Commit afe44833 authored by Bharath Ramsundar's avatar Bharath Ramsundar
Browse files

Merge branch 'master' of https://github.com/deepchem/deepchem into binding_pocket_feat

parents 399f650e c0a17207

README.md

+62 −79
Original line number Diff line number Diff line
@@ -46,48 +46,28 @@ Installation from source is the only currently supported format. ```deepchem``` 
   conda install -c omnia openbabel=2.4.0

   ``` 



3. `pandas`

   ```bash

   conda install pandas 

   ```



4. `rdkit`

3. `rdkit`

   ```bash

   conda install -c omnia rdkit

   ```



5. `boost`

   ```bash

   conda install -c omnia boost=1.59.0

   ```



6. `joblib`

4. `joblib`

   ```bash

   conda install joblib 

   ```



7. `keras`

   ```bash

   pip install keras --user

   ```

   `deepchem` only supports the `tensorflow` backend for keras. To set the backend to `tensorflow`,

   add the following line to your `~/.bashrc`

5. `keras`

   ```bash

   export KERAS_BACKEND=tensorflow

   pip install keras

   ```

   See [keras docs](https://keras.io/backend/) for more details and alternate methods of setting backend.

   `deepchem` only supports the `tensorflow` (default) backend for keras.

   

8. `mdtraj`

6. `mdtraj`

   ```bash

   conda install -c omnia mdtraj

   ```



9. `scikit-learn`

   ```bash

   conda install scikit-learn 

   ```



10. `tensorflow`: Installing `tensorflow` on older versions of Linux (which

7. `tensorflow`: Installing `tensorflow` on older versions of Linux (which

    have glibc < 2.17) can be very challenging. For these older Linux versions,

    contact your local sysadmin to work out a custom installation. If your

    version of Linux is recent, then the following command will work:
@@ -95,12 +75,7 @@ Installation from source is the only currently supported format. ```deepchem``` 
    conda install -c https://conda.anaconda.org/jjhelmus tensorflow

    ```



11. `h5py`:

    ```

    conda install h5py

    ```



12. `deepchem`: Clone the `deepchem` github repo:

8. `deepchem`: Clone the `deepchem` github repo:

   ```bash

   git clone https://github.com/deepchem/deepchem.git

   ```
@@ -109,9 +84,9 @@ Installation from source is the only currently supported format. ```deepchem``` 
   python setup.py install

   ```



13. To run test suite, install `nosetests`:

9. To run test suite, install `nosetests`:

   ```bash

    pip install nose --user

   pip install nose

   ```

   Make sure that the correct version of `nosetests` is active by running

   ```bash
@@ -120,7 +95,7 @@ Installation from source is the only currently supported format. ```deepchem``` 
   You might need to uninstall a system install of `nosetests` if

   there is a conflict.



14. If installation has been successful, all tests in test suite should pass:

10. If installation has been successful, all tests in test suite should pass:

    ```bash

    nosetests -v deepchem --nologcapture 

    ```
@@ -181,10 +156,12 @@ Environmental Protection Agency, Environmental Research Laboratory, 1987. 
Most machine learning algorithms require that input data form vectors.

However, input data for drug-discovery datasets routinely come in the

format of lists of molecules and associated experimental readouts. To

transform lists of molecules into vectors, we need to use the DeepChem

loader class ``dc.load.DataLoader``. Instances of this class must be

passed a ``Featurizer`` object. DeepChem provides a number of

different subclasses of ``Featurizer`` for convenience:

transform lists of molecules into vectors, we need to subclasses of DeepChem

loader class ```dc.data.DataLoader``` such as ```dc.data.CSVLoader``` or 

```dc.data.SDFLoader```. Users can subclass ```dc.data.DataLoader``` to

load arbitrary file formats. All loaders must be

passed a ```dc.feat.Featurizer``` object. DeepChem provides a number of

different subclasses of ```dc.feat.Featurizer``` for convenience.



### Performances

* Classification
@@ -218,26 +195,26 @@ Random splitting 


|Dataset    |Model               |Train score/ROC-AUC|Valid score/ROC-AUC|

|-----------|--------------------|-------------------|-------------------|

|tox21      |logistic regression |0.903              |0.741              |

|           |Multitask network   |0.846              |0.812              |

|           |robust MT-NN        |0.844              |0.793              |

|           |graph convolution   |0.872              |0.816              |

|muv        |logistic regression |0.961              |0.696              |

|           |Multitask network   |0.895              |0.740              |

|           |robust MT-NN        |0.914              |0.667              |

|           |graph convolution   |0.846              |0.776              |

|pcba       |logistic regression |0.807        	     |0.772              |

|           |Multitask network   |0.811        	     |0.787              |

|           |robust MT-NN        |0.809              |0.778              |

|           |graph convolution   |0.875       	     |0.844              |

|sider      |logistic regression |0.932        	     |0.628              |

|           |Multitask network   |0.779        	     |0.665              |

|           |robust MT-NN        |0.761              |0.621              |

|           |graph convolution   |0.706        	     |0.638              |

|toxcast    |logistic regression |0.737        	     |0.543              |

|           |Multitask network   |0.831        	     |0.684              |

|           |robust MT-NN        |0.814              |0.692              |

|           |graph convolution   |0.820        	     |0.692              |

|tox21      |logistic regression |0.903              |0.735              |

|           |Multitask network   |0.856              |0.783              |

|           |robust MT-NN        |0.855              |0.773              |

|           |graph convolution   |0.865              |0.827              |

|muv        |logistic regression |0.957              |0.719              |

|           |Multitask network   |0.902              |0.734              |

|           |robust MT-NN        |0.933              |0.732              |

|           |graph convolution   |0.860              |0.730              |

|pcba       |logistic regression |0.808        	     |0.776              |

|           |Multitask network   |0.811        	     |0.778              |

|           |robust MT-NN        |0.811              |0.771              |

|           |graph convolution   |0.872       	     |0.844              |

|sider      |logistic regression |0.929        	     |0.656              |

|           |Multitask network   |0.777        	     |0.655              |

|           |robust MT-NN        |0.804              |0.630              |

|           |graph convolution   |0.705        	     |0.618              |

|toxcast    |logistic regression |0.725        	     |0.586              |

|           |Multitask network   |0.836        	     |0.684              |

|           |robust MT-NN        |0.822              |0.681              |

|           |graph convolution   |0.820        	     |0.717              |



Scaffold splitting
@@ -269,11 +246,14 @@ Scaffold splitting 
|Dataset    |Model               |Splitting   |Train score/R2|Valid score/R2|

|-----------|--------------------|------------|--------------|--------------|

|delaney    |MT-NN regression    |Index       |0.773         |0.574         |

|           |graphconv regression|Index       |0.964         |0.829         |

|           |graphconv regression|Index       |0.991         |0.825         |

|           |MT-NN regression    |Random      |0.769         |0.591         |

|           |graphconv regression|Random      |0.959         |0.821         |

|           |graphconv regression|Random      |0.996         |0.873         |

|           |MT-NN regression    |Scaffold    |0.782         |0.426         |

|           |graphconv regression|Scaffold    |0.976         |0.581         |

|           |graphconv regression|Scaffold    |0.994         |0.606         |

|nci        |MT-NN regression    |Index       |0.890         |0.890         |

|           |MT-NN regression    |Random      |0.891         |0.888         |

|           |MT-NN regression    |Scaffold    |0.912         |0.020         |

|kaggle     |MT-NN regression    |User-defined|0.748         |0.452         |



* General features
@@ -289,6 +269,7 @@ Number of tasks and examples in the datasets 
|toxcast    |617        |8615       |

|delaney    |1          |1128       |

|kaggle     |15         |173065     |

|nci        |60         |1057371    |



Time needed for benchmark test(~20h in total)
@@ -315,6 +296,8 @@ Time needed for benchmark test(~20h in total) 
|           |robust MT-NN        |80              |4000           |

|           |graph convolution   |80              |900            |

|delaney    |MT-NN regression    |10              |40             |

|           |graphconv regression|10              |40             |

|nci        |MT-NN regression    |2000            |30000          |

|kaggle     |MT-NN regression    |2200            |3200           |

deepchem/dock/docking.py

+2 −2
Original line number Diff line number Diff line
@@ -34,7 +34,7 @@ class VinaGridRFDocker(Docker): 
    """Builds model."""

    self.base_dir = tempfile.mkdtemp()

    print("About to download trained model.")

    call(("wget http://deepchem.io.s3-website-us-west-1.amazonaws.com/trained_models/random_full_RF.tar.gz").split())

    call(("wget -c http://deepchem.io.s3-website-us-west-1.amazonaws.com/trained_models/random_full_RF.tar.gz").split())

    call(("tar -zxvf random_full_RF.tar.gz").split())

    call(("mv random_full_RF %s" % (self.base_dir)).split())

    self.model_dir = os.path.join(self.base_dir, "random_full_RF")
@@ -60,7 +60,7 @@ class VinaGridDNNDocker(object): 
    """Builds model."""

    self.base_dir = tempfile.mkdtemp()

    print("About to download trained model.")

    call(("wget http://deepchem.io.s3-website-us-west-1.amazonaws.com/trained_models/random_full_DNN.tar.gz").split())

    call(("wget -c http://deepchem.io.s3-website-us-west-1.amazonaws.com/trained_models/random_full_DNN.tar.gz").split())

    call(("tar -zxvf random_full_DNN.tar.gz").split())

    call(("mv random_full_DNN %s" % (self.base_dir)).split())

    self.model_dir = os.path.join(self.base_dir, "random_full_DNN")

deepchem/dock/pose_generation.py

+1 −1
Original line number Diff line number Diff line
@@ -67,7 +67,7 @@ class VinaPoseGenerator(PoseGenerator): 
      print("Vina not available. Downloading")

      # TODO(rbharath): May want to move this file to S3 so we can ensure it's

      # always available.

      wget_cmd = "wget http://vina.scripps.edu/download/autodock_vina_1_1_2_linux_x86.tgz"

      wget_cmd = "wget -c http://vina.scripps.edu/download/autodock_vina_1_1_2_linux_x86.tgz"

      call(wget_cmd.split())

      print("Downloaded Vina. Extracting")

      download_cmd = "tar xzvf autodock_vina_1_1_2_linux_x86.tgz"

deepchem/dock/tests/test_pose_scoring.py

+1 −1
Original line number Diff line number Diff line
@@ -25,7 +25,7 @@ class TestPoseScoring(unittest.TestCase): 
  """

  def setUp(self):

    """Downloads dataset."""

    call("wget http://deepchem.io.s3-website-us-west-1.amazonaws.com/featurized_datasets/core_grid.tar.gz".split())

    call("wget -c http://deepchem.io.s3-website-us-west-1.amazonaws.com/featurized_datasets/core_grid.tar.gz".split())

    call("tar -zxvf core_grid.tar.gz".split())

    self.core_dataset = dc.data.DiskDataset("core_grid/")

deepchem/feat/graph_features.py

+1 −1
Original line number Diff line number Diff line
@@ -110,7 +110,7 @@ def atom_features(atom, bool_id_feat=False): 
         'Sb', 'Sn', 'Ag', 'Pd', 'Co', 'Se', 'Ti', 'Zn', 'H',    # H?

         'Li', 'Ge', 'Cu', 'Au', 'Ni', 'Cd', 'In', 'Mn', 'Zr',

         'Cr', 'Pt', 'Hg', 'Pb', 'Unknown']) +

        one_of_k_encoding(atom.GetDegree(), [0, 1, 2, 3, 4, 5, 6]) +

        one_of_k_encoding(atom.GetDegree(), [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]) +

        one_of_k_encoding_unk(atom.GetTotalNumHs(), [0, 1, 2, 3, 4]) +

        one_of_k_encoding_unk(atom.GetImplicitValence(), [0, 1, 2, 3, 4, 5, 6]) +

        [atom.GetFormalCharge(), atom.GetNumRadicalElectrons()] +

CRA Git | Maintained and supported by SUSTech CRA and CCSE