A method for predicting protein complexes based on sample data

A technology for protein complexes and sample data, applied in the field of predicting protein complexes based on sample data, to improve the accuracy, improve the defects of overfitting or underfitting, and reduce noise.

Active Publication Date: 2022-04-05
CAPITAL NORMAL UNIVERSITY
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, accurate and efficient protein complex prediction methods need further research

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 method for predicting protein complexes based on sample data
  • A method for predicting protein complexes based on sample data
  • A method for predicting protein complexes based on sample data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0188] System Process Reference image 3 .

[0189] The protein interaction data is public data, and the PPI data set used by the inventor is the yeast protein interaction network, because the yeast data is relatively complete among all organisms. The DIP data set is used as the protein interaction data set, and GSE3431 is used as the gene expression data; the yeast genome database is used to calculate the GO semantic similarity; the CYC2008 database is used as the reference set.

[0190] S1: Construction of weighted network.

[0191] The PPI network is constructed based on the DIP data. In the DIP data set, there is a connection between the two proteins that interact. If there is no interaction between the two proteins, there is no connection between the two proteins. refer to Figure 6 , the nodes represent proteins, and the edges represent the interactions between proteins, Figure 6 (a) and (b) represent the unweighted PPI network and the weighted PPI network respectiv...

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 present invention relates to methods for predicting protein complexes based on sample data. The method includes: (1) constructing a weighted PPI network based on the sample data and performing denoising processing on the weighted PPI network, wherein the denoising processing is weighted by using the semantic similarity of the gene ontology as the weight of the PPI network ; (2) Constructing a dynamic weighted PPI network based on the weighted PPI network after de-drying treatment; (3) Predicting protein complexes using a hybrid clustering algorithm. This method effectively reduces the noise of PPI data through the introduction of GO semantic similarity, and has biological significance; at the same time, it reflects the real protein activity and reflects the dynamics of the PPI network; in addition, it improves the traditional clustering The defects of overfitting or underfitting in the algorithm improve the accuracy of the clustering algorithm, thereby effectively improving the accuracy of the protein complex prediction results.

Description

technical field [0001] The present invention relates to the field of bioinformatics, in particular, the present invention relates to a method and system for predicting protein complexes based on sample data. Background technique [0002] A protein complex is a group of proteins that are bound together by interactions of multiple proteins at the same time or space. The number of protein complexes detected by experimental methods is small and the cost is high. How to use computational methods to mine effective protein complexes from a large amount of protein interaction data has become a new research direction. The prediction of protein complexes is of great significance for understanding cell life activities and protein functions. [0003] However, accurate and efficient protein complex prediction methods need further research. Contents of the invention [0004] This application is based on the inventor's discovery and recognition of the following facts and problems: [...

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): G16B40/30G16B40/20G16B20/00
CPCG16B20/00G16B40/00
Inventor 刘丽珍孙晓武宋巍
Owner CAPITAL NORMAL UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap