Comparison of partial least squares-discriminant analysis and soft independent modeling of class analogy methods for classification of Saccharomyces cerevisiae cells based on mid-infrared spectroscopy

• Autor(a) principal: Sampaio, Pedro
• Data de Publicação: 2021
• Outros Autores: Calado, Cecília
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10400.21/13223
• topic: Chemometrics; Mid-infrared spectroscopy; Partial least squares-discriminant analysis; Principal component analysis; Soft independent modeling of class analogies

Saccharomyces cerevisiae is a widely studied and highly utilized eukaryotic organism, ideally suited to high throughput metabolic analysis, being a powerful model for understanding basic cell biology. This study compares the models developed by two supervised methods, such as the partial least squares-discriminant analysis (PLS-DA) and soft independent modeling of class analogy (SIMCA), using mid-infrared (MIR) spectra registered during the growth of S. cerevisiae in bioreactor. The spectra were analyzed using the principal component analysis (PCA), with resolution in five different classes, which were well defined in terms of their biochemical parameters. The SIMCA model showed a significant fitting, 99%, validation, 98%, and prediction parameters, 97%, comparatively with PLS-DA model. Regarding accuracy, sensitivity, and specificity parameters, a value between 83% and 100% was achieved for both methods, but the SIMCA method showed significant specificity and sensitivity values, 98%-100%, representing a suitable classification tool of yeast cells. According to these results, the MIR spectra associated with chemometric tools can be considered a valued strategy for a classification and detailed analysis for an accurate control, allowing to predict the evolution of the corrected process in advance, avoiding losses of time and costs associated with new fermentations, identifying a significant number of samples in any biotechnological process.