<tool name="MA2C" id="peakcalling_ma2c">
  <description>Peak Calling for ChIP-chip (Nimblegen)</description>
  <command interpreter="command">/bin/bash $shscript</command>
  <inputs>
    <repeat name="replicates" title="Replicate">
      <param name="tfile" type="data" label="Treatment file"/>
      <param name="cfile" type="data" label="Control file"/>
    </repeat>
    <param name="ndf" type="data" label="NDF file"/>
    <param name="pos" type="data" label="POS file" optional="true"/>
    <param name="bandwidth" type="text" label="Bandwidth" value="300">
      <validator type="in_range" max="1000" min="100" message="Bandwidth is out of range, Bandwidth has to be between 100 to 1000" />
    </param>
    <param name="max_gap" type="text" label="Max Gap" value="250">
      <validator type="in_range" max="1000" min="100" message="Max_Gap is out of range, Max_Gap has to be between 100 to 1000" />
    </param>
    <param name="min_probes" type="text" label="Min Probes" value="5">
      <validator type="in_range" max="10" min="2" message="Min_Probes is out of range, Min_Probes has to be between 2 to 10" />
    </param>
    <conditional name="threshold">
      <param name="method1" type="select" label="Threshold method">
        <option value="Pvalue">Pvalue</option>
        <option value="FDR">FDR</option>
      </param>
      <when value="Pvalue">
        <param name="value" type="text" label="Value (e.g. P=0.00001)" 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>
      </when>
      <when value="FDR">
        <param name="value" type="text" label="Value (e.g. FDR=5 for 5%)" value="5">
          <validator type="in_range" max="100" min="0" message="FDR is out of range, FDR has to be between 0 to 100" />
        </param>
      </when>
    </conditional>
    <conditional name="normalization">
      <param name="method2" type="select" label="Normalization Method">
        <option value="Robust">Robust</option>
        <option value="Simple">Simple</option>
      </param>
      <when value="Robust">
        <!--NOTE: C value only when Robust-->
        <param name="cvalue" type="text" label="C value" value="2">
          <validator type="in_range" max="5" min="2" message="The C value for the robust normalization is out of range, the parameter has to be between 2 to 5" />
        </param>
      </when>
      <when value="Simple"></when>
    </conditional>
  </inputs>
  <configfiles>
    <configfile name="tag_file">
[sample]
#set $tmp = ""
#set $tmp2 = ""
#set $tmp3 = ""
#for $i, $rep in enumerate($replicates)
#set $tmp = $tmp + str($rep.tfile) + " "
#set $tmp2 = $tmp2 + str($rep.cfile) + " "
#set $tmp3 = $tmp3 + "chip_id_foo "
#end for
IP_FILE = $tmp
INPUT_FILE = $tmp2
NDF_FILE = $ndf
##POS files are optional
#if $pos.name != "None": 
POS_FILE = $pos
#end if
DESIGN_ID = design_id_foo
CHIP_ID = $tmp3

[peak detection]
METHOD = $threshold.method1
BANDWIDTH = $bandwidth
MAX_GAP = $max_gap
MIN_PROBES = $min_probes
THRESHOLD = $threshold.value

[normalization]
METHOD = $normalization.method2
##C values are only relevant w/ Robust
#if $normalization.method2 == "Robust": 
C = $normalization.cvalue
#end if
    </configfile>
    <configfile name="shscript">
#!/bin/bash

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

#for $i, $rep in enumerate($replicates)
#set $tmp1 = str($rep.tfile)
#set $tmp2 = str($rep.cfile)

    tfilesize=`du -b $tmp1 | awk '{print ${dollar}1}'`
    cfilesize=`du -b $tmp2 | awk '{print ${dollar}1}'`
    if [[ ${dollar}tfilesize -gt 1048576000 ]];then
        echo "treatment file is too big! 1G is the maximum!" ${gt}${ad}2
        exit;
    fi

    if [[ ${dollar}cfilesize -gt 1048576000 ]];then
        echo "control file is too big! 1G is the maximum!" ${gt}${ad}2
        exit;
    fi
#end for
ndfsize=`du -b $ndf | awk '{print ${dollar}1}'`

if [[ ${dollar}ndfsize -gt 1048576000 ]];then
    echo "ndf file is too big! 1G is the maximum!" ${gt}${ad}2
    exit;
fi

if [ $pos != "None" ];then
    possize=`du -b $pos | awk '{print ${dollar}1}'`
    
    if [[ ${dollar}possize -gt 1048576000 ]];then
        echo "pos file is too big! 1G is the maximum!" ${gt}${ad}2
        exit;
    fi
fi

mv $tag_file ${tag_file}.tag

ma2c `basename ${tag_file}`.tag ${ad}${gt} $log
mv MA2C_Output/`basename ${tag_file}`_peaks.bed $bedoutput
gunzip MA2C_Output/`basename ${tag_file}`_MA2Cscore.wig.gz
mv MA2C_Output/`basename ${tag_file}`_MA2Cscore.wig $wigoutput

    </configfile>
  </configfiles>
  <outputs>
    <data format="bed" name="bedoutput" />
    <data format="wig" name="wigoutput" />
    <data format="txt" name="log" label="MA2C job log" />
  </outputs>
  <tests>
    <test maxseconds="3600" name="TreatmentFile">
      <param name="tfile" value="ma2c_treatment_ce4.pair" />
      <param name="cfile" value="ma2c_control_ce4.pair" />
      <param name="ndf" value="ma2c_ndf_ce4.ndf" />
      <param name="pos" value="ma2c_pos_ce4.pos" />
      <param name="bandwidth" value="300" />
      <param name="max_gap" value="250" />
      <param name="min_probes" value="5" />
      <param name="method1" value="Pvalue" />
      <param name="value" value="0.001" />
      <param name="method2" value="Robust" />
      <param name="cvalue" value="2" />
      <output name="output" file="ma2c_1/sample_peaks.bed" />
      <output name="output" file="ma2c_1/sample_MA2Cscore.wig" lines_diff = "2" />
      <output name="output" file="ma2c_1/sample_log.bed" lines_diff = "100"/>
    </test>
    <test maxseconds="3600" name="ControlFile">
      <param name="tfile" value="ma2c_treatment_ce4.pair" />
      <param name="cfile" value="ma2c_control_ce4.pair" />
      <param name="ndf" value="ma2c_ndf_ce4.ndf" />
      <param name="pos" value="ma2c_pos_ce4.pos" />
      <param name="bandwidth" value="300" />
      <param name="max_gap" value="250" />
      <param name="min_probes" value="5" />
      <param name="method1" value="Pvalue" />
      <param name="value" value="0.001" />
      <param name="method2" value="Robust" />
      <param name="cvalue" value="2" />
      <output name="output" file="ma2c_2/sample_peaks.bed" />
      <output name="output" file="ma2c_2/sample_MA2Cscore.wig" lines_diff = "2" />
      <output name="output" file="ma2c_2/sample_log.bed" lines_diff = "100"/>
    </test>
    <test maxseconds="3600" name="NDFFile">
      <param name="tfile" value="ma2c_treatment_ce4.pair" />
      <param name="cfile" value="ma2c_control_ce4.pair" />
      <param name="ndf" value="ma2c_ndf_ce4.ndf" />
      <param name="pos" value="ma2c_pos_ce4.pos" />
      <param name="bandwidth" value="300" />
      <param name="max_gap" value="250" />
      <param name="min_probes" value="5" />
      <param name="method1" value="Pvalue" />
      <param name="value" value="0.001" />
      <param name="method2" value="Robust" />
      <param name="cvalue" value="2" />
      <output name="output" file="ma2c_3/sample_peaks.bed" />
      <output name="output" file="ma2c_3/sample_MA2Cscore.wig" lines_diff = "2" />
      <output name="output" file="ma2c_3/sample_log.bed" lines_diff = "100"/>
    </test>
    <test maxseconds="3600" name="POSFile">
      <param name="tfile" value="ma2c_treatment_ce4.pair" />
      <param name="cfile" value="ma2c_control_ce4.pair" />
      <param name="ndf" value="ma2c_ndf_ce4.ndf" />
      <param name="pos" value="ma2c_pos_ce4.pos" />
      <param name="bandwidth" value="300" />
      <param name="max_gap" value="250" />
      <param name="min_probes" value="5" />
      <param name="method1" value="Pvalue" />
      <param name="value" value="0.001" />
      <param name="method2" value="Robust" />
      <param name="cvalue" value="2" />
      <output name="output" file="ma2c_4/sample_peaks.bed" />
      <output name="output" file="ma2c_4/sample_MA2Cscore.wig" lines_diff = "2" />
      <output name="output" file="ma2c_4/sample_log.bed" lines_diff = "100"/>
    </test>
    <test maxseconds="3600" name="BandWidth">
      <param name="tfile" value="ma2c_treatment_ce4.pair" />
      <param name="cfile" value="ma2c_control_ce4.pair" />
      <param name="ndf" value="ma2c_ndf_ce4.ndf" />
      <param name="pos" value="ma2c_pos_ce4.pos" />
      <param name="bandwidth" value="300" />
      <param name="max_gap" value="250" />
      <param name="min_probes" value="5" />
      <param name="method1" value="Pvalue" />
      <param name="value" value="0.001" />
      <param name="method2" value="Robust" />
      <param name="cvalue" value="2" />
      <output name="output" file="ma2c_5/sample_peaks.bed" />
      <output name="output" file="ma2c_5/sample_MA2Cscore.wig" lines_diff = "2" />
      <output name="output" file="ma2c_5/sample_log.bed" lines_diff = "100"/>
    </test>
    <test maxseconds="3600" name="MaxGap">
      <param name="tfile" value="ma2c_treatment_ce4.pair" />
      <param name="cfile" value="ma2c_control_ce4.pair" />
      <param name="ndf" value="ma2c_ndf_ce4.ndf" />
      <param name="pos" value="ma2c_pos_ce4.pos" />
      <param name="bandwidth" value="300" />
      <param name="max_gap" value="250" />
      <param name="min_probes" value="5" />
      <param name="method1" value="Pvalue" />
      <param name="value" value="0.001" />
      <param name="method2" value="Robust" />
      <param name="cvalue" value="2" />
      <output name="output" file="ma2c_6/sample_peaks.bed" />
      <output name="output" file="ma2c_6/sample_MA2Cscore.wig" lines_diff = "2" />
      <output name="output" file="ma2c_6/sample_log.bed" lines_diff = "100"/>
    </test>
    <test maxseconds="3600" name="MinProbes">
      <param name="tfile" value="ma2c_treatment_ce4.pair" />
      <param name="cfile" value="ma2c_control_ce4.pair" />
      <param name="ndf" value="ma2c_ndf_ce4.ndf" />
      <param name="pos" value="ma2c_pos_ce4.pos" />
      <param name="bandwidth" value="300" />
      <param name="max_gap" value="250" />
      <param name="min_probes" value="5" />
      <param name="method1" value="Pvalue" />
      <param name="value" value="0.001" />
      <param name="method2" value="Robust" />
      <param name="cvalue" value="2" />
      <output name="output" file="ma2c_7/sample_peaks.bed" />
      <output name="output" file="ma2c_7/sample_MA2Cscore.wig" lines_diff = "2" />
      <output name="output" file="ma2c_7/sample_log.bed" lines_diff = "100"/>
    </test>
    <test maxseconds="3600" name="Pvalue">
      <param name="tfile" value="ma2c_treatment_ce4.pair" />
      <param name="cfile" value="ma2c_control_ce4.pair" />
      <param name="ndf" value="ma2c_ndf_ce4.ndf" />
      <param name="pos" value="ma2c_pos_ce4.pos" />
      <param name="bandwidth" value="300" />
      <param name="max_gap" value="250" />
      <param name="min_probes" value="5" />
      <param name="method1" value="Pvalue" />
      <param name="value" value="0.001" />
      <param name="method2" value="Robust" />
      <param name="cvalue" value="2" />
      <output name="output" file="ma2c_8/sample_peaks.bed" />
      <output name="output" file="ma2c_8/sample_MA2Cscore.wig" lines_diff = "2" />
      <output name="output" file="ma2c_8/sample_log.bed" lines_diff = "100"/>
    </test>
    <test maxseconds="3600" name="FDR">
      <param name="tfile" value="ma2c_treatment_ce4.pair" />
      <param name="cfile" value="ma2c_control_ce4.pair" />
      <param name="ndf" value="ma2c_ndf_ce4.ndf" />
      <param name="pos" value="ma2c_pos_ce4.pos" />
      <param name="bandwidth" value="300" />
      <param name="max_gap" value="250" />
      <param name="min_probes" value="5" />
      <param name="method1" value="FDR" />
      <param name="value" value="5" />
      <param name="method2" value="Robust" />
      <param name="cvalue" value="2" />
      <output name="output" file="ma2c_9/sample_peaks.bed" />
      <output name="output" file="ma2c_9/sample_MA2Cscore.wig" lines_diff = "2" />
      <output name="output" file="ma2c_9/sample_log.bed" lines_diff = "100"/>
    </test>
    <test maxseconds="3600" name="Robust">
      <param name="tfile" value="ma2c_treatment_ce4.pair" />
      <param name="cfile" value="ma2c_control_ce4.pair" />
      <param name="ndf" value="ma2c_ndf_ce4.ndf" />
      <param name="pos" value="ma2c_pos_ce4.pos" />
      <param name="bandwidth" value="300" />
      <param name="max_gap" value="250" />
      <param name="min_probes" value="5" />
      <param name="method1" value="Pvalue" />
      <param name="value" value="0.001" />
      <param name="method2" value="Robust" />
      <param name="cvalue" value="2" />
      <output name="output" file="ma2c_10/sample_peaks.bed" />
      <output name="output" file="ma2c_10/sample_MA2Cscore.wig" lines_diff = "2" />
      <output name="output" file="ma2c_10/sample_log.bed" lines_diff = "100"/>
    </test>
    <test maxseconds="3600" name="Simple_1">
      <param name="tfile" value="ma2c_treatment_ce4.pair" />
      <param name="cfile" value="ma2c_control_ce4.pair" />
      <param name="ndf" value="ma2c_ndf_ce4.ndf" />
      <param name="pos" value="ma2c_pos_ce4.pos" />
      <param name="bandwidth" value="300" />
      <param name="max_gap" value="250" />
      <param name="min_probes" value="5" />
      <param name="method1" value="Pvalue" />
      <param name="value" value="0.001" />
      <param name="method2" value="Simple" />
      <output name="output" file="ma2c_11/sample_peaks.bed" />
      <output name="output" file="ma2c_11/sample_MA2Cscore.wig" lines_diff = "2" />
      <output name="output" file="ma2c_11/sample_log.bed" lines_diff = "100"/>
    </test>
    <test maxseconds="3600" name="Simple_2">
      <param name="tfile" value="ma2c_treatment_ce4.pair" />
      <param name="cfile" value="ma2c_control_ce4.pair" />
      <param name="ndf" value="ma2c_ndf_ce4.ndf" />
      <param name="pos" value="ma2c_pos_ce4.pos" />
      <param name="bandwidth" value="300" />
      <param name="max_gap" value="250" />
      <param name="min_probes" value="5" />
      <param name="method1" value="Pvalue" />
      <param name="value" value="0.001" />
      <param name="method2" value="Simple" />
      <param name="cvalue" value="231" />
      <output name="output" file="ma2c_12/sample_peaks.bed" />
      <output name="output" file="ma2c_12/sample_MA2Cscore.wig" lines_diff = "2" />
      <output name="output" file="ma2c_12/sample_log.bed" lines_diff = "100"/>
    </test>
  </tests>
  <help>
This tool performs peak calling for ChIP-chip (Nimblegen) data. MA2C
is developped in Xiaole Shirley Liu's lab, by Jun Song, and rewritten
in python by Tao Liu. The original java version is published on Genome
Biology (pubmed: 17727723). The version deployed here is pMA2C 1.1.3.

.. class:: infomark

**TIP:** Please first upload your treatment and control files using the **Upload File from your computer tool**.

.. class:: warningmark

**NEED IMPROVEMENT**

-----

**Parameters**

- **Replicates** click *Add new Replicate* button to choose NimbleGen
  pair data files from history.
- **Treatment file** The input file for ChIP/treatment channel chosen from the
  history.
- **Control file** The input file for input/control channel chosen
  from the history. 
- **NDF file** is the NimbleGen design file.
- **POS file** is the optional NimbleGen design file.
- **Bandwidth** is the bandwidth to detect peaks.
- **Max Gap** is the maximum gap allowed for joining two significant
  probes to call peak.
- **Min Probes** is the minimum number of probes required in the sliding window
  centered at each probe; a probe having fewer probes than this
  required number in its window will be ignored in the analysis.
- **Threshold method** is the criteria used for detecting
  ChIP-enriched regions. Can be Pvalue or FDR or MA2C score.
- **Value** is the cutoff used in the threshold method.
- **Normalization Method** is the normalization method. Choices are
  Robust or Simple normalization.
- **C value** is the parameter only for Robust normalization method.

-----

**Outputs**

- **BED file** for peak locations in BED format
- **WIGGLE file** for MA2C scores in WIGGLE format


  </help>

</tool>