pytoda - PaccMann PyTorch Dataset Classes
A python package that eases handling biochemical data for deep learning applications with pytorch.
pytoda ships via PyPI:
pip install pytodaPlease find the full documentation here.
For development setup, we recommend to work in a dedicated conda environment:
conda env create -f conda.ymlActivate the environment:
conda activate pytodaInstall in editable mode:
pip install -r dev_requirements.txt
pip install --user --no-use-pep517 -e .NOTE: The conda env ships with the official rdkit
implementation. But the pip installation overwrites the rdkit package with the
community-contributed PyPI package
called rdkit-pypi.
This is intentional because pytoda is distributed via PyPI too and most users will
thus depend on rdkit-pypi. Keep in mind that rdkit-pypi might contain bugs or
be outdated wrt rdkit. If developers experience issues with rdkit-pypi,
they can temporarily uninstall rdkit-pypi and will then fall back on using
the proper rdkit package.
For some examples on how to use pytoda see here
If you use pytoda in your projects, please cite the following:
@article{born2021datadriven,
author = {
Born, Jannis and Manica, Matteo and Cadow, Joris and Markert, Greta and
Mill,Nil Adell and Filipavicius, Modestas and Janakarajan, Nikita and
Cardinale, Antonio and Laino, Teodoro and
{Rodr{\'{i}}guez Mart{\'{i}}nez}, Mar{\'{i}}a
},
doi = {10.1088/2632-2153/abe808},
issn = {2632-2153},
journal = {Machine Learning: Science and Technology},
number = {2},
pages = {025024},
title = {{
Data-driven molecular design for discovery and synthesis of novel ligands:
a case study on SARS-CoV-2
}},
url = {https://iopscience.iop.org/article/10.1088/2632-2153/abe808},
volume = {2},
year = {2021}
}
@article{born2021paccmannrl,
title = {
PaccMann$^{RL}$: De novo generation of hit-like anticancer molecules from
transcriptomic data via reinforcement learning
},
journal = {iScience},
volume = {24},
number = {4},
year = {2021},
issn = {2589-0042},
doi = {https://doi.org/10.1016/j.isci.2021.102269},
url = {https://www.cell.com/iscience/fulltext/S2589-0042(21)00237-6},
author = {
Jannis Born and Matteo Manica and Ali Oskooei and Joris Cadow and Greta Markert
and Mar{\'\i}a Rodr{\'\i}guez Mart{\'\i}nez}
}
}