Gene sequence representation learning method based on virus propagation network

A technology of spreading network and gene sequence, applied in the field of gene sequence representation learning based on virus spreading network, which can solve the problem of time-consuming learning

Active Publication Date: 2021-10-19
NAT UNIV OF DEFENSE TECH
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, in practical applications, as pointed out in Non-Patent Document 5, it is very time-consuming to learn features directly from genome sequences due to complex interdependence and long-term interactions between genome sequences, and as Non-Patent Document 5 As pointed out in literature 6, successful forecasting often depends to a large extent on the correct use of biological knowledge

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
  • Gene sequence representation learning method based on virus propagation network
  • Gene sequence representation learning method based on virus propagation network
  • Gene sequence representation learning method based on virus propagation network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0064] The present invention will be further described below in conjunction with the accompanying drawings, but the present invention is not limited in any way. Any transformation or replacement based on the teaching of the present invention belongs to the protection scope of the present invention.

[0065] The virus propagation network is a complex network, which can be expressed as G=(V,E,A), where V Represents a collection of nodes in the network, and each node represents a virus infected person. E Represents the set of connected edges, each edge represents a node v i spread the disease to v j , since the disease spread is directed, the network is a directed graph; A Represents the collection of node attributes, in G middle, represents a node i of the viral gene sequence.

[0066] given a network G , the core task of network-based gene sequence representation is to combine the features of the network into the gene sequence, so as to learn a unified low-dimension...

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 discloses a gene sequence representation learning method based on a virus propagation network. The method comprises the following steps: coding a virus gene sequence, and inputting a sequence code into a hidden layer with a specific length to obtain dimensionality reduction embedding; extracting a neighbor node set with high association degree with each node in the virus propagation network, and acquiring topological information of the nodes from the virus propagation network; respectively aggregating graph context node information of the nodes by using a forward LSTM and a reverse LSTM; aggregating sequence information of neighbor nodes by using an attention mechanism to obtain a new expression of a target node gene sequence; and carrying out model training and target optimization on the gene sequence representation model by taking graph context loss as a loss function. Experiments carried out on a simulated virus transmission network, a real Australian new coronal virus transmission network and a real AIDS virus transmission network verify the effectiveness and high efficiency of the method.

Description

technical field [0001] The invention belongs to the technical field of biological information, and in particular relates to a gene sequence representation learning method based on a virus transmission network. Background technique [0002] Genome data is currently one of the most popular types of bioinformatics data. Since the beginning of the Human Genome Project, biological gene sequence data has grown exponentially. How to extract effective bioinformatics features from massive high-dimensional biological sequence data is one of the most important issues in the field of bioinformatics. [0003] In recent years, there has been a surge in research on deep learning models based on gene sequences, and one of the main reasons for adopting this method is that representation learning or feature learning can be performed directly from raw data. Deep learning can automatically extract features, saving a lot of manual feature selection workload. At the same time, deep learning mod...

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 & AuthorityApplications(China)
IPC IPC(8): G16B40/00G16B5/00G06N3/04G06N3/08
CPCG16B40/00G16B5/00G06N3/08G06N3/044
Inventor程光权马扬刘泽一阳方杰梁星星成清刘忠
OwnerNAT UNIV OF DEFENSE TECH