echemi logo
Product
  • Product
  • Supplier
  • Inquiry
    Home > Biochemistry News > Microbiology News > Advances have been made in the identification of microbiological single-cell artificial intelligence.

    Advances have been made in the identification of microbiological single-cell artificial intelligence.

    • Last Update: 2020-07-28
    • Source: Internet
    • Author: User
    Search more information of high quality chemicals, good prices and reliable suppliers, visit www.echemi.com
    Rapid identification of microorganisms with high specificity and high sensitivity is widely needed in many fields, such as clinical inspection, food safety, customs border inspection and so on.with the increasing importance of national biosafety, the demand for accurate and rapid detection of microorganisms is more urgent.the current microbial detection and identification methods mostly rely on pure culture, which usually takes a long time, and it is difficult to achieve accurate identification at the minute level.Raman spectrum is a discontinuous band formed by inelastic scattering between photons and chemical molecules.each chemical molecule has its own specific Raman spectrum, which can be accurately identified according to the characteristics of Raman spectrum, so Raman spectrum is called "fingerprint spectrum" of chemical molecule.due to the advantages of non-contact, non-destructive, non labeling, fast, accurate and less interference from water environment, the identification and characterization of complex biological samples by Raman spectroscopy has become a hot spot and frontier.Fu Yu research group of Institute of Microbiology, Chinese Academy of Sciences has long been committed to the rapid identification of microorganisms at the single cell level by Raman spectroscopy.recently, the research group published a research paper entitled combination of an artificial intelligence approach and laser tweezers Raman spectroscopy for microbiological identification online in analytical chemistry. Raman optical tweezers combined with artificial intelligence technology was used to realize rapid and accurate identification of micro biological single cells.Fu Yu's research group has independently built a laser Raman acquisition system. The system uses 785 nm monochromatic continuous laser light source to capture microbial single cells and stimulate cells to produce Raman scattering while manipulating single cells.after laser irradiation of Saccharomyces cerevisiae, Escherichia coli and halophilic archaea, the statistical results showed that the survival rate of single microbial cells was 95.22% to 97.66% after manipulation and collection of Raman spectra by optical tweezers, which proved that Raman optical tweezers were non-destructive to single cells, and showed that Raman identification could be seamlessly aligned with subsequent single cell culture, sequencing and other operations Then.because the Raman group of a cell (the sum of all Raman signals of a cell) includes hundreds of Raman shift peaks, which contains a large amount of information of nucleic acids, proteins, lipids, polysaccharides and various metabolites in the cell. In view of this feature, the research group designed a convolutional neural network machine learning algorithm, established a Raman group database, carried out model validation and The results showed that the average accuracy of single cell identification reached 95.64%, and the whole identification process was completed in 5 minutes.in view of the "black box" of artificial intelligence analysis, a new algorithm for extracting the characteristic peaks of microorganism Raman spectrum was established by the idea of masking spectrum one by one, which realized the visualization of how to analyze the Raman spectrum of microorganisms by artificial intelligence, broke the black box of artificial intelligence identification process, and laid a foundation for further characterization of microbial biochemical characteristics.Lu Weilai, assistant researcher of Fu Yu research group, and Chen xiuqiang, a postgraduate student, are the co first authors of this paper, and Fu Yu is the corresponding author. The research has been funded by the National Natural Science Foundation of China, the key R & D program of the Ministry of science and technology, the strategic high-tech innovation fund project of the Chinese Academy of Sciences, and the strategic pilot research program of the Chinese Academy of Sciences.Raman tweezers combined with artificial intelligence to identify microbial cells and the extraction process of characteristic spectra quickly and schematic pictures. The official account was hosted by the Microbiological Resource Center of the Institute of Microbiology and the big data center of the Chinese Academy of Sciences. In 2019, the hot TOP101. TOP101. reversed the type 2 diabetes. Daniel sent out the following text: type 2 diabetes is a simple disease, reducing weight or reversing the condition. 2. Just now, science released ten scientific breakthroughs in 2019! 3. Science! Broccoli awakens anti-tumor gene! Chinese medical doctor's letter to his father published in Chinese by lancet! Your "honey", my "arsenic..." 6. Drinking, especially those who blush, may face a higher risk of dementia. 7. Nature weighs heavily! The first creature to completely synthesize and completely change the DNA code was born. 8. This is not a big hazelnut! Science has published a new oral insulin, or will replace the traditional injection 9. Science to prevent baldness: start from never losing hair... 10. Can changing sperm speed affect the sex of offspring?
    This article is an English version of an article which is originally in the Chinese language on echemi.com and is provided for information purposes only. This website makes no representation or warranty of any kind, either expressed or implied, as to the accuracy, completeness ownership or reliability of the article or any translations thereof. If you have any concerns or complaints relating to the article, please send an email, providing a detailed description of the concern or complaint, to service@echemi.com. A staff member will contact you within 5 working days. Once verified, infringing content will be removed immediately.

    Contact Us

    The source of this page with content of products and services is from Internet, which doesn't represent ECHEMI's opinion. If you have any queries, please write to service@echemi.com. It will be replied within 5 days.

    Moreover, if you find any instances of plagiarism from the page, please send email to service@echemi.com with relevant evidence.