Method and system for predicting interaction between miRNA and gene based on multi-relational graph convolutional network

A convolutional network and relational graph technology, applied in deep learning in the field of bioinformatics, can solve problems such as relying on manual extraction, achieve the effect of improving prediction accuracy and enriching prediction methods

Pending Publication Date: 2022-02-25
HUNAN UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

With the accumulation of biological data in the era of big data, the construction of relevant databases provides a reliable data source for machine

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
  • Method and system for predicting interaction between miRNA and gene based on multi-relational graph convolutional network
  • Method and system for predicting interaction between miRNA and gene based on multi-relational graph convolutional network
  • Method and system for predicting interaction between miRNA and gene based on multi-relational graph convolutional network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] Such as figure 1 As shown, the prediction method of miRNA and gene interaction based on a multi-relational graph convolutional network provided in this embodiment includes the following steps:

[0058] Step S1: Construction of miRNA-gene heterogeneous information network. Among them, miRNA-gene heterogeneous information network is obtained by integrating miRNA similarity network, gene similarity network and known miRNA-gene bipartite network.

[0059] In this embodiment, the miRNA sequence is obtained from the miRBase database, and the sequence similarity scores between all miRNA-miRNA pairs are calculated by the overall sequence comparison algorithm Needleman-Wunsch, and the 10 most related neighbor nodes are reserved for each miRNA, namely The 10 miRNA-miRNA relationship data with the highest similarity score were retained, and then the miRNA similarity network was constructed. It should be understood that the present invention is not limited to retaining 10 neighbo...

Embodiment 2

[0104] Embodiment 2: This embodiment provides a system based on the prediction method of the above-mentioned miRNA and gene interaction, which includes:

[0105] The miRNA-gene heterogeneous information network building block is used to construct the miRNA-gene heterogeneous information network, and the miRNA-gene heterogeneous information network includes relationship data between miRNA-miRNA and association data of known miRNA-gene pairs , gene-gene relationship data;

[0106] The prediction model building block is used to construct the prediction model of miRNA and gene interaction, in which, based on the multi-relational graph convolutional network, the network topology feature representation of the heterogeneous information network nodes is extracted, and for the miRNA-gene pair, the miRNA and gene correspondence are fused The network topology feature representation and gene feature information are used as the input value of the prediction function of the prediction model...

Embodiment 3

[0112] This embodiment provides an electronic terminal, which includes:

[0113] one or more processors;

[0114] memory storing one or more computer programs;

[0115] The processor invokes the computer program to:

[0116] Steps in a method for predicting miRNA and gene interactions based on multi-relational graph convolutional networks. Implementation:

[0117] Step S1: Construction of miRNA-gene heterogeneous information network.

[0118] Step S2: Construct a predictive model of miRNA-gene interaction.

[0119] Step S3: Using the miRNA-gene heterogeneous information network data in step S1 to train the prediction model constructed in step S2.

[0120] Step S4: Using the trained prediction model to calculate the association score of miRNA-gene pairs with unknown association data.

[0121] For the specific implementation process of each step, please refer to the description of the foregoing method.

[0122] It should be understood that in the embodiment of the present...

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 method and a system for predicting interaction between miRNA and a gene based on a multi-relational graph convolutional network. The method comprises: constructing a heterogeneous information network of miRNA and genes, and learning network topology features of nodes by using a multi-relational graph convolutional network based on the heterogeneous network; meanwhile, capturing effective characteristics of the gene sequence by using a recurrent neural network; and finally, combining network topology characteristics with sequence characteristics, and calculating an association prediction score of the miRNA-gene pair by using the obtained miRNA and gene embedding. According to the method, manual feature construction is not needed in the implementation process, representation learning is combined, the advantages of the multi-relation graph convolutional network are fully utilized, effective gene sequence information is mined, and feature representation of miRNA and gene nodes is better captured. Experimental results show that the MRMTI is superior to other comparison methods in the aspect of association prediction of miRNA and genes, and has good prediction performance.

Description

technical field [0001] The present invention relates to the application of deep learning in the field of bioinformatics, specifically to predicting genes that interact with miRNA, and provides a method and system for predicting the interaction between miRNA and genes based on multi-relational graph convolutional networks. Background technique [0002] MicroRNA (miRNA) is a small non-coding RNA molecule with a length of about 22nt, which plays an important role in various biological processes such as cell growth and differentiation. MiRNA regulates the post-transcriptional expression of genes by binding to the 3'UTRs of mRNA, and its abnormal expression can lead to abnormal function of target genes, and then lead to a variety of complex diseases. Therefore, identifying the interaction between miRNA and genes is of great significance for revealing the regulatory mechanism of miRNA and its role in the development and development of complex diseases. [0003] Compared with time...

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): G16B30/00G06N3/04G06N3/08
CPCG16B30/00G06N3/08G06N3/048
Inventor 骆嘉伟欧阳文珏申聪蔡洁
Owner HUNAN UNIV
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