Merge pull request #615 from LRParser/master

Installation from source is the only currently supported format. ```deepchem``` currently supports both Python 2.7 and Python 3.5, but is not supported on any OS'es except 64 bit linux. Please make sure you follow the directions below precisely. While you may already have system versions of some of these packages, there is no guarantee that `deepchem` will work with alternate versions than those specified below.

Note that when using Ubuntu 16.04 server or similar environments, you may need to ensure libxrender is provided via e.g.:

```bash

sudo apt-get install -y libxrender-dev

```

### Using a conda environment

You can install deepchem in a new conda environment using the conda commands in scripts/install_deepchem_conda.sh

# Setting up PDBBind example

First, ensure that you are in the correct environment, and then download the pdbbind reference database:

```bash

source activate deepchem

(deepchem) user@server:~/deepchem/examples/pdbbind$ ./get_pdbbind.sh

```

You will see a large number of directories created with PDB (protein) and SDF (ligand) files, for instance:

```bash

v2015/3d1g/3d1g_ligand.mol2

v2015/3d1g/3d1g_pocket.pdb

v2015/3d1g/3d1g_protein.pdb

v2015/3d1g/3d1g_ligand.sdf

```

Next, you can train the Random Forest-based classifier via:

```bash

(deepchem) ubuntu@ip-172-31-12-186:~/deepchem/examples/pdbbind$ python pdbbind_rf.py 

```

TODO: Add notes about how to expand the v2015 dataset, e.g. to add protein 14HR as associated with NF2 to the analysis