First pass at a simple static website.

_sources/analysis.rst.txt

@@ -0,0 +1,47 @@
+.. _ref_analysis:
+
+==============
+Error Analysis
+==============
+
+The ``emle-analyze`` executable facilitates analysis of the performance of
+EMLE-based simulations. It requires a set of single point reference calculations
+for a trajectory generated with ``emle-engine`` (currently only
+`ORCA <https://orcaforum.kofo.mpg.de>`__ is supported). It also requires
+Minimal Basis Iterative Stockholder (MBIS) decomposition of the in-vacuo
+electronic density of the QM region with
+`HORTON <https://theochem.github.io/horton/2.1.1/index.html>`__.
+
+Usage:
+
+.. code-block:: text
+
+    emle-analyze --qm-xyz qm.xyz \
+                 --pc.xyz pc.xyz \
+                 --emle-model model.mat \
+                 --orca-tarball orca.tar \
+                 --backend [deepmd, ani2x]
+                 --alpha
+                 result.mat
+
+Here ``qm.xyz`` and ``pc.xyz`` are the QM and MM XYZ trajectories written out by
+``emle-engine`` during dynamics. ``model.mat`` specifies the path to the ``EMLE``
+model used. ``orca.tar`` is a tarball containing single point ``ORCA`` calculations
+and corresponding ``HORTON`` outputs. All files should be named as ``index.*``
+where index is a numeric value identifying the snapshot (does not have to
+be consecutive) and the extensions are:
+
+- ``.vac.orca``: ``ORCA`` output for gas phase calculation. When ``--alpha``
+  argument is provided, must also include molecular dipolar polarizability (``%elprop Polar``)
+- ``.h5``: ``HORTON`` output for gas phase calculation
+- ``.pc.orca``: ``ORCA`` output for calculation with point charges
+- ``.pc``: charges and positions of the point charges (the ones used for ``.pc.orca``
+  calculation)
+- ``.vpot``: output of ``orca_vpot``, electrostatic potential of gas phase system at
+  the positions of the point charges
+
+The optional ``--backend`` argument allows extraction of energies from the
+in vacuo backend. Currently, only the ``deepmd``, ``mace``, and ``ani2x``
+backends are supported by ``emle-analyze``.  When the ``deepmd`` or ``mace``
+backend is used a model file must be provided with the ``--deepmd-model`` or
+``--mace-model`` arguments.

_sources/api/index.rst.txt

@@ -0,0 +1,18 @@
+.. _ref_api:
+
+=================
+API Documentation
+=================
+
+The Python API (Application Programming Interface) is divided into a collection
+of modules.
+
+.. toctree::
+   :maxdepth: 1
+
+   index_models
+   index_calculator
+   index_train
+   index_backends
+   index_analyzer
+   index_orca_parser

_sources/api/index_analyzer.rst.txt

@@ -0,0 +1,11 @@
+.. _ref-analyzer:
+
+emle._analyzer
+==============
+
+The *analyzer* module contains analyzing output from EMLE simulations.
+This is an internal module used by the ``emle-analyze`` script when
+performing :ref:`ref_analysis` on the output of an EMLE simulation.
+
+.. autoclass:: emle._analyzer.EMLEAnalyzer
+   :no-show-inheritance:

_sources/api/index_backends.rst.txt

@@ -0,0 +1,29 @@
+.. _ref-backends:
+
+emle._backends
+==============
+
+The *backends* module classes for computing in-vacuo energies and gradients.
+This is an internal module. Backends are used by the :ref:`ref-calculator` and
+:ref:`ref-analyzer` modules.
+
+.. autoclass:: emle._backends._backend.Backend
+   :no-show-inheritance:
+
+.. autoclass:: emle._backends.DeePMD
+   :no-show-inheritance:
+
+.. autoclass:: emle._backends.ORCA
+   :no-show-inheritance:
+
+.. autoclass:: emle._backends.Rascal
+   :no-show-inheritance:
+
+.. autoclass:: emle._backends.Sander
+   :no-show-inheritance:
+
+.. autoclass:: emle._backends.SQM
+   :no-show-inheritance:
+
+.. autoclass:: emle._backends.XTB
+   :no-show-inheritance:

_sources/api/index_calculator.rst.txt

@@ -0,0 +1,14 @@
+.. _ref-calculator:
+
+emle.calculator
+===============
+
+The *calculator* module contains a calculator for computing energies and
+gradients. This is used by the ``emle-engine`` script to compute energies
+and gradients when interfacing with `sander <https://ambermd.org>`__.
+The calculator can also be used by `Sire <https://sire.openbiosim.org>`__
+to interface with `OpenMM <http://openmm.org>`__.
+
+.. autoclass:: emle.calculator.EMLECalculator
+   :members:
+   :no-show-inheritance:

_sources/api/index_models.rst.txt

@@ -0,0 +1,21 @@
+.. _ref-models:
+
+emle.models
+===========
+
+The *models* module contains Torch modules for creating EMLE models.
+
+.. autoclass:: emle.models.EMLEAEVComputer
+   :no-show-inheritance:
+
+.. autoclass:: emle.models.EMLEBase
+   :no-show-inheritance:
+
+.. autoclass:: emle.models.EMLE
+   :no-show-inheritance:
+
+.. autoclass:: emle.models.ANI2xEMLE
+   :no-show-inheritance:
+
+.. autoclass:: emle.models.MACEEMLE
+   :no-show-inheritance:

_sources/api/index_orca_parser.rst.txt

@@ -0,0 +1,13 @@
+.. _ref-orca-parser:
+
+emle._orca_parser
+=================
+
+The *orca_parser* module provides a parser for ORCA output files.
+This is an internal module used by the ``emle-analyze`` and
+``emle-train`` scripts to load simulation output prior to
+performing :ref:`error analysis <ref_analysis>` or
+:ref:`training <ref_training>`.
+
+.. autoclass:: emle._orca_parser.ORCAParser
+   :no-show-inheritance:

_sources/api/index_train.rst.txt

@@ -0,0 +1,11 @@
+.. _ref-train:
+
+emle.train
+==========
+
+The *train* module contains functionality for :ref:`training <ref_training>`
+EMLE models. The ``EMLETrainer`` class is used internally by the ``emle-train``
+script but can also be used directly in Python.
+
+.. autoclass:: emle.train.EMLETrainer
+   :no-show-inheritance:

_sources/changelog.rst.txt

@@ -0,0 +1,10 @@
+.. _ref_changelog:
+
+=========
+Changelog
+=========
+
+`v1.0.0 <https://github.com/chemle/emle-engine/releases/tag/v1.0.0>`_ - Oct 10 2024
+-----------------------------------------------------------------------------------
+
+* Initial release of ``emle-engine``.

_sources/contributing.rst.txt

@@ -0,0 +1,29 @@
+.. _ref_contributing:
+
+============
+Contributing
+============
+
+We welcome bug-fixes and ehanchements to the codebase via pull requests to
+our `GitHub repository <https://github.com/chemle/emle-engine>`_. When
+submitting a PR, please make sure that you rebase your branch on the latest
+``main`` branch and that all tests pass.
+
+If you are adding a new :ref:`model <ref-models>`, please make sure that
+it is `TorchScript <https://pytorch.org/docs/stable/jit.html>`_
+compatible. This is necessary for the model to be used with
+`OpenMM <http://openmm.org>`_, since the Torch models are serialized
+from Python, then deserialized in C++.
+
+.. note::
+
+    What works with `PyTorch <https://pytorch.org>`_ may not work with
+    TorchScript. The use of TorchScript is the reason why some of the
+    model code looks quite un-Pythonic, e.g. there is no inheritance.
+
+The test suite for our existing models can be found
+`here <https://github.com/chemle/emle-engine/blob/main/tests/test_models.py>`_.
+For each model we test that: 1) the model can be instantiated,
+2) the model can be serialiazed via TorchScript, and 3) the model
+can be evaluated using standard input data. If you are adding a new
+model, please make sure that it passes these tests.