ARG-SHINE: improve antibiotic resistance class prediction by integrating Sequence Homology, functIoNal information, and deep convolutional nEural network

Requirements

InterProScan

Users need to install InterProScan before using ARG-SHINE. The documents for the InterProScan installation are available at https://github.com/ebi-pf-team/interproscan/wiki/HowToDownload.

Git LFS

Installation

Conda

We recommend using conda to run ARG-SHINE.

Obtain ARG-SHINE and create an environment

After installing Anaconda (or miniconda), fisrt obtain ARG-SHINE:

git lfs clone https://github.com/ziyewang/ARG_SHINE

Then simply create an argshine_env environment

cd ARG-SHINE
conda env create -f argshine_env.yaml
conda activate argshine_env

You can run ARG_SHINE against a fasta file (protein sequences) with the following commmand

bash argshine_prediction.sh fasta_file output_path PATH_to_interproscan
example: bash argshine_prediction.sh test_data/test.fasta test_data $HOME/interproscan-5.44-79.0

Contacts and bug reports

Please send bug reports or questions to Ziye Wang: zwang17@fudan.edu.cn

References

[1] Arango-Argoty, G., Garner, E., Pruden, A., Heath, L.S., Vikesland, P., Zhang, L.: Deeparg: a deep learning approach for predicting antibiotic resistance genes from metagenomic data. Microbiome 6(1), 1–15 (2018)

[2] Hamid, M.N., Friedberg, I.: Transfer learning improves antibiotic resistance class prediction. BioRxiv (2020)