Drug pathogenic relationship extraction method based on domain knowledge

A technology of domain knowledge and relation extraction, applied in drug reference, neural learning method, biological neural network model, etc., can solve problems such as labor-intensive cost, time-consuming, expensive, etc., and achieve the effect of feasible structure

Active Publication Date: 2020-06-12
DALIAN UNIV OF TECH
View PDF4 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method can model a limited number of training samples manually labeled, obtain a model through a multi-round iterative training

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 pathogenic relationship extraction method based on domain knowledge
  • Drug pathogenic relationship extraction method based on domain knowledge
  • Drug pathogenic relationship extraction method based on domain knowledge

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The present invention will be further described below in conjunction with accompanying drawing.

[0029] Such as figure 1 As shown, a drug-pathogenic relationship extraction method based on domain knowledge includes the following steps:

[0030] Step 1. Process the drug-pathogenic relationship data set. Collect the drug-pathogenic relationship data set from the existing drug-pathogenic relationship extraction and evaluation task. The data set has marked the drug entity and the disease entity. Take the sentence as the unit, the drug entity Form an entity pair with a disease entity, process it into a sentence-level instance according to the relationship marked in the training set, and then deduplicate the instance, stem it, remove stop words, determine the position information of each word relative to the entity, and finally get Sentence-level training set;

[0031]Step 2. Build a domain knowledge set, count the drug entities and disease entities in the training example...

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 biomedical text mining. The invention discloses a drug pathogenic relationship extraction method based on domain knowledge. The method comprises the following steps: (1) processing a drug pathogenic relationship data set; (2) constructing a domain knowledge set; (3) constructing an entity-relationship graph according to the domain knowledge; (4) completing vector representation of the words in the example; (5) building a KB-GCN neural network model. The drug pathogenic relationship extraction method based on domain knowledge is practicable and clear in structure and has reference value. The method is suitable for automatically identifying the drug pathogenic relationship from a biomedical text by applying domain knowledge in a database, and is helpful for constructing a drug pathogenic database, assisting drug side effect prediction and the like.

Description

technical field [0001] The invention relates to a method for extracting drug-pathogenic relationship based on domain knowledge, and belongs to the technical field of biomedical text mining. Background technique [0002] Drug-induced disease refers to the process in which a person causes a certain disease or disease due to the side effects of a drug while taking a certain drug. The research on drug-causative relationship has received widespread attention in the stages of drug development, testing and administration. At the same time, take the Comparative Toxicogenomics database as an example, which artificially includes some known drug-induced disease relationship information. Furthermore, descriptions of many drug-causative relationships still exist in the vast biomedical literature. These drug-pathogenic relationships have great theoretical and practical value for expanding the database of pathotoxicology and guiding drug development and testing. [0003] Reading the bio...

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): G16H70/40G06N3/08G06N3/04G06F16/36G06F40/295
CPCG16H70/40G06N3/088G06F16/367G06N3/044G06N3/045
Inventor 杨志豪李智恒
Owner DALIAN UNIV OF TECH
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