aiida-mlip

machine learning interatomic potentials aiida plugin

Features (in development)

Supports multiple MLIPs
- MACE
- M3GNET
- CHGNET
Single point calculations
Geometry optimisation
Molecular Dynamics:
- NVE
- NVT (Langevin(Eijnden/Ciccotti flavour) and Nosé-Hoover (Melchionna flavour))
- NPT (Nosé-Hoover (Melchiona flavour))
Training ML potentials (MACE only planned)
Fine tunning MLIPs (MACE only planned)

The code relies heavily on janus-core, which handles mlip calculations using ASE.

Installation

pip install aiida-mlip
verdi quicksetup  # better to set up a new profile
verdi plugin list aiida.calculations

The last command should show a list of AiiDA pre-installed calculations and the aiida-mlip plugin calculations (janus.opt, janus.sp)

Registered entry points for aiida.calculations:
* core.arithmetic.add
* core.templatereplacer
* core.transfer
* janus.opt
* janus.sp

Usage

A quick demo of how to submit a calculation using the provided example files submit_singlepoint.py and submit_geomopt.py:

verdi daemon start     # make sure the daemon is running
cd examples/calculations
verdi run submit_singlepoint.py "janus@localhost" --architecture mace --model "/path/to/model"    # run test calculation
verdi run submit_geomopt.py "janus@localhost" --structure "path/to/structure" --model "path/to/model" --steps 5 --fully-opt True
verdi process list -a  # check record of calculation

Development

Install poetry
(Optional) Create a virtual environment
Install aiida-mlip with dependencies:

git clone https://github.com/stfc/aiida-mlip
cd aiida-mlip
pip install --upgrade pip
poetry install --with pre-commit,dev,docs  # install extra dependencies
pre-commit install  # install pre-commit hooks
pytest -v  # discover and run all tests

See the developer guide for more information.

Repository contents

.github/: Github Actions configuration
- ci.yml: runs tests, checks test coverage and builds documentation at every new commit
- publish-on-pypi.yml: automatically deploy git tags to PyPI - just generate a PyPI API token for your PyPI account and add it to the pypi_token secret of your github repository
- docs.yml: builds and deploys the documentation
aiida_mlip/: The main source code of the plugin package
- data/: Plugin Data classes
  - model.py/ ModelData class to save mlip models as AiiDA data types
- calculations/: Plugin Calcjob classes
  - singlepoint.py: Calcjob class to run single point calculations using mlips
  - geomopt.py: Calcjob class to perform geometry optimization using mlips
- parsers/: Parsers for the calculations
  - sp_parser.py: Parser for Singlepoint calculation.
  - opt_parser.py: Parser for Geomopt calculation.
- helpers/: Helpers to run calculations.
docs/: Code documentation
- apidoc/: API documentation
- developer_guide/: Documentation for developers
- user_guide/: Documentation for users
- images/: Logos etc used in the documentation
examples/: Examples for submitting calculations using this plugin
- calculations/: Scripts for submitting calculations
  - submit_singlepoint.py: Script for submitting a singlepoint calculation
  - submit_geomopt.py: Script for submitting a geometry optimisation calculation
tests/: Basic regression tests using the pytest framework (submitting a calculation, ...). Install pip install -e .[testing] and run pytest.
- conftest.py: Configuration of fixtures for pytest
- calculations/: Calculations
  - test_singlepoint.py: Test SinglePoint calculation
  - test_geomopt.py: Test Geomopt calculation
- data/: ModelData
  - test_model.py: Test ModelData type
.gitignore: Telling git which files to ignore
.pre-commit-config.yaml: Configuration of pre-commit hooks that sanitize coding style and check for syntax errors. Enable via pip install -e .[pre-commit] && pre-commit install
LICENSE: License for the plugin
README.md: This file
tox.ini: File to set up tox
pyproject.toml: Python package metadata for registration on PyPI and the AiiDA plugin registry (including entry points)

License

BSD 3-Clause License

Funding

Contributors to this project were funded by

alinelena/aiida-mlip