Harnessing computational technologies to facilitate antibody-drug conjugate development

Area of Science:

• Biochemistry
• Computational Biology
• Pharmacology

Background:

• Antibody-drug conjugates (ADCs) combine monoclonal antibodies with cytotoxic agents for targeted cancer therapy.
• Despite clinical success, ADC development faces challenges due to complex structural dynamics and limited 3D information.

Purpose of the Study:

• To discuss computational methods for enhancing ADC design and development.
• To explore how machine learning and physics-based simulations can address structural complexities in ADCs.

Main Methods:

• Review of computational approaches, including machine learning and physics-based modeling.
• Analysis of 3D molecular modeling and simulation data for model ADCs.

Main Results:

• Computational methods can interpret experimental data and predict optimal ADC design parameters.
• Physics-based simulations provide insights into the flexibility of antibodies and drug payloads.

Conclusions:

• Computational strategies can accelerate ADC development by minimizing design iterations.
• Integrating computational modeling with experimental data is crucial for optimizing ADC efficacy and safety.