Exploring NIR spectroscopy data: A practical chemometric tutorial for analyzing freeze-dried pharmaceutical formulations

Abstract

Chemometrics tools are of fundamental importance for data analysis in the pharmaceutical field, especially with the increasingly strong assertion of the Process Analytical Technologies (PAT). In fact, analytical technologies such as Near-Infrared or Raman spectroscopies generate a lot of data, the spectra, that must be analyzed in a proper way. Typically, it is quite difficult to deeply understand the information hidden within the raw data. Therefore, careful, and efficient data exploration is needed to highlight the chemical and physical features of the analyzed samples.

Here, a tutorial on all the fundamental steps and concepts needed to perform a proper data analysis based on a case-study of different freeze-dried formulations in the pharmaceutical field is proposed. The data analysis pipeline begins with the dataset explanation, to better point out the main known differences and similarities among the investigated formulations. After the first step of data preprocessing, Principal Component Analysis (PCA), Partial Least Squares (PLS) for regression, and Partial Least Squares-Discriminant Analysis (PLS-DA) for classification are presented and applied to show how to obtain deep comprehension of the real-case NIR dataset at hand. The experimental results demonstrate that trends related to increasing levels of sucrose and/or arginine, as well as distinct clusters related to the sample type and to the operator who conducted the analysis can be found and modelled in the example data.

The tutorial aims at providing clear practical steps to conduct a robust data analysis, starting from the extraction and organization of the raw data, up to building more advanced predictive models (regression and classification). At each step some key questions are asked and answered to stimulate critical thinking in the reader. Also, commented MATLAB scripts are provided together with the real-case example NIR data, so that anyone could reproduce the whole data analysis in the tutorial, and try first hand to work with the data.