Skip to content

A unified framework for machine learning collective variables for enhanced sampling simulations

License

Notifications You must be signed in to change notification settings

luigibonati/mlcolvar

Folders and files

NameName
Last commit message
Last commit date

Latest commit

b61bdb7 · Oct 25, 2023
May 31, 2023
Jul 9, 2023
Oct 25, 2023
Oct 25, 2023
Sep 21, 2021
Apr 18, 2023
Apr 18, 2023
Apr 18, 2023
Jul 9, 2023
Sep 21, 2021
May 31, 2023
Apr 18, 2023
Jul 9, 2023
Jun 1, 2023
Jul 9, 2023
Mar 2, 2023
Jun 1, 2023
Apr 18, 2023

Repository files navigation

Machine Learning Collective Variables for Enhanced Sampling

CODE Documentation Status GitHub Actions Build Status codecov license

PAPER paper preprint


mlcolvar is a Python library aimed to help design data-driven collective-variables (CVs) for enhanced sampling simulations. The key features are:

  1. A unified framework to help test and use (some) of the CVs proposed in the literature.
  2. A modular interface to simplify the development of new approaches and the contamination between them.
  3. A streamlined distribution of CVs in the context of advanced sampling.

The library is built upon the PyTorch ML library as well as the Lightning high-level framework.


Some of the CVs which are implemented, organized by learning setting:

  • Unsupervised: PCA, (Variational) AutoEncoders [1,2]
  • Supervised: LDA [3], DeepLDA [4], DeepTDA [5]
  • Time-informed: TICA [6], DeepTICA/SRVs [7,8], VDE [9]

And many others can be implemented based on the building blocks or with simple modifications. Check out the documentation and the examples section!


PLUMED interface: the resulting CVs can be deployed for enhancing sampling with the PLUMED package via the pytorch interface, available since version 2.9.


Notes: in early versions (v<=0.2.*) the library was called mlcvs. This is still accessible for compatibility with PLUMED masterclasses in the releases or by cloning the pre-lightning branch.


Copyright (c) 2023 Luigi Bonati, Enrico Trizio, Andrea Rizzi and Michele Parrinello. Structure of the project is based on Computational Molecular Science Python Cookiecutter.

About

A unified framework for machine learning collective variables for enhanced sampling simulations

Topics

Resources

License

Code of conduct

Citation

Stars

Watchers

Forks

Packages

No packages published