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

Key protein identification method based on fusion of biological and topological features

A technology of topological features and identification methods, applied in the field of bioinformatics, can solve the problems of lack of key protein biological characteristics, low accuracy of key proteins, and dependence on the accuracy of protein interaction networks, so as to expand the scope of application and practicability, and improve efficiency , the effect of improving accuracy

Active Publication Date: 2021-12-03
YANGZHOU UNIV
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The disadvantages of these methods to identify key proteins are: (1) For a certain protein, some of its centralities are high, but other centralities may not be high, which will lead to low accuracy of key proteins identified; (2) Key protein prediction methods based on protein topological properties not only rely on the accuracy of protein interaction networks, but also lack of consideration of the biological characteristics of key proteins

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
  • Key protein identification method based on fusion of biological and topological features
  • Key protein identification method based on fusion of biological and topological features
  • Key protein identification method based on fusion of biological and topological features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0077] The method proposed in this paper (Co-MTB) will be compared with the existing methods of DC, EC, BC, NC, LBCC, SON, COEWC in DIP dataset and MIPS dataset. For each method, we select the top 100 to 600 protein results as the candidate set.

[0078] The prediction results of the DIP data set are as follows Figure 2a , Figure 2b , Figure 2c , Figure 2d , Figure 2e , Figure 2f shown. The method Co-MTB proposed in this paper can achieve better results than other methods in identifying key proteins. When taking the top 100-600 proteins as candidate proteomes, the prediction accuracy of Co-MTB is 25%, 19%, 23%, 24%, 24%, 28% higher than CoEWC, respectively. However, Co-MTB improves the prediction accuracy by 11%, 8%, 8%, 6%, 7% and 5% at six levels compared with the recently developed method SON.

[0079] The prediction results of the MIPS data set are as follows Figure 3a , Figure 3b , Figure 3c , Figure 3d , Figure 3e , Figure 3f shown. The algorit...

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 belongs to the technical field of biological information, and specifically relates to a method for identifying key proteins based on the fusion of biological and topological features: each protein vertex is assigned a score representing its importance, and the scores of all vertices constitute a vector of n columns, given The initial value of the score, according to the value of biological information and topological properties, constitutes the attribute value of the protein vertex, and constitutes the attribute matrix. Finally, the scores are arranged from large to small, and the output scores correspond to k protein is the final result. Combining the topological properties of protein interaction networks with protein biological properties helps to improve the accuracy of identifying key proteins and improves the efficiency of key protein identification.

Description

technical field [0001] The invention belongs to the technical field of biological information, and mainly relates to a technology for identifying key proteins in a protein interaction network by fusing biological and topological features, in particular to a method for identifying key proteins in a PPI network based on network topology information and protein biological attributes. Background technique [0002] In biological cells, key proteins are indispensable for the realization of cell functions, and have important application value for the survival of organisms, drug target design, disease treatment and prediction, etc. Therefore, the identification of key proteins has become one of the important research tasks in the field of proteomics. Although some achievements have been made in the identification of key proteins in protein interaction networks, due to the high complexity and randomness of living systems, effective methods in other fields often do not necessarily ach...

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): G16B25/00G16B40/00
Inventor 刘维马良玉陈昕
Owner YANGZHOU UNIV