Molegro Virtual Docker for Docking Screens.

Area of Science:

• Computational chemistry
• Drug discovery
• Machine learning in bioinformatics

Background:

• Protein-ligand docking is crucial for identifying potential drug candidates.
• Virtual screening requires efficient and accurate methods for predicting molecular interactions.
• Cyclin-dependent kinase 2 (CDK2) is a key target in anticancer drug development.

Purpose of the Study:

• To develop an integrated workflow for docking screens using Molegro Virtual Docker (MVD).
• To build a machine learning regression model for predicting cyclin-dependent kinase 2 (CDK2) inhibition.
• To enhance virtual screening accuracy through a custom-built predictive model.

Main Methods:

• Utilized Molegro Virtual Docker (MVD) for protein-ligand docking simulations.
• Integrated binding affinity data from BindingDB.
• Employed Molegro Data Modeller (MDM) to construct a machine learning regression model.
• Leveraged Jupyter Notebooks on Google Colab for workflow integration.

Main Results:

• Developed a regression model using MDM for CDK2 inhibition prediction.
• The MDM-built model demonstrated superior predictive performance compared to standard docking scoring functions.
• The model is validated and ready for virtual screening applications.

Conclusions:

• The integrated workflow provides an effective approach for docking screens.
• Machine learning models built with MDM offer enhanced predictive power for drug discovery targets like CDK2.
• This methodology facilitates efficient identification of potential anticancer agents.