view tools/new_operations/intersect.xml @ 1:cdcb0ce84a1b

Uploaded
author xuebing
date Fri, 09 Mar 2012 19:45:15 -0500
parents 9071e359b9a3
children
line wrap: on
line source

<tool id="gops_intersect_1" name="Intersect">
  <description>the intervals of two datasets</description>
  <command interpreter="python">gops_intersect.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 name="returntype" type="select" label="Return" help="(see figure below)">
          <option value="">Overlapping Intervals</option>
          <option value="-p">Overlapping pieces of Intervals</option>
      </param>
      <param format="interval,gff" name="input1" type="data" help="First dataset">
          <label>of</label>
      </param>
      <param format="interval,gff" name="input2" type="data" help="Second dataset">
          <label>that intersect</label>
      </param>
      <param name="min" size="4" type="integer" value="1" min="1" help="(bp)">
          <label>for at least</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_intersect_out.bed" />
    </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_intersect_diffCols.bed" />
    </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="Overlapping pieces of Intervals" />
      <output name="output" file="gops_intersect_p_diffCols.bed" />
    </test>
    <test>
      <param name="input1" value="1.bed" />
      <param name="input2" value="2.bed" />
      <param name="min" value="10" />
      <param name="returntype" value="Overlapping pieces of Intervals" />
      <output name="output" file="gops_intersect_p_out.bed" />     
    </test>
    <test>
      <param name="input1" value="gops_bigint.interval" ftype="interval" />
      <param name="input2" value="gops_bigint2.interval" ftype="interval" />
      <param name="min" value="1" />
      <param name="returntype" value="" />
      <output name="output" file="gops_intersect_bigint_out.interval" />     
    </test>
    <test>
      <param name="input1" value="gops_bigint2.interval" ftype="interval" />
      <param name="input2" value="gops_bigint.interval" ftype="interval" />
      <param name="min" value="1" />
      <param name="returntype" value="" />
      <output name="output" file="gops_intersect_bigint_out.interval" />     
    </test>
    <test>
      <param name="input1" value="12.bed" ftype="bed" />
      <param name="input2" value="1.bed" ftype="bed" />
      <param name="min" value="1" />
      <param name="returntype" value="" />
      <output name="output" file="gops_intersect_no_strand_out.bed" />     
    </test>
    <!-- Intersect 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_intersect_out2.gff" />        
    </test>
    <!-- Intersect GFF file and bed 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_intersect_out2.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
- **Overlapping Intervals** returns entire intervals from the first dataset  that overlap the second dataset.  The returned intervals are completely unchanged, and this option only filters out intervals that do not overlap with the second dataset.
- **Overlapping pieces of Intervals** returns intervals that indicate the exact base pair overlap between the first dataset and the second dataset.  The intervals returned are from the first dataset, and all fields besides start and end are guaranteed to remain unchanged.

-----

**Example**

.. image:: ./static/operation_icons/gops_intersect.gif

</help>
</tool>