diff --git a/src/aidsorb/data.py b/src/aidsorb/data.py
index 2ab9e2a..cc4765f 100644
--- a/src/aidsorb/data.py
+++ b/src/aidsorb/data.py
@@ -384,7 +384,7 @@ def __call__(self, samples):
 
 class PCDDataset(Dataset):
     r"""
-    ``Dataset`` for point clouds.
+    :class:`~torch.utils.data.Dataset` for point clouds.
 
     Indexing the dataset returns ``(x, None)`` if data are unlabeled, i.e.
     ``path_to_Y=None``, else ``(x, y)``, where ``x`` and ``y`` are the results of
diff --git a/src/aidsorb/datamodules.py b/src/aidsorb/datamodules.py
index 0bb3faf..f938b69 100644
--- a/src/aidsorb/datamodules.py
+++ b/src/aidsorb/datamodules.py
@@ -28,9 +28,10 @@
 
 class PCDDataModule(L.LightningDataModule):
     r"""
-    ``LightningDataModule`` for the :class:`~.PCDDataset`.
+    :class:`~lightning.pytorch.core.LightningDataModule` for the
+    :class:`~.PCDDataset`.
 
-    This datamodule assumes the following directory structure::
+    Given the following directory structure::
 
         project_root
         ├── source      <-- path_to_X
@@ -41,8 +42,8 @@ class PCDDataModule(L.LightningDataModule):
         ├── train.json
         └── validation.json
 
-    and setups the train, validation, and test datasets, all of which are
-    instances of :class:`~.PCDDataset`.
+    train, validation, and test datasets are set up, all of which are instances
+    of :class:`~.PCDDataset`.
 
     .. note::
         For validation and test dataloaders, ``shuffle=False`` and
@@ -70,7 +71,7 @@ class PCDDataModule(L.LightningDataModule):
     labels : sequence, optional
         Column names of the ``.csv`` file containing the properties to be
         predicted.
-    train_size : int, optional
+    train_size : int, default=None
         Number of training samples. If :obj:`None`, all training samples are used.
     train_transform_x : callable, optional
         Transformation to apply to point cloud during training.
@@ -148,7 +149,7 @@ def __init__(
 
     def setup(self, stage=None):
         r"""
-        Setup train, validation and test datasets.
+        Set up train, validation and test datasets.
 
         .. tip::
             Datasets are accesible via ``self.{train,validation,test}_dataset``.
diff --git a/src/aidsorb/litmodels.py b/src/aidsorb/litmodels.py
index 0404d38..2a065f6 100644
--- a/src/aidsorb/litmodels.py
+++ b/src/aidsorb/litmodels.py
@@ -26,7 +26,8 @@
 
 class PCDLit(L.LightningModule):
     r"""
-    ``LightningModule`` for supervised learning on point clouds.
+    :class:`~lightning.pytorch.core.LightningModule` for supervised learning on
+    point clouds.
 
     .. note::
         * ``metric`` is logged on epoch-level.