Mixture analysis using non‐negative elastic net for Raman spectroscopy

Abstract

Raman spectrum is wealth of structural information, which can be used as molecular fingerprint to identify compounds. There are relations between the intensities of Raman peaks and the concentrations of compound, and they can be used to estimate relative concentrations of the compounds in mixture. However, it is still challenging to interpret the Raman spectrum of mixture. The non-negative lasso (NN-LASSO) has been used to solve this problem, but it failed to identify highly correlated compounds. The quadratic term of nonnegative elastic net (NN-EN) can ensure the stability of the fitted model. Therefore, a novel mixture analysis method was developed based on NN-EN in this study. It has been applied to analyze the simulated, liquid, powder, tablet, and quantitative mixture datasets. Results showed that NN-EN can identify the compounds in mixture with high accuracy and estimate their relative concentrations with small deviation. Furthermore, NN-EN was more stable than NN-LASSO when the spectra of some compounds are highly correlated. It is a promising approach for analyzing Raman spectra of mixtures.

RamanFormer: A Transformer-Based Quantification Approach for Raman Mixture Components

“…Similarly, Zhang et al 57 exploit a modified reverse searching method and non-negative least squares for identification and quantification of the components in a mixture, respectively. Zeng et al 58 propose a mixture analysis approach based on a non-negative elastic net to quantify the components in mixtures that are measured or generated using the spectra of the components. Li et al 59 introduce a CNN-based approach for spectral unmixing of a mixture of various dyes for mRNA biomarker detection.…”

A review of artificial intelligence methods combined with Raman spectroscopy to identify the composition of substances

“…In addition, when the spectra of certain compounds are highly correlated, NN‐EN is more stable than nonnegative lasso (NN‐LASSO). [ 67 ] As a chemical analysis tool, Raman spectroscopy was applied to study the crystallization of calcium carbonate in salt solutions at different temperatures. Using advanced mixture analysis algorithms based on Bayesian theory (BPSS), the Raman spectra of three pure anhydrous polymorphs (vaterite, aragonite, and calcite) can be recovered.…”

A Universal and Accurate Method for Easily Identifying Components in Raman Spectroscopy Based on Deep Learning

“…However, they often fail in component identification of mixtures due to interference from coexisting components, noise, baselines, and deviations between instruments in realworld applications. 6,7 In order to analyze the Raman spectra of mixtures more efficiently, some methods have been developed, such as the interactive self-modeling method (SIMPLISMA), 8 spectral reconstruction, 9 partial correlation, 10 sparse regularized model, 11 reverse searching and non-negative least-squares (RSearch-NNLS), 12 non-negative elastic net, 13 weighted segmental hit-quality index, 14 and adaptive hit-quality index. 15 However, most of those methods are still based on the similarity or distance between spectra.…”

“…It predicts the similarities between the spectrum of an unknown sample and all the spectra in a database and obtains possible candidates for the sample. Then, non-negative elastic net (NN-EN) 13 is used to estimate their ratios and further filter out false positives.…”