improve documentation

docs/source/GNINA.rst

@@ -1,28 +1,56 @@
 GNINA_ Models
 =============
 
-Thanks to `Andrew McNutt`_, who converted the original Caffe_ models to PyTorch_, all GNINA_ models are available in gninatorch_.
+Thanks to `Andrew McNutt`_, who converted the weights of the original Caffe_ models to PyTorch_, all GNINA_ models are available in gninatorch_.
 
 You can find more information about the Caffe_ implementation at `gnina/models`_.
 
 Loading GNINA_ Models
 ---------------------
 
-The pre-trained models can be easily loaded as follows:
+The pre-trained models can be loaded as follows:
 
 .. code-block:: python
 
  from gninatorch import gnina
 
  model, ensemble: bool = setup_gnina_model(model_name)
 
-where :code:`model_name` corresponds accepts the same values as the :code:`--cnn` argument in GNINA_.
-
+where :code:`model_name` accepts the same values as the :code:`--cnn` argument in GNINA_ (see :ref:`gnina-models` and :ref:`gnina-models-ensemble`).
 :code:`ensemble` is a boolean flag that indicates whether the model is an ensemble of models or not.
 
+A single model returns :code:`log_CNNscore`, and :code:`CNNaffinity`:
+
+.. code-block:: python
+
+ assert ensemble == False
+
+ # Grid based-representation of protein-ligand binding site
+ # x : torch.Tensor
+
+ log_CNNscore, CNNaffinity = model(x)
+ CNNscore = torch.exp(log_CNNscore)
+
+An ensemble of models returns :code:`log_CNNscore`, :code:`CNNaffinity` and :code:`CNNvariance`:
+
+.. code-block:: python
+
+ assert ensemble == True
+
+ # Grid based-representation of protein-ligand binding site
+ # x : torch.Tensor
+
+ log_CNNscore, CNNaffinity, CNNvariance = model(x)
+ CNNscore = torch.exp(log_CNNscore)
+
 .. warning::
  In contrast to GNINA_, which returns :code:`CNNscore`, the PyTorch models return :code:`log_CNNscore`.
 
+.. _gnina-models:
+
+Supported GNINA Models
+~~~~~~~~~~~~~~~~~~~~~~
+
 The following models are provided:
 
 * :code:`default2017` :cite:`ragoza2017protein`
@@ -31,7 +59,12 @@ The following models are provided:
 * :code:`crossdock_default2018` or :code:`crossdock_default2018_[1-4]` :cite:`francoeur2020three`
 * :code:`dense` or :code:`dense_[1-4]` :cite:`francoeur2020three`
 
-The following ensembles of models are also provided:
+.. _gnina-models-ensemble:
+
+Supported GNINA Ensembles of Models
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+The following ensembles of models are also available:
 
 * :code:`default` (GNINA_ default model) :cite:`mcnutt2021gnina` :cite:`francoeur2020three`
 * :code:`redock_default2018_ensemble` :cite:`francoeur2020three`
@@ -53,7 +86,7 @@ You can build your own ensemble of models as follows:
 
  from gninatorch import gnina
 
- model = gnina.setup_gnina_models([model_name1, model_name2, ...])
+ model = gnina.load_gnina_models([model_name1, model_name2, ...])
 
 The :code:`default` model used by GNINA_ corresponds to the following ensemble:
 
@@ -71,7 +104,8 @@ The :code:`default` model used by GNINA_ corresponds to the following ensemble:
 
  model = gnina.load_gnina_models(names)
 
-The :code:`default` optimises accuracy and inference speed. See :cite:`mcnutt2021gnina` for more information.
+The :code:`default` model is chosen to optimise accuracy and inference speed.
+See :cite:`mcnutt2021gnina` for more information.
 
 Inference with GNINA_ Models
 ----------------------------

docs/source/getting_started.rst

@@ -14,14 +14,14 @@ Installation
 Installation from Source
 ~~~~~~~~~~~~~~~~~~~~~~~~
 
-Clone the repository from GitHub:
+Clone the repository from GitHub_:
 
 .. code-block:: bash
 
  git clone https://github.com/RMeli/gnina-torch.git
  cd gnina-torch
 
-Create conda_ or mamba_ environment with all the dependencies:
+Create a conda_ or mamba_ environment with all the dependencies:
 
 .. code-block:: bash
 
@@ -69,4 +69,5 @@ Run tests with pytest_ and report code coverage:
 .. _libmolgrid: https://gnina.github.io/libmolgrid/
 .. _NVIDIA: https://www.nvidia.com/
 .. _PyTorch: https://pytorch.org/
-.. _pytest: https://docs.pytest.org/en/7.1.x/contents.html
+.. _pytest: https://docs.pytest.org/en/7.1.x/contents.html
+.. _GitHub: https://github.com/