Mercurial > repos > devteam > picard
annotate picard_macros.xml @ 17:fc288950c3b7 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
| author | iuc |
|---|---|
| date | Thu, 13 Apr 2017 19:09:24 -0400 |
| parents | 6741a8ace658 |
| children | 5053a18d9bc8 |
| rev | line source |
|---|---|
| 5 | 1 <macros> |
| 2 <xml name="VS"> | |
| 3 <param name="validation_stringency" type="select" label="Select validation stringency" help=" Setting stringency to SILENT can improve performance when processing a BAM file in which variable-length data (read, qualities, tags) do not otherwise need to be decoded."> | |
| 4 <option value="LENIENT" selected="True">Lenient</option> | |
| 5 <option value="SILENT">Silent</option> | |
| 6 <option value="STRICT">Strict</option> | |
| 7 </param> | |
| 8 </xml> | |
|
8
3a3234d7a2e8
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
9 |
|
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
8
diff
changeset
|
10 <token name="@TOOL_VERSION@">2.7.1</token> |
|
8
3a3234d7a2e8
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
11 |
|
3a3234d7a2e8
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
12 <xml name="requirements"> |
|
3a3234d7a2e8
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
13 <requirements> |
|
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
8
diff
changeset
|
14 <requirement type="package" version="2.7.1">picard</requirement> |
|
8
3a3234d7a2e8
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
15 <yield/> |
|
3a3234d7a2e8
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
16 </requirements> |
|
3a3234d7a2e8
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
17 </xml> |
|
3a3234d7a2e8
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
18 |
|
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
19 <token name="@symlink_element_identifier@"><![CDATA[ |
|
14
465cbb0cf2eb
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 74ee0f0b594075fab7f707aaffb4a7f9dac35f2f
devteam
parents:
13
diff
changeset
|
20 #import re |
|
465cbb0cf2eb
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 74ee0f0b594075fab7f707aaffb4a7f9dac35f2f
devteam
parents:
13
diff
changeset
|
21 #set escaped_element_identifier = re.sub('[^\w\-]', '_', str($inputFile.element_identifier)) |
|
465cbb0cf2eb
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 74ee0f0b594075fab7f707aaffb4a7f9dac35f2f
devteam
parents:
13
diff
changeset
|
22 ln -f -s '$inputFile' '$escaped_element_identifier' && |
|
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
23 ]]></token> |
|
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
24 |
|
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
8
diff
changeset
|
25 <token name="@java_options@"><![CDATA[ |
|
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
8
diff
changeset
|
26 _JAVA_OPTIONS=\${_JAVA_OPTIONS:-'-Xmx2048m -Xms256m'} && |
|
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
8
diff
changeset
|
27 export _JAVA_OPTIONS && |
|
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
8
diff
changeset
|
28 ]]></token> |
|
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
8
diff
changeset
|
29 |
| 5 | 30 <token name="@more_info@"> |
| 31 ------ | |
| 32 | |
| 33 **Additional information** | |
| 34 | |
|
16
6741a8ace658
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 2bfbb5ae6b801e43355fdc3f964a5111fe3fe3a1
iuc
parents:
14
diff
changeset
|
35 Additional information about Picard tools is available from Picard web site at http://broadinstitute.github.io/picard/ . |
| 5 | 36 </token> |
|
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
8
diff
changeset
|
37 |
| 5 | 38 |
| 39 <token name="@description@"> | |
| 40 ------ | |
| 41 | |
| 42 **Inputs, outputs, and parameters** | |
| 43 | |
| 44 Either a SAM file or a BAM file must be supplied. Galaxy automatically coordinate-sorts all uploaded BAM files. | |
| 45 | |
| 46 From Picard documentation( http://broadinstitute.github.io/picard/):: | |
| 47 | |
| 48 </token> | |
| 49 <token name="@RG@"> | |
| 50 ------- | |
| 51 | |
| 52 **Read Groups are Important!** | |
| 53 | |
| 54 Setting read groups correctly from the start will simplify your life greatly because you can merge multiple BAM files into one significantly reducing the number of analysis steps. Below we provide an explanation of read groups fields taken from GATK FAQ webpage: | |
| 55 | |
| 56 .. csv-table:: | |
| 57 :header-rows: 1 | |
|
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
8
diff
changeset
|
58 |
| 5 | 59 Tag,Importance,Definition,Meaning |
| 60 "ID","Required","Read group identifier. Each @RG line must have a unique ID. The value of ID is used in the RG tags of alignment records. Must be unique among all read groups in header section. Read group IDs may be modified when merging SAM files in order to handle collisions.","Ideally, this should be a globally unique identify across all sequencing data in the world, such as the Illumina flowcell + lane name and number. Will be referenced by each read with the RG:Z field, allowing tools to determine the read group information associated with each read, including the sample from which the read came. Also, a read group is effectively treated as a separate run of the NGS instrument in tools like base quality score recalibration (a GATK component) -- all reads within a read group are assumed to come from the same instrument run and to therefore share the same error model." | |
| 61 "SM","Sample. Use pool name where a pool is being sequenced.","Required. As important as ID.","The name of the sample sequenced in this read group. GATK tools treat all read groups with the same SM value as containing sequencing data for the same sample. Therefore it's critical that the SM field be correctly specified, especially when using multi-sample tools like the Unified Genotyper (a GATK component)." | |
| 62 "PL","Platform/technology used to produce the read. Valid values: ILLUMINA, SOLID, LS454, HELICOS and PACBIO.","Important. Not currently used in the GATK, but was in the past, and may return. The only way to known the sequencing technology used to generate the sequencing data","It's a good idea to use this field." | |
| 63 "LB","DNA preparation library identify","Essential for MarkDuplicates","MarkDuplicates uses the LB field to determine which read groups might contain molecular duplicates, in case the same DNA library was sequenced on multiple lanes." | |
| 64 | |
| 65 **Example of Read Group usage** | |
| 66 | |
| 67 Support we have a trio of samples: MOM, DAD, and KID. Each has two DNA libraries prepared, one with 400 bp inserts and another with 200 bp inserts. Each of these libraries is run on two lanes of an illumina hiseq, requiring 3 x 2 x 2 = 12 lanes of data. When the data come off the sequencer, we would create 12 BAM files, with the following @RG fields in the header:: | |
| 68 | |
| 69 Dad's data: | |
| 70 @RG ID:FLOWCELL1.LANE1 PL:illumina LB:LIB-DAD-1 SM:DAD PI:200 | |
| 71 @RG ID:FLOWCELL1.LANE2 PL:illumina LB:LIB-DAD-1 SM:DAD PI:200 | |
| 72 @RG ID:FLOWCELL1.LANE3 PL:illumina LB:LIB-DAD-2 SM:DAD PI:400 | |
| 73 @RG ID:FLOWCELL1.LANE4 PL:illumina LB:LIB-DAD-2 SM:DAD PI:400 | |
|
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
8
diff
changeset
|
74 |
| 5 | 75 Mom's data: |
| 76 @RG ID:FLOWCELL1.LANE5 PL:illumina LB:LIB-MOM-1 SM:MOM PI:200 | |
| 77 @RG ID:FLOWCELL1.LANE6 PL:illumina LB:LIB-MOM-1 SM:MOM PI:200 | |
| 78 @RG ID:FLOWCELL1.LANE7 PL:illumina LB:LIB-MOM-2 SM:MOM PI:400 | |
| 79 @RG ID:FLOWCELL1.LANE8 PL:illumina LB:LIB-MOM-2 SM:MOM PI:400 | |
|
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
8
diff
changeset
|
80 |
| 5 | 81 Kid's data: |
| 82 @RG ID:FLOWCELL2.LANE1 PL:illumina LB:LIB-KID-1 SM:KID PI:200 | |
| 83 @RG ID:FLOWCELL2.LANE2 PL:illumina LB:LIB-KID-1 SM:KID PI:200 | |
| 84 @RG ID:FLOWCELL2.LANE3 PL:illumina LB:LIB-KID-2 SM:KID PI:400 | |
| 85 @RG ID:FLOWCELL2.LANE4 PL:illumina LB:LIB-KID-2 SM:KID PI:400 | |
| 86 | |
| 87 Note the hierarchical relationship between read groups (unique for each lane) to libraries (sequenced on two lanes) and samples (across four lanes, two lanes for each library). | |
| 88 </token> | |
| 89 <token name="@dataset_collections@"> | |
| 90 ------ | |
| 91 | |
| 92 **Dataset collections - processing large numbers of datasets at once** | |
| 93 | |
| 94 This will be added shortly | |
| 95 | |
| 96 | |
| 97 </token> | |
|
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
8
diff
changeset
|
98 |
| 5 | 99 |
| 100 </macros> |