From Deep Learning to the Discovery of Promising VEGFR-2 Inhibitors

Area of Science:

• Medicinal Chemistry
• Computational Biology
• Oncology

Background:

• Vascular Endothelial Growth Factor Receptor 2 (VEGFR-2) is crucial for tumor angiogenesis, growth, and metastasis.
• Existing VEGFR-2 inhibitors have side effects, necessitating the search for novel therapeutics.

Purpose of the Study:

• To identify novel and effective VEGFR-2 inhibitors using a combination of computational and experimental methods.
• To evaluate the anti-proliferative and toxicity profiles of identified compounds.

Main Methods:

• Development of a deep learning classification model to screen an in-house chemical library.
• Molecular docking to assess binding affinity of shortlisted compounds to VEGFR-2.
• In vitro anti-proliferative assays against MCF-7 breast cancer cells and toxicity assessment against WI-38 cells.

Main Results:

• Two compounds, RHE-334 and EA-11, were identified as potent VEGFR-2 inhibitors.
• RHE-334 and EA-11 demonstrated significant anti-proliferative activity against MCF-7 cells with IC50 values of 26.78±4.02 μM and 38.73±3.84 μM, respectively.
• RHE-334 showed VEGFR-2 inhibition comparable to imatinib.

Conclusions:

• The integrated workflow effectively identifies potential VEGFR-2 inhibitors.
• This approach can be adapted for other drug discovery and medicinal chemistry objectives.
• RHE-334 and EA-11 represent promising candidates for further development as anti-cancer agents.