Skip to main content

Detecting novel human viruses from DNA reads with reverse-complement neural networks.

Project description


DeePaC-vir is a plugin for DeePaC (see below) shipping built-in models for novel human virus detection directly from NGS reads. For details, see our preprint on bioRxiv:


DeePaC is a python package and a CLI tool for predicting labels (e.g. pathogenic potentials) from short DNA sequences (e.g. Illumina reads) with interpretable reverse-complement neural networks. For details, see our preprint on bioRxiv: and the paper in Bioinformatics: For details regarding the interpretability functionalities of DeePaC, see the preprint here:

Documentation can be found here: See also the main repo here:


With Bioconda (recommended)

install with bioconda

You can install DeePaC with bioconda. Set up the bioconda channel first (channel ordering is important):

conda config --add channels defaults
conda config --add channels bioconda
conda config --add channels conda-forge

We recommend setting up an isolated conda environment:

# python 3.6, 3.7 and 3.8 are supported
conda create -n my_env python=3.8
conda activate my_env

and then:

# For GPU support (recommended)
conda install tensorflow-gpu deepacvir
# Basic installation (CPU-only)
conda install deepacvir

With pip

We recommend setting up an isolated conda environment (see above). Alternatively, you can use a virtualenv virtual environment (note that deepac requires python 3):

# use -p to use the desired python interpreter (python 3.6 or higher required)
virtualenv -p /usr/bin/python3 my_env
source my_env/bin/activate

You can then install DeePaC with pip. For GPU support, you need to install CUDA and CuDNN manually first (see TensorFlow installation guide for details). Then you can do the same as above:

# For GPU support (recommended)
pip install tensorflow-gpu
pip install deepacvir

Alternatively, if you don't need GPU support:

# Basic installation (CPU-only)
pip install deepacvir


DeePaC-vir may be used exactly as the base version of DeePaC. To use the plugin, substitute the deepac command for deepac-vir. Visit for a DeePaC readme describing basic usage.

For example, you can use the following commands:

# See help
deepac-vir --help

# Run quick tests (eg. on CPUs)
deepac-vir test -q
# Full tests
deepac-vir test -a

# Predict using a rapid CNN (trained on VHDB data)
deepac-vir predict -r input.fasta
# Predict using a sensitive LSTM (trained on VHDB data)
deepac-vir predict -s input.fasta

More examples are available at

Supplementary data and scripts

Training, validation and test datasets are available here: In the main DeePaC repository ( you can find the R scripts and data files used in the papers for dataset preprocessing and benchmarking.

Cite us

If you find DeePaC useful, please cite:

    author = {Bartoszewicz, Jakub M and Seidel, Anja and Rentzsch, Robert and Renard, Bernhard Y},
    title = "{DeePaC: predicting pathogenic potential of novel DNA with reverse-complement neural networks}",
    journal = {Bioinformatics},
    year = {2019},
    month = {07},
    issn = {1367-4803},
    doi = {10.1093/bioinformatics/btz541},
    url = {},
    eprint = {},

@article {Bartoszewicz2020.01.29.925354,
    author = {Bartoszewicz, Jakub M. and Seidel, Anja and Renard, Bernhard Y.},
    title = {Interpretable detection of novel human viruses from genome sequencing data},
    elocation-id = {2020.01.29.925354},
    year = {2020},
    doi = {10.1101/2020.01.29.925354},
    publisher = {Cold Spring Harbor Laboratory},
    URL = {},
    eprint = {},
    journal = {bioRxiv}

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for deepacvir, version 0.2.2
Filename, size File type Python version Upload date Hashes
Filename, size deepacvir-0.2.2-py3-none-any.whl (34.8 MB) File type Wheel Python version py3 Upload date Hashes View
Filename, size deepacvir-0.2.2.tar.gz (34.8 MB) File type Source Python version None Upload date Hashes View

Supported by

AWS AWS Cloud computing Datadog Datadog Monitoring DigiCert DigiCert EV certificate Facebook / Instagram Facebook / Instagram PSF Sponsor Fastly Fastly CDN Google Google Object Storage and Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Salesforce Salesforce PSF Sponsor Sentry Sentry Error logging StatusPage StatusPage Status page