Drug interaction relationship extraction method and system based on external knowledge
A technology of relation extraction and external knowledge, applied in neural learning methods, special data processing applications, biological neural network models, etc., can solve problems such as large differences, low recall rate, and large impact on extraction performance.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0068] refer to figure 1 , is a schematic structural diagram of a drug interaction relationship extraction system based on external knowledge in the present invention, specifically, a drug interaction relationship extraction system based on external knowledge, including:
[0069] The drug information data set building block 1 is used to analyze and process the content of the drug database, extract and generate interacting drug pairs, and at the same time retain the description information of all drugs to form a drug interaction data set with drug description information;
[0070] In this embodiment, a commonly used drug database can be used, such as the DrugBank database, which contains related information such as drug type, drug structure, drug description information, and other drugs that interact with the drug;
[0071] In this embodiment, the drug information data set construction module 1 finds that the description information of the drug is a detailed introduction to the...
Embodiment 2
[0100] Based on the system of embodiment 1, this embodiment provides a method for extracting drug interaction relationship based on external knowledge, refer to image 3 , is a schematic flow chart of the method, specifically: a method for extracting drug interaction relationships based on external knowledge, including the following steps:
[0101] S400: Analyze and process the content of the drug database, extract and generate interacting drug pairs, and save all drug description information at the same time to form a drug interaction data set with drug description information; then perform step S402;
[0102] In this embodiment, commonly used drug databases, such as the DrugBank database, contain relevant information such as drug types, drug structures, drug description information and other drugs that interact with the drug; through the drug database DrugBank The knowledge is analyzed and processed, and drug pairs with interactions are extracted from them, and drug pairs wi...
Embodiment 3
[0125] In this example, the validity of the system of Example 1 and the method of Example 2 is verified, and the DDIExtraction2013 data set is used for experiments. This data set is composed of 792 medical texts in DrugBank and 233 abstracts in MedLine Composition, and the drug entity is marked in advance, the detailed information of the data set is shown in Table 1:
[0126] Table 1 DDIExtraction2013 data description
[0127] type of drug interaction Training set test set total Advice 826 221 1047 Effect 1687 360 2047 Mechanism 1319 302 1621 Int 188 96 284 Negative 23772 4737 28509
[0128] The length of the drug description information in this chapter is set to 50, and the word is converted into a 300-dimensional Glove word vector. For words that do not appear in the Glove vocabulary, the word vector of the word is randomly initialized. The number of iterations of the capsule network Set to 3, Batchsize to 64, drop...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
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