Unlock instant, AI-driven research and patent intelligence for your innovation.

A Single Particle Image Clustering Method for Cryo-EM Analysis

An image clustering and single-particle technology, applied in the field of structural biology analysis, can solve problems such as smaller distances between classes, larger distances within classes, and difficult to distinguish classes

Active Publication Date: 2020-04-28
SHANGHAI JIAOTONG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] Furthermore, the input single-particle image data itself has class structure information, and the distance between images belonging to the same class is relatively close, but due to the influence of noise, the inter-class distance becomes smaller and the intra-class distance becomes larger. methods for indistinguishable classes

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
  • A Single Particle Image Clustering Method for Cryo-EM Analysis
  • A Single Particle Image Clustering Method for Cryo-EM Analysis
  • A Single Particle Image Clustering Method for Cryo-EM Analysis

Examples

Experimental program
Comparison scheme
Effect test

example

[0043] There is an existing data set that contains four classes, each class has 60 images, and the signal-to-noise ratio is 1 / 30. We select an image for each class to display as figure 2 shown.

[0044] Use the software processing result of the inventive method to output as follows:

[0045] real class 1 real class 2 real class 3 real class 4 output class 1 55 1 0 0 output class 2 4 54 3 0 output class 3 0 5 54 0 output class 4 1 0 3 60

[0046] Therefore, we get an accuracy rate of 92.92% for this method.

[0047] The output class center image is image 3 .

[0048] The true value of the class center is Figure 4 shown.

[0049] It can be seen from the results that this method effectively clusters single particle images with low signal-to-noise ratio, and the accuracy rate in the current data set reaches 92.92%.

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 relates to a single particle image clustering method for cryo-electron microscope analysis. A single-particle image clustering method for single-particle image analysis, comprising: step 1: accepting user input initial class number k 0 , the number of final classes k n And the input data set, the random initialization data set is k 0 A class, calculate the class center, and establish a shared K-nearest neighbor network for the input data set; step 2: perform a KMeans clustering, when measuring the similarity between the input image and the class center, add the class center to the network, and update the network to calculate the nodes The network-based similarity between; Step 3: Determine whether the number K of the current class is equal to the user input k n , if yes, output each class and class average image, and exit, otherwise split the largest class and return to step 2 to continue.

Description

technical field [0001] The invention belongs to the technical field of structural biology analysis, in particular to a single particle image clustering method for cryo-electron microscope analysis. Background technique [0002] Cryo-electron microscopy is a technique in which a sample is placed in an ultra-cold environment and then a two-dimensional image is sampled using an electron microscope to generate a three-dimensional model of the sample. Compared with X-ray crystallography and nuclear magnetic resonance techniques, two mature structural biology research methods, cryo-electron microscopy can directly obtain molecular morphology and phase information, and can resolve those that are not suitable for X-ray crystallography and nuclear magnetic resonance. Other advantages of resonance technology for analysis of proteins. With the improvement of biological sample preparation technology, the advancement of electron microscope equipment and the development of digital image ...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06K9/00
CPCG06V20/69G06F18/23213
Inventor 沈红斌殷硕
Owner SHANGHAI JIAOTONG UNIV