DeepChem aims to provide a high quality open-source toolchain that democratizes the use of deep-learning in drug discovery, materials science, and quantum chemistry. DeepChem is a package developed by the Pande group at Stanford and originally created by Bharath Ramsundar.

• Requirements
• Installation from Source
• FAQ
• Getting Started
  • Input Formats
  • Data Featurization
• Contributing to DeepChem
  • Code Style Guidelines
  • Documentation Style Guidelines
• DeepChem Publications
• Examples
• About Us

• openbabel
• pandas
• rdkit
• boost
• joblib
• sklearn
• numpy
• keras
• six
• dill
• ipyparallel
• mdtraj
• tensorflow

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.

1. Download the 64-bit Python 2.7 or Python 3.5 versions of Anaconda for linux here.

   Follow the installation instructions

2. openbabel

   conda install -c omnia openbabel=2.4.0

3. pandas

   conda install pandas 

4. rdkit

   conda install -c omnia rdkit

5. boost

   conda install -c omnia boost=1.59.0

6. joblib

   conda install joblib 

7. keras

   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

   export KERAS_BACKEND=tensorflow

   See keras docs for more details and alternate methods of setting backend.

8. six

   conda install six

9. dill

   conda install dill

10. ipyparallel

    conda install ipyparallel

11. mdtraj

conda install -c omnia mdtraj

12. scikit-learn

    conda install scikit-learn 

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 work:

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

14. h5py:

    conda install h5py
    

15. deepchem: Clone the deepchem github repo:

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

    cd into the deepchem directory and execute

    python setup.py install

16. To run test suite, install nosetests:

    pip install nose --user

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

    which nosetests 

    You might need to uninstall a system install of nosetests if there is a conflict.

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

    nosetests -v deepchem --nologcapture 

    Note that the full test-suite uses up a fair amount of memory. Try running tests for one submodule at a time if memory proves an issue.

1. Question: I'm seeing some failures in my test suite having to do with MKL Intel MKL FATAL ERROR: Cannot load libmkl_avx.so or libmkl_def.so.

   Answer: This is a general issue with the newest version of scikit-learn enabling MKL by default. This doesn't play well with many linux systems. See BVLC/caffe#3884 for discussions. The following seems to fix the issue

   conda install nomkl numpy scipy scikit-learn numexpr
   conda remove mkl mkl-service

2. Question: The test suite is core-dumping for me. What's up?

   [rbharath]$ nosetests -v deepchem --nologcapture
   Illegal instruction (core dumped)
   

   Answer: This is often due to openbabel issues on older linux systems. Open ipython and run the following

   In [1]: import openbabel as ob
   

   If you see a core-dump, then it's a sign there's an issue with your openbabel install. Try reinstalling openbabel from source for your machine.

The first step to getting started is looking at the examples in the examples/ directory. Try running some of these examples on your system and verify that the models train successfully. Afterwards, to apply deepchem to a new problem, try starting from one of the existing examples and modifying it step by step to work with your new use-case.

Accepted input formats for deepchem include csv, pkl.gz, and sdf files. For example, with a csv input, in order to build models, we expect the following columns to have entries for each row in the csv file.

1. A column containing SMILES strings [1].
2. A column containing an experimental measurement.
3. (Optional) A column containing a unique compound identifier.

Here's an example of a potential input file.

Here the "smiles" column contains the SMILES string, the "measured log solubility in mols per litre" contains the experimental measurement and "Compound ID" contains the unique compound identifier.

[2] Anderson, Eric, Gilman D. Veith, and David Weininger. "SMILES, a line notation and computerized interpreter for chemical structures." US 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 deechem featurization class DataFeaturizer. Instances of this class must be passed a Featurizer object. deepchem provides a number of different subclasses of Featurizer for convenience:

We actively encourage community contributions to DeepChem. The first place to start getting involved is by running our examples locally. Afterwards, we encourage contributors to give a shot to improving our documentation. While we take effort to provide good docs, there's plenty of room for improvement. All docs are hosted on Github, either in this README.md file, or in the docs/ directory.

Once you've got a sense of how the package works, we encourage the use of Github issues to discuss more complex changes, raise requests for new features or propose changes to the global architecture of DeepChem. Once consensus is reached on the issue, please submit a PR with proposed modifications. All contributed code to DeepChem will be reviewed by a member of the DeepChem team, so please make sure your code style and documentation style match our guidelines!

DeepChem broadly follows the Google Python Style Guide. In terms of practical changes, the biggest effect is that all code uses 2-space indents instead of 4-space indents. We encourage new contributors to make use of pylint. Aim for a score of at least 8/10 on contributed files.

DeepChem uses NumPy style documentation. Please follow these conventions when documenting code, since we use Sphinx+Napoleon to automatically generate docs on deepchem.io.

1. Computational Modeling of β-secretase 1 (BACE-1) Inhibitors using Ligand Based Approaches

DeepChem is a package by the Pande group at Stanford. DeepChem was originally created by Bharath Ramsundar, and has grown through the contributions of a number of undergraduate, graduate, and postdoctoral researchers working with the Pande lab.