view tools/new_operations/subtract_query.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="subtract_query1" name="Subtract Whole Dataset">
  <description>from another dataset</description>
  <command interpreter="python">subtract_query.py $input1 $input2 $begin_col $end_col $output</command>
  <inputs>
    <param format="txt" name="input2" type="data" label="Subtract" help="Second dataset" />
    <param format="txt" name="input1" type="data" label="from" help="First dataset" />
    <param name="begin_col" type="data_column" data_ref="input1" force_select="False" label="Restrict subtraction between 'begin column'" />
    <param name="end_col" type="data_column" data_ref="input1" force_select="False" label="and 'end column'" help="Specifying columns for restricting subtraction is available only for tabular formatted datasets" />
  </inputs>
  <outputs>
    <data format="input" name="output" metadata_source="input1" />
  </outputs>
  <tests>
  	<!-- Subtract 2 non-tabular files with no column restrictions. -->
  	<!-- Cannot figure out why this test won't pass, it works in real time...
    <test>
      <param name="input1" value="1.txt" />
      <param name="input2" value="2.txt" />
      <param name="begin_col" value="None" />
      <param name="end_col" value="None" />
      <output name="output" file="subtract-query-1.dat" />
    </test>
    -->
  	<!-- Subtract 2 tabular files with no column restrictions. -->
    <test>
      <param name="input1" value="eq-showbeginning.dat" />
      <param name="input2" value="eq-showtail.dat" />
      <param name="begin_col" value="None" />
      <param name="end_col" value="None" />
      <output name="output" file="subtract-query-2.dat" />
    </test>
  	<!-- Subtract 2 tabular files with column restrictions. -->
    <test>
      <param name="input1" value="eq-showbeginning.dat" />
      <param name="input2" value="eq-removebeginning.dat" />
      <param name="begin_col" value="c1" />
      <param name="end_col" value="c3" />
      <output name="output" file="subtract-query-3.dat" />
    </test>
  	<!-- Subtract a non-tabular file from a tabular file with no column restrictions. -->
    <test>
      <param name="input1" value="eq-showbeginning.dat" />
      <param name="input2" value="2.txt" />
      <param name="begin_col" value="None" />
      <param name="end_col" value="None" />
      <output name="output" file="subtract-query-4.dat" />
    </test>
  </tests>
  <help>

.. class:: infomark

**TIP:** This tool complements the tool in the **Operate on Genomic Intervals** tool set which subtracts the intervals of two datasets.


-----

**Syntax**

This tool subtracts an entire dataset from another dataset.  

- Any text format is valid.
- If both dataset formats are tabular, you may restrict the subtraction to specific columns **contained in both datasets** and the resulting dataset will include only the columns specified. 
- The begin column must be less than or equal to the end column.  If it is not, begin column is switched with end column.
- If begin column is specified but end column is not, end column will default to begin_column (and vice versa).
- All blank and comment lines are skipped and not included in the resulting dataset (comment lines are lines beginning with a # character).
- Duplicate lines are eliminated from both dataset prior to subtraction.  If any duplicate lines were eliminated from the first dataset, the number is displayed in the resulting history item.

-----

**Example**

If this is the **First dataset**::

  chr1            4225    19670
  chr10           6       8
  chr1            24417   24420
  chr6_hla_hap2   0       150
  chr2            1       5
  chr10           2       10
  chr1            30      55
  chrY            1       20
  chr1            1225979 42287290
  chr10           7       8 

and this is the **Second dataset**::

  chr1            4225    19670
  chr10           6       8
  chr1            24417   24420
  chr6_hla_hap2   0       150
  chr2            1       5
  chr1            30      55
  chrY            1       20
  chr1            1225979 42287290

Subtracting the **Second dataset** from the **First dataset** (including all columns) will yield::

  chr10           7       8 
  chr10           2       10

Conversely, subtracting the **First dataset** from the **Second dataset** (including all columns) will result in an empty dataset.

Subtracting the **Second dataset** from the **First dataset** (restricting to columns c1 and c2) will yield::

  chr10           7
  chr10           2

  </help>
</tool>