<tool id="mismatch_frequencies" name="Mismatch Frequencies" version="0.0.5" hidden="false" >
  <description>Analyze mismatch frequencies in BAM/SAM alignments</description>
  <requirements>
    <requirement type="package" version="0.8.1">pysam</requirement>
    <requirement type="package" version="0.14.1">pandas</requirement>
    <requirement type="package" version="1.4">matplotlib</requirement>
  </requirements>
  <command interpreter="python">mismatch_frequencies.py --input 
		#for i in $rep
			"$i.input_file" 
		#end for
		--name 
		#for i in $rep
			"$i.input_file.name"
		#end for
		 --output_pdf $output_pdf --output_tab $output_tab --min $min_length --max $max_length
                 --n_mm $number_of_mismatches
                 --five_p $five_p
                 --three_p $three_p
  </command>
  <inputs>
    <repeat name="rep" title="alignment files" min="1">
      <param name="input_file" type="data" format="bam,sam" label="Alignment file" help="The input alignment file(s) for which you want to calculate mismatch frequencies."/>
    </repeat>
    <param name="number_of_mismatches" label="Maximum number of allowed mismatches per read" help="Discard reads with more than the chosen number of mismatches from the frequency calculation" type="integer" value="3"/>
    <param name="min_length" label="Minumum read length to analyse" type="integer" value="21"/>
    <param name="max_length" label="Maximum read length to analyse" type="integer" value="21"/>
    <param name="five_p" label="Ignore mismatches in the first N nucleotides of a read" type="integer" value="0"/>
    <param name="three_p" label="Ignore mismatches in the last N nucleotides of a read" help="useful to discriminate between tailing events and editing events" type="integer" value="3"/>
  </inputs>
  <outputs>
    <data format="tabular" name="output_tab" />
    <data format="pdf" name="output_pdf" />
  </outputs>
  <tests>
    <test>
      <param name="rep_0|input_file" value="3mismatches_ago2ip_s2.bam" ftype="bam" />
      <param name="rep_1|input_file" value="3mismatches_ago2ip_ovary.bam" ftype="bam" />
      <param name="number_of_mismatches" value="1" />
      <param name="min_length" value="21" />
      <param name="max_length" value="21" />
      <output name="tabular" file="mismatch.tab" ftype="tabular"/>
    </test>
  </tests>
  <help>

.. class:: infomark


***What it does***

This tool reconstitues for each aligned read of an alignment file in SAM/BAM format whether
a mismatch is annotated in the MD tag, and if that is the case counts the identity of the 
mismatch relative to the reference sequence. The output is a PDF document with the calculated
frequency for each mismatch that occured relative to the total number of valid reads and a table
with the corresponding values. Read length can be limited to a specific read length, and 5 prime and 
3 prime-most nucleotides of a read can be ignored.

----

.. class:: warningmark

***Warning***

This tool skips all read that have insertions and has been tested only with bowtie and bowtie2
generated alignment files.

Written by Marius van den Beek, m.vandenbeek at gmail . com
  </help>
</tool>