Related Experiment Video
Updated: Apr 23, 2026
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Screening and classification of anti-angiogenic VEGFR2 inhibitors with supervised machine learning, deep learning and
Leila Karami1, Sara Heidari1, Arman Dinarvand1
1Department of Cell and Molecular Biology, Faculty of Biological Sciences, Kharazmi University, Tehran, Iran.
Abstract:
Vascular Endothelial Growth Factor Receptor 2 (VEGFR2) is a critical therapeutic target in cancer due to its role in pathological angiogenesis and tumor progression. Despite available FDA-approved VEGFR2 tyrosine kinase inhibitors (TKIs), challenges like resistance, off-target toxicities, and low discovery success rates persist, necessitating more efficient and scalable approaches to identify novel inhibitors. We trained five machine learning (ML) and two deep learning (DL) models on a dataset of 17,750 compounds derived from three public databases (e.g., PubChem, ChEMBL, and BindingDB). The best-performing model, Support Vector Machine (SVM) using an ECFP-like fingerprint (91.7% test accuracy), was used to select top-predicted compounds for subsequent ADMET analysis and molecular docking. We also introduce a custom ML/DL program predicting VEGFR2 inhibition probability based on SMILES input. Models demonstrated strong performance, achieving an average Matthews Correlation Coefficient (MCC) of 0.775; ECFP and RDKit fingerprints yielded the highest predictive performance. ADMET analysis indicated favorable pharmacokinetic properties (e.g., good passive GI absorption, low BBB permeation) for 11 of 17 top-ranked novel small molecules, suitable for oral peripheral administration. Molecular docking confirmed strong binding affinities to the VEGFR2 ATP-binding site (ranging -7.9 to -11.4 kcal/mol) for all 17 candidates. Notably, molecule 4 (-11.4 kcal/mol) and molecule 8 (-11.3 kcal/mol) exhibited affinities superior to FDA-approved inhibitors Sorafenib and Ponatinib. Molecular dynamics simulation results (structural and thermodynamics analysis) confirm these data. These findings identify promising novel VEGFR2 inhibitors with favorable drug-like properties. To facilitate the identification of potential VEGFR2 kinase inhibitors, we developed VEGFR2pred, a user-friendly graphical interface that integrates pretrained machine learning models, including RF, SVM, and XGB, and two best-performing molecular representations based on our results: ECFP and RDKit. To enhance accessibility and reproducibility, the complete tool, along with source code and installation instructions, has been made publicly available on GitHub.
Insights
Machine learning models identified novel small molecules as potent Vascular Endothelial Growth Factor Receptor 2 (VEGFR2) inhibitors. These candidates show promising drug-like properties and strong binding affinities, offering new therapeutic avenues for cancer treatment.
Area of Science:
- Medicinal Chemistry
- Computational Chemistry
- Drug Discovery
Background:
- Vascular Endothelial Growth Factor Receptor 2 (VEGFR2) is a key target in cancer therapy, crucial for angiogenesis and tumor growth.
- Existing VEGFR2 tyrosine kinase inhibitors (TKIs) face challenges including resistance, toxicity, and low success rates in discovery.
Purpose of the Study:
- To develop efficient and scalable machine learning (ML) and deep learning (DL) models for identifying novel VEGFR2 inhibitors.
- To predict VEGFR2 inhibition probability and assess drug-like properties of potential candidates.
Main Methods:
- Trained five ML and two DL models on 17,750 compounds from public databases.
- Utilized Support Vector Machine (SVM) with ECFP fingerprints, achieving 91.7% test accuracy.
- Performed ADMET analysis, molecular docking, and molecular dynamics simulations on top-ranked compounds.
Main Results:
- The best ML model achieved an average Matthews Correlation Coefficient (MCC) of 0.775, with ECFP and RDKit fingerprints showing high predictive performance.
- 11 of 17 novel small molecules exhibited favorable pharmacokinetics for oral administration.
- Two candidates, molecule 4 and molecule 8, demonstrated superior binding affinities to VEGFR2 compared to approved drugs.
Conclusions:
- Identified promising novel VEGFR2 inhibitors with favorable drug-like properties and strong binding affinities.
- Developed VEGFR2pred, a user-friendly tool integrating ML models for predicting VEGFR2 kinase inhibitors.
- Made the tool, source code, and instructions publicly available on GitHub to promote accessibility and reproducibility.
More Related Videos
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
14:34A Bilingual Computational Workflow for Identifying Potential PLK1 Inhibitors in American Sign Language and English
Published on: April 3, 2026