Leveraging machine learning to streamline the development of liposomal drug delivery systems - article summary

Q: Why is liposome size important for drug delivery performance?

Liposome size strongly influences physiological processes such as hepatic uptake, tissue diffusion, extravasation, and renal clearance, with 50–200 nm often considered optimal for systemic parenteral administration.

Q: What challenge limits microfluidic liposomal production today?

Microfluidic production is often optimized case-by-case because there is insufficient comprehensive understanding and robust methodologies, compounded by limited data across different lipid compositions.

Q: How does machine learning support microfluidic liposome development in this study?

Machine learning models are used to predict critical quality attributes and process parameters, and the validated models forecast liposome formation and size while improving interpretability and investigating underlying mechanisms.

Aug 4, 2026

Upload by Oliver

Drug delivery systems must administer therapeutic agents efficiently and safely to targeted body sites, and liposomes—phospholipid bilayer vesicles—are widely used, especially as microfluidic manufacturing grows. Microfluidic liposome production remains difficult due to limited mechanistic understanding and constrained datasets across varying lipid compositions. This work applies machine learning to predict critical quality attributes and key process parameters for microfluidic-based liposome production. Validated models forecast liposome formation, size, and operating parameters, improving interpretability and probing underlying mechanisms, enabling more reliable microfluidic development and faster pharmaceutical innovation.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Liposomes in drug delivery

Size-dependent effects on systemic delivery

Limitations of traditional liposome production

Microfluidics as an alternative

Journal of Controlled Release 376 (2024) 1025–1038 Contents lists available at ScienceDirect Journal of Controlled Release journal [homepage: www.elsevier.com/locate/jconrel](homepage: www.elsevier.com/locate/jconrel) | Leveraging machine learning to drug delivery systems | | | streamline the development of liposomal | | | --- | --- | --- | --- | --- | | Remo Eugstera, Markus Orsia, Giorgio Buttittab, Nicola Serafinic, Mattia Tibonic, Luca Casettaric, Jean-Louis Reymonda, Simone Aleandria, Paola Luciania,*
a Department of Chemistry, Biochemistry and Pharmaceutical Sciences, University of Bern, Bern, Switzerland b Department of Chemistry and Technologies of Drugs, Sapienza University of Rome, Rome, Lazio, Italy c Department of Biomolecular Sciences, University of Urbino Carlo Bo, Urbino, PU, Italy | | | | | | A R T I C L E I N F O | | A B S T R A C T | | | | Keywords:
Artificial intelligence Machine learning
Drug delivery & development Liposomes
Microfluidics | | Drug delivery systems efficiently and safely administer therapeutic agents to specific body sites. Liposomes, spherical vesicles made of phospholipid bilayers, have become a powerful tool in this field, especially with the rise of microfluidic manufacturing during the COVID-19 pandemic. Despite its efficiency, microfluidic liposomal production poses challenges, often requiring laborious, optimization on a case-by-case basis. This is due to a lack of comprehensive understanding and robust methodologies, compounded by limited data on microfluidic production with varying lipids. Artificial intelligence offers promise in predicting lipid behaviour during microfluidic production, with the still unexploited potential of streamlining development. Herein we employ machine learning to predict critical quality attributes and process parameters for microfluidic-based liposome production. Validated models predict liposome formation, size, and production parameters, significantly advancing our understanding of lipid behaviour. Extensive model analysis enhanced interpretability and investigated underlying mechanisms, supporting the transition to microfluidic production. Unlocking the potential of machine learning in drug development can accelerate pharmaceutical innovation, making drug delivery systems more adaptable and accessible. | | | 1. Introduction Liposomes, have revolutionized the field of drug delivery (Fig. 1a). [1] Due to their versatile applications and the pandemic-driven push to standardize lipid-based delivery methods, these vesicles have garnered increasing attention. [2] However, while their potential is vast, challenges such as scalability, and cost-effectiveness still need to be addressed to fully realize their widespread application in clinical settings. [3] Nevertheless, over the last three decades, more than 14 liposome-based drug products have been approved, with applications ranging from cancer treatments to vaccines. [2] Liposomal carriers can encapsulate both hydrophilic and hydrophobic drugs, offering a protective environment and enhancing their solubility, stability, and bioavailability. [1,4] Further, the liposomal surface can be engineered to circulate longer in the bloodstream, improving the pharmacokineticsand biodistribution. [5,6] Systemic drug delivery is profoundly impacted by liposome size, affecting physiological processes such as hepatic uptake, tissue diffusion, extravasation, and renal clearance. [7–9] The size range of 50- 200 nm is considered optimal for drug nanocarriers in systemic parenteral administration, balancing tissue and capillary pore size limitations.[7,10,11] Additionally, smaller liposomes (<150 nm) demonstrate enhanced lymphatic uptake and transport, crucial for effective drug delivery. [10,12] Further, larger liposomes might escape clearance and act as long-acting depot systems. [13,14] Liposomes mainly consist of phosphatidylcholine (PC) lipids, essential for drug delivery due to th

FAQs

Why is liposome size important for drug delivery performance?

Liposome size strongly influences physiological processes such as hepatic uptake, tissue diffusion, extravasation, and renal clearance, with 50–200 nm often considered optimal for systemic parenteral administration.

What challenge limits microfluidic liposomal production today?

Microfluidic production is often optimized case-by-case because there is insufficient comprehensive understanding and robust methodologies, compounded by limited data across different lipid compositions.

How does machine learning support microfluidic liposome development in this study?

Machine learning models are used to predict critical quality attributes and process parameters, and the validated models forecast liposome formation and size while improving interpretability and investigating underlying mechanisms.

Aug 4, 2026

Upload by Oliver