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:


Recommended: set up an environment

We recomment setting up an isolated conda environment:

conda create -n my_env python=3.6
conda activate my_env

or, alternatively, a virtualenv:

virtualenv --system-site-packages my_env
source my_env/bin/activate

With conda (recommended)

install with bioconda

You can install DeePaC-vir with bioconda. Set up the bioconda channel first, and then:

conda install deepacvir

DeePaC will be installed automatically.

With pip

You can also install DeePaC-vir with pip:

pip install deepacvir

Note: TensorFlow 2.0 is not yet supported.

GPU support

To use GPUs, you need to install the GPU version of TensorFlow. In conda, install tensorflow-gpu from the defaults channel before deepac:

conda remove tensorflow
conda install -c defaults tensorflow-gpu=1.15 
conda install deepacvir

DeePaC will be installed automatically. Note: TensorFlow 2.0 is not yet supported.

If you're using pip, you need to install CUDA and CuDNN first (see TensorFlow installation guide for details). Then you can do the same as above:

pip uninstall tensorflow
pip install tensorflow-gpu==1.15


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 on a GPU
deepac-vir test -a -g 1

# Predict using a rapid CNN (trained on VHDB data) using a GPU
deepac-vir predict -r -g 1 input.fasta
# Predict using a sensitive LSTM (trained on VHDB data) using a GPU
deepac-vir predict -s -g 1 input.fasta

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

Release history Release notifications

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 0.1.0
Filename, size File type Python version Upload date Hashes
Filename, size deepacvir-0.1.0-py3-none-any.whl (34.8 MB) File type Wheel Python version py3 Upload date Hashes View
Filename, size deepacvir-0.1.0.tar.gz (34.8 MB) File type Source Python version None Upload date Hashes View

Supported by

Pingdom Pingdom Monitoring Google Google Object Storage and Download Analytics Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page