mirror of
https://github.com/galaxyproject/galaxy.git
synced 2026-09-24 16:30:27 +08:00
Dave Clements
9d0e631203
"Operate on Genomic Invervals" tool pages. Old onew were looking dated. New ones look, well, newer, and cover more cases.
118 lines
4.8 KiB
XML
118 lines
4.8 KiB
XML
<tool id="gops_join_1" name="Join">
|
|
<description>the intervals of two datasets side-by-side</description>
|
|
<command interpreter="python">gops_join.py $input1 $input2 $output -1 ${input1.metadata.chromCol},${input1.metadata.startCol},${input1.metadata.endCol},${input1.metadata.strandCol} -2 ${input2.metadata.chromCol},${input2.metadata.startCol},${input2.metadata.endCol},${input2.metadata.strandCol} -m $min -f $fill</command>
|
|
<inputs>
|
|
<param format="interval" name="input1" type="data" help="First dataset">
|
|
<label>Join</label>
|
|
</param>
|
|
<param format="interval" name="input2" type="data" help="Second dataset">
|
|
<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 dataset (fill null with ".")</option>
|
|
<option value="left">All records of second dataset (fill null with ".")</option>
|
|
<option value="both">All records of both datasets (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>
|
|
<test>
|
|
<param name="input1" value="1.bed" />
|
|
<param name="input2" value="2.bed" />
|
|
<param name="min" value="500" />
|
|
<param name="fill" value="none" />
|
|
<output name="output" file="gops-join-none-500.dat" />
|
|
</test>
|
|
<test>
|
|
<param name="input1" value="1.bed" />
|
|
<param name="input2" value="2.bed" />
|
|
<param name="min" value="100" />
|
|
<param name="fill" value="both" />
|
|
<output name="output" file="gops-join-both-100.dat" />
|
|
</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** 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 dataset that join to a record in the second dataset. This is analogous to an INNER JOIN.
|
|
- **Return all records of first dataset (fill null with ".")** returns all intervals of the first dataset, and any intervals that do not join an interval from the second dataset are filled in with a period(.). This is analogous to a LEFT JOIN.
|
|
- **Return all records of second dataset (fill null with ".")** returns all intervals of the second dataset, and any intervals that do not join an interval from the first dataset 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 datasets (fill nulls with ".")** returns all records from both datasets, 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.**
|
|
|
|
-----
|
|
|
|
**Examples**
|
|
|
|
.. image:: ./static/operation_icons/gops_joinRecordsList.gif
|
|
|
|
Only records that are joined (inner join):
|
|
|
|
.. image:: ./static/operation_icons/gops_joinInner.gif
|
|
|
|
All records of first dataset:
|
|
|
|
.. image:: ./static/operation_icons/gops_joinLeftOuter.gif
|
|
|
|
All records of second dataset:
|
|
|
|
.. image:: ./static/operation_icons/gops_joinRightOuter.gif
|
|
|
|
All records of both datasets:
|
|
|
|
.. image:: ./static/operation_icons/gops_joinFullOuter.gif
|
|
|
|
|
|
</help>
|
|
</tool>
|