annotate restore_attributes.xml @ 28:184d14e4270d

Update to Miller Lab devshed revision 4ede22dd5500
author Richard Burhans <burhans@bx.psu.edu>
date Wed, 17 Jul 2013 12:46:46 -0400
parents 91e835060ad2
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
26
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
1 <tool id="gd_restore_attributes" name="Restore Attributes" version="1.1.0">
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
2 <description>: Fill in missing properties for a gd_snp or gd_genotype dataset</description>
22
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
3
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
4 <command interpreter="python">
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
5 cp.py "$dst" "$output"
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
6 </command>
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
7
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
8 <inputs>
26
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
9 <conditional name="input_type">
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
10 <param name="choice" type="select" format="integer" label="Input format">
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
11 <option value="0" selected="true">gd_snp</option>
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
12 <option value="1">gd_genotype</option>
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
13 </param>
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
14
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
15 <when value="0">
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
16 <param name="input" type="data" format="gd_snp" label="SNP dataset to copy attributes from" />
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
17 <param name="dst" type="data" format="gd_snp" label="SNP dataset to receive attributes" />
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
18 </when>
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
19 <when value="1">
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
20 <param name="input" type="data" format="gd_genotype" label="Genotype dataset to copy attributes from" />
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
21 <param name="dst" type="data" format="gd_genotype" label="Genotype dataset to receive attributes" />
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
22 </when>
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
23 </conditional>
22
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
24 </inputs>
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
25
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
26 <outputs>
26
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
27 <data name="output" format="input" format_source="input" metadata_source="input" />
22
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
28 </outputs>
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
29
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
30 <help>
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
31
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
32 **Dataset formats**
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
33
26
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
34 All of the input and output datasets are in gd_snp_ or gd_genotype_ format. (`Dataset missing?`_)
22
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
35
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
36 .. _gd_snp: ./static/formatHelp.html#gd_snp
26
91e835060ad2 Updates to Admixture, Aggregate Individuals, and Restore Attributes to support gd_genotype
Richard Burhans <burhans@bx.psu.edu>
parents: 22
diff changeset
37 .. _gd_genotype: ./static/formatHelp.html#gd_genotype
22
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
38 .. _Dataset missing?: ./static/formatHelp.html
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
39
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
40 -----
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
41
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
42 **What it does**
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
43
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
44 This tool copies metadata information from one SNP dataset to another, leaving
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
45 the actual SNP data itself unchanged. Datasets in gd_snp format have a number
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
46 of "extra" properties associated with them, such as the focus species (which
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
47 may be different from the reference assembly), names of individuals, column
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
48 numbers containing certain data fields, etc. These values are stored in the
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
49 dataset's metadata, in addition to the more usual attributes like dataset name,
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
50 assembly build, and so forth. You can see some of these by clicking on the
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
51 pencil icon for the dataset.
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
52
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
53 The Genome Diversity tools need this information to perform their tasks.
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
54 However, these additional attributes may be lost if the datatype is changed.
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
55 For example, suppose you want to see which SNPs overlap some other dataset in
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
56 your history, like coding regions or TAL1 binding sites. The Intersect tool
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
57 only works on datasets that are in interval format, so you might use the Compute
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
58 tool to append a new column with the End position of the SNP (= Start + 1),
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
59 then use the pencil icon to change the datatype to "interval". This works
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
60 great for doing the intersection, but if you then want to run one of the Genome
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
61 Diversity tools on the resulting SNPs, there's a problem: you can change the
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
62 datatype back to gd_snp easily enough, but the extra attributes have been lost
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
63 in the conversion to interval.
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
64
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
65 As long as the proper values of the lost attributes have not changed, then this
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
66 tool can restore them by copying from the old gd_snp dataset in your history.
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
67 In the above example, appending a column does not change the numbering of the
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
68 earlier columns, and deleting rows via Intersect does not affect the extra
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
69 attributes either. Note that all of the metadata is copied, not just the extra
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
70 attributes specific to gd_snp (though standard items like the assembly build,
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
71 the number of lines, and the name for the output dataset are updated
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
72 automatically by the Galaxy framework).
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
73
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
74 </help>
95a05c1ef5d5 update to devshed revision aaece207bd01
Richard Burhans <burhans@bx.psu.edu>
parents:
diff changeset
75 </tool>