Updated installation direction

deepchem

=============

Deep Learning Toolchain for Cheminformatics and Protein Analysis

Deep Learning Toolchain for Drug Discovery and Quantum Chemistry

Requirements

------------

* [openbabel](http://openbabel.org/wiki/Main_Page)

* [pandas](http://pandas.pydata.org/)

* [rdkit](http://www.rdkit.org/docs/Install.html)

* [boost](http://www.boost.org/)

* [joblib](https://pypi.python.org/pypi/joblib)

* [sklearn](https://github.com/scikit-learn/scikit-learn.git)

* [numpy](https://store.continuum.io/cshop/anaconda/)

* [theano](http://deeplearning.net/software/theano/)

* [keras](http://keras.io)

* [six](https://pypi.python.org/pypi/six)

* [dill](https://pypi.python.org/pypi/dill)

* [ipyparallel](https://ipyparallel.readthedocs.io/en/latest/)

* [mdtraj](http://mdtraj.org/)

* [tensorflow](https://www.tensorflow.org/)

Linux (64-bit) Installation 

------------------

---------------------------

```deepchem``` currently requires Python 2.7

```deepchem``` currently requires Python 2.7, and is not supported on any platforms except 64 bit linux. Please make sure you follow the directions below precisely. While you may already have system version of some of these packages, there is no guarantee that `deepchem` will work with alternate versions than those specified below. This is especially true for the `keras` library, where `deepchem` is known not to work with the latest default version.

###Anaconda 2.7

1. Anaconda 2.7

   Download the **64-bit Python 2.7** version of Anaconda for linux [here](https://www.continuum.io/downloads#_unix).  

   Follow the [installation instructions](http://docs.continuum.io/anaconda/install#linux-install)

###openbabel

2. `openbabel`

   ```bash

   conda install -c omnia openbabel

   ```  

Follow the onscreen installation instructions

###rdkit

3. `pandas`

   ```bash

   conda install pandas 

   ```

4. `rdkit`

   ```bash

   conda install -c omnia rdkit

   ```

5. `boost`

   ```bash

   conda install -c omnia boost=1.59.0

   ```

6. `joblib`

   ```bash

   conda install joblib 

   ```

7. `theano`

   ```bash

   conda install -c omnia theano

   ```

8. `keras`

   ```bash

   conda install -c omnia keras

   ```

9. `six`

   ```bash

   conda install six

   ```

10. `dill`

    ```bash

    conda install dill

    ```

Follow the onscreen installation instructions

###keras

Clone the keras git repository

11. `ipyparallel`

    ```bash

git clone https://github.com/fchollet/keras.git

    conda install ipyparallel

    ```

Cd into the keras directory and execute

12. `mdtraj`

   ```bash

python setup.py install

   conda install -c omnia mdtraj

   ```

###deepchem

Clone the deep_chem git repository

13. `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 perform the

    installation.

    ```

    conda install -c https://conda.anaconda.org/jjhelmus tensorflow

    ```

14. `deepchem`: Only installation from github is supported for the time being. Start by cloning the `deepchem` github repo:

    ```bash

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

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

    ```

    `cd` into the `deepchem` directory and execute

    ```bash

    python setup.py install

    ```

Cd into the deepchem directory and execute 

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

    ```bash

python setup.py develop

    nosetests -v deepchem --nologcapture 

    ```