Discriminating cell line specific features of antibiotic-resistant strains of Escherichia coli from Raman spectra via machine learning analysis.
Discriminating cell line specific features of antibiotic-resistant strains of Escherichia coli from Raman spectra via machine learning analysis.
复制标题
通过机器学习分析从拉曼光谱中鉴别大肠杆菌耐药菌株的细胞系特异性特征。
DOI：
10.1002/jbio.202100274
复制
发表时间：
2022-07
影响因子：
2.8
通讯作者：
Cicerone, Marcus T.
中科院分区：
文献类型：
--
作者：
Zahn, Jessica;Germond, Arno;Lundgren, Alice Y.;Cicerone, Marcus T.
关键词：
虽然拉曼光谱可以提供高度相似的生物物种之间的无标记的歧视，歧视往往是边际，光谱信息的最佳使用是必要的。在这里，我们比较两个机器学习模型，人工神经网络和支持向量机之间的拉曼光谱的大肠杆菌MDS 42的11个细菌突变体的区别。虽然我们发现两种模型都以同样高的准确性、灵敏度和特异性区分了11种细菌菌株，但很明显，这两种模型形成了不同的类别边界。通过提取特定于应变（和特定功能）的光谱特征所利用的模型，我们发现，这两种模型利用一个小的子集的高强度峰，而单独的子集的低强度峰利用只有一种方法或其他。该分析强调了更有效地使用完整光谱信息的方法的必要性，首先要更好地理解从每个模型中获得的不同信息。在这里，我们比较了两种机器学习模型的性能，用于分类大肠杆菌MDS 42的11个细菌突变体的拉曼光谱。我们讨论了模型的性能方面的功能和训练样本的数量存在于数据集，以及强调每个模型，我们提取的应变特定的光谱特征。
While Raman spectroscopy can provide label-free discrimination between highly similar biological species, the discrimination is often marginal, and optimal use of spectral information is imperative. Here we compare two machine learning models, an Artificial Neural Network and a Support Vector Machine for discriminating between Raman spectra of eleven bacterial mutants of Escherichia coli MDS42. While we find that both models discriminate the eleven bacterial strains with similarly high accuracy, sensitivity, and specificity, it is clear that the models form different class boundaries. By extracting strain-specific (and function-specific) spectral features utilized by the models, we find that both models utilize a small subset of high intensity peaks while separate subsets of lower intensity peaks are utilized by only one method or the other. This analysis highlights the need for methods to use the complete spectral information more effectively, beginning with a better understanding of the distinct information gained from each model. Here we compare the performance two machine learning models used to classify Raman spectra of eleven bacterial mutants of Escherichia coli MDS42. We discuss model performance in terms of the number of features and training samples present in the dataset as well as the strain-specific spectral features emphasized by each model, which we extract.
登录
查看更多内容
影响因子：
35
作者：
通讯作者：
--
影响因子：
5.9
作者：
Germond A;Ichimura T;Horinouchi T;Fujita H;Furusawa C;Watanabe TM
通讯作者：
Watanabe TM
影响因子：
3.4
作者：
Chan, JW;Taylor, DS;Huser, T
通讯作者：
Huser, T
影响因子：
4.2
作者：
Fan, Xiaqiong;Ming, Wen;Lu, Hongmei
通讯作者：
Lu, Hongmei
影响因子：
7.4
作者：
Germond, Arno;Panina, Yulia;Watanabe, Tomonobu M.
通讯作者：
Watanabe, Tomonobu M.