DeepChem is an open-source library that democratizes deep learning applications in drug discovery, quantum chemistry, materials science, and biology.
Democratizing Deep-Learning for Drug Discovery, Quantum Chemistry, Materials Science and Biology
DeepChem is primarily used by researchers and developers in pharmaceutical and materials science fields to build, train, and deploy deep learning models for molecular and biological data analysis. It enables the application of AI to accelerate drug discovery, chemical property prediction, and biological research through a comprehensive and accessible toolchain.
DeepChem requires Python 3.7 to 3.10 and several scientific Python packages as mandatory dependencies. GPU support requires prior installation of CUDA and the respective deep learning framework's GPU version. Users should consult the soft requirements documentation if encountering import errors related to optional dependencies.
Install stable version via pip: pip install deepchem
Or install via conda: conda install -c conda-forge deepchem
For TensorFlow support: pip install deepchem[tensorflow]
For PyTorch support: pip install deepchem[torch]
For JAX support: pip install deepchem[jax]
Ensure CUDA is installed for GPU support before installing deep learning frameworks
Install TensorFlow, PyTorch, or JAX GPU versions following their official instructions prior to DeepChem installationpip install deepchem
Installs the stable version of DeepChem with default dependencies
pip install deepchem[tensorflow]
Installs DeepChem with TensorFlow dependencies for model usage
pip install deepchem[torch]
Installs DeepChem with PyTorch dependencies for model usage
pip install deepchem[jax]
Installs DeepChem with JAX dependencies for model usage
conda install -c conda-forge deepchem
Installs DeepChem using conda package manager from conda-forge channel