Single cell Raman spectrum acquisition number estimation method, data processing method and device
A Raman spectrum and single-cell technology, applied in the field of data processing, can solve the problem of inaccurate calculation of the number of Raman spectra collected
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment approach
[0106] 1. When the purpose of pattern recognition is cell visualization analysis, according to the dimensionality reduction analysis method or cluster analysis method selected by the user on the operation interface, the different substances in the single cell in the Raman spectral data are classified, and according to the different substances Classification information is used for data reorganization to obtain single-cell visualization information to establish a pattern recognition model.
[0107] In the cell visualization analysis, the input Raman spectrum data of the cell visualization analysis consists of a spectral matrix, the size of which is the number of pixels of Raman spectrum x the number of wavelengths. Before cell visual analysis, the number of Raman spectrum collection points can be displayed on the operation interface, and then the user can input the number of horizontal and vertical data collection points and select a specific wavelength through the operation int...
example
[0129] Analysis Example (2): Cell Classification Analysis
[0130] Data introduction: human induced pluripotent stem cells (HiPSC, 1560), neural stem cells (NSC, 979) and nerve cells (Neuron cell, 1128) in 010S cell line;
[0131] Raman spectroscopic conditions: HR Evolution confocal Raman microscope Raman confocal spectroscopic system (Horiba Jobin-Yvon), excitation wavelength: 532 (NA=1), repeated measurement for each cell three times;
[0132] Raman spectral data: raw Raman spectral data such as Figure 18 As shown, the data size is 3667 (number of cell samples)*1019 (number of wavelengths). 3667 is the number of Raman spectrum measurements, including some repeated samples.
[0133] Analysis results: After removing noise, cosmic rays and background, and smoothing, the original Raman spectral data is classified using the t-SNE algorithm. The analysis results of the t-SNE algorithm are as follows: Figure 19 shown, from Figure 19 As can be seen in , three different cells...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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