Application of a kNN-based similarity method to biopharmaceutical manufacturing.

Machine learning-based similarity analysis is commonly found in many artificial intelligence applications like the one utilized in e-commerce and digital marketing. In this study, a kNN-based (k-nearest neighbors) similarity method is proposed for rapid biopharmaceutical process diagnosis and process performance monitoring. Our proposed application measures the spatial distance between batches, identifies the most similar historical batches, and ranks them in order of similarity.

Glucose monitoring and adaptive feeding of mammalian cell culture in the presence of strong autofluorescence by near infrared Raman spectroscopy.

Raman spectroscopy offers an attractive platform for real-time monitoring and control of metabolites and feeds in cell culture processes, including mammalian cell culture for biopharmaceutical production. However, specific cell culture processes may generate substantial concentrations of chemical species and byproducts with high levels of autofluorescence when excited with the standard 785 nm wavelength. Shifting excitation further toward the near-infrared allows reduction or elimination of process autofluorescence.

Monitoring of mannitol phase behavior during freeze-drying using non-invasive Raman spectroscopy.

In this study, the feasibility of using Raman spectroscopy as a fast, non-invasive, non-destructive technique to monitor crystallization and polymorphic transformations during freeze-drying is assessed using mannitol as the model compound. In-line process monitoring was achieved by interfacing a Raman spectrometer with a fiber-optically coupled, long-working-distance probe to a freeze-drier. By analyzing the process data using principal component analysis, it was possible to extract valuable information pertaining to ice and mannitol crystallization points, the polymorphic form of mannitol, and dehydration of the mannitol hydrate.

On-line content uniformity determination of tablets using low-resolution Raman spectroscopy.

Analytical techniques for rapid and nondestructive content uniformity determination of pharmaceutical solid dosage forms have been studied for several years in an effort to replace the traditional wet chemistry procedures, which are labor intensive and time consuming. Both Raman spectroscopy and near-infrared spectroscopy have been used for this purpose, and predictability errors are approaching those of the traditional techniques. In this study, a low-resolution Raman spectrometer was utilized to demonstrate the feasibility of both rapid at-line and on-line determination of tablet content uniformity.

Raman spectroscopy for tablet coating thickness quantification and coating characterization in the presence of strong fluorescent interference.

We report a novel approach to the measurement of colored tablet coating thickness, which employs Raman spectroscopy with univariate and multivariate data analysis. Our results suggest that Raman sensing can serve as a viable non-invasive means to quantify tablet coating thickness in the presence of a fluorescent ingredient in the coating formulation (food colorant Alphazurine FG or D&C Blue No. 4).

Raman spectroscopic measurement of tablet-to-tablet coating variability.

We report new results suggesting the feasibility of Raman spectrometry as a tool by which to examine the variability of tablet coatings. Our experiments feature a probe that can operate with a revolving laser focus to average content and coating non-uniformity. Raman spectral changes are correlated with tablet exposure times in a pan coater by means of partial least squares (PLS) multivariate analysis.

Blend uniformity analysis using stream sampling and near infrared spectroscopy.

A near infrared spectroscopic method was developed to determine drug content in a 20% (wt/wt) ibuprofen and spray-dried hydrous lactose blend. A blending profile was obtained after blending for 0.5, 1, 3, 5, 10, and 20 minutes.