Revolutionizing drug discovery: Integrating artificial intelligence with quantitative systems pharmacology

Area of Science:

• Pharmacology
• Computational biology
• Artificial intelligence

Background:

• Quantitative systems pharmacology (QSP) integrates biological, physiological, and pharmacological data for drug development.
• Artificial intelligence (AI) offers potential advancements in QSP model generation, parameter estimation, and predictive power.

Purpose of the Study:

• To critically evaluate the integration of AI within QSP.
• To highlight novel AI-driven methodologies and discuss current limitations.
• To outline strategies for future AI integration in drug discovery and development.

Main Methods:

• Review of current literature on AI applications in QSP.
• Discussion of AI-driven databases, cloud platforms, and QSP as a service (QSPaaS).
• Exploration of novel methodologies including surrogate modeling, virtual patient generation, and digital twins.

Main Results:

• AI can enhance QSP model generation, parameter estimation, and predictive capabilities.
• AI-driven platforms can support QSP model development and QSPaaS.
• Novel methodologies like surrogate modeling and digital twins show promise for AI-QSP integration.

Conclusions:

• AI integration in QSP faces challenges like computational complexity, explainability, and data integration.
• Future integration strategies should focus on enhancing precision medicine, regulatory acceptance, and mechanistic interpretability.
• AI holds significant potential to transform drug discovery and development through advanced QSP.