Mercurial > repos > devteam > join

comparison join.xml @ 0:cb9ed67cb329

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Imported from capsule None
author devteam
date Tue, 01 Apr 2014 09:13:30 -0400
parents
children 4ce471410d01
comparison
equal deleted inserted replaced
-1:000000000000 0:cb9ed67cb329
1 <tool id="gops_join_1" name="Join" version="0.0.1">
2 <description>the intervals of two datasets side-by-side</description>
3 <requirements>
4 <requirement type="package" version="0.7.1">bx-python</requirement>
5 <requirement type="package" version="1.0.0">galaxy-ops</requirement>
6 </requirements>
7 <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>
8 <inputs>
9 <param format="interval" name="input1" type="data" help="First dataset">
10 <label>Join</label>
11 </param>
12 <param format="interval" name="input2" type="data" help="Second dataset">
13 <label>with</label>
14 </param>
15 <param name="min" size="4" type="integer" value="1" help="(bp)">
16 <label>with min overlap</label>
17 </param>
18 <param name="fill" type="select" label="Return">
19 <option value="none">Only records that are joined (INNER JOIN)</option>
20 <option value="right">All records of first dataset (fill null with ".")</option>
21 <option value="left">All records of second dataset (fill null with ".")</option>
22 <option value="both">All records of both datasets (fill nulls with ".")</option>
23 </param>
24 </inputs>
25 <outputs>
26 <data format="interval" name="output" metadata_source="input1" />
27 </outputs>
28 <code file="operation_filter.py"/>
29 <tests>
30 <test>
31 <param name="input1" value="1.bed" />
32 <param name="input2" value="2.bed" />
33 <param name="min" value="1" />
34 <param name="fill" value="none" />
35 <output name="output" file="gops-join-none.dat" />
36 </test>
37 <test>
38 <param name="input1" value="1.bed" />
39 <param name="input2" value="2.bed" />
40 <param name="min" value="1" />
41 <param name="fill" value="right" />
42 <output name="output" file="gops-join-right.dat" />
43 </test>
44 <test>
45 <param name="input1" value="1.bed" />
46 <param name="input2" value="2.bed" />
47 <param name="min" value="1" />
48 <param name="fill" value="left" />
49 <output name="output" file="gops-join-left.dat" />
50 </test>
51 <test>
52 <param name="input1" value="1.bed" />
53 <param name="input2" value="2.bed" />
54 <param name="min" value="1" />
55 <param name="fill" value="both" />
56 <output name="output" file="gops-join-both.dat" />
57 </test>
58 <test>
59 <param name="input1" value="1.bed" />
60 <param name="input2" value="2.bed" />
61 <param name="min" value="500" />
62 <param name="fill" value="none" />
63 <output name="output" file="gops-join-none-500.dat" />
64 </test>
65 <test>
66 <param name="input1" value="1.bed" />
67 <param name="input2" value="2.bed" />
68 <param name="min" value="100" />
69 <param name="fill" value="both" />
70 <output name="output" file="gops-join-both-100.dat" />
71 </test>
72 </tests>
73 <help>
74
75 .. class:: infomark
76
77 **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.
78
79 -----
80
81 **Screencasts!**
82
83 See Galaxy Interval Operation Screencasts_ (right click to open this link in another window).
84
85 .. _Screencasts: http://wiki.g2.bx.psu.edu/Learn/Interval%20Operations
86
87 -----
88
89 **Syntax**
90
91 - **Where overlap** specifies the minimum overlap between intervals that allows them to be joined.
92 - **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.
93 - **Return all records of first dataset (fill null with &quot;.&quot;)** 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.
94 - **Return all records of second dataset (fill null with &quot;.&quot;)** 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.**
95 - **Return all records of both datasets (fill nulls with &quot;.&quot;)** 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.**
96
97 -----
98
99 **Examples**
100
101 .. image:: ${static_path}/operation_icons/gops_joinRecordsList.gif
102
103 Only records that are joined (inner join):
104
105 .. image:: ${static_path}/operation_icons/gops_joinInner.gif
106
107 All records of first dataset:
108
109 .. image:: ${static_path}/operation_icons/gops_joinLeftOuter.gif
110
111 All records of second dataset:
112
113 .. image:: ${static_path}/operation_icons/gops_joinRightOuter.gif
114
115 All records of both datasets:
116
117 .. image:: ${static_path}/operation_icons/gops_joinFullOuter.gif
118
119
120 </help>
121 </tool>