Data Mining Crystallization Kinetics
Cameron J. Brown,Diego A. Maldonado,Antony D. Vassileiou,Blair F. Johnston,Alastair J. Florence +4 more
TL;DR: In this article, the authors built a database with information on solute, solvent, kinetic expression, parameters, crystallization method and seeding, which is used for population balance model.
read more
Abstract: Population balance model is a valuable modelling tool which facilitates the optimization and understanding of crystallization processes. However, in order to use this tool, it is necessary to have previous knowledge of the crystallization kinetics, specifically crystal growth and nucleation. The majority of approaches to achieve proper estimations of kinetic parameters required experimental data. Across time, a vast literature about the estimation of kinetic parameters and population balances have been published. Considering the availability of data, this work built a database with information on solute, solvent, kinetic expression, parameters, crystallization method and seeding. Correlations were assessed and clusters structures identified by hierarchical clustering analysis. The final database contains 336 data of kinetic parameters from 185 different sources. The data were analysed using kinetic parameters of the most common expressions. Subsequently, clusters were identified for each kinetic model. With these clusters, classification random forest models were made using solute descriptors, seeding, solvent, and crystallization methods as classifiers. Random forest models had an overall classification accuracy higher than 70% whereby they were useful to provide rough estimates of kinetic parameters, although these methods have some limitation
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Figures
Table 1. Search strategies and databases. 
Figure 6. A-D Association growth kinetic parameters and crystallization technique. E-F Association primary nucleation parameters and crystallization technique. From left to right, techniques are placed in ascending order of medians 
Figure 2. Histograms of kinetic parameters: A) Primary nucleation rate constants; B) Growth rate constants; C) Exponential term associated with supersaturation in primary nucleation rate; D) Exponential term associated with supersaturation in growth rate. 
Figure 8. Scatter plot of standardised 𝑙𝑜𝑔 𝑘𝑔 and 𝑔 for the model 𝐺 = 𝑘𝑔𝛥𝐶 𝑔 (G1). The labels represent the identification number of the observations. Cluster observations are distributed as 
Figure 9. Scatter plot of standardised 𝑙𝑜𝑔𝑘𝑔 and 𝑔 for the model 𝐺 = 𝑘𝑔(𝑆 − 1) 𝑔 (G2). The labels represent the identification number of the observations. Cluster observations are 
Table 4. Expected values (standard deviation) of the 3 most important classifiers for each cluster.
Citations
Identifying the Polymorphic Outcome of Hypothetical Polymorphs in Batch and Continuous Crystallizers by Numerical Simulation
TL;DR: The strategy to crystallize the desired polymorph has not been extensively investigated, especially in pharmaceutical manufacturing, and the need for further research into this area is urgently needed.
7
References
Categorical Data Analysis
TL;DR: In this article, categorical data analysis was used for categorical classification of categorical categorical datasets.Categorical Data Analysis, categorical Data analysis, CDA, CPDA, CDSA
15.1K
Modernizing Pharmaceutical Manufacturing: from Batch to Continuous Production
Sau L. Lee,Thomas F. O’Connor,Xiaochuan Yang,Celia N. Cruz,Sharmista Chatterjee,Rapti D. Madurawe,Christine M. V. Moore,Lawrence X. Yu,Janet Woodcock +8 more
TL;DR: The Food and Drug Administration (FDA) regulates pharmaceutical drug products to ensure a continuous supply of high-quality drugs in the USA as mentioned in this paper, where the FDA supports the implementation of continuous manufacturing using science-and risk-based approaches.
The Future of Pharmaceutical Manufacturing Sciences.
Jukka Rantanen,Johannes Khinast +1 more
TL;DR: This review covers important elements of manufacturing sciences, beginning with risk management strategies and design of experiments (DoE) techniques and addressing future manufacturing solutions, covering continuous processing and hot‐melt processing and printing‐based technologies.
388
Random Forest Models To Predict Aqueous Solubility
TL;DR: The Random Forest regression model predicted aqueous solubility more accurately than those created by PLS, SVM, and ANN and offered methods for automatic descriptor selection, an assessment of descriptor importance, and an in-parallel measure of predictive ability, all of which serve to recommend its use.
357
A perspective on PSE in pharmaceutical process development and innovation
TL;DR: The central role of Process Systems Engineering methods and tools in pharmaceutical process development and innovation is discussed, and questions such as: Which PSE methods can be applied readily?
147