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

Abstract

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.

Highlights

• Analyzing a dataset of over 1300 microfluidically produced liposomes, forming a robust base for machine learning.
• XGBoost (XGB) models reliably predict liposome formation and size during microfluidic production across a broad design space.
• Explainable AI explored lipid behaviour and effects of process parameters on microfluidic liposome production.
• Inverse prediction methods enabled predicting process parameters to produce specific formulations with desired sizes.
• Extensive wet lab validation confirmed the models’ reliability and generalizability across a diverse lipid space.

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.

Download the full article as PDF here Leveraging machine learning

or read it here

Materials

The phospholipids DMPC (1,2-dimyristoyl-sn-glycero-3-phosphatidylcholine), DOPC (1,2-dioleoylglycerol-3-phosphorylcholine), DPPC (1,2-dipalmitoyl-sn-glycero-3-phosphatidylcholine), HSPC (hydrogenated soy phosphatidylcholine), DSPE-PEG2000 (1,2-distearoyl-sn-glycero-3-phosphoethanolamine-N-[methoxy(polyethylene glycol) monosodium salt), POPC (1-palmitoyl-2-oleoyl-glycero-3-phosphocholine) were purchased from Lipoid, Germany. Cholesterol was purchased from Sigma Aldrich, USA. Purified water was obtained using a Barnstead Smart2Pure system from Thermo Fisher Scientific Inc., Germany. PBS (phosphate buffered saline, pH 7.4) was obtained using KCl (potassium chloride), KH2PO4 (Potassium Dihydrogen Phosphate), NaCl (sodium chloride), NaH2PO4 (Sodium Phosphate Monobasic), Na2HPO4 (Sodium Phosphate Dibasic), NaOH (sodium hydroxide) from Carl Roth LLC, Germany. NaOH (sodium hydroxide in pellet form) from Haenseler, Switzerland. Absolute Ethanol (EtOH) was purchased from VWR International SAS, France. Ethanol denatured with ketone (EtOH 94 %) was purchased from Dr. Grogg Chemie AG, Switzerland. Methanol (MeOH) was purchased from Fisher Chemical, Belgium.

Remo Eugster, Markus Orsi, Giorgio Buttitta, Nicola Serafini, Mattia Tiboni, Luca Casettari, Jean-Louis Reymond, Simone Aleandri, Paola Luciani, Leveraging machine learning to streamline the development of liposomal drug delivery systems, Journal of Controlled Release, Volume 376, 2024, Pages 1025-1038, ISSN 0168-3659, https://doi.org/10.1016/j.jconrel.2024.10.065.

Read more on the World Diabetes Day 2024 here:

14th November 2024