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

Mode identification method based on artificial immune antigen-antibody binding energy

A pattern recognition and artificial immune technology, applied in the field of recognition, can solve problems such as the accuracy rate needs to be improved, the intelligent algorithm is complex, etc.

Inactive Publication Date: 2012-09-12
SHANGHAI UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The intelligent algorithm applied in the field of pattern recognition is relatively complex, and the accuracy rate needs to be improved

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
  • Mode identification method based on artificial immune antigen-antibody binding energy
  • Mode identification method based on artificial immune antigen-antibody binding energy
  • Mode identification method based on artificial immune antigen-antibody binding energy

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0046] seefigure 1 , the pattern recognition method based on the binding energy of artificial immune antigen-antibody is characterized in that: firstly, the overall recognition is carried out, and the affinity between the antigen epitope and the antibody paraposition is calculated by using the Euclidean distance, and the initial pattern recognition is completed; then, The secondary pattern recognition is performed by judging whether the local binding energy of the corresponding position between the antigen epitope and the antibody parasite satisfies the matching parameters. The optimal value range of the matching parameters is obtained according to various international standard classification data tests.

Embodiment 2

[0048] This embodiment is basically the same as Embodiment 1, and the special features are as follows:

[0049] The affinity calculation method between the antigen epitope and the antibody paraposition is:

[0050] The training sample given by the user is used as the antibody alignment, using n Dimensional real number vector representation, the first i Category k antibodies can show

[0051] Shown as:

[0052] (1)

[0053] in , Antibody paratope middle n a local binding site, for n set of real numbers.

[0054] No. j epitope It can be expressed as:

[0055] (2)

[0056] in , epitope of n a local binding site. During recognition, the antibody against epitope The local binding sites at the corresponding positions in the protein bind to each other.

[0057] The affinity between the antigen epitope and the antibody parasite is obtained by calculating the Euclidean distance between the two, and the specific calculation formula is as follows:...

Embodiment 3

[0067] This embodiment is basically the same as Embodiment 2, combined with specific implementation, the special features are as follows:

[0068] Using the international standard classification data Iris as a specific example, Iris data is 4-dimensional data, a total of three categories, each category has 50 samples, a total of 150 samples, the first 10 samples of each category are selected as training samples (antibody Counterpoint), and the remaining 40 are used as test samples (antigenic epitopes) for testing the performance of the algorithm. The specific steps of the algorithm are as follows:

[0069] Use formula (1) and formula (2) to calculate the average affinity between each antigenic epitope and each antibody parasite of each class, and perform initial pattern recognition on the antigenic epitope according to the affinity. At this point, most of the antigenic epitopes can be classified into the correct category, and the misclassified antigenic epitopes are shown in ...

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 mode identification method based on artificial immune antigen-antibody binding energy. The mode identification method based on the artificial immune antigen-antibody binding energy is a process for identifying antibody by antigen in an immune system, actually is a binding process of chemical bonds of antibody paratope and antigen epitope. Identification effects depend on the binding energy quantity of the chemical bonds. Under inspiration of the binding process, the overall identification, namely the primary mode identification performed by calculating the affinity between the antibody paratope and the antigen epitope, and the secondary mode identification, namely the local identification performed according to the binding energy quantity of the local binding site of the chemical bonds, are realized sequentially. The mode identification method based on the artificial immune antigen-antibody binding energy includes the steps: (1) calculating the affinity between the antibody paratope and the antigen epitope by utilizing the Euclidean distance, and performing the primary mode identification according to the affinity size; (2) determining matched parameters of the local binding energy according to variously typical categorical data; (3) performing the secondary mode identification for the antigen epitope by the antibody paratope according to the local binding energy quantity, and simply and effectively completing antigen epitope identification under the combined actions of the overall identification and the local identification.

Description

technical field [0001] The invention relates to a pattern recognition method inspired by the contrapositional combination mechanism of an antigen epitope and an antibody in an artificial immune system, which belongs to the field of recognition. Background technique [0002] As an important part of information science and artificial intelligence, pattern recognition classifies pattern samples to be recognized based on the learning of known patterns. [0003] As an important branch of artificial intelligence, artificial immunity has solved many complex problems by referring to the model, function and principle of the immune system of organisms, and has received more and more attention in recent years. The immune system has an innate, parallel, non-linear recognition ability, and can effectively distinguish self from foreign body under normal immune response conditions. The artificial immune system inspired by the biological immune system also has strong pattern recognition abi...

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): G06K9/62
Inventor 刘颖慧刘树林张宏利李栋姜锐红唐友福
Owner SHANGHAI UNIV
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