Drug-target interaction prediction algorithm based on graph convolution and similarity

A prediction algorithm and similarity technology, applied in the fields of chemical property prediction, genomics, biological systems, etc., can solve the problems of unpredictable drug-target interactions and complex biological systems, so as to accelerate the process of drug development and improve the overall Efficiency, the effect of reducing feature loss

Pending Publication Date: 2022-06-10
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

The main reason for this is that the biological systems of most diseases are extremely complex, making drug-target interactions difficult to predict

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 interaction prediction algorithm based on graph convolution and similarity
  • Drug-target interaction prediction algorithm based on graph convolution and similarity

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] The following technical solutions of the present invention are further elaborated in conjunction with specific embodiments.

[0029] The theme scheme of this system mainly embodies the basic idea of feature extraction method based on graph convolution and similarity, so as to rapidly predict drug-target interactions to assist in accelerating drug development. A drug-target interaction prediction algorithm based on graph convolution and similarity, including intermolecular structure information extraction module, molecular graph structure information extraction module and drug-target interaction prediction module, the basic steps are as follows:

[0030] 1) Get DTI data from the DugBank database. Each sample contains a drug protein pair and an annotated DTIs. The drug was identified again in The DrugBank to collect its SMILES representation. Proteins are identified in the RCSB protein database, collecting their standard structure PDB files;

[0031] 2) The intermolecular struc...

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 relates to the field of drug-target interaction prediction technology and deep learning, in particular to a drug-target interaction prediction algorithm based on graph convolution and similarity. Comprising the following steps: 1) acquiring related data of drugs, proteins and DTI through public databases such as DygBank and RCSB; 2) extracting intermolecular structure information through global structure similarity; 3) extracting monomer characteristic information of the drug molecules and the protein molecules through DeepChem; 4) obtaining a drug-target interaction prediction result through feature dimension reduction, feature fusion and normalization processing; and 5) parameter adjustment and optimization are performed on the model, the prediction accuracy is continuously improved, and the optimal model is used for assisting research on drug discovery, drug verification, drug side effects and the like.

Description

Technical field [0001] The present invention relates to the field of drug - target interaction prediction technology, specifically a drug - target interaction prediction algorithm based on graph convolution and similarity. Background [0002] Drug-target interaction (DTI) is a drug that affects the pharmacological effect of the target protein by acting on the target protein and interacting with the target protein, which is the premise of the drug to produce a drug effect. The study of drug-target interactions has important theoretical guiding significance and practical application value. For a long time, the number of newly designed and approved drugs was not only scarce, but also the effect of treating diseases was not up to expectations. The main reason for this is that biological systems for most diseases are extremely complex, making drug-target interactions difficult to predict. Therefore, identifying and predicting potential drug-target interactions to complement research s...

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): G16B5/00G16B20/00G16B30/10G16C20/10G16C20/30G06N3/04G06N3/08
CPCG16B5/00G16B30/10G16B20/00G16C20/30G16C20/10G06N3/08G06N3/045
Inventor 宋弢高畅楠张旭东李雪韩佩甫
Owner CHINA UNIV OF PETROLEUM (EAST CHINA)
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