Strain-Level Identification and Analysis of Avian Coronavirus Using Raman Spectroscopy and Interpretable Machine Learning
Strain-Level Identification and Analysis of Avian Coronavirus Using Raman Spectroscopy and Interpretable Machine Learning
复制标题
DOI：
10.1109/isbi53787.2023.10230416
复制
发表时间：
2023-04
期刊：
影响因子：
--
通讯作者：
Peng Jin;Y. Yeh;Jiarong Ye;Ziyang Wang;Yuan Xue;Na Zhang;Shengxi Huang;E. Ghedin;Huaguang Lu-H
中科院分区：
文献类型：
--
作者：
Peng Jin;Y. Yeh;Jiarong Ye;Ziyang Wang;Yuan Xue;Na Zhang;Shengxi Huang;E. Ghedin;Huaguang Lu-H
毒株水平的病毒鉴定对公共卫生管理决策具有重要意义。近年来，拉曼光谱技术在病毒鉴定中获得了极大的关注，因为它能够快速和无标记分析。在本文中，我们提出了一种基于拉曼光谱的禽冠状病毒株级鉴定的可解释机器学习方法。具体来说，我们设计了一个光谱转换器来对32株禽冠状病毒的拉曼光谱进行分类。训练完成后，通过梯度和关联传播生成相关图，进一步了解每个波数对识别的贡献。实验结果表明，该方法优于几种机器学习和深度学习基线模型，在32类识别问题中准确率达到72.72%。生成的相关图揭示了一些波数范围，这些波数范围对几乎所有菌株的鉴定都很重要，并且这些范围与脂质、核酸和蛋白质的拉曼峰范围相关。
Strain-level identification of viruses is important for decision making in public health management. Recently, Raman spectroscopy has attained great attention in virus identification since it enables rapid and label-free analysis. In this paper, we present an interpretable machine learning approach for strain-level identification of avian coronaviruses based on Raman spectra. Specifically, we design a spectral transformer to classify the Raman spectra of 32 avian coronavirus strains. After training, relevance maps can be generated through gradient and relevance propagation to further understand the contribution of each wavenumber to the identification. Experimental results show that the proposed method outperforms several machine learning and deep learning baseline models, and achieves 72.72% accuracy in the 32-class identification problem. The relevance maps generated reveal some wavenumber ranges that are important for the identification of almost all strains, and these ranges correlate with Raman peak ranges for lipids, nucleic acids, and proteins.