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

A Virtual Screening Approach for Drug Targets Based on Interaction Fingerprints and Machine Learning

A virtual screening and machine learning technology, applied in instrumentation, informatics, biostatistics, etc., can solve problems such as high false positives and untargeted specific proteins, and achieve the effect of avoiding insufficient fitting

Active Publication Date: 2018-11-09
EAST CHINA NORMAL UNIV
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] On the one hand, the existing scoring function is difficult to take into account the coupling between different interactions due to the limitations of the data set, on the other hand, it is not specific for specific proteins
Ultimately resulting in a high probability of false positives in virtual screening

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
  • A Virtual Screening Approach for Drug Targets Based on Interaction Fingerprints and Machine Learning
  • A Virtual Screening Approach for Drug Targets Based on Interaction Fingerprints and Machine Learning
  • A Virtual Screening Approach for Drug Targets Based on Interaction Fingerprints and Machine Learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0073] The present invention will be described in detail by taking the establishment of a screening model of VGFR2 target as an example in conjunction with the accompanying drawings.

[0074] refer to figure 1 , the first thing to do is to change the evaluation index in the SVM software libsvm. Download eval.cpp and eval.h from the libsvm official website, recompile, and change the evaluation criteria of grid search and cross-validation to AUC.

[0075] (1) The activity data of VGFR2 were collected from the DUD-E library, which contained 409 active small molecules and 24950 inactive small molecules. PDB files are 2P2I.

[0076] (2) Calculate the center coordinates of the self-ligand in 2P2I, (38, 35, 12).

[0077] (3) Molecular docking was performed using the Schrödinger molecular docking software Glide.

[0078] (4) Each molecule after docking only adopts the conformation with the lowest GlideScore score. Use the glide_ensemble_merge and glide_sort tools for this purpose...

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 a drug target virtual screening method based on interactive fingerprints and machine learning. According to the method, based on traditional molecular docking, the interactive fingerprints of known active and non-active micromolecules and target protein are trained through machine learning to obtain a screening model of targets, and the obtained model is used for virtual screening. The specific targets are specifically trained, the specificity of each kind of targets is fully considered, and the defect of insufficient fitting of a traditional scoring function is avoided; interaction energy of each micromolecule and each residue in a binding pocket is calculated, so that effective binding sites or binding modes can be found; non-linear fitting is carried out through machine learning, and compared with linear fitting, the correlation or coupling effect between all the interaction energy can be better processed; by means of the method, enrichment of active molecules is better promoted.

Description

technical field [0001] The invention relates to the technical field of drug virtual screening. In particular, a virtual screening method for drug targets based on interaction fingerprints and machine learning. On the basis of traditional molecular docking, this method uses machine learning to analyze the interaction fingerprints of known active and inactive small molecules and target proteins. A screening model trained to yield targets. Background technique [0002] In the process of new drug discovery, the application of virtual screening can increase the enrichment of active molecules and reduce the cost of screening. In recent years, it has attracted great attention from scientific research institutions and pharmaceutical companies. Commonly used virtual screening methods can be divided into structure-based virtual screening (SBVS) and ligand-based virtual screening (LBVS). The main research effort of ligand-based virtual screening is on the generation of various molec...

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 Patents(China)
IPC IPC(8): G06F19/24
CPCG16B40/00
Inventor 季长鸽闫玉娜张增辉
Owner EAST CHINA NORMAL UNIV
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