Advances in the Application of Artificial Intelligence-Based Spectral Data Interpretation: A Perspective

Abstract

The interpretation of spectral data, including mass, nuclear magnetic resonance, infrared, and ultraviolet–visible spectra, is critical for obtaining molecular structural information. The development of advanced sensing technology has multiplied the amount of available spectral data. Chemical experts must use basic principles corresponding to the spectral information generated by molecular fragments and functional groups. This is a time-consuming process that requires a solid professional knowledge base. In recent years, the rapid development of computer science and its applications in cheminformatics and the emergence of computer-aided expert systems have greatly reduced the difficulty in analyzing large quantities of data. For expert systems, however, the problem-solving strategy must be known in advance or extracted by human experts and translated into algorithms. Gratifyingly, the development of artificial intelligence (AI) methods has shown great promise for solving such problems. Traditional algorithms, including the latest neural network algorithms, have shown great potential for both extracting useful information and processing massive quantities of data. This Perspective highlights recent innovations covering all of the emerging AI-based spectral interpretation techniques. In addition, the main limitations and current obstacles are presented, and the corresponding directions for further research are proposed. Moreover, this Perspective gives the authors’ personal outlook on the development and future applications of spectral interpretation.

Cr-Detector: A simple chemosensing system for onsite Cr (VI) detection in water

“…Moreover, the advancement in soft computing has revolutionized data analytics for sensor development. The rapid emergence of deep learning has been successfully applied to improve the analytical performance of colorimetric determination (e.g., UV-Vis spectrophotometer and colorimetric test paper), including denoising, recognition, and summary of every small characteristic change from each image [49][50][51][52]. One example is Deep Convolutional Neural Networks (DCNNs) [51].…”

Cross-Modal Retrieval Between 13C NMR Spectra and Structures Based on Focused Libraries

“…Structures are identified by comparing the query spectra with each spectrum in the reference library. , The large chemical shift ranges and narrow peak widths contribute to the prevalence of 13 C spectral-library-matching systems in compound identification . However, as the traditional libraries contain only tens or hundreds of millions of known compound structures, they do not meet the growing demand for structure identification. ,, Over the last few decades, with the significant advancement in artificial intelligence, deep learning has been developed in the field of analytical chemistry …”

Discriminative feature analysis of dairy products based on machine learning algorithms and Raman spectroscopy

“…The study showed that under single algorithm conditions, the accuracy of brand classification for dairy products exceeded 90%, and when these algorithms were combined and coordinated, the accuracy could reach 99% ( Zikang et al, 2024 ). However, there are also some issues that urgently need improvement, such as spectral feature analysis ( Ji et al, 2023 ; Xue et al, 2023 ). For machine learning discriminative algorithms, they often act as a black box with limited interpretability.…”