Metadata-Version: 2.1
Name: mddatasetbuilder
Version: 1.3.0
Summary: A script to make molecular dynamics (MD) datasets for neural networks from given LAMMPS trajectories automatically.
Home-page: https://github.com/njzjz/mddatasetbuilder
Author: Jinzhe Zeng
Author-email: jzzeng@stu.ecnu.edu.cn
License: UNKNOWN
Description: # MDDatasetBuilder
        
        [![arxiv:1910.12690](http://img.shields.io/badge/arXiv-1911.12252-B31B1B.svg?maxAge=86400)](https://arxiv.org/abs/1911.12252)
        [![python version](https://img.shields.io/pypi/pyversions/mddatasetbuilder.svg?logo=python&logoColor=white)](https://pypi.org/project/mddatasetbuilder)
        [![PyPI](https://img.shields.io/pypi/v/mddatasetbuilder.svg)](https://pypi.org/project/mddatasetbuilder)
        [![codecov](https://codecov.io/gh/njzjz/mddatasetbuilder/branch/master/graph/badge.svg)](https://codecov.io/gh/njzjz/mddatasetbuilder)
        [![Research Group](https://img.shields.io/website-up-down-green-red/http/computchem.cn.svg?label=Research%20Group)](http://computchem.cn)
        
        MDDatasetBuilder is a script to construct reference datasets for the training of neural network potentials from given LAMMPS trajectories.
        
        Neural Network Based in Silico Simulation of Combustion Reactions, arXiv:1911.12252
        
        **Author**: Jinzhe Zeng
        
        **Email**: jzzeng@stu.ecnu.edu.cn
        
        ## Installation
        
        Firstly, the latest version of [Anaconda or Miniconda](https://conda.io/projects/continuumio-conda/en/latest/user-guide/install/index.html) shoule be installed. And then use conda to install [openbabel](https://github.com/openbabel/openbabel):
        
        ```sh
        conda install openbabel -c conda-forge
        ```
        
        Then install mddatasetbuilder can be installed with pip:
        ```
        pip install git+https://github.com/tongzhugroup/mddatasetbuilder
        ```
        
        The installation process should be very quick, taking only a few minutes on a “normal” desktop computer. 
        
        ## Usage
        ### Simple example
        
        A [LAMMPS dump file](https://lammps.sandia.gov/doc/dump.html) should be prepared. A [LAMMPS bond file](http://lammps.sandia.gov/doc/fix_reax_bonds.html) can be added for the addition information.
        
        ```bash
        datasetbuilder -d dump.ch4 -b bonds.reaxc.ch4_new -a C H O -n ch4 -i 25
        ```
        
        Here, `dump.ch4` is the name of the dump file. `bonds.reaxc.ch4_new` is the name of the bond file, which is optional. `C H O` is the element in the trajectory. `ch4` is the name of the dataset. `25` means the time step interval and the default value is 1.
        
        Then you can generate Gaussian input files for each structure in the dataset and calculate the potential energy & atomic forces (assume the Gaussian 16 has already been installed.):
        
        ```bash
        qmcalc -d dataset_ch4_GJf/000
        qmcalc -d dataset_ch4_GJf/001
        ```
        
        Next, prepare a DeePMD dataset and use [DeePMD-kit](https://github.com/deepmodeling/deepmd-kit) to train a NN model.
        
        ```bash
        preparedeepmd -p dataset_ch4_GJf -a C H O
        cd train && dp train train.json
        ```
        
        The runtime of the software depends on the amount of data. It is more suited to running on a server rather than desktop computer.
        
        ### DP-GEN
        The MDDatasetBuilder package has been integrated into [DP-GEN](https://github.com/deepmodeling/dpgen) software.
        
Keywords: molecular dynamics dataset
Platform: UNKNOWN
Classifier: Natural Language :: English
Classifier: Operating System :: POSIX :: Linux
Classifier: Operating System :: Microsoft :: Windows
Classifier: Programming Language :: Python :: 3.6
Classifier: Programming Language :: Python :: 3.7
Classifier: Programming Language :: Python :: 3.8
Classifier: Topic :: Scientific/Engineering :: Chemistry
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Topic :: Software Development :: Version Control :: Git
Requires-Python: ~=3.6
Description-Content-Type: text/markdown
Provides-Extra: test
