Drug activity prediction method based on machine learning

A technology of drug activity and machine learning, applied in the fields of genomics, instrumentation, informatics, etc., can solve problems such as failure to obtain the expected return on investment, and achieve the effect of low cost, high efficiency, and improved efficiency

Active Publication Date: 2016-07-06
HUAZHONG AGRI UNIV
View PDF4 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, such a huge investmen

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 activity prediction method based on machine learning
  • Drug activity prediction method based on machine learning
  • Drug activity prediction method based on machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0064] Using the method of the present invention to predict the drug activity for the treatment of schizophrenia

[0065] 1. Collect human successfully marketed or researched drugs and their targets

[0066] Search the drug target database (including DGIdb: http: / / dgidb.genome.wustl.edu / ), and get a batch of drug targets corresponding to the drug. Taking DGIdb as the starting point, this experiment found a total of 2,271 targets with clear drug activity (the drug corresponds to the treatment of diseases), and 3,678 drugs corresponding to the above targets.

[0067] 2. Search for genes related to genetic information of schizophrenia

[0068] Genetic information-related genes of schizophrenia are composed of two parts of information. The first part is to find a total of 940 schizophrenia-related genes through the SZGene (http: / / www.szgene.org / ) database, and the second part is through the GWASdb ( http: / / jjwanglab.org / gwasdb ), GAD ( http: / / geneticassociationdb.nih.gov / ...

Embodiment 2

[0097] Using the method of the present invention to predict the drug activity for the treatment of Parkin's syndrome

[0098] 1. Collect human successfully marketed or researched drugs and their targets

[0099] Search the drug target database (including DGIdb: http: / / dgidb.genome.wustl.edu / ), and get a batch of drug targets corresponding to the drug. In this experiment, DGIdb was used as the starting point to find a total of 2,348 targets with clear drug activity (the drug corresponds to the treatment of diseases), and 3,678 drugs corresponding to the above targets.

[0100] 2. Find genes related to Parkin's syndrome genetic information

[0101] Genetic information related to Parkin's syndrome is composed of two parts of information. The first part is to find a total of 87 genes related to Parkin's syndrome through the PDGene (http: / / www.pdgene.org / ) database, and the second part is to use the GWASdb ( http: / / jjwanglab.org / gwasdb ), GAD ( http: / / geneticassociationdb.n...

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 activity prediction method based on machine learning. The method comprises following steps of (1), obtaining drug targets corresponding to sample drugs; (2), obtaining related gene information corresponding to hereditary diseases; (3), screening out target genes associated with the hereditary diseases from the drug targets obtained in the step (1); (4), obtaining characteristic attribute of each sample drug, wherein the characteristic attribute is a relationship of the drug target corresponding to the sample drug and the target gene associated with the hereditary disease; building a model by taking the characteristic attribute of each sample drug as an input vector and taking the activity of the sample drug as output; (5), obtaining the characteristic attribute of a to-be-tested drug, substituting into the model in the step (4), thus predicting the activity of the to-be-tested drug. The drug screening method provided by the invention is low in cost and high in efficiency. The method has wide application prospects in fields such as repositioning, structure optimization and design of the drugs.

Description

technical field [0001] The invention belongs to the technical field of biomedicine, and in particular relates to a method for predicting drug activity based on machine learning. Background technique [0002] Drug research and development is a systematic project with long cycle, high cost, high risk, fierce competition and high profit. According to statistics, it takes 10-15 years for a new drug to be produced from conception, laboratory lead compound identification, optimization, clinical trials to final marketing, and the research and development costs are as high as more than 800 million US dollars (DiMasi, J.A., Hansen, R.W., and Grabowski, H.G. (2003). The price of innovation: new estimates of drug development costs. J. Health Econ. 22: 151-185.), and this cost is still increasing year by year. According to the 2014 report of Tufts Center for the Study of Drug Development (CSDD), this figure has now grew to $2.558 billion (http: / / csdd.tufts.edu / news / complete_story / pr_tu...

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): G06F19/00
CPCG16B20/00G16B40/00
Inventor 张红雨朱丽达罗志辉全源朱强杨庆勇
Owner HUAZHONG AGRI UNIV
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