Metadata-Version: 2.5
Name: polen
Version: 0.0.1
Summary: POLEN: polarizable embedding of neural-network potentials (ML/MM with mutually polarizable AMOEBA embedding for OpenMM). Placeholder release; under active development.
Project-URL: Repository, https://github.com/cmobiolab/polen
Author-email: "Renato D. Cunha" <renato.cunha8@gmail.com>
License-Expression: LGPL-3.0-or-later
License-File: COPYING
License-File: COPYING.LESSER
Keywords: AMOEBA,ML/MM,OpenMM,QM/MM,machine learning potentials,molecular dynamics,polarizable force field
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Science/Research
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Chemistry
Classifier: Topic :: Scientific/Engineering :: Physics
Requires-Python: >=3.10
Description-Content-Type: text/markdown

# polen

**POLEN** — *POLarizable Embedding of Neural-network potentials*.

POLEN is an ML/MM framework for [OpenMM](https://openmm.org) in which a machine-learning interatomic potential (e.g. MACE)
describes a region of interest embedded in the AMOEBA polarizable force field, with **mutual polarization** between
the two regions (MuPE, *Mutual Polarizable Embedding*), periodic boundary conditions (PME) and GPU support. In the MuPE(ML)
variant, atomic multipoles, valence (charge-penetration) parameters and polarizabilities of the ML region are predicted by
a neural network at every step.

This is a **placeholder release** that reserves the package name while the code and the accompanying paper are being
finalized. The first functional release will be announced at https://github.com/cmobiolab/polen.

License: GNU Lesser General Public License v3.0 or later (LGPL-3.0-or-later).
