Toward simplified oral lipid-based drug delivery using mono-/di-glycerides as single component excipients

Ilie, Alexandra; Griffin, Brendan T.; Vertzoni, Maria; Kuentz, Martin; Cuyckens, Filip; Wuyts, Koen; Kolakovic, Ruzica; Holm, René

doi:10.1080/03639045.2020.1843475

Cited by 7 publications

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PLS regression models produced from the same dataset facilitated a comparison of the two computational techniques for this dataset. Two medium-chain (MC) and long-chain (LC)-based mono/di-glycerides formulations were chosen as mono-/di-glyceride systems that previously facilitated improved supersaturation propensity and streamlined drug-excipient screenings [ 38 , 45 , 46 ]. PLS has been previously employed in computational modelling for LBFs [ 29 , 30 ].…”

Section: Introductionmentioning

confidence: 99%

Artificial Neural Networks to Predict the Apparent Degree of Supersaturation in Supersaturated Lipid-Based Formulations: A Pilot Study

et al. 2021

Self Cite

View full text Add to dashboard Cite

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 60 °C 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 sLBFCapmulMC (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.

show abstract