Review of machine learning for lipid nanoparticle formulation and process development.

Area of Science:

• Pharmaceutical Nanotechnology
• Drug Delivery Systems
• Biotechnology

Background:

• Lipid nanoparticles (LNPs) are advanced pharmaceutical formulations for encapsulating and delivering nucleic acid cargoes.
• LNP applications span genetic disorders, vaccines, and therapeutic protein delivery.
• Robust LNP formulation is critical for drug development, yet research is often empirical and resource-intensive.

Purpose of the Study:

• To review challenges and opportunities in developing robust nucleic acid LNP formulations.
• To examine the application of machine learning (ML) in LNP formulation research.
• To discuss data science challenges and foster collaboration for AI/ML advancement in LNP development.

Main Methods:

• Review of existing literature on LNP formulation and AI/ML applications.
• Analysis of studies applying machine learning to experimental LNP datasets.
• Discussion of data science methodologies relevant to LNP formulation.

Main Results:

• LNP formulation involves complex physical phenomena and numerous parameters, making research empirical.
• AI/ML offers potential for in silico modeling, prediction, and deeper understanding of LNP processes.
• Data science challenges exist in integrating experimental data for AI/ML models.

Conclusions:

• AI/ML can significantly improve the efficiency and fundamental understanding of LNP formulation and process optimization.
• Collaboration between formulation scientists and data scientists is key to accelerating AI/ML adoption in LNP development.
• Addressing data science challenges will facilitate the advancement of AI/ML for robust nucleic acid LNP formulations.