Prediction of B-cell epitopes from amino acid sequences using deep neural networks. Supported on Linux and Mac.
-
Create a Conda environment with Python 3.7
conda create -n epidope python=3.7
-
Activate the Conda environment. You will need to activate the Conda environment in each terminal in which you want to use epidope.
conda activate epidope
-
Install epidope via conda
conda install -c flomock -c conda-forge -c pytorch epidope
-
Install other dependencies
pip install allennlp
Example
epidope -i /path_to/multifasta.fa -o ./results/ -t 0.8 -e /known/epitopes.txt
Options:
command | what it does |
---|---|
-i, --infile | Multi- or Singe- Fasta file with protein sequences. [required] |
-o, --outdir | Specifies output directory. Default = . |
--delim | Delimiter char for fasta header. Default = White space |
--idpos | Position of gene ID in fasta header. Zero based. Default = 0 |
-t, --threshold | Threshold for epitope score. Default = 0.818 |
-l, --slicelen | Length of the sliced predicted epitopes. Default = 15 |
-s, --slice_shiftsize | Shiftsize of the slices on predited epitopes. Default = 5 |
-p, --processes | Number of processes used for predictions. Default = #CPU-cores |
-e, --epitopes | File containing a list of known epitope sequences for plotting |
-n, --nonepitopes | File containing a list of non epitope sequences for plotting |
-h, --help | show this message and exit |