Predicting Spray Dried Dispersion Particle Size Via Machine Learning Regression Methods

Selective recognition between aromatics and aliphatics by cage-shaped borates supported by a machine learning approach

Selective recognition between hydrocarbon moieties is a longstanding issue. Although we developed a π-pocket Lewis acid catalyst with high selectivity for aromatic aldehydes over aliphatic ones, a general strategy for catalyst design remains elusive. As an approach that transfers the molecular recognition based on multiple cooperative non-covalent interactions within the π-pocket to a rational catalyst design, herein, we demonstrate Lewis acid catalysts showing improved selectivity through the support of an ensemble algorithm with random forest, Ada Boost, and XG Boost as a machine learning (ML) approach. Using 7963 explanatory variables extracted from model hetero-Diels-Alder reactions, the ensemble algorithm predicted the chemoselectivity of unlearned catalysts. Experiments confirmed the prediction. The proposed catalyst shows the highest selective recognition, reminiscing enzymatic catalytic activity. Additionally, a SHapley Additive exPlanations (SHAP) method suggested that the selectivity originates from the polarizability and three-dimensional size of the catalyst. This insight leads to rational design guidelines for Lewis acid catalysts with dispersion forces.

Revolutionizing drug formulation development: The increasing impact of machine learning

Over the past few years, the adoption of machine learning (ML) techniques has rapidly expanded across many fields of research including formulation science. At the same time, the use of lipid nanoparticles to enable the successful delivery of mRNA vaccines in the recent COVID-19 pandemic demonstrated the impact of formulation science. Yet, the design of advanced pharmaceutical formulations is non-trivial and primarily relies on costly and time-consuming wet-lab experimentation. In 2021, our group published a review article focused on the use of ML as a means to accelerate drug formulation development. Since then, the field has witnessed significant growth and progress, reflected by an increasing number of studies published in this area. This updated review summarizes the current state of ML directed drug formulation development, introduces advanced ML techniques that have been implemented in formulation design and shares the progress on making self-driving laboratories a reality. Furthermore, this review highlights several future applications of ML yet to be fully exploited to advance drug formulation research and development.

Development of Inhalable Spray Dried Nitrofurantoin Formulations for the Treatment of Emphysema

A central characteristic of emphysematous progression is the continuous destruction of the lung extracellular matrix (ECM). Current treatments for emphysema have only addressed symptoms rather than preventing or reversing the loss of lung ECM. Nitrofurantoin (NF) is an antibiotic that has the potential to induce lung fibrosis as a side effect upon oral administration. Our study aims to repurpose NF as an inhalable therapeutic strategy to upregulate ECM expression, thereby reversing the disease progression within the emphysematous lung. Spray-dried (SD) formulations of NF were prepared in conjunction with a two-fluid nozzle (2FN) and three-fluid nozzle (3FN) using hydroxypropyl methylcellulose (HPMC) and NF at 1:1 w/w. The formulations were characterized for their physicochemical properties (particle size, morphology, solid-state characteristics, aerodynamic behaviour, and dissolution properties) and characterized in vitro with efficacy studies on human lung fibroblasts. The 2FN formulation displayed a mass mean aerodynamic diameter (MMAD) of 1.8 ± 0.05 µm and fine particle fraction (FPF) of 87.4 ± 2.8% with significantly greater deposition predicted in the lower lung region compared to the 3FN formulation (MMAD: 4.4 ± 0.4 µm; FPF: 40 ± 5.8%). Furthermore, drug dissolution studies showed that NF released from the 2FN formulation after 3 h was significantly higher (55.7%) as compared to the 3FN formulation (42.4%). Importantly, efficacy studies in human lung fibroblasts showed that the 2FN formulation induced significantly enhanced ECM protein expression levels of periostin and Type IV Collagen (203.2% and 84.2% increase, respectively) compared to untreated cells, while 3FN formulations induced only a 172.5% increase in periostin and a 38.1% increase in type IV collagen. In conclusion, our study highlights the influence of nozzle choice in inhalable spray-dried formulations and supports the feasibility of using SD NF prepared using 2FN as a potential inhalable therapeutic agent to upregulate ECM protein production.