机器学习驱动的中药银杏叶 SERS 多维度鉴定

Machine-learning-driven Multidimensional Identification of Traditional Chinese Medicine Ginkgo Folium Using SERS

摘要

建立了一种基于表面增强拉曼光谱(SERS)结合机器学习的银杏叶(Ginkgo folium)多维鉴别策略, 从产地、 干燥工艺、 贮藏品质及农药残留4个维度开展研究, 实现了银杏叶的智能分类与质量判别. 结果显示, 银杏叶提取液的SERS光谱具有典型的黄酮类(槲皮素、 山奈酚、 异鼠李素)和银杏内酯特征峰. 基于SERS结合偏最小二乘判别分析(PLS-DA)模型, 对来自5个产地及4种干燥方式的银杏叶样品均实现了100%的分类准确率, 表明产地差异与干燥工艺均对其化学组成产生显著影响. 进一步地, SERS结合偏最小二乘回归(PLS)可准确预测贮藏时间(训练集, R ²=0.991, 交叉验证集R ²=0.841), 并实现对草甘膦和福美双农药残留的高灵敏定量检测. SERS 结合机器学习为银杏叶及其它中药材的产地溯源、 工艺监控、 贮藏评估与农残检测提供了一种快速、 高灵敏度的分析新策略, 为中药材质量控制与安全监管开辟了新的技术路径.

Abstract

This study establishes a multidimensional discrimination strategy for ginkgo folium based on surface-enhanced Raman spectroscopy(SERS) combined with machine learning. A systematic investigation was conducted across four dimensions(geographical origin, drying process, storage quality, and pesticide residues), enabling intelligent classification and quality assessment of ginkgo folium. The results showed that the SERS spectra of ginkgo folium extracts exhibited characteristic peaks of flavonoids(quercetin, kaempferol, isorhamnetin) and ginkgolides. Based on SERS combined with partial least squares discriminant analysis(PLS-DA), 100% classification accuracy was achieved for ginkgo folium samples from five origins and processed by four drying methods, indicating that both origin differences and drying processes significantly affect their chemical composition. Furthermore, SERS combined with partial least squares regression(PLS) accurately predicted storage time(training set, R²=0.991； cross-validation set, R²=0.841) and enabled highly sensitive quantitative detection of pesticide residues, including glyphosate and thiram. In summary, SERS combined with machine learning provides a rapid, highly sensitive, and reliable analytical strategy for origin tracing, process monitoring, storage evaluation, and pesticide residue detection of ginkgo folium and other traditional Chinese medicinal materials. This approach opens a novel technical pathway for quality control and safety supervision in traditional Chinese medicines field.

关键词

银杏叶 / 表面增强拉曼光谱 / 机器学习 / 多维度鉴定 / 中药质量鉴定

Key words

Ginkgo folium / Surface-enhanced Raman spectroscopy / Machine learning / Multidimensional identification / Quality assessment of traditional Chinese medicine

参考文献

[1] Wang S. J., Kang A., Di L Q., Zhang S. J., Tian L., Zhou W., Yun F., Shan J. J., Zhao X. L., Chin. Tradit. Herb. Drugs, 2013, 44(5), 626-631

[2] (汪素娟, 康安, 狄留庆, 张圣洁, 田乐, 周伟, 恽菲, 单进军, 赵晓莉. 中草药, 2013, 44(5), 626-631)

[3] Chen X., Jiangsu Agric. Sci., 2004, (5), 109-110

[4] (陈学林. 江苏农业科学, 2004, (5), 109-110)

[5] Li X. B., Tu P. F., Chin. Tradit. Herb. Drugs, 2003, 34(5), 4-6

[6] (李晓波, 屠鹏飞. 中草药, 2003, 34(5), 4-6)

[7] Zhang Y., Zhou B., Li Q., Jin M., Bai Y., Chem. Res. Chinese Universities, 2024, 40(2), 237-254

[8] Yu Y., Fan J., Liu H., Nie Z., Chem. Res. Chinese Universities, 2025, 41(2), 254-265

[9] Wu L., Ouyang Z. H., Cao S. C., Yi D. L., Qin X. R., Sun S. X., Liu X., Chin. J. Light Scatter., 2005, 17(2), 180-186

[10] (伍林, 欧阳兆辉, 曹淑超, 易德莲, 秦晓蓉, 孙少学, 刘峡. 光散射学报, 2005, 17(2), 180-186)

[11] Bao H. M., Leong S. X., Chen J. R. T., Shi Z., Chen S., Lv Y., Liu T. X., Phang I. Y., Ling X. Y., CCS Chem., 2024, 6(6), 1403-1421

[12] Yang Y., Dong H., Wang S., Sang Y. S., Li Z. G., Zhang L., Wang C. W., Liu Y., Chin. J. Lasers, 2022, 49(15), 193-202

[13] (杨勇, 董浩, 王澍, 桑瑶烁, 李志刚, 张龙, 汪崇文, 刘勇. 中国激光, 2022, 49(15), 193-202)

[14] Lu Y. Y., Qiao Y., Bao H. M., Chen K., Wei Y., Zhao Q., Leon G. K., Zhang H. W., Ling X. Y., Cai W. P., Anal. Chem., 2025, 97, 8537-8544

[15] Wang Z., Li X., Song W., Wang C., Wang Z., Peng X., Chem. Res. Chinese Universities, 2025, 41(4), 704-715

[16] Rong H., Chen Y. Zhang S., Chen Y., Shen L., Fang W., Chem. Res. Chinese Universities, 2025, 41(5), 1014-1020

[17] Zhu T., Yuan X., Mao G., Wei L., Xiao L., Chem. Res. Chinese Universities, 2024, 40(2), 320-325

[18] Bao H. M, Zhang H., Zhou L., Fu H., Liu G. Q., Li Y., Cai W. P., ACS Appl. Mater. Interfaces, 2019, 11(3), 28145-28153

[19] Bao H. M., Motobayashi K., Ikeda K., Anal. Chem., 2022, 94(49), 17169-17176

[20] Yadav B., Yadav R. K., Srivastav G., Yadav R. A., J. Mol. Struct., 2022, 1258, 132637

[21] Wiercigroch E., Szafraniec E., Czamara K., Pacia M. Z., Majzner K., Kochan K., Kaczor A., Baranska M., Malek K., Spectrochim. Acta A Mol. Biomol. Spectrosc., 2017, 185, 317-335

[22] Krysa M., Szymańska-Chargot M., Zdunek A., Food Chem., 2022, 393, 133430

[23] Uyeki S. C., Pacheco C. M., Simeral M. L., Hafner J. H., J. Phys. Chem. A, 2023, 127(6), 1387-1394

[24] Li L. H., Wei R., Zhang X., Li Y. Z., Wang A. X., Xia Q. Y., J. At. Mol. Phys., 2024, 41(6), 41-44

[25] (李丽华, 魏冉, 张鑫, 李云志, 王爱香, 夏其英. 原子与分子物理学报, 2024, 41(6), 41-44)

[26] Liang X., Li L., Xu T., Xu F., Dong W., J. Clin. Med. Lit., 2018, 5(43), 168-169

[27] (梁鑫, 李莉, 徐涛, 许凤, 董巍. 临床医药文献电子杂志, 2018, 5(43), 168-169)

基金资助

安徽省高等学校科学研究项目(2024AH051986)

天津市光电检测技术与系统重点实验室开放课题(2025LODTS112)

天津市光电检测技术与系统重点实验室开放课题(2025LODTS106)