Quantitative Analysis of Fluorescent Sensor Arrays

Fluorescent sensor arrays address the limitations of a single sensor by leveraging multiple sensing elements to generate unique response patterns for each of the analyte of interest. This approach has emerged as a powerful tool for identifying and analyzing intricate chemical and biological environments using various multivariate analytical tools such as principal component analysis (PCA), linear discriminant analysis (LDA), and hierarchical cluster analysis (HCA). Nevertheless, the extraction of reliable quantitative information from these arrays presents a greater challenge, primarily due to the complexity associated with managing large datasets using conventional regression methods. In recent years, there has been a notable surge in exploring diverse statistical multivariate techniques and deep learning models (including PCA, LDA, HCA, partial least square regression, support vector regression, Gaussian processes regression, and neural networks) as modern regression tools to handle multidimensional data. These analytical tools facilitate the simultaneous acquisition of both qualitative and quantitative information for various analytes using sensor arrays.