Monte Carlo Method Based QSAR Studies of Mer Kinase Inhibitors in Compliance with OECD Principles

Area of Science:

• Medicinal Chemistry
• Computational Chemistry
• Drug Discovery

Background:

• Mer kinase is a potential novel target for cancer treatment.
• Developing effective inhibitors is crucial for cancer therapy.

Purpose of the Study:

• To perform Quantitative Structure-Activity Relationship (QSAR) studies on Mer kinase inhibitors.
• To develop predictive models for identifying potent anti-cancer agents targeting Mer kinase.

Main Methods:

• Utilized Monte Carlo method and balance of correlation technique for QSAR model development.
• Employed hybrid optimal descriptors derived from SMILES and hydrogen-filled graphs.
• Data was randomly split into three distinct sets for robust validation.

Main Results:

• Developed QSAR models with excellent fitting (R²=0.9502), robustness, and generalizability (Q²=0.9388).
• External predictive ability was validated using multiple criteria (R²test=0.9469, Q²test=0.9083).
• Identified key structural features influencing Mer kinase inhibitor activity.

Conclusions:

• The developed QSAR models demonstrate high predictive power for Mer kinase inhibitors.
• These findings support the potential of Mer kinase as a cancer therapeutic target.
• The study aligns with OECD principles for QSAR model validation.