adding docs

    conda install -y -c conda-forge rdkit

Latest version

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

Deepchem provides support tensorflow, pytorch, jax and each require

a induvidual pip Installation.

For using general utilites like Molnet, Featurisers, Datasets, etc, then, you install deepchem via pip.  

.. code-block:: bash

    pip install deepchem

For using models with tensorflow dependencies, you install using

.. code-block:: bash

    pip install --pre deepchem[tensorflow]

For using models with Pytorch dependencies, you install using

.. code-block:: bash

    pip install --pre deepchem[torch]

For using models with Jax dependencies, you install using

.. code-block:: bash

    pip install --pre deepchem[jax]

If `cuda` support is required, then make sure its installed and then install the NN library using the below links before installing deepchem

1. tensorflow - just cuda installed

2. pytorch - https://pytorch.org/get-started/locally/#start-locally

3. jax - https://github.com/google/jax#pip-installation-gpu-cuda

Nightly build version

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

    pytest -m "not slow" deepchem # optional

From source lightweight guide

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

**Installing via these steps will ensure you are installing from the source**.

**Prerequisite**

- Shell: Bash, Zsh, PowerShell

- Conda: >4.6

First, please clone the deepchem repository from GitHub.

.. code-block:: bash

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

    cd deepchem

We would advise all users to use with a conda environment, following below-

.. code-block:: bash

    conda create --name deepchem python=3.7

    conda activate deepchem

    pip install -e .

If one also wants to build the tensorflow environment, add this

.. code-block:: bash

    pip install -e .[tensorflow]

If one also wants to build the Pytorch environment, add this

.. code-block:: bash

    pip install -e .[torch]

If one also wants to build the Jax environment, add this

.. code-block:: bash

    pip install -e .[tensorflow]

DeepChem has soft requirements, which can be installed on the fly during development but if you would a install

all the packages at once, then take a look `deepchem/requirement/`_

.. _`DeepChem Tutorials`: https://github.com/deepchem/deepchem/tree/master/examples/tutorials

.. _`forum post`: https://forum.deepchem.io/t/getting-deepchem-running-in-colab/81/7

.. _`DockerHub`: https://hub.docker.com/repository/docker/deepchemio/deepchem