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

Drug-target relationship prediction method based on deep forest and PU learning

A prediction method and drug technology, applied in the field of systems biology, can solve problems such as inability to predict relationship

Active Publication Date: 2021-04-13
HUNAN UNIV OF TECH
View PDF7 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Secondly, some use the arithmetic mean method to fuse the data of different drugs and targets, so noise may be introduced
Some methods cannot predict the relationship between a new drug and a new target

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 relationship prediction method based on deep forest and PU learning
  • Drug-target relationship prediction method based on deep forest and PU learning
  • Drug-target relationship prediction method based on deep forest and PU learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0073] The present invention will be further described below in combination with specific embodiments.

[0074] A drug-target relationship prediction method based on deep forest and PU learning: the specific process is as follows Figure 1 shown.

[0075] 1. Drug similarity and target similarity calculation

[0076] 1) Construction of the drug-target matrix; based on the known drug-target positive correlation, the present invention first constructs a drug-target matrix where each row corresponds to a drug, and each column corresponds to a target; if the known drug d i and target t j There is a relationship, then Y 1 (i, j) is equal to 1; otherwise, Y 1 (i,j) is equal to 0; where i=1,2,K,m; j=1,2,K,n; m and n are the number of known drugs and targets respectively.

[0077] 2) Drug similarity calculation

[0078] Based on the structural information of the drug, a graph-based method SIMCOMP is used, in which the structural information of the drug is regarded as a 2D structu...

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 provides a drug target relationship prediction method based on deep forest and PU learning. The drug-target relationship prediction method comprises the following steps: S1, acquiring structural information of a drug, sequence information of a target and a known drug-target relationship; s2, respectively constructing a similarity matrix between drugs and a similarity matrix between targets based on the drug structure information and the target sequence information; s3, screening a potential drug-target negative correlation relationship by adopting PU learning; and S4, based on the hypothesis that similar drugs share similar targets, predicting the drug-target relationship by using a deep forest model. According to the method, the drug target relationship can be predicted more accurately, time and resources required by biological experiments can be reduced, and a research basis is provided for drug discovery and drug relocation.

Description

technical field [0001] The present invention relates to the field of systems biology, more specifically, to a drug-target relationship prediction method based on deep forest and PU learning. Background technique [0002] Drug discovery is a complex, expensive process with a low success rate. Over the past few decades, FDA-approved new drugs have remained stagnant despite enormous financial investments by pharmaceutical companies in drug development. Drug repositioning is the process of discovering new therapeutic leads beyond the original medical use of existing drugs, which can speed up the drug development process and thereby reduce the cost of drug development. One of the key steps in drug repurposing is to search for possible drug-target interactions. Drug-targets are usually related to specific diseases, and can effectively improve disease symptoms by regulating the physiological activities of targets. Determining target molecules related to specific diseases is the b...

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): G16B5/00G16B15/30G16B30/10G16B40/00G06F17/16
CPCG16B15/30G16B30/10G16B5/00G16B40/00G06F17/16Y02A90/10
Inventor 彭利红田雄飞周立前王娟娟
Owner HUNAN UNIV OF TECH
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