Raman spectra-based deep learning: A tool to identify microbial contamination.

Raman spectra-based deep learning: A tool to identify microbial contamination.
复制标题

DOI:
10.1002/mbo3.1122
复制
发表时间:
2020-11
期刊:
影响因子:
3.4
通讯作者:
Verma MS
Verma MS
中科院分区:
生物学3区
文献类型:
--
作者:
Maruthamuthu MK;Raffiee AH;De Oliveira DM;Ardekani AM;Verma MS

文献摘要

参考文献

被引文献

相似文献

深度学习有可能提高用于制药行业过程分析技术的在线,在线和在线仪器的输出。在这里,我们使用基于拉曼光谱的深度学习策略来开发一种检测微生物污染的工具。我们建立了一个拉曼数据集的微生物是常见的污染物在制药行业的中国卵巢(CHO)细胞,这是经常用于生产生物制品。使用卷积神经网络(CNN),我们以95%-100%的准确度对包括单个微生物和与CHO细胞混合的微生物的不同样品进行分类。这组12种微生物跨越革兰氏阳性和革兰氏阴性细菌以及真菌。我们还为不同的微生物和CHO细胞创建了一个注意力地图,以突出显示拉曼光谱的哪些部分对帮助区分不同物种贡献最大。该数据集和算法为实现拉曼光谱法检测制药行业中的微生物污染提供了途径。我们使用拉曼光谱来识别制药行业中常见的微生物污染物。这些污染物跨越革兰氏阴性菌、革兰氏阳性菌和真菌。卷积神经网络的使用实现了95%-100%的范围内的识别精度。
Deep learning has the potential to enhance the output of in‐line, on‐line, and at‐line instrumentation used for process analytical technology in the pharmaceutical industry. Here, we used Raman spectroscopy‐based deep learning strategies to develop a tool for detecting microbial contamination. We built a Raman dataset for microorganisms that are common contaminants in the pharmaceutical industry for Chinese Hamster Ovary (CHO) cells, which are often used in the production of biologics. Using a convolution neural network (CNN), we classified the different samples comprising individual microbes and microbes mixed with CHO cells with an accuracy of 95%–100%. The set of 12 microbes spans across Gram‐positive and Gram‐negative bacteria as well as fungi. We also created an attention map for different microbes and CHO cells to highlight which segments of the Raman spectra contribute the most to help discriminate between different species. This dataset and algorithm provide a route for implementing Raman spectroscopy for detecting microbial contamination in the pharmaceutical industry. We use Raman spectroscopy to identify microbial contaminants that are common in the pharmaceutical industry. These contaminants span across Gram‐negative bacteria, Gram‐positive bacteria, and fungi. The use of a convolution neural network achieves identification accuracy in the range of 95%–100%.
DOI: 10.1039/b701160a
发表时间: 2007-01-01
期刊: ANALYST
影响因子: 4.2
作者:
Naja, Ghinwa;Bouvrette, Pierre;Luong, John H. T.
通讯作者: Luong, John H. T.
DOI: 10.1128/jcm.01548-18
发表时间: 2019-02-01
影响因子: 9.4
作者:
England, Matthew R.;Stock, Frida;Lau, Anna F.
通讯作者: Lau, Anna F.
DOI: 10.1002/bit.26476
发表时间: 2018-02-01
影响因子: 3.8
作者:
Rangan, Shreyas;Kamal, Sepehr;Piret, James M.
通讯作者: Piret, James M.
使用拉曼光谱和化学计量学在单细胞水平上鉴定干酪乳杆菌张在分批培养过程中的生长阶段
DOI: 10.1186/s12934-017-0849-8
发表时间: 2017-12-23
影响因子: 6.4
作者:
Ren Y;Ji Y;Teng L;Zhang H
通讯作者: Zhang H
DOI: 10.5731/pdajpst.2014.005165
发表时间: 2016-05-01
影响因子: --
作者:
Deal, Amanda;Klein, Dan;Schwarz, John Spencer
通讯作者: Schwarz, John Spencer