Modelling the effect of base component properties and processing conditions on mixture products using probabilistic, knowledge-guided neural networks.

Development of materials by mixing different base components is a widespread methodology to create materials with improved properties compared to those of its base components. However, efficient determination of the properties of mixture-based materials during design remains challenging without prior knowledge of the underlying physical phenomena. In this work a new data-based methodology is proposed involving the use of probabilistic, knowledge-guided artificial neural networks to jointly model the properties of the base components, the proportions in which they are mixed, and the processing conditions used during manufacture to predict properties of final products.

A multivariate formulation and process development platform for direct compression.

The efficient development of robust tableting processes is challenging due to the lack of mechanistic understanding on the impact of raw material properties and process parameters on tablet quality. The experimental determination of the effect of process and formulation parameters on tablet properties and subsequent optimization is labor-intensive, expensive and time-consuming. The combined use of an extensive raw material property database, process simulation tools and multivariate modeling allows more efficient and more optimized development of the direct compression (DC) process.

A multivariate methodology for material sparing characterization and blend design in drug product development.

This study developed a material and time saving method for powder characterization. Building on an earlier developed raw material property database for use towards development of pharmaceutical dry powder processes, blends were selected in an efficient way to include maximal variability of the underlying raw material dataset. For both raw materials and blends, powder characterization methods were kept to a minimum by selecting the testing methods that described the highest amount of variability in physical powder properties based on principal component analysis (PCA).

Powder filling of electrospun material in vials: A proof-of-concept study.

The present paper reports the powder filling of milled electrospun materials in vials, which contained voriconazole and sulfobutylether-β-cyclodextrin. High-speed electrospinning was used for the production of the fibrous sample, which was divided into 6 parts. Each portion was milled using different milling methods and sizes of sieves to investigate whether the milling influences the powder and filling properties.

A multivariate raw material property database to facilitate drug product development and enable in-silico design of pharmaceutical dry powder processes.

In current study a holistic material characterization approach was proposed and an extensive raw material property database was developed including a wide variety of APIs and excipients with different functionalities. In total 55 different materials were characterized and described by over 100 raw material descriptors related to particle size and shape distribution, specific surface area, bulk, tapped and true density, compressibility, electrostatic charge, moisture content, hygroscopicity, permeability, flowability and wall friction. Principal component analysis (PCA) was applied to reveal similarities and dissimilarities between materials and to identify overarching properties.