Molecular structure and chemical reaction energy function building method based on neural network

A neural network and chemical reaction technology, applied in the field of quantum chemistry, can solve problems such as unfavorable development and improvement, complex reaction force field functions, etc., and achieve the effect of easy expansion and high precision

Active Publication Date: 2018-11-13
SHENZHEN JINGTAI TECH CO LTD +1
View PDF2 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The function form of the reaction force field is very complicated, and many function item...

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
  • Molecular structure and chemical reaction energy function building method based on neural network
  • Molecular structure and chemical reaction energy function building method based on neural network
  • Molecular structure and chemical reaction energy function building method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0024] The specific technical solutions of the present invention are described in conjunction with the examples.

[0025] TASELISIB is a selective inhibitor of PIK3CA with the structural formula:

[0026]

[0027] This molecule contains 62 atoms, the molecular weight is 460.542g / mol, the molecule has 6 flexible single bonds that can rotate, and a relatively large flexible ring. Quantum chemical calculations were performed on this system, and the density functional energies of 2138 conformations were obtained.

[0028] The embodiment adopts such as figure 1 process shown.

[0029] The force field for the molecule was extracted from the general force field parameter library. The molecular force field energy is calculated with 2138 structures, and the calculation results are as follows figure 2 shown. The coefficient of determination after linear fitting was 0.2942. The coefficient of determination is defined as the ratio of 1 minus y to the variance of the regression e...

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 belongs to the technical field of quantum chemistry, and particularly relates to a molecular structure and chemical reaction energy function building method based on a neural network. The method comprises the steps of performing sampling on each degree of freedom of a molecular or chemical reaction; searching for a low-energy conformation structure through quantitative calculation; performing energy calculation on the structure, and preparing a training set and a test set; selecting a proper coordinate representation structure; according to different coordinates, constructing different features to describe the structure; selecting a proper neural network; selecting a proper method to train the neural network; after the training is completed, performing error statistics on thetest set, and when an error is smaller than 1.0 kcal/mol, ending the training; and if the error is greater than 1.0 kcal/mol, following a re-searching model. The precision of obtained conformation energy, reaction energy and the like is higher; the method can be widely applied to the quantum dynamics and molecular dynamics processes; and not only a single molecule conformation but also the chemical reaction including intramolecular or intermolecular bond breaking and generating can be simulated.

Description

technical field [0001] The invention belongs to the technical field of quantum chemistry, and in particular relates to a neural network-based molecular structure and chemical reaction energy function construction method, which constructs a potential energy surface through a backpropagation neural network. Background technique [0002] The molecular structure plays a decisive role in chemistry (such as organic chemical reactions, conformational polymorphisms) and biology (such as the active conformation of drug molecules, enzyme-catalyzed reactions). The structure of organic molecules is not static, and has various conformational degrees of freedom including rotation, stretching, bending and other motions. The distance between molecules, relative orientation, formation and breaking of bonds, etc. exist in the molecular reaction process. Each structure will correspond to a different energy. The conformational changes and chemical reactions of molecules are very sensitive to ...

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): G06F19/16
Inventor 张佩宇方栋杨明俊马健赖力鹏温书豪
Owner SHENZHEN JINGTAI TECH CO LTD
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