[DGL-LifeSci] Final release preparation for 0.2.1

README.md

@@ -24,16 +24,21 @@ DGL is an easy-to-use, high performance and scalable Python package for deep lea
 
 **A data scientist** may want to apply a pre-trained model to your data right away. For this you can use DGL's [Application packages, formally *Model Zoo*](https://github.com/dmlc/dgl/tree/master/apps). Application packages are developed for domain applications, as is the case for [DGL-LifeScience](https://github.com/dmlc/dgl/tree/master/apps/life_sci). We will soon add model zoo for knowledge graph embedding learning and recommender systems. Here's how you will use a pretrained model:
 ```python
-from dgl.data.chem import Tox21, smiles_to_bigraph, CanonicalAtomFeaturizer
-from dgl import model_zoo
+from dgllife.data import Tox21
+from dgllife.model import load_pretrained
+from dgllife.utils import smiles_to_bigraph, CanonicalAtomFeaturizer
 
 dataset = Tox21(smiles_to_bigraph, CanonicalAtomFeaturizer())
-model = model_zoo.chem.load_pretrained('GCN_Tox21') # Pretrained model loaded
+model = load_pretrained('GCN_Tox21') # Pretrained model loaded
 model.eval()
 
 smiles, g, label, mask = dataset[0]
 feats = g.ndata.pop('h')
 label_pred = model(g, feats)
+print(smiles)                   # CCOc1ccc2nc(S(N)(=O)=O)sc2c1
+print(label_pred[:, mask != 0]) # Mask non-existing labels
+# tensor([[ 1.4190, -0.1820,  1.2974,  1.4416,  0.6914,  
+# 2.0957,  0.5919,  0.7715, 1.7273,  0.2070]])
 ```
 
 **Further reading**: DGL is released as a managed service on AWS SageMaker, see the medium posts for an easy trip to DGL on SageMaker([part1](https://medium.com/@julsimon/a-primer-on-graph-neural-networks-with-amazon-neptune-and-the-deep-graph-library-5ce64984a276) and [part2](https://medium.com/@julsimon/deep-graph-library-part-2-training-on-amazon-sagemaker-54d318dfc814)).

apps/life_sci/README.md

@@ -12,6 +12,68 @@ featurization, and evaluation, model architectures, training scripts and pre-tra
 
 **For a full list of work implemented in DGL-LifeSci, see [here](examples/README.md).**
 
+## Installation
+
+### Requirements
+
+DGL-LifeSci should work on
+
+* all Linux distributions no earlier than Ubuntu 16.04
+* macOS X
+* Windows 10
+
+DGL-LifeSci requires python 3.6+, DGL 0.4.3+ and PyTorch 1.2.0+.
+
+Additionally, we require `RDKit 2018.09.3` for cheminformatics. We recommend installing it with
+
+```
+conda install -c conda-forge rdkit==2018.09.3
+```
+
+For other installation recipes for RDKit, see the [official documentation](https://www.rdkit.org/docs/Install.html).
+
+### Pip installation for DGL-LifeSci
+
+```
+pip install dgllife
+```
+
+### Conda installation for DGL-LifeSci
+
+```
+conda install -c dglteam dgllife
+```
+
+### Installation from source
+
+If you want to try experimental features, you can install from source as follows:
+
+```
+git clone https://github.com/dmlc/dgl.git
+cd apps/life_sci/python
+python setup.py install
+```
+
+### Verifying successful installation
+
+Once you have installed the package, you can verify the success of installation with 
+
+```python
+import dgllife
+
+print(dgllife.__version__)
+# 0.2.1
+```
+
+If you are new to DGL, the first time you import dgl a message will pop up as below:
+
+```
+DGL does not detect a valid backend option. Which backend would you like to work with?
+Backend choice (pytorch, mxnet or tensorflow):
+```
+
+and you need to enter `pytorch`.
+
 ## Example Usage
 
 To apply graph neural networks to molecules with DGL, we need to first construct `DGLGraph` -- 
@@ -78,7 +140,8 @@ print(label_pred[:, mask != 0]) # Mask non-existing labels
 # 2.0957,  0.5919,  0.7715, 1.7273,  0.2070]])
 ```
 
-Similarly, we can load a pre-trained model for generating molecules.
+Similarly, we can load a pre-trained model for generating molecules. If possible, we recommend running 
+the code block below with Jupyter notebook.
 
 ```python
 from dgllife.model import load_pretrained
@@ -108,30 +171,6 @@ SVG(Draw.MolsToGridImage(mols, molsPerRow=4, subImgSize=(180, 150), useSVG=True)
 ```
 
 ![](https://data.dgl.ai/dgllife/dgmg/dgmg_model_zoo_example2.png)
-
-## Installation
-
-DGL-LifeSci requires python 3.5+, DGL 0.4.3+ and PyTorch 1.2.0+.
-
-Additionally, we require `RDKit 2018.09.3` for cheminformatics. We recommend installing it with 
-`conda install -c conda-forge rdkit==2018.09.3`. For other installation recipes, 
-see the [official documentation](https://www.rdkit.org/docs/Install.html).
-
-We provide installation of `DGL-LifeSci` with pip. Once you have installed the package, 
-verify the success of installation with 
-
-```python
-import dgllife
-
-print(dgllife.__version__)
-# 0.2.0
-```
-
-### Using pip
-
-```
-pip install dgllife
-```
 
 ## Speed Reference
 

apps/life_sci/conda/dgllife/build.sh

@@ -1,4 +1 @@
-git submodule init
-git submodule update --recursive
-cd python
-$PYTHON setup.py install --single-version-externally-managed --record=record.txt
+$PYTHON setup.py install --single-version-externally-managed --record=record.txt    # Python command to install the script. 

apps/life_sci/conda/dgllife/conda_build_config.yaml

@@ -1,4 +1,3 @@
 python:
-  - 3.5
   - 3.6
   - 3.7

apps/life_sci/conda/dgllife/meta.yaml

@@ -1,10 +1,10 @@
 package:
   name: dgllife{{ environ.get('APP_PACKAGE_SUFFIX', '') }}
-  version: "0.2.0"
+  version: "0.2.1"
 
 source:
-  git_rev: 0.2.0
-  git_url: https://github.com/dmlc/dgl/tree/master/apps/dgllife
+  url: https://files.pythonhosted.org/packages/7d/ca/543802eca0e8d263a73309379f79a054b3bb7e7377ead0b69d2451728465/dgllife-0.2.1.tar.gz
+  sha256: 11a1622ba587f7ff67f42ad8bc88d238faaa459ab554cf59e1b69a10079d41c0
 
 requirements:
   build:
@@ -19,12 +19,9 @@ requirements:
     - scikit-learn
     - pandas
     - tqdm
-
-test:
-  imports:
-    - dgllife
+    - numpy
+    - scipy
+    - networkx
 
 about:
-  home: https://github.com/dmlc/dgl/tree/master/apps/dgllife
-  license_file: {{ environ.get('SRC_DIR') }}/LICENSE
-  license: Apache
+  license: Apache

apps/life_sci/python/dgllife/libinfo.py

@@ -1,2 +1,4 @@
 """Information for the library."""
-__version__ = '0.2.0'
+
+# current version
+__version__ = '0.2.1'

apps/life_sci/python/setup.py

@@ -31,16 +31,17 @@ def get_lib_path():
         'life-science',
         'drug-discovery'
     ],
-    zip_safe=False,
     maintainer='DGL Team',
     packages=[package for package in find_packages()
               if package.startswith('dgllife')],
     install_requires=[
-        'torch>=1.1'
         'scikit-learn>=0.22.2',
-        'pandas>=0.24.2',
+        'pandas',
         'requests>=2.22.0',
-        'tqdm'
+        'tqdm',
+        'numpy>=1.14.0',
+        'scipy>=1.1.0',
+        'networkx>=2.1',
     ],
     url='https://github.com/dmlc/dgl/tree/master/apps/life_sci',
     classifiers=[

apps/life_sci/python/update_version.py

@@ -8,7 +8,7 @@
 import os
 import re
 
-__version__ = "0.2.0"
+__version__ = "0.2.1"
 print(__version__)
 
 # Implementations