<tool id="pdaug_peptide_ngrams" name="PDAUG Peptide Ngrams" version="0.1.0" python_template_version="2.7">
	<description>Counts n-grams in the entire sequence set and fitting their distribution with the power-law distribution (Zipf’s law)</description>
  
    <requirements>
      <requirement type="package" version="2.7.18">python</requirement>
      <requirement type="package" version="1.4.6">powerlaw</requirement>
      <requirement type="package" version="0.2.4">quantiprot</requirement>
    </requirements>

    <command detect_errors="exit_code"><![CDATA[

        python2 '$__tool_directory__/PDAUG_Peptide_Ngrams.py' -f1 '$fasta1' -f2 '$fasta2'  --OutFile 'out.png'
             
    ]]></command>

    <inputs>
      <param name="fasta1" type="data" format="fasta" label="First fasta file" argument= "--fasta1" help="First fasta file"/>
      <param name="fasta2" type="data" format="fasta" label="Second fasta file" argument= "--fasta2" help="First fasta file"/>
    </inputs>

    <outputs>   
        <data name='output2' format='png' label="${tool.name} on $on_string - (PNG)" from_work_dir="out.png"/>
    </outputs>
 
    <tests>
        <test>
            <param name="fasta1" value="test1.fasta"/>
            <param name="fasta2" value="test2.fasta"/>
            <output name="output2" file="out.png"/>
        </test>
    </tests>

    <help><![CDATA[
.. class:: infomark

**What it does**

This tool counts n-grams in the entire  peptide sequence set and fitting their distribution with the power-law distribution (Zipf’s law) and plot the results.

-----

**Inputs**
    * **--InFile** Takes fasta file as input with peptide sequences. 

-----

**Outputs**
    * Returns html report file.]]></help>
<citations>
  <citation type="bibtex">
    @misc{PDAUGGITHUB, 
      author = {Joshi, Jayadev  and Blankenberg, Daniel}, 
      year = {2020}, 
      title ={PDAUG - a Galaxy based toolset for peptide library analysis, visualization, and machine learning modeling}, 
      publisher = {GitHub}, 
      journal = {GitHub repository}, 
      url =
      {https://github.com/jaidevjoshi83/pdaug.git}, 
      }
  </citation>
  <citation type="bibtex">
    @article{konopka_marciniak_dyrka_2017,
       title={Quantiprot - a Python package for quantitative analysis of protein sequences}, 
       volume={18},
       DOI={10.1186/s12859-017-1751-4}, 
       number={1}, 
       journal={BMC Bioinformatics},
       author={Konopka, Bogumił M. and Marciniak, Marta and Dyrka, Witold}, 
       year={2017}
     }
  </citation>
</citations>
</tool>