Artificial neural networks to predict the apparent degree of supersaturation in supersaturated lipid-based formulations: A pilot study

Harriet Bennett-Lenane, Joseph P. O’Shea, Jack D. Murray, Alexandra Roxana Ilie, René Holm, Martin Kuentz, Brendan T. Griffin*

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review

1 Downloads (Pure)

Abstract

In response to the increasing application of machine learning (ML) across many facets of pharmaceutical development, this pilot study investigated if ML, using artificial neural networks (ANNs), could predict the apparent degree of supersaturation (aDS) from two supersaturated LBFs (sLBFs). Accuracy was compared to partial least squares (PLS) regression models. Equilibrium solubility in Capmul MCM and Maisine CC was obtained for 21 poorly water-soluble drugs at ambient temperature and 60C to calculate the aDS ratio. These aDS ratios and drug descriptors were used to train the ML models. When compared, the ANNs outperformed PLS for both sLBFCapmul MC (r2 0.90 vs. 0.56) and sLBFMaisineLC (r2 0.83 vs. 0.62), displaying smaller root mean square errors (RMSEs) and residuals upon training and testing. Across all the models, the descriptors involving reactivity and electron density were most important for prediction. This pilot study showed that ML can be employed to predict the propensity for supersaturation in LBFs, but even larger datasets need to be evaluated to draw final conclusions.

Original languageEnglish
Article number1398
JournalPharmaceutics
Volume13
Issue number9
Number of pages14
ISSN1999-4923
DOIs
Publication statusPublished - Sep 2021

Keywords

  • Computational pharmaceutics
  • Lipid-based drug delivery
  • Machine learning
  • Supersatu-rated lipid-based formulations

Fingerprint

Dive into the research topics of 'Artificial neural networks to predict the apparent degree of supersaturation in supersaturated lipid-based formulations: A pilot study'. Together they form a unique fingerprint.

Cite this