<tool id="pdaug_word_vector_model" name="PDAUG Word Vector Model" python_template_version="3.7" version="0.1.0">
  <description>Generates the skip-gram model</description>
  <requirements>
    <requirement type="package" version="1.0.3">pandas</requirement>
    <requirement type="package" version="1.76">biopython</requirement> 
    <requirement type="package" version="3.5">nltk</requirement> 
    <requirement type="package" version="3.8.0">gensim</requirement>
    <requirement type="package" version="0.23.1">scikit-learn</requirement>
    <requirement type="package" version="1.18.4">numpy</requirement>
  </requirements>
  <stdio>
    <exit_code range="1" level="fatal" />
  </stdio>
    <command detect_errors="exit_code"><![CDATA[

        python '$__tool_directory__/PDAUG_Word_Vector_Model.py' -I '$input' -M '$meanCount' -W '$window' -O '$OutFile' --SG '$sg'
        
    ]]></command>

  <inputs>
    <param name="input" type="data" label="Input fasta file" format="fasta" argument= "--Input" help="Input fasta file with peptides"/>
    <param name="meanCount" type="integer" label="Mean Count" value="0" format="fasta" argument= "--min_count" help="Ignores a all words with total frequency lower than this"/>
    <param name="window" type="integer" label="window" value="5" argument="--window" help="Maximum distance between the current and predicted word within a sentence"/>
    <param name="sg" type="select" label="Select algorithm" help="Training algorithm skip-gram or  CBOW.">
        <option value="skip-gram">Skip-gram</option>
        <option value="CBOW" >CBOW</option>
    </param>

  </inputs>

  <outputs>
    <data name='OutFile' format='txt' label="${tool.name} on $on_string - (text)" />
  </outputs>

  <tests>
    <test>
      <param name="input" value="test.fasta"/>
      <param name="meanCount" value="0"/>
      <param name="window" value="5"/>
      <output name="OutFile" value="model.txt" lines_diff="2268" />
    </test>
  </tests>
    <help><![CDATA[
.. class:: infomark

**What it does**

This tool calculates the skip-gram model which is a neural network where the inputs and outputs of the network are one-hot vectors calculated based on training data that contains input word and output word. 

-----

**Inputs**
    * **--Input** Fasta file with protein sequences.
    * **--min_count** Ignores all words with total frequency lower than this 
    * **--window** Maximum distance between the current and predicted word within a sentence, accepts integer value.
    * **--SG** Select training algorithm skip-gram or CBOW.

-----

**Outputs**
    * **--OutFile** Return "model.txt" model 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">
  @inproceedings{rehurek_lrec,
      title = {{Software Framework for Topic Modelling with Large Corpora}},
      author = {Radim {\v R}eh{\r u}{\v r}ek and Petr Sojka},
      booktitle = {{Proceedings of the LREC 2010 Workshop on New
           Challenges for NLP Frameworks}},
      pages = {45--50},
      year = 2010,
      month = May,
      day = 22,
      publisher = {ELRA},
      address = {Valletta, Malta},
      url={http://is.muni.cz/publication/884893/en},
      language={English}
    }
  </citation>

  <citation type="bibtex">
    @article{Md_Nafiz, 
      title= {Identifying antimicrobial peptides using word embedding with deep recurrent neural networks},
      volume={35},
      DOI={https://doi.org/10.1093/bioinformatics/bty937},
      issue={12},
      year={2018},
      pages={2009-2016},
      journal={Europe PMC}, 
      author={Hamid, Md-Nafiz and  Friedberg,  Iddo}
    }

  </citation>
</citations>
</tool>