BP Neural Network Prediction Calculation Method of Dipeptide Model Multipole Expansion Attributes

A BP neural network and calculation method technology, which is applied in the field of combining quantum mechanics and molecular mechanics calculations, can solve problems such as unreachable levels, and achieve the effects of short time consumption, reduced calculation amount, and high precision

Inactive Publication Date: 2017-08-25
DALIAN INST OF CHEM PHYSICS CHINESE ACAD OF SCI
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

AMOEBA considers this phenomenon, but it is still a synthesis of various conformational physical and chemical parameters, which cannot reach the level of specific physical and chemical parameters for a specific conformation to describe the atomic state

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
  • BP Neural Network Prediction Calculation Method of Dipeptide Model Multipole Expansion Attributes
  • BP Neural Network Prediction Calculation Method of Dipeptide Model Multipole Expansion Attributes
  • BP Neural Network Prediction Calculation Method of Dipeptide Model Multipole Expansion Attributes

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0065] Below in conjunction with example the present invention is described in further detail.

[0066] The content of the present invention is to provide an algorithm method for predicting the multi-pole expansion properties of dipeptide model based on BP neural network. Among them, the properties of multipole expansion include charge, dipole moment, and quadrupole moment of atoms. Non-multipolar distance attributes include the energy of the dipeptide model.

[0067] Such as figure 1 Shown, the present invention comprises the following steps:

[0068] First, the quantum mechanical calculation software Gaussian is used to optimize the structure of different dipeptide conformations under the premise of fixing the dihedral angle of the dipeptide conformation, and calculate the physical and chemical parameters such as the energy and multipolar expansion properties of the dipeptide conformation. Then, the interatomic distances of partial dipeptide conformations and the physicoc...

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 method for calculating the multi-pole expansion properties of a dipeptide model based on a BP neural network, comprising the following steps: optimizing the structures of different dipeptide conformations through the quantum mechanics calculation software Gaussian, and calculating its physical and chemical parameters and the mutual distance between atoms; selecting the part The physical and chemical parameters of the atoms of the dipeptide conformation and the distance between atoms are trained to obtain the physical and chemical parameters of the BP neural network; and the remaining dipeptide conformation is used as a test set to verify the prediction results of the BP neural network. The invention uses BP neural network prediction to replace the quantum mechanical calculation performed by the quantum mechanical calculation Gaussian software. On the basis of the molecular mechanics simulation based on the force field information, the present invention can quickly provide information on dipeptide energy, multipole distance and other physical and chemical parameters for different conformations. Within the acceptable error range, the calculation time and calculation amount are greatly reduced, and the accuracy in the dynamic simulation process is greatly improved.

Description

technical field [0001] The invention belongs to the field of combining quantum mechanics and molecular mechanics calculations, calculation methods and artificial intelligence, and specifically relates to a calculation method for predicting the multi-pole expansion properties of a dipeptide model through a BP neural network. Background technique [0002] Molecular Simulation is a computer-based simulation method developed in the late 20th century. With the improvement of the theory of quantum mechanics, the update of the empirical force field, and the improvement of computing speed and capacity driven by the development of computer hardware, the theory and method of molecular simulation have developed rapidly, and have played a key role in many disciplines and application fields. effect. From the principle of simulation, molecular simulation can be divided into two categories: theoretical calculation of quantum mechanics simulation QM (Quantum Mechanics) and empirical calcul...

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): G06F17/50G06N3/02
Inventor 李国辉李焱彭向达张鼎林
Owner DALIAN INST OF CHEM PHYSICS CHINESE ACAD OF SCI
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