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

Drug-target affinity prediction system based on graph convolutional neural network, computer equipment and storage medium

A convolutional neural network and neural network technology, applied in the field of drug repositioning prediction, to achieve the effect of reducing material cost, high cost and long development cycle

Pending Publication Date: 2022-07-12
CHINA UNIV OF PETROLEUM (EAST CHINA)
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, predicting the binding strength between a drug and its target is more informative and, at the same time, more challenging
If this intensity is not enough, such DTI may not be useful

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 affinity prediction system based on graph convolutional neural network, computer equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] The technical solutions of the present invention are further described below in conjunction with specific embodiments.

[0020] like figure 1 As shown, the specific situation of the drug target affinity prediction system based on graph convolutional neural network described in this embodiment:

[0021] 1) Select two datasets, Davis and KIBA, and divide the datasets according to 80% as the training set and 20% as the test set.

[0022] 2) Using the RDKIT tool, convert SMILES into a two-dimensional matrix representation, convert SMILES into a vector form against the dictionary, encode the protein sequence, and save all data in a pt file.

[0023] 3) Call the data in the pt file, and input the two-dimensional matrix representation of SMILES into four kinds of graph convolutional neural networks to obtain 128-dimensional feature vectors. The graph convolutional neural network to which it belongs can be selected by the user, and the vector of SMILES can be selected by the 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 system for predicting drug target affinity based on a graph convolutional neural network, and belongs to the technical field of drug relocation. The system comprises three channels which are used for respectively extracting a feature vector of two-dimensional representation of a drug, a feature vector of a context association relationship of a drug SMILES expression and a feature vector of a context association relationship of a protein sequence, then splicing the three feature vectors together, and inputting the spliced three feature vectors into a full-connection neural network, and obtaining a predicted value of the drug target affinity. The input of the model is the two-dimensional representation of the drug, the SMILES expression of the drug and the protein sequence, and finally obtaining the affinity prediction value of the drug and the target.

Description

technical field [0001] The invention relates to the technical field of drug relocation prediction, in particular to a drug-target affinity prediction system, computer equipment and storage medium based on graph convolutional neural network. Background technique [0002] Experimentally confirming new drug-target interactions (DTIs) is not an easy task because in vitro experiments are laborious and time-consuming. Even if confirmed DTIs are used to develop new drugs (including unapproved ones), it could take many years for such a new drug to be approved for human use, and the estimated cost could exceed $1 billion. Also, while developing new drugs requires huge investments, they often fail. In fact, between 2008 and 2010, of 108 Phase 2 failures of new and repurposed drugs, 51 percent were due to insufficient efficacy, according to a report by Thomson Reuters life sciences consulting firm. This observation highlights the need for (1) new, more suitable drug targets, and (2) ...

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): G16B15/30G16B40/00G16B15/20G06N3/08G06N3/04
CPCG16B15/30G16B15/20G16B40/00G06N3/049G06N3/08G06N3/045G06N3/044
Inventor 宋弢田庆雨刘嘉丽刘大岩杜珍珍钟悦
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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