Drug target interaction prediction method based on multi-channel graph convolutional network

A technology of convolution network and prediction method, which is applied in the field of prediction of the relationship between drugs and targets, and can solve problems such as poor accuracy of drug targets and inaccurate features

Active Publication Date: 2021-05-28
NORTHEAST FORESTRY UNIVERSITY
View PDF7 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to solve the problem that the existing method relies on the inaccuracy of manually extracted features, resulting in the poor accuracy of drug-target interaction prediction, and proposes a drug-target interaction based on multi-channel graph convolutional network. Action prediction method

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
  • Drug target interaction prediction method based on multi-channel graph convolutional network
  • Drug target interaction prediction method based on multi-channel graph convolutional network
  • Drug target interaction prediction method based on multi-channel graph convolutional network

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0029] Specific implementation mode 1. Combination figure 1 This embodiment will be described. A drug-target interaction prediction method based on a multi-channel graph convolutional network described in this embodiment, the method specifically includes the following steps:

[0030] Step 1. Extract drug information, protein information, disease information, and drug side effects information from the database, and construct a heterogeneous network based on the extracted information;

[0031] Then use the Jaccard similarity method and the random restart walk method to process the constructed heterogeneous network, and obtain the drug diffusion state matrix and protein diffusion state matrix;

[0032] Step 2, performing noise reduction and dimensionality reduction on the drug diffusion state matrix and the protein diffusion state matrix, respectively, to obtain the drug characteristic matrix and the protein characteristic matrix;

[0033] Step 3. Splice the drug feature matrix...

specific Embodiment approach 2

[0050] Specific embodiment 2: The difference between this embodiment and specific embodiment 1 is that in the first step, drug information, protein information, disease information, and drug side effects information are extracted from the database, and a heterogeneous network; its specific process is:

[0051] Extract drug information from the DrugBank database, the drug information includes drug-drug interaction information and known drug-target interaction information;

[0052] Extracting protein information from the HPRD database, the protein information is protein-protein interaction information;

[0053] Extracting disease information from the toxicogenomics database, the disease information including the relationship information between the disease and the drug and the relationship information between the disease and the protein;

[0054] Extract drug side effect information from the SIDER database, where the drug side effect information is the relationship information ...

specific Embodiment approach 3

[0058] Specific embodiment three: the difference between this embodiment and specific embodiment two is that in the first step, the Jaccard similarity method and the random restart walk method are used to process the constructed heterogeneous network to obtain the drug diffusion state matrix and protein Diffusion state matrix; the specific process is:

[0059] For the drug and drug side effect relationship network, the drug and drug side effect relationship network is expressed in the form of matrix C:

[0060]

[0061] Among them, c i′j′ = 0 or 1, c i′j′ = 1 means that the i′th drug is related to the side effect of the j′th drug, c i′j′ =0 means that the i'th drug has no relationship with the side effects of the j'th drug, i'=1,2,...,M, j'=1,2,...O;

[0062] Use the Jaccard similarity method to calculate the similarity between the i-th row and the j-th row of the matrix C, i=1, 2,..., M, j=1, 2,..., M, the calculated i-th row and j-th row The similarity of the row is u...

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 drug-target interaction prediction method based on a multi-channel graph convolutional network, and belongs to the technical field of drug-target relationship prediction. According to the method, the problem that the accuracy of drug target interaction prediction is poor due to the fact that the existing method depends on inaccurate features extracted manually is solved. The method comprises the following steps: constructing a drug protein pair network according to an obtained drug feature matrix and an obtained protein feature matrix, performing feature extraction on a topological relation between drug protein pairs in the drug protein pair network and a proximity relation between drug protein pair features by adopting a multichannel graph convolutional network, and obtaining topological relation embedding and feature proximity relation embedding; processing topological relation embedding and feature proximity relation embedding to obtain common embedding; and finally, fusing topological relation embedding, feature proximity relation embedding and common embedding through an attention mechanism, and inputting a fusion result into a multi-layer perceptron to predict the drug target relation. The method can be applied to prediction of the relationship between the drug and the target.

Description

technical field [0001] The invention belongs to the technical field of predicting the relationship between drugs and targets, and in particular relates to a method for predicting drug-target interactions based on a multi-channel graph convolutional network. Background technique [0002] Drug targets are molecules that can bind to drugs and exert special effects in cells, and proteins are the main molecular targets of drugs. [0003] We need to test and experiment with thousands of compounds to find safe and effective drugs. Therefore, drug discovery is a time-consuming and labor-intensive process with risks of failure. But by calculating the probability of drug-target interaction, costly losses in the drug discovery process can be reduced. [0004] To achieve this goal, more and more researchers are exploring other methods to predict the relationship between drugs and targets. Drug-target relationship prediction can not only reduce the loss in the drug discovery process, ...

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 Applications(China)
IPC IPC(8): G16H70/40G16B15/30G16B40/00G06N3/04G06N3/08
CPCG16H70/40G16B15/30G16B40/00G06N3/08G06N3/045
Inventor 汪国华李洋乔冠宇
Owner NORTHEAST FORESTRY 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