgent need for the development of novel VEGFR2 inhibitors. In this study, we propose a novel strategy to design potential candidates targeting VEGFR2 using three-dimensional (3D) deep learning and structural modeling methods. A geometric-enhanced molecular representation learning method (GEM) model employing a graph neural network (GNN) as its underlying predictive algorithm was used to predict the activity of the candidates. In the structural modeling method, flexible docking was performed to screen data with high affinity and explore the mechanism of the inhibitors. Small -molecule compounds with consistently improved properties were identified based on the intersection of the scores obtained from both methods. Candidates identified using the GEM-GNN model were selected for in silico modeling using molecular dynamics simulations to further validate their efficacy. The GEM-GNN model enabled the identification of candidate compounds with potentially more favorable properties than the existing drug, axitinib, while achieving higher efficacy.
Insights
Researchers developed a novel deep learning strategy to identify new vascular endothelial growth factor receptor 2 (VEGFR2) inhibitors. This approach identified promising drug candidates with potentially better efficacy and fewer side effects than existing treatments.
Area of Science:
- Oncology
- Pharmacology
- Computational Chemistry
Background:
- Angiogenesis is crucial for tumor growth, invasion, and metastasis, making it a key target for cancer drug discovery.
- Vascular Endothelial Growth Factor Receptor 2 (VEGFR2) inhibitors are clinically used but often have significant side effects and limited tolerability.
- There is a critical need for novel VEGFR2 inhibitors with improved safety and efficacy profiles.
Purpose of the Study:
- To propose and validate a novel strategy for designing potential drug candidates targeting VEGFR2.
- To leverage three-dimensional (3D) deep learning and structural modeling for efficient inhibitor discovery.
- To identify novel small-molecule compounds with superior properties compared to existing VEGFR2 inhibitors.
Main Methods:
- Utilized a geometric-enhanced molecular representation learning method (GEM) with a graph neural network (GNN) for activity prediction.
- Employed flexible docking for high-affinity screening and mechanistic exploration of potential inhibitors.
- Conducted in silico molecular dynamics simulations to validate the efficacy of identified candidates.
Main Results:
- Identified small-molecule compounds with consistently improved properties by integrating GEM-GNN predictions and docking scores.
- The GEM-GNN model successfully identified candidate compounds with potentially superior properties and higher efficacy than axitinib.
- In silico validation confirmed the potential efficacy of the selected drug candidates.
Conclusions:
- The proposed 3D deep learning and structural modeling strategy is effective for discovering novel VEGFR2 inhibitors.
- The identified candidate compounds show promise for developing more effective and tolerable cancer therapies.
- This approach offers a viable alternative for overcoming the limitations of current VEGFR2-targeted drugs.
