PLS-DA wavenumber selection for the categorization of medicine samples based on multiple criteria

Wavenumber selection based on Singular Value Decomposition for sample classification

The dissemination of falsified medicines is a public health risk. Techniques such as attenuated total reflectance Fourier transform infrared (ATR-FTIR) spectroscopy are commonly adopted for fraudulent drug detection. However, the spectrum generated by the ATR-FTIR typically results in hundreds of wavenumbers, reducing the performance of classification methods aimed at discriminating between authentic and falsified medicines. This article proposes a novel method for selecting a reduced size subset of wavenumbers that improves the classifier performance. The singular value decomposition SVD is used to generate a wavenumber importance index. An iterative process creates k-nearest neighbor (KNN) models by adding the wavenumbers in a decreasing order according to the importance index. Wavenumbers that increase classification accuracy are selected. When applied to Cialis® ATR-FTIR data, the proposed approach retained average 0.51% of the original wavenumbers with 100% accurate classifications; as for the Viagra® data set, the method yielded perfect classifications retaining average 0.17% of the original wavenumbers.

Enhancing counterfeit and illicit medicines grouping via feature selection and X-ray fluorescence spectrometry

In this paper, we propose a novel framework to select the most relevant X-Ray Fluorescence (XRF) energy values (i.e., features) to enhance the clustering (grouping) of counterfeit and illicit medical tablets. The framework is based on the integration of multidimensional scaling (MDS) and Procrustes analysis (PA) multivariate techniques. MDS provides a projection of the original data into a lower dimension, while PA finds a projection matrix from the original data. Such outputs give rise to a feature importance index that guides an iterative feature selection process; after each feature is inserted in the subset, an optimization procedure based on a greedy search method is carried out to maximize the clustering quality assessed through the Silhouette Index (SI). The inorganic chemical fingerprinting of 41 commercial samples (Viagra®, Cialis®, Lazar®, Libiden®, Maxfil®, Plenovit®, Potent 75®, Rigix®, V-50®, Vimax® and Pramil®) and 56 seized counterfeit samples (Viagra and Cialis) was used to validate the proposed framework. From the original 2048 data points in the full spectra, we identified a subset comprised of 41 energy values that substantially improved clustering quality; the obtained groups were assessed by visual inspection of the PCA plots.

Evaluating the freezing impact on the proximate composition of immature cowpea (Vigna unguiculata L.) pods: classical versus spectroscopic approaches

BACKGROUND

Freezing represents a common conservation practice regarding vegetal foodstuffs. Since compositional features need to be monitored during storage, the development of rapid monitoring tools suitable for assessing nutritional characteristics arises as a pertinent issue. In this study, cowpea (Vigna unguiculata L.) pods, both fresh and after 6 and 9 months of freezing at -18 °C, were evaluated by high-performance liquid chromatography for their content of protein as well as of essential and nonessential amino acids, while their Fourier transform infrared spectra in the mid infrared (MIR) and near infrared (NIR) ranges were concomitantly registered to assess the feasibility of this approach for the traceability of these frozen matrices.

RESULTS

For the NIR interval, the application of the 1st derivative to the spectral data retrieved the best results, while for lower concentrations the application of the Savitzky-Golay algorithm was indispensable to achieve quantification models for the amino acids. MIR is also suitable for this purpose, though being unable to quantify amino acids with concentrations below 0.07 mmol g^-1 dry weight, irrespective of the data treatment used.

CONCLUSIONS

The spectroscopic approach constitutes a methodology suitable for monitoring the impact of freezing on the nutritional properties of cowpea pods, allowing accurate quantification of the protein and amino acid contents, while NIR displayed better performance. © 2017 Society of Chemical Industry.

Spectrophotometric versus NIR-MIR assessments of cowpea pods for discriminating the impact of freezing

BACKGROUND

Freezing represents an important storage method for vegetal foodstuffs, such as cowpea pods, and thus the impact of this process on the chemical composition of these matrices arises as a prominent issue. In this sense, the phytochemical contents in frozen cowpea pods (i.e. at 6 and 9 months) have been compared with fresh cowpea pods material, with the samples being concomitantly assessed by Fourier-transform infrared spectroscopy (FTIR), both mid-infrared (MIR) and near infrared (NIR), aiming to evaluate the potential of these techniques as a rapid tool for the traceability of these matrices.

RESULTS

A decrease in phytochemical contents during freezing was observed, allowing the classification of samples according to the freezing period based on such variations. Also, MIR and NIR allowed discrimination of samples: the use of the first derivative demonstrated a better performance for this purpose, whereas the use of the normalized spectra gave the best correlations between the spectra and specific contents. In both cases, NIR displayed the best performance.

CONCLUSION

Freezing of cowpea pods leads to a decrease of phytochemical contents, which can be monitored by FTIR spectroscopy, both within the MIR and NIR ranges, whereas the use of this technique, in tandem with chemometrics, constitutes a suitable methodology for the traceability of these matrices. © 2017 Society of Chemical Industry.