Ligand molecular fingerprint generation method based on deep Hash in drug screening

A technology of ligand molecules and molecular fingerprints, applied in the field of computer-aided drug design, can solve the problem of high technical threshold

Active Publication Date: 2017-05-31
NANJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that the traditional molecular fingerprint technology requires developers to have a deep understanding of domain knowledge and the technical threshold is high

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
  • Ligand molecular fingerprint generation method based on deep Hash in drug screening
  • Ligand molecular fingerprint generation method based on deep Hash in drug screening
  • Ligand molecular fingerprint generation method based on deep Hash in drug screening

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] The present invention will be further described below in conjunction with accompanying drawings and examples.

[0021] The method proposed by the invention only needs to input the molecular structure formula file, which will be converted into an image file, and the optimal molecular fingerprint is automatically generated by optimizing the target loss function by using the DPSH deep hash algorithm. The method proposed by the invention will realize the first "end-to-end" molecular fingerprint generation framework, developers do not need to manually design features, and solve the difficult problem of "developers need to have a deep understanding of domain knowledge". The present invention provides a general framework for generating molecular fingerprints from a brand new perspective, which can be used as an important supplement to existing molecular fingerprint generating methods, and will also promote the wider application of molecular fingerprints in drug discovery and vi...

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 ligand molecular fingerprint generation method based on deep Hash in drug screening. Firstly, a molecular structural formula image file is generated. Secondly, a pairwise label of a ligand molecular pair is defined, and a DPSH deep Hash learning model is trained. Finally, molecular fingerprint of new ligand molecules is predicted. A ligand molecular structural formula is converted into the image file, a target loss function is optimized by a deep Hash algorithm, and the molecular fingerprint is automatically generated. A first 'end-to-end' molecular fingerprint generation framework can be realized without manually extracting characteristics, and the method solves the problem that developers need to deeply understand field knowledge in an existing molecular fingerprint generation method. The universal molecular fingerprint generation framework is provided from a new perspective and serves as an important supplement for the existing molecular fingerprint generation method, and wider application of the molecular fingerprint to drug screening can be promoted.

Description

technical field [0001] The invention relates to a method for generating and designing ligand molecular fingerprints based on deep hashing in drug screening, and belongs to the technical field of computer-aided drug design. Background technique [0002] Molecular Fingerprint represents chemical molecules as "bit strings" and is used to describe the structural or functional similarity of chemical molecules, due to its ease of use and high efficiency in substructure and similarity searches , has been widely used in drug discovery and virtual screening. [0003] At present, many molecular fingerprint generation methods have been proposed, and different methods reflect different aspects of molecular information. Molecular fingerprint generation methods mainly include: key substructure-based molecular fingerprint generation methods, path-based molecular fingerprint generation methods, ring fingerprint generation methods, pharmacophore fingerprint generation methods, and hybrid fi...

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): G06F19/00
CPCG16C20/20G16C20/30G16C20/70
Inventor 吴建盛尹新宇胡海峰
Owner NANJING UNIV OF POSTS & TELECOMM
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