view dnp_binary_strings.xml @ 0:611156829647 draft default tip

"planemo upload commit 1a32efb8343938e8d49190003f251c78b5a58225-dirty"

<tool id="dnp_binary_strings" name="Binary strings from fasta" version="0.1.0">
    <requirements>
        <requirement type="package" version="1.0">dnp-binstrings</requirement>
    </requirements>
    <command detect_errors="exit_code" interpreter="sh"><![CDATA[
        dnp-binary-strings.sh '$input1' '$input2' '$output1'
    ]]></command>
    <inputs>
      <param type="data" name="input1" format="fasta" label="From fasta" />
      <param name="input2" type="text" value="AA AC" label="Dinucleotides" />
    </inputs>
    <outputs>
        <data name="output1" format="tabular" />
    </outputs>
    <tests>
        <test>
            <param name="input1" value="seq4.fasta"/>
            <param name="input2" value="AA AC"/>
            <output name="output1" file="seq4.tabular"/>
        </test>
    </tests>
    <help><![CDATA[

Description::


   Convert fasta sequences to a binary sequence of 01 
   in which ones indicate a presence of a given 
   dinucleotide at that position.

   Each input fasta sequence has a corresponding output
   row with tab separated columns- binary string, dinucleotide,  
   original fasta string, number of the dinucleotide occurrences


Example::

   Input fasta:
      chr9:42475963-42476182 
      CCAGGCAGACCCCATA
   
   Output tabular:
      100000000111000 CC chr9:42475963-42476182 CCAGGCAGACCCCATA 4


    ]]></help>
    <citations>
        <citation type="bibtex">
@article{pranckeviciene2020nucleosome,
  title={Nucleosome positioning sequence patterns as packing or regulatory. S1 Appendix},
  author={Pranckeviciene, Erinija and Hosid, Sergey and Liang, Nathan and Ioshikhes, Ilya},
  journal={PLoS computational biology},
  volume={16},
  number={1},
  pages={e1007365},
  year={2020},
  publisher={Public Library of Science},
  url = {https://doi.org/10.1371/journal.pcbi.1007365}
}</citation>
    </citations>
</tool>