1. kmdaily
  2. galaxy-central (ngs)

Source

galaxy-central (ngs) / tools / new_operations / subtract.xml

<tool id="gops_subtract_1" name="Subtract">
  <description>the intervals of two datasets</description>
  <command interpreter="python">gops_subtract.py 
      $input1 $input2 $output

      #if isinstance( $input1.datatype, $__app__.datatypes_registry.get_datatype_by_extension('gff').__class__):
        -1 1,4,5,7 --gff1
      #else:
        -1 ${input1.metadata.chromCol},${input1.metadata.startCol},${input1.metadata.endCol},${input1.metadata.strandCol}
      #end if

      #if isinstance( $input2.datatype, $__app__.datatypes_registry.get_datatype_by_extension('gff').__class__):
        -2 1,4,5,7 --gff2
      #else:
          -2 ${input2.metadata.chromCol},${input2.metadata.startCol},${input2.metadata.endCol},${input2.metadata.strandCol} 
      #end if

      -m $min $returntype
  </command>
  <inputs>
    <param format="interval,gff" name="input2" type="data" help="Second dataset">
      <label>Subtract</label>
    </param>

    <param format="interval,gff" name="input1" type="data" help="First dataset">
      <label>from</label>
    </param>

    <param name="returntype" type="select" label="Return" help="of the first dataset (see figure below)">
      <option value="">Intervals with no overlap</option>
      <option value="-p">Non-overlapping pieces of intervals</option>
    </param>
    
    <param name="min" size="4" type="integer" value="1" min="1" help="(bp)">
      <label>where minimal overlap is</label>
    </param>
   </inputs>
  <outputs>
    <data format="input" name="output" metadata_source="input1"/>
  </outputs>
  <code file="operation_filter.py"/>
  <trackster_conf/>
  <tests>
    <test>
      <param name="input1" value="1.bed" />
      <param name="input2" value="2.bed" />
      <param name="min" value="1" />
      <param name="returntype" value="" />
      <output name="output" file="gops-subtract.dat" />
    </test>
    <test>
      <param name="input1" value="1.bed" />
      <param name="input2" value="2_mod.bed" ftype="interval"/>
      <param name="min" value="1" />
      <param name="returntype" value="" />
      <output name="output" file="gops_subtract_diffCols.dat" />
    </test>
    <test>
      <param name="input1" value="gops_subtract_bigint.bed" />
      <param name="input2" value="2.bed" />
      <param name="min" value="1" />
      <param name="returntype" value="" />
      <output name="output" file="gops-subtract.dat" />
    </test>
    <test>
      <param name="input1" value="1.bed" />
      <param name="input2" value="2.bed" />
      <param name="min" value="10" />
      <param name="returntype" value="Non-overlapping pieces of intervals" />
      <output name="output" file="gops-subtract-p.dat" />     
    </test>
    <!-- Subtract two GFF files. -->
    <test>
        <param name="input1" value="gops_subtract_in1.gff" />
        <param name="input2" value="gops_subtract_in2.gff" />
        <param name="min" value="1" />
        <param name="returntype" value="" />
        <output name="output" file="gops_subtract_out1.gff" />
    </test>
    <!-- Subtract BED file from GFF file. -->
    <test>
        <param name="input1" value="gops_subtract_in1.gff" />
        <param name="input2" value="gops_subtract_in2.bed" />
        <param name="min" value="1" />
        <param name="returntype" value="" />
        <output name="output" file="gops_subtract_out1.gff" />
    </test>
  </tests>
  <help>

.. class:: infomark

**TIP:** If your dataset does not appear in the pulldown menu, it means that it is not in interval format. Use "edit attributes" to set chromosome, start, end, and strand columns.

-----

**Screencasts!**

See Galaxy Interval Operation Screencasts_ (right click to open this link in another window).

.. _Screencasts: http://wiki.g2.bx.psu.edu/Learn/Interval%20Operations

-----

**Syntax**

- **Where overlap is at least** sets the minimum length (in base pairs) of overlap between elements of the two datasets.
- **Intervals with no overlap** returns entire intervals from the first dataset that do not overlap the second dataset.  The returned intervals are completely unchanged, and this option only filters out intervals that overlap with the second dataset.
- **Non-overlapping pieces of intervals** returns intervals from the first dataset that have the intervals from the second dataset removed.  Any overlapping base pairs are removed from the range of the interval.  All fields besides start and end are guaranteed to remain unchanged.

-----

**Example**

.. image:: ./static/operation_icons/gops_subtract.gif

</help>
</tool>