Machine learning approaches to the prediction of powder flow behaviour of pharmaceutical materials from physical properties

Diaz, Laura Pereira; Brown, Cameron J.; Ojo, Ebenezer; Mustoe, Chantal L.; Florence, Alastair J.

doi:10.1039/d2dd00106c

Cited by 4 publications

(4 citation statements)

References 36 publications

(52 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One such technique involves the use of molecular modeling to compute interactions between solvents and surfaces, , as well as surface–surface interaction energies. , This method provides a detailed understanding of the molecular-level behavior of materials in different conditions. Moreover, statistical techniques such as machine learning models can be employed to predict processing behaviors . These models are based on large data sets and can identify patterns and relationships between different variables.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Surface Analysis─From Crystal Structures to Particle Properties

Moldovan,

Maloney

2024

Crystal Growth & Design

View full text Add to dashboard Cite

Understanding the surface properties of particles is crucial for optimizing the performance of formulated products in various industries. However, acquiring this understanding often requires expensive trial-and-error studies. Here, we present advanced surface analysis tools that enable the visualization and quantification of chemical and topological information derived from crystallographic data. By employing functional group analysis, roughness calculations, and statistical interaction data, we facilitate direct comparisons of surfaces. We further demonstrate the practicality of our approach by correlating the sticking propensity of distinct ibuprofen morphologies with surface and particle descriptors calculated from a single crystal structure. Our findings support and expand upon previous work, demonstrating that the presence of a carboxylic acid group on the {011} facet leads to significant differences in particle properties and explains the higher electrostatic potential observed in the block-like morphology. While our surface analysis tools are not intended to replace the importance of chemical intuition and expertise, they provide valuable insights for formulators and particle engineers, facilitating informed, data-driven decisions to mitigate formulation risks. This research represents a significant step toward a comprehensive understanding of particle surfaces and their impact on products.

show abstract

Section: Introductionmentioning

confidence: 99%

“…Moreover, statistical techniques such as machine learning models can be employed to predict processing behaviors. 15 These models are based on large data sets and can identify patterns and relationships between different variables.…”

Section: Introductionmentioning

confidence: 99%

Surface Analysis─From Crystal Structures to Particle Properties

Moldovan,

Maloney

2024

Crystal Growth & Design

View full text Add to dashboard Cite

show abstract

“…20,[34][35][36][37][38] Furthermore, precision automation enables acceleration of materials discovery with machine learning by reducing noise that can slow learning. Already, the community has proven benets of black-box models and physics informed models to facilitate materials screening [39][40][41] and performance prediction. [42][43][44] Halide perovskites hold particular promise for use in tandem solar cells, which may lower overall costs of solar electricity via a higher power conversion efficiency.…”

Section: Introductionmentioning

confidence: 99%

“…20,34–38 Furthermore, precision automation enables acceleration of materials discovery with machine learning by reducing noise that can slow learning. Already, the community has proven benefits of black-box models and physics informed models to facilitate materials screening 39–41 and performance prediction. 42–44…”

Section: Introductionmentioning

confidence: 99%