Fixed documentation

Fixed some minor typos as well as fixing formatting for references, which were not displaying correctly in the readthedocs.

deepchem/models/graph_models.py

@@ -75,9 +75,9 @@ class WeaveModel(KerasModel):
 
   References
   ----------
-  .. [1] Kearnes, Steven, et al. "Molecular graph convolutions: moving beyond
-  fingerprints." Journal of computer-aided molecular design 30.8 (2016):
-  595-608.
+  .. [1] Kearnes, Steven, et al. "Molecular graph convolutions: moving beyond 
+         fingerprints." Journal of computer-aided molecular design 30.8 (2016): 
+         595-608.
 
   """
 
@@ -410,8 +410,8 @@ class DTNNModel(KerasModel):
 
   References
   ----------
-  .. [1] Schütt, Kristof T., et al. "Quantum-chemical insights from deep
-  tensor neural networks." Nature communications 8.1 (2017): 1-8.
+  .. [1] Schütt, Kristof T., et al. "Quantum-chemical insights from deep 
+         tensor neural networks." Nature communications 8.1 (2017): 1-8.
   """
 
   def __init__(self,
@@ -896,9 +896,9 @@ class GraphConvModel(KerasModel):
 
   References
   ----------
-  .. [1] Duvenaud, David K., et al. "Convolutional networks on graphs for
-  learning molecular fingerprints." Advances in neural information processing
-  systems. 2015.
+  .. [1] Duvenaud, David K., et al. "Convolutional networks on graphs for 
+         learning molecular fingerprints." Advances in neural information processing 
+         systems. 2015.
   """
 
   def __init__(self,
@@ -1028,8 +1028,8 @@ class MPNNModel(KerasModel):
 
   References
   ----------
-  .. [1] Vinyals, Oriol, Samy Bengio, and Manjunath Kudlur. "Order matters:
-  Sequence to sequence for sets." arXiv preprint arXiv:1511.06391 (2015).
+  .. [1] Vinyals, Oriol, Samy Bengio, and Manjunath Kudlur. "Order matters: 
+         Sequence to sequence for sets." arXiv preprint arXiv:1511.06391 (2015).
   """
 
   def __init__(self,

deepchem/models/keras_model.py

@@ -52,7 +52,7 @@ class KerasModel(Model):
      models with Keras.
 
   3. It provides various additional features not found in the
-     Keras Model class, such as uncertainty prediction and
+     Keras model class, such as uncertainty prediction and
      saliency mapping.
 
   Here is a simple example of code that uses KerasModel to train
@@ -137,7 +137,7 @@ def __init__(self,
                log_frequency: int = 100,
                wandb_logger: Optional[WandbLogger] = None,
                **kwargs) -> None:
-    """Create a new KerasModel.
+    """Create a new Keras Model.
 
     Parameters
     ----------
@@ -1183,7 +1183,7 @@ def load_from_pretrained(self,
     `value_map` is created. `assignment_map` is a dictionary mapping variables
     from the `source_model` to the current model. If no `assignment_map` is
     provided, one is made from scratch and assumes the model is composed of
-    several different layers, with the final one being a dense layer. include_top
+    several different layers, with the final one being a dense layer. 'include_top'
     is used to control whether or not the final dense layer is used. The default
     assignment map is useful in cases where the type of task is different
     (classification vs regression) and/or number of tasks in the setting.

deepchem/models/molgan.py

@@ -49,8 +49,8 @@ class BasicMolGANModel(WGAN):
 
   References
   ----------
-  .. [1] Nicola De Cao et al. "MolGAN: An implicit generative model
-  for small molecular graphs", https://arxiv.org/abs/1805.11973
+  .. [1] Nicola De Cao et al. "MolGAN: An implicit generative model 
+         for small molecular graphs", https://arxiv.org/abs/1805.11973
   """
 
   def __init__(self,

deepchem/models/robust_multitask.py

@@ -212,7 +212,7 @@ class RobustMultitaskRegressor(KerasModel):
 
   The key idea of this model is to have bypass layers that feed
   directly from features to task output. This might provide some
-  flexibility toroute around challenges in multitasking with
+  flexibility to route around challenges in multitasking with
   destructive interference.
 
   References