Git Product home page Git Product logo

dralgroup / mlatom Goto Github PK

View Code? Open in Web Editor NEW
46.0 3.0 8.0 97.28 MB

AI-enhanced computational chemistry

Home Page: http://mlatom.com

License: Other

Python 75.71% Fortran 23.99% Makefile 0.13% Gnuplot 0.01% C++ 0.12% Shell 0.05%
artificial-intelligence computational-chemistry machine-learning machine-learning-potential quantum-chemistry quantum-chemistry-programs quantum-mechanics deep-learning kernel-method kernel-ridge-regression

mlatom's People

Contributors

dralgroup avatar terrell032 avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar

mlatom's Issues

missing input files for KREG example

i am just learning mlatom, and i found that the input files are missing for the example of KREG at http://mlatom.com/kreg/

the tutorial says to go to XACS to use the example, but in XACS, the folder /home/mlatom/tutorial is also missing
image

image

so, where can i get the input files for GREG example? thanks.

by the way, this example looks like being written in "command line" type, can this be written in python type?

something missing with the model KREG

I am a beginner for mlatom. And now I have some problem run the example in the MLP tutorial

my code is just copied from the tutorial:

import mlatom as ml

molDB = ml.data.molecular_database.from_xyz_file(filename = 'H2.xyz')
molDB.add_scalar_properties_from_file('H2_HF.en', 'energy')
molDB.add_xyz_vectorial_properties_from_file('H2_HF.grad', 'energy_gradients')

# Here we define the KREG model for demonstration purposes as it is the fastest
model = ml.models.kreg(model_file='kreg.npz')

the first problem is that the data files contain different numbers of value: the H2.xyz has 361 values while the other two (H2_HF.en and H2_HF.grad) both have 451 values.
so it results in the following error:

Traceback (most recent call last):
  File "/home/ilcpm/MD/mlp/testMLP.py", line 4, in <module>
    molDB.add_scalar_properties_from_file('H2_HF.en', 'energy')
  File "/home/ilcpm/.local/lib/python3.10/site-packages/mlatom/data.py", line 863, in add_scalar_properties_from_file
    self.molecules[ii].__dict__[property_name] = yy
IndexError: list index out of range

it can be solved by use the test_H2.xyz, test_H2_HF.en and test_H2_HF.grad, or just delete the values in H2_HF.en and H2_HF.grad.

then the biggest problem appears:

Traceback (most recent call last):
  File "/home/ilcpm/MD/mlp/testMLP.py", line 8, in <module>
    model = ml.models.kreg(model_file='kreg.npz')
  File "/home/ilcpm/.local/lib/python3.10/site-packages/mlatom/models.py", line 951, in __init__
    from .kreg_api import KREG_API
  File "/home/ilcpm/.local/lib/python3.10/site-packages/mlatom/kreg_api.py", line 5, in <module>
    from .fortran import KREG
ImportError: cannot import name 'KREG' from 'mlatom.fortran' (/home/ilcpm/.local/lib/python3.10/site-packages/mlatom/fortran/__init__.py)

it looks like there should be a python file named KREG.py in the folder mlatom/fortran, but I can't find it
image


then I try to run the Command-line (input file)

my command is mlatom train_KREG.inp, it can be successfully finish and get the output
then I found the following line in the output:

> /home/ilcpm/.local/lib/python3.10/site-packages/mlatom/MLatomF createMLmodel XYZfile=H2.xyz Yfile=H2_HF.en YgradXYZfile=H2_HF.grad MLmodelOut=kreg.unf sigma=1.0 lambda=1e-06

it seems that there is a binary executable program named MLatomF, so the missing of KREG.py didn't cause problem.

and the values in the three files are not equal:

 <!> File H2_HF.en contains 451 reference values
     but only first 361 will be used

 
    Charge        X            Y            Z
       1     0.000000     0.000000     0.000000
       1     0.000000     0.000000     1.350000
 
  Equilibrium distances: 
1     1-2      1.350000000000
 <!> File H2_HF.en contains 451 reference values
     but only first 361 will be used

 <!> File H2_HF.grad contains 451 reference values
     but only first 361 will be used

Feature Request: Integration of PLUMED Interface for Enhanced Sampling

Could you consider adding this to the development roadmap? Integrating a PLUMED interface within the molecular dynamics simulation module of the MLAtom project would significantly enhance its sampling capabilities. This integration could streamline the study of complex processes and improve the accuracy of potential energy surface representations. Thank you very much!

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.