Anti-HBV small molecule drug prediction model based on expression learning and construction method thereof

A technology for prediction models and construction methods, which can be used in chemical property prediction, molecular design, etc., and can solve problems such as delaying drug research and development.

Pending Publication Date: 2022-01-11
NANTONG UNIVERSITY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Limited by the routine drug development process, large-scale drug molecule design, synthesis, and anti-HBV acti...

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
  • Anti-HBV small molecule drug prediction model based on expression learning and construction method thereof
  • Anti-HBV small molecule drug prediction model based on expression learning and construction method thereof
  • Anti-HBV small molecule drug prediction model based on expression learning and construction method thereof

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0095] 1. Evaluation of anti-HBV activity and cytotoxicity: The in vitro anti-HBV activity and cytotoxicity of all compounds in HepG2 2.2.15 cells were evaluated by real-time quantitative PCR and MTT method, respectively. The concentration of compound required to inhibit DNA replication by 50% was defined as IC50 and the concentration of compound that induced 50% death of HepG2 2.2.15 cell cultures was defined as CC50.

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 an anti-HBV small molecule drug prediction model based on expression learning and a construction method thereof, relates to the technical field of drug research, and aims to perform expression learning on SMILES codes by using an NLP method through processing the SMILES codes. A machine learning method is used for a supervised classification model of SMILES coded space vectors, and the activity of small molecules to specific targets is predicted in a classified mode in the model. Compared with the prior art, the performance superior to that of traditional Word2vec is embodied on different target point data sets. Meanwhile, in downstream tasks after vector training, deterministic advantages are generated in the aspects of predicting the inhibition rate of the compound to HBV and the toxicity of the compound to hepatocytes, and the model has good capacity of screening potential anti-HBV drugs. The method can be widely applied to drug-likeness prediction of other different target compounds, so that the drug research and development process is simplified.

Description

technical field [0001] The invention relates to the technical field of drug research and development, in particular to a method for constructing a predictive model of anti-HBV small molecule drugs based on representation learning. Background technique [0002] In the process of drug development, designing and synthesizing compounds with high activity against specific targets is the primary task of medicinal chemistry. Usual drug design relies more on various types of high-throughput virtual screening, fragment or structure-based drug design and the experience of drug developers, and lacks a convenient, quick and accurate way to evaluate the pharmacological activity of drug molecules against specific targets. [0003] Limited by the routine drug development process, large-scale drug molecule design, synthesis, and anti-HBV activity experiments consume a lot of manpower, material resources, time, and capital costs, delaying the speed of drug development. Through the artificia...

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): G16C20/50G16C20/30
CPCG16C20/50G16C20/30
Inventor 王理邵劲松尹泽宇潘文洁
Owner NANTONG UNIVERSITY
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