Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Single-cell analysis and authentication method at high flux by combining Raman spectrum with artificial intelligence

A technology of Raman spectroscopy and artificial intelligence, applied in the field of cell analysis and identification, can solve problems such as broken cells, difficulty in realizing rapid analysis and identification of single cells, and inability to obtain information research on cell dynamics

Active Publication Date: 2018-12-14
青岛明德生物科技研究院有限公司
View PDF16 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Compared with traditional methods, molecular detection methods improve the sensitivity of cell detection and identification and shorten the detection time, but it is difficult to achieve rapid analysis and identification of single cells
MALDI-TOF mass spectrometry identifies cells by determining the differential analysis of specific protein profiles of cells, but this method is currently not able to achieve in situ detection, requires pure cultures, and requires a large amount of cellular proteins
Methods such as single-cell sequencing can realize the identification and analysis of single cells, but this method is an invasive and damaging method that needs to break the cells and cannot perform in-situ operations, nor can it obtain dynamic information and follow-up research on cells. Therefore, it is urgent to develop high-tech High-throughput, rapid, non-destructive single-cell analysis and identification technology

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Single-cell analysis and authentication method at high flux by combining Raman spectrum with artificial intelligence
  • Single-cell analysis and authentication method at high flux by combining Raman spectrum with artificial intelligence
  • Single-cell analysis and authentication method at high flux by combining Raman spectrum with artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] The embodiment of the present invention provides a high-throughput single-cell analysis and identification method combining Raman spectroscopy with artificial intelligence, including the following steps:

[0039] S1. Obtain the living cell fluid to be tested, and prepare the cell fluid into a single-cell array on the chip using microfluidic technology;

[0040] S2. Acquiring the Raman spectrum of the single-cell array and preprocessing the Raman spectrum data;

[0041] S3. Using the preprocessed data to perform model training, verification and inspection, and finally obtain an optimal model, and use the optimal model to identify and predict the preprocessed Raman spectral data.

[0042] in,

[0043] Step S1 is specifically:

[0044] Obtain the living cell liquid to be tested, and wash the cells in the obtained living cell liquid to be tested with saline or cell isotonic pressure solution for 3 times; the saline is 0.85% NaCl or NaCl suitable for the physiological conc...

Embodiment 2

[0062] 本发明实施例利用拉曼光谱仪采集获得Escherichia coli DH5α, Pseudomouasaeruginosa PAO1, Haloferax mediterranei ATu33sin, Sulfolobus islandicusE233S, Methanococcus maripaludis S2, Metallosphaera cuprina JCM 15769T,Acidianus brierleyi DSM 1651, Candida albicans SC5314, Cryptococcusneoformans JEC21, Saccharomyces cerevisiae W303-10D , S. arboricolusHZZt16L.1, S. kudriavzevii XS29L.2, S. mikatae FJSB44.3 and S. paradoxusCBS2908, a total of 14 microbial single-cell Raman spectra, and a total of 1301 Raman group data were obtained. These data were smoothed by convolution smoothing filter (Savitzky-Golay filter), baseline was removed by polynomial fitting method, and finally processed by vector normalization.

[0063] Input the preprocessed data into the built machine learning artificial intelligence algorithm model. The structural framework of the machine learning algorithm is shown in figure 1 . The structure contains 2 layers of convolutional layers, 2 layers of maximum pooling layers, and 1 ...

Embodiment 3

[0065] The embodiment of the present invention detects and analyzes the drug resistance of pathogenic microorganisms from clinic. We used a Raman spectrometer to obtain the Raman spectra of Aspergillus fumigatus (Aspergillus fumigatus) itraconazole-resistant strains and Candida albicans (Candida albicans) fluconazole-resistant strains from the clinic, as well as the wild strains of these two microorganisms. 723 Raman group data. The data pre-processing and machine learning training methods adopted are as in the above-mentioned embodiment 2. The result is as image 3 The results showed that the optimal model could well distinguish the drug-resistant strains of Aspergillus fumigatus from the wild strains, and also the drug-resistant strains of Candida albicans from the wild strains, with a sensitivity and specificity of 98%.

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a single-cell analysis and authentication method at high flux by combining a Raman spectrum with artificial intelligence, and belongs to the technical field of cell analysis and authentication. The technical scheme of the method comprises the following steps that: firstly, obtaining living body cytosol to be detected, and preparing the cytosol into a single-cell array on achip by a microfluidic technology; then, obtaining the Raman spectrum of the single-cell array, and preprocessing Raman spectrum data; utilizing the preprocessed data to carry out model training, verification and checkout; and finally, obtaining an optimal model, and utilizing the optimal model to carry out authentication prediction on the preprocessed Raman spectrum data. The method has the beneficial effects that the microfluidic technology is used for separating single cells at high flux, the Raman spectrum of the single cell is quickly collected, an artificial intelligence technology is applied to analyze single-cell Raman spectrum characteristics, the single-cell Raman spectrum characteristics are classified and authenticated, authentication accuracy is high, sensitivity is high, andthe problems that the single cell can not be nondestructively and quickly analyzed and authenticated at the high flux at present are solved.

Description

technical field [0001] The invention relates to the technical field of cell analysis and identification, in particular to a high-throughput single-cell analysis and identification method combined with Raman spectroscopy and artificial intelligence. Background technique [0002] High-throughput and rapid cell analysis and identification technology plays an important role in scientific research, industrial production, food safety and other fields. The traditional method of cell analysis and identification technology is mainly based on staining, culture, physiological and biochemical, serum characteristics, etc., which has problems such as cumbersome operation, long detection cycle, and high requirements for staff technical operation level and professional knowledge. At present, molecular detection methods such as nucleic acid molecular hybridization, PCR amplification technology, and gene chip technology are commonly used to determine the differences between cells by detecting...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G01N21/65
CPCG01N21/65
Inventor 傅钰卢维来陈秀强王苹苹
Owner 青岛明德生物科技研究院有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com