Advancing Cellular-Specific Delivery: Machine Learning Insights into Lipid Nanoparticles Design and Cellular Tropism

Area of Science:

• Biotechnology
• Nanomedicine
• Drug Delivery Systems

Background:

• Lipid nanoparticles (LNPs) are advanced nucleic acid delivery systems, but their primary liver targeting limits broader therapeutic use.
• Developing LNPs with specific immune cell tropism is crucial for expanding their applications in treating immune-related diseases.

Purpose of the Study:

• To engineer lipid nanoparticles (LNPs) for preferential immune cell targeting using a data-driven approach.
• To identify LNP formulations that enhance immune cell specificity and reduce hepatic uptake.
• To demonstrate the potential of tailored LNP compositions for selective cellular tropism.

Main Methods:

• A data-driven approach combining design of experiments (DoE), high-throughput screening (HTS), and machine learning (ML).
• Generation and in vitro screening of 180 LNP formulations with varied lipid compositions.
• In vivo validation of selected LNPs for immune cell targeting and biodistribution.

Main Results:

• Identification of LNP formulations with improved immune cell selectivity profiles through ML analysis.
• Demonstration of preferential spleen expression in vivo for selected LNPs.
• Successful redirection of LNP tropism away from hepatic cells towards immune cells.

Conclusions:

• Tailoring LNP composition is essential for achieving selective cellular tropism.
• The implemented data-driven workflow effectively identifies LNPs with desired immune cell targeting capabilities.
• This strategy broadens the therapeutic potential of LNPs beyond liver-targeted applications.