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

Drug-disease relation identification method, system and device

A technology for relation recognition, disease, applied in medicine or prescription, neural learning methods, character and pattern recognition, etc.

Active Publication Date: 2018-05-22
GUANGDONG PHARMA UNIV +1
View PDF3 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the huge number of drug-disease relationship pairs, traditional medical, biological or chemical experimental methods cannot study these drug-disease relationship pairs one by one in a reasonable time.

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-disease relation identification method, system and device
  • Drug-disease relation identification method, system and device
  • Drug-disease relation identification method, system and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0077] A drug-disease relationship recognition method disclosed in the present invention, such as figure 1 shown, including the following steps:

[0078] Obtain the drug-disease relationship two-dimensional matrix and / or grayscale image corresponding to the drug-disease relationship pair to be identified;

[0079] The obtained drug-disease relationship two-dimensional matrix and / or grayscale image are input into the convolutional neural network for processing, so as to output the drug-disease relationship recognition result.

[0080] The convolutional neural network can process the image or the matrix corresponding to the image to output the processing result. In the method of the present invention, in order to identify whether a certain drug D can treat the disease d, the drug D and the disease d are regarded as or matched into a drug-disease relationship pair D-d, and the two-dimensional drug-disease relationship of the drug-disease relationship pair D-d is obtained Matrix...

Embodiment 2

[0082] The present invention will be further described below in conjunction with the preferred content of this embodiment. The drug-disease relationship identification method in this embodiment can be realized by the drug-disease relationship identification system in Example 3 and the drug-disease relationship identification device in Example 4.

[0083] A drug-disease relationship identification method, comprising the following steps:

[0084] Obtain the drug-disease relationship two-dimensional matrix and / or grayscale image corresponding to the drug-disease relationship pair to be identified;

[0085] The obtained drug-disease relationship two-dimensional matrix and / or grayscale image are input into the convolutional neural network for processing, so as to output the drug-disease relationship recognition result.

[0086] The convolutional neural network can process the image or the matrix corresponding to the image to output the processing result.

[0087] Further as a pre...

Embodiment 3

[0120] In this embodiment, the method described in Embodiment 2 will be applied to test the performance of the convolutional neural network model and the experimental results will be given.

[0121] Further as a preferred embodiment, the specific parameters of the convolutional neural network model used when applying the method described in Example 2 are as follows: it includes 1 input layer, 3 convolutional layers (each layer contains 32, 64 and 128 convolution kernels of size 5×5, each convolution layer is followed by a modified linear unit activation function and a downsampling layer of size 2×2), 4 fully connected layers (each layer contains 500 neurons, each layer is connected to a dropout layer, and 50% of the neurons do not update the connection weight each time during the training process), 1 fully connected layer (only contains two neurons), 1 softmax layer and A deep convolutional neural network model with 1 classification layer. The stochastic gradient descent algo...

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-disease relation identification method, system and device. The method includes the following steps that: a drug-disease relation two-dimensional matrix and / or grayscaleimage corresponding to a drug-disease relation to be identified is acquired; and the drug-disease relation two-dimensional matrix and / or the grayscale image is inputted into a convolutional neural network for processing, and an identification result is obtained. The system includes an acquisition module which is used for acquiring a drug-disease relation two-dimensional matrix and / or grayscale image and a processing module which is used for inputting the drug-disease relation two-dimensional matrix and / or grayscale image into the convolutional neural network for processing so as to output an identification result. The device includes a memory that stores at least one program and a processor that executes the at least one program. According to the drug-disease relation identification method, system and device of the present invention, the processing function of the convolutional neural network is utilized, and therefore, a drug-disease treatment relationship can be identified quickly and efficiently, potential drug-disease interaction effects can be identified, and lead compound identification and drug relocation research can be conducted. The identification method, system and device of the present invention are widely applied to the computer aided drug design field.

Description

technical field [0001] The invention relates to the field of computer-aided drug design, in particular to a drug-disease relationship recognition method, system and device. Background technique [0002] New drug development has always been a time-consuming, laborious, high-input, and high-risk process. Fully exploiting the new therapeutic effects of existing drugs and repositioning drugs has become a method to reduce risk and investment and improve success rate in the development of new drugs. At present, there are more than 2,000 drugs approved by the U.S. Food and Drug Administration, and more than 25,000 diseases have been collected in the medical integrated language system database. These drugs and diseases constitute hundreds of millions of drug-disease relationship pairs. How to discover drug-disease relationships with potential therapeutic relationships from these relationship pairs is the key to drug repositioning and new drug research. Due to the huge number of d...

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): G06K9/62G06N3/04G06N3/08G16H20/10
CPCG06N3/08G06N3/045G06F18/214
Inventor 李占潮邹小勇戴宗
Owner GUANGDONG PHARMA 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