Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for predicting drug-side effect relationship based on graph neural network

A technology of neural network and side effects, applied in the field of biomedicine, to achieve the effect of convenient and fast data collection, enhanced effect, and improved quality

Active Publication Date: 2021-01-12
FUDAN UNIV
View PDF9 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of the present invention is to solve the problem of how to use the method of deep learning and fully consider the information of edges and nodes to represent the nodes in the network, and propose a method for predicting the relationship between drugs and side effects based on graph neural network

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 for predicting drug-side effect relationship based on graph neural network
  • Method for predicting drug-side effect relationship based on graph neural network
  • Method for predicting drug-side effect relationship based on graph neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Apparently, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0046] see Figure 1-3 As shown, a method for predicting drug-side effect relationship based on graph neural network, the method includes:

[0047] S1: Use autonomous crawlers or other collectors to obtain drug-related data from different platforms; collect drug-related data, obtain data on drug-related characteristics, and organize the content of these data into documents;

[0048] S2: Carry out the data cleaning, filtering and association process; screen out the fields of drugs related to side effects;

[0049] S3: Prepro...

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 for predicting a drug side effect relationship based on a graph neural network. The method is used for solving the problem of how to express nodes in the network by using a deep learning method and fully considering information of edges and nodes. The method comprises the following steps: collecting drug data for preprocessing, and establishing relationships between drugs and between side effects of the drugs; constructing a drug side effect heterogeneous network model; and using a graph neural network to carry out vectorization representation on nodes and multi-relation edges in the network. According to the method, a multi-relation network is constructed, and nodes in the network are represented by utilizing a neural network; and crawling is carried out through public data of different platforms, thus features of drugs are described more comprehensively, data acquisition is convenient and rapid, the data are preprocessed and then analyzed, the miningeffect is enhanced, the quality of the mining data is improved, a heterogeneous network model capable of representing multi-modal data is constructed, a graph neural network method is used, and pointand edge information is combined.

Description

technical field [0001] The invention relates to the field of biomedicine, in particular to a method for predicting the drug-side effect relationship based on a graph neural network. Background technique [0002] As we all know, in the field of biomedicine, the research and development of new drugs not only requires huge capital investment, but also has a very long cycle. While drugs treat patients' diseases, they may be accompanied by side effects that endanger the lives and health of patients. Therefore, how to quickly and accurately discover information about potential drug side effects has become an important link in the drug development process. In recent years, drug safety issues caused by drug side effects have attracted much attention. The main reason is that people's lack of understanding of drug side effects has led to clinical drug treatment errors, acute and chronic poisoning of patients, and morbidity and mortality related to drug side effects. rise. Even after...

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): G16H50/70G16H70/40G06N3/08
CPCG16H50/70G16H70/40G06N3/08
Inventor 赵兴明杨凯
Owner FUDAN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com