mirror of
https://github.com/galaxyproject/galaxy.git
synced 2026-10-25 00:12:08 +08:00
125 lines
4.7 KiB
XML
125 lines
4.7 KiB
XML
<tool id="gops_join_1" name="Join">
|
|
<description>the intervals of two queries side-by-side</description>
|
|
<command interpreter="python">gops_join.py $input1 $input2 $output -1 $input1_chromCol,$input1_startCol,$input1_endCol,$input1_strandCol -2 $input2_chromCol,$input2_startCol,$input2_endCol,$input2_strandCol -m $min -f $fill</command>
|
|
<inputs>
|
|
<param format="interval" name="input1" type="data" help="First query">
|
|
<label>Join</label>
|
|
</param>
|
|
<param format="interval" name="input2" type="data" help="Second query">
|
|
<label>with</label>
|
|
</param>
|
|
<param name="min" size="4" type="integer" value="1" help="(bp)">
|
|
<label>with min overlap</label>
|
|
</param>
|
|
<param name="fill" type="select" label="Return">
|
|
<option value="none">Only records that are joined (INNER JOIN)</option>
|
|
<option value="right">All records of first query (fill null with ".")</option>
|
|
<option value="left">All records of second query (fill null with ".")</option>
|
|
<option value="both">All records of both queries (fill nulls with ".")</option>
|
|
</param>
|
|
</inputs>
|
|
<outputs>
|
|
<data format="interval" name="output" metadata_source="input1" />
|
|
</outputs>
|
|
<code file="operation_filter.py"/>
|
|
<tests>
|
|
<test>
|
|
<param name="input1" value="1.bed" />
|
|
<param name="input2" value="2.bed" />
|
|
<param name="min" value="1" />
|
|
<param name="fill" value="none" />
|
|
<output name="output" file="gops-join-none.dat" />
|
|
</test>
|
|
<test>
|
|
<param name="input1" value="1.bed" />
|
|
<param name="input2" value="2.bed" />
|
|
<param name="min" value="1" />
|
|
<param name="fill" value="right" />
|
|
<output name="output" file="gops-join-right.dat" />
|
|
</test>
|
|
<test>
|
|
<param name="input1" value="1.bed" />
|
|
<param name="input2" value="2.bed" />
|
|
<param name="min" value="1" />
|
|
<param name="fill" value="left" />
|
|
<output name="output" file="gops-join-left.dat" />
|
|
</test>
|
|
<test>
|
|
<param name="input1" value="1.bed" />
|
|
<param name="input2" value="2.bed" />
|
|
<param name="min" value="1" />
|
|
<param name="fill" value="both" />
|
|
<output name="output" file="gops-join-both.dat" />
|
|
</test>
|
|
</tests>
|
|
<help>
|
|
|
|
.. class:: infomark
|
|
|
|
**TIP:** If your query does not appear in the pulldown menu -> 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://www.bx.psu.edu/cgi-bin/trac.cgi/wiki/GopsDesc
|
|
|
|
-----
|
|
|
|
**Syntax**
|
|
|
|
- **Where overlap** specifies the minimum overlap between intervals that allows them to be joined.
|
|
- **Return only records that are joined** returns only the records of the first query that join to a recond in the second query. This is analogous to an INNER JOIN.
|
|
- **Return all records of first query (fill null with ".")** returns all intervals of the first query, and any intervals that do not join an interval from the second query are filled in with a period(.). This is analogous to a LEFT JOIN.
|
|
- **Return all records of second query (fill null with ".")** returns all intervals of the second query, and any intervals that do not join an interval from the first query are filled in with a period(.). **Note that this may produce an invalid interval file, since a period(.) is not a valid chrom, start, end or strand.**
|
|
- **Return all records of both queries (fill nulls with ".")** returns all records from both queries, and fills on either the right or left with periods. **Note that this may produce an invalid interval file, since a period(.) is not a valid chrom, start, end or strand.**
|
|
|
|
-----
|
|
|
|
**Example**
|
|
|
|
If **First query** is::
|
|
|
|
chr1 10 100 Query1.1
|
|
chr1 500 1000 Query1.2
|
|
chr1 1100 1250 Query1.3
|
|
|
|
and **Second query** is::
|
|
|
|
chr1 20 80 Query2.1
|
|
chr1 2000 2204 Query2.2
|
|
chr1 2500 3000 Query2.3
|
|
|
|
|
|
The four return options will generate:
|
|
|
|
|
|
- **Return only records that are joined**::
|
|
|
|
chr1 10 100 Query1.1 chr1 20 80 Query2.1
|
|
|
|
- **Return all records of first query**::
|
|
|
|
chr1 10 100 Query1.1 chr1 20 80 Query2.1
|
|
chr1 500 1000 Query1.2 . . . .
|
|
chr1 1100 1250 Query1.3 . . . .
|
|
|
|
- **Return all records of second query**::
|
|
|
|
chr1 10 100 Query1.1 chr1 20 80 Query2.1
|
|
. . . . chr1 2000 2204 Query2.2
|
|
. . . . chr1 2500 3000 Query2.3
|
|
|
|
- **Return all records of both queries**::
|
|
|
|
chr1 10 100 Query1.1 chr1 20 80 Query2.1
|
|
chr1 500 1000 Query1.2 . . . .
|
|
chr1 1100 1250 Query1.3 . . . .
|
|
. . . . chr1 2000 2204 Query2.2
|
|
. . . . chr1 2500 3000 Query2.3
|
|
|
|
|
|
</help>
|
|
</tool> |