<tool name="MMChIP-seq" id="peakcalling_MMChIP-seq">
  <description>can combine ChIP-seq libraries from different batches with different fragment sizes.</description>
  <command interpreter="command">/bin/bash $shscript</command>
  <inputs>
    <conditional name="genome_size_cond">
      <param name="genome_size" type="select" label="mappable genome size">
        <option value="2770000000">Human (hg18)</option>
        <option value="2790000000">Human (hg19)</option>
        <option value="1870000000">Mouse (mm8)</option>
        <option value="1910000000">Mouse (mm9)</option>
        <option value="90300000">C elegans (ce4)</option>
        <option value="90300000">C elegans (ce6)</option>
        <option value="119000000">Drosophila (dm2)</option>
        <option value="152000000">Drosophila (dm3)</option>
        <option value="OTHER">Other</option>
      </param>
      <when value="OTHER">
        <param name="genome_size_other" type="text" label="Custom Genome Size"/>
      </when>
      <when value="2770000000"/>
      <when value="2790000000"/>
      <when value="1870000000"/>
      <when value="1910000000"/>
      <when value="90300000"/>
      <when value="90300000"/>
      <when value="119000000"/>
      <when value="152000000"/>
    </conditional>
    <param name="pvalue" type="float" label="p-value cutoff for peak detection" value="0.00001">
      <validator type="in_range" max="1" min="0" message="Pvalue is out of range, Pvalue has to be between 0 to 1" />
    </param>
    <repeat name="more" title="more bed file">
      <param format="bed" name="tfile" type="data" label="select treat file"/>
      <param format="bed" name="cfile" type="data" label="select control file" />
      <param name="frag" type="integer" label="fragment size" value="0" />
    </repeat>
  </inputs>
  <outputs>
    <data format="bed" name="peakfile" label="MMChIP-seq peaks output" />
    <data format="txt" name="xlsfile" label="MMChIP-seq xls output" />
    <data format="wig" name="wigfile" label="MMChIP-seq wig output" />
    <data format="txt" name="log" label="MMChIP-seq log" />
  </outputs>
  <configfiles>
    <configfile name="shscript">
#!/bin/bash
#import os

#set $ad = chr(38)
#set $gt = chr(62)
#set $dollar = chr(36)

#set $genomeSize = $genome_size_cond.genome_size
#if $genome_size_cond.genome_size == "OTHER"
#set $genomeSize = $genome_size_cond.genome_size_other
#end if

#set $files = ""
#for $m in $more

#set $path = os.path.abspath($__app__.config.tool_path)

format=`$path/validation/fcfunc.py $m.tfile`
if [[ ${dollar}format != "passed" ]]; then
   echo ${dollar}format ${gt}${ad}2
   exit;
fi
format=`$path/validation/fcfunc.py $m.cfile`
if [[ ${dollar}format != "passed" ]]; then
   echo ${dollar}format ${gt}${ad}2
   exit;
fi

#set $temp = str($m.tfile)+","+str($m.cfile)+","+str($m.frag)
#set $files = $files + " " + str($temp)
#end for

paths=`python $path/peakcalling/GetPath.py $files`
echo ${dollar}paths 
MMChIP-seq ${dollar}paths $genomeSize $pvalue ${ad}${gt} $log
mv MMChIP-seq_peaks.bed $peakfile
mv MMChIP-seq_peaks.xls $xlsfile
zcat MMChIP-seq_MACS_wiggle/treat/*.gz ${gt} $wigfile
###mv MMChIP-seq_peaks.wig $wigfile
    </configfile>
  </configfiles>
  <help>
For ChIP-seq data, it is recommended to use MM-ChIP when inter-library
size difference is comparatively large. Otherwise, one can simply uses
MACS on the merged tag data (see more details in our paper, entitled
"MM-ChIP enables integrative analysis of cross-platform and
between-laboratory ChIP-chip or ChIP-seq data" published in Genome
Biology.

**TIP:** CAUTIONS: For ChIP-seq data,MM-ChIP was only tested on Illumina data
because of the lack of public ChIP-seq datasets for the same protein of
interest under similar biological conditions from technical platforms
other than Ilumina. For cross-platform data, different statistical models
may be needed to account for inter-platform variations besides variation
in inter-library size (see the discussion part in our paper).

This tool is for integrative analysis of ChIP-seq datasets. Original code is
written by Yiwen Chen. 

.. class:: warningmark

**NEED IMPROVEMENT**

-----

**Parameters**

- **mappable genome size** Effective genome size. It can be 1.0e+9 or 1000000000
- **P-VALUE** the p-value cutoff for peak detection
- **Add More BED file** click the *Add new More BED files* to add
  more. 
- **select treat file** the name of mapped read files for ChIP samples.
- **select control file** the name of the mapped read file for input samples.
  If there is no control sample, the 2nd column can be ommitted. 
- **fragment size** the fragment size(d) of individual datasets, which 
  is estimated by MACS program. 


-----

**Outputs**

- *bed file* This file contains the peak information.
- *xls file* This file contains peaks' detail information.
- *wig file* This file contains the score for each region.
  </help>
</tool>