Mercurial > repos > miller-lab > genome_diversity
annotate specify.xml @ 24:248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
| author | Richard Burhans <burhans@bx.psu.edu> |
|---|---|
| date | Tue, 28 May 2013 16:24:19 -0400 |
| parents | fdb4240fb565 |
| children | 8997f2ca8c7a |
| rev | line source |
|---|---|
|
24
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
1 <tool id="gd_specify" name="Specify Individuals" version="1.1.0"> |
| 13 | 2 <description>: Define a collection of individuals from a gd_snp dataset</description> |
| 3 | |
|
24
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
4 <command interpreter="python"> |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
5 specify.py "$input" "$output" |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
6 #for $individual, $individual_col in zip($input.dataset.metadata.individual_names, $input.dataset.metadata.individual_columns) |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
7 #set $individual_arg = 'individual:%s:%s' % ($individual_col, $individual) |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
8 "$individual_arg" |
| 13 | 9 #end for |
|
24
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
10 #if str($individuals).strip() != 'None' |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
11 #for $individual in str($individuals).split(',') |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
12 #set $individual_idx = $input.dataset.metadata.individual_names.index($individual) |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
13 #set $individual_col = str( $input.dataset.metadata.individual_columns[$individual_idx] ) |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
14 #set $cb_arg = 'checkbox:%s:%s' % ($individual_col, $individual) |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
15 "$cb_arg" |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
16 #end for |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
17 #end if |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
18 #if str($string).strip() != '' |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
19 #set str_arg = 'string:%s' % ( __import__('base64').b64encode( str($string) ) ) |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
20 "$str_arg" |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
21 #end if |
| 13 | 22 </command> |
| 23 | |
| 24 <inputs> | |
|
24
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
25 <param name="input" type="data" format="gd_snp,gd_genotype" label="SNP or Genotype dataset"/> |
| 13 | 26 <param name="individuals" type="select" display="checkboxes" multiple="true" label="Individuals to include"> |
| 27 <options> | |
| 28 <filter type="data_meta" ref="input" key="individual_names" /> | |
| 29 </options> | |
| 30 </param> | |
| 31 <param name="outname" type="text" size="20" label="Label for this collection"> | |
| 32 <validator type="empty_field" message="You must enter a label."/> | |
| 33 #used to be "Individuals from ${input.hid}" | |
| 34 </param> | |
|
24
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
35 <param name="string" type="text" size="40" label="Individuals to include"> |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
36 <sanitizer> |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
37 <valid initial="string.printable"/> |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
38 </sanitizer> |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
39 </param> |
| 13 | 40 </inputs> |
| 41 | |
| 42 <outputs> | |
| 43 <data name="output" format="gd_indivs" label="${outname}" /> | |
| 44 </outputs> | |
| 45 | |
| 46 <tests> | |
| 47 <test> | |
| 48 <param name="input" value="test_in/sample.gd_snp" ftype="gd_snp" /> | |
| 49 <param name="individuals" value="PB1,PB2" /> | |
| 50 <output name="output" file="test_in/a.gd_indivs" /> | |
| 51 </test> | |
| 52 </tests> | |
| 53 | |
| 54 <help> | |
| 55 | |
| 56 **Dataset formats** | |
| 57 | |
|
24
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
58 The input dataset is in gd_snp_ or gd_genotype_ format; |
| 13 | 59 the output is in gd_indivs_ format. (`Dataset missing?`_) |
| 60 | |
| 61 .. _gd_snp: ./static/formatHelp.html#gd_snp | |
|
24
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
62 .. _gd_genotype: ./static/formatHelp.html#gd_genotype |
| 13 | 63 .. _gd_indivs: ./static/formatHelp.html#gd_indivs |
| 64 .. _Dataset missing?: ./static/formatHelp.html | |
| 65 | |
| 66 ----- | |
| 67 | |
| 68 **What it does** | |
| 69 | |
|
24
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
70 This tool makes a list of selected entities, i.e., the sets of four |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
71 columns representing individuals or groups from a gd_snp dataset, or |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
72 sets of single columns in a gd_genotype file. It does not copy the |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
73 data; it just records which entities should be considered as belonging |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
74 to some collection or population. The label you specify is used to |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
75 name the output dataset in your history. This list can then be used |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
76 to instruct other tools to work on just part of the original gd_snp or |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
77 gd_genotype dataset. The entities can be specified with the checklist |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
78 and/or by pasting their names (possibly with extraneous characters, as |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
79 in a portion of the Newick-format output of the Phylogenetic Tree tool) |
|
248b06e86022
Added gd_genotype datatype. Modified tools to support new datatype.
Richard Burhans <burhans@bx.psu.edu>
parents:
13
diff
changeset
|
80 into the box provided at the bottom of the page. |
| 13 | 81 |
| 82 ----- | |
| 83 | |
| 84 **Example** | |
| 85 | |
| 86 - input:: | |
| 87 | |
| 88 Contig161_chr1_4641264_4641879 115 C T 73.5 chr1 4641382 C 6 0 2 45 8 0 2 51 15 0 2 72 5 0 2 42 6 0 2 45 10 0 2 57 Y 54 0.323 0 | |
| 89 Contig48_chr1_10150253_10151311 11 A G 94.3 chr1 10150264 A 1 0 2 30 1 0 2 30 1 0 2 30 3 0 2 36 1 0 2 30 1 0 2 30 Y 22 +99. 0 | |
| 90 Contig20_chr1_21313469_21313570 66 C T 54.0 chr1 21313534 C 4 0 2 39 4 0 2 39 5 0 2 42 4 0 2 39 4 0 2 39 5 0 2 42 N 1 +99. 0 | |
| 91 etc. | |
| 92 | |
| 93 - input metadata:: | |
| 94 | |
| 95 #{"column_names":["scaf","pos","A","B","qual","ref","rpos","rnuc", | |
| 96 #"1A","1B","1G","1Q","2A","2B","2G","2Q","3A","3B","3G","3Q","4A","4B","4G","4Q","5A","5B","5G","5Q","6A","6B","6G","6Q", | |
| 97 #"pair","dist","prim","rflp"],"dbkey":"canFam2","individuals":[["PB1",9],["PB2",13],["PB3",17],["PB4",21],["PB6",25],["PB8",29]], | |
| 98 #"pos":2,"rPos":7,"ref":6,"scaffold":1,"species":"bear"} | |
| 99 | |
| 100 - output when individuals PB1, PB2, and PB3 are selected:: | |
| 101 | |
| 102 9 PB1 | |
| 103 13 PB2 | |
| 104 17 PB3 | |
| 105 | |
| 106 </help> | |
| 107 </tool> |