framework for developing sequence-level deep learning networks
You have found Selene, a Python library and command line interface for training deep neural networks from biological sequence data such as genomes.
Selene is a Python 3+ package. We recommend using it with Python 3.6 or above.
Installing selene with Anaconda (for Linux):
conda install -c bioconda selene-sdk
Installing selene with pip:
pip install selene-sdk
Installing selene from source:
First, download the latest commits from the source repository (or download the latest tagged version of Selene for a stable release):
git clone https://github.com/FunctionLab/selene.git
setup.py script requires NumPy. Please make sure you have this already installed.
If you plan on working in the
selene repository directly, we recommend setting up a conda environment using
selene-gpu.yml (if CUDA is enabled on your machine) and activating it.
Selene contains some Cython files. You can build these by running
python setup.py build_ext --inplace
Otherwise, if you would like to locally install Selene, you can run
python setup.py install
docopt before running the command-line script
selene_cli.py provided in the repository.
Selene is composed of a command-line interface and an API (the
selene-sdk Python package).
Users supply their data, model architecture, and configuration parameters, and Selene runs the user-specified operations (training, evaluation, prediction) for that sequence-based model.
For a more detailed overview of the components in the Selene software development kit (SDK), please consult the page here.
Tutorials and examples
Tutorials for selene are available here.
The documentation for selene is available here.