Simultaneous quantitative analysis of multiple metabolites using label-free surface-enhanced Raman spectroscopy and explainable deep learning

Xianli Tian; Peng Wang; Guoqiang Fang; Xiang Lin; Jing Gao

doi:10.1016/j.saa.2024.125386

Simultaneous quantitative analysis of multiple metabolites using label-free surface-enhanced Raman spectroscopy and explainable deep learning

Spectrochim Acta A Mol Biomol Spectrosc. 2024 Nov 3:327:125386. doi: 10.1016/j.saa.2024.125386. Online ahead of print.

Authors

Xianli Tian¹, Peng Wang², Guoqiang Fang³, Xiang Lin⁴, Jing Gao⁵

Affiliations

¹ School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei 230026, China; Jiangsu Key Laboratory of Medical Optics, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, Jiangsu 215163, China.
² Jiangsu Key Laboratory of Medical Optics, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, Jiangsu 215163, China. Electronic address: [email protected].
³ National Key Laboratory of Laser Spatial Information, Harbin Institute of Technology, Harbin 150080, China; Zhengzhou Research Institute, Harbin Institute of Technology, Zhengzhou 450018, China.
⁴ School of Physics and Materials Engineering, Dalian Minzu University, Dalian 116600, China.
⁵ School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei 230026, China; Jiangsu Key Laboratory of Medical Optics, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, Jiangsu 215163, China. Electronic address: [email protected].

PMID: 39509865
DOI: 10.1016/j.saa.2024.125386

Abstract

Metabolites serve as vital biomarkers, reflecting physiological and pathological states and offering insights into disease progression and early detection. This study introduces an advanced analytical technique integrating label-free Surface-Enhanced Raman Spectroscopy (SERS) with deep learning, and leverages SHAP (SHapley Additive exPlanations) to provide a visual interpretative analysis of the predictive rationale of the deep learning model, facilitating simultaneous detection and quantitative analysis of multiple metabolites. Monolayer silver nanoparticle SERS substrates were fabricated via a triple-phase interfacial self-assembly method, which captured complex spectral information of target metabolites in mixed solutions. A custom-built deep neural network model with multi-channel feature extraction was employed to predict the concentrations of uric acid (R² = 0.976), xanthine (R² = 0.971), hypoxanthine (R² = 0.977), and creatinine (R² = 0.940). The method's scalability was validated as the performance remained consistent with an increasing number of simultaneous targets. This approach offers a sensitive, cost-effective, and rapid alternative for metabolite analysis, with significant implications for clinical diagnostics and personalized medicine.

Keywords: Explainable Deep Learning; Metabolites; Quantitative Analysis; SHAP; Surface-Enhanced Raman Spectroscopy (SERS).