Mercurial > repos > devteam > bwa
annotate bwa_macros.xml @ 7:d8c9597bfb09 draft
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
author | devteam |
---|---|
date | Tue, 03 Nov 2015 09:36:45 -0500 |
parents | 09a7281d24c5 |
children | 7bee165c3a44 |
rev | line source |
---|---|
0 | 1 <macros> |
5
fbf460831036
planemo upload commit d0e3412c58bd3bdc1a483a1e2f7f9c2aa5c87a1f-dirty
devteam
parents:
4
diff
changeset
|
2 <import>read_group_macros.xml</import> |
2 | 3 <token name="@set_rg_string@"> |
7
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
4 #set $rg_string = "@RG\\tID:" + str($rg_id) |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
5 #set $rg_string += $format_read_group("\\tSM:", $rg_sm) |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
6 #set $rg_string += $format_read_group("\\tPL:", $rg_pl) |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
7 #set $rg_string += $format_read_group("\\tLB:", $rg_lb) |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
8 #set $rg_string += $format_read_group("\\tCN:", $rg_cn) |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
9 #set $rg_string += $format_read_group("\\tDS:", $rg_ds) |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
10 #set $rg_string += $format_read_group("\\tDT:", $rg_dt) |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
11 #set $rg_string += $format_read_group("\\tFO:", $rg_fo) |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
12 #set $rg_string += $format_read_group("\\tKS:", $rg_ks) |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
13 #set $rg_string += $format_read_group("\\tPG:", $rg_pg) |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
14 #set $rg_string += $format_read_group("\\tPI:", $rg_pi) |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
15 #set $rg_string += $format_read_group("\\tPU:", $rg_pu) |
2 | 16 </token> |
6
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
17 |
7
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
18 <xml name="requirements"> |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
19 <requirements> |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
20 <requirement type="package" version="0.7.10.039ea20639">bwa</requirement> |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
21 <requirement type="package" version="1.2">samtools</requirement> |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
22 </requirements> |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
23 </xml> |
d8c9597bfb09
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/bwa commit ddb8bdb9d62399f086b06b3469450d0aad2113bd
devteam
parents:
6
diff
changeset
|
24 |
6
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
25 <xml name="stdio"> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
26 <stdio> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
27 <exit_code range="1:" /> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
28 <exit_code range=":-1" /> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
29 <regex match="Error:" /> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
30 <regex match="Exception:" /> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
31 </stdio> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
32 </xml> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
33 |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
34 <macro name="dbKeyActionsBwa"> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
35 <expand macro="dbKeyActions"> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
36 <option type="from_data_table" name="bwa_indexes" column="1" offset="0"> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
37 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
38 <filter type="param_value" ref="reference_source.ref_file" column="0"/> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
39 </option> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
40 </expand> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
41 </macro> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
42 |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
43 <macro name="dbKeyActionsBwaMem"> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
44 <expand macro="dbKeyActions"> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
45 <option type="from_data_table" name="bwa_mem_indexes" column="1" offset="0"> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
46 <filter type="param_value" column="0" value="#" compare="startswith" keep="False"/> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
47 <filter type="param_value" ref="reference_source.ref_file" column="0"/> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
48 </option> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
49 </expand> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
50 </macro> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
51 |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
52 <macro name="dbKeyActions"> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
53 <actions> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
54 <conditional name="reference_source.reference_source_selector"> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
55 <when value="cached"> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
56 <action type="metadata" name="dbkey"> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
57 <yield /> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
58 </action> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
59 </when> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
60 <when value="history"> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
61 <action type="metadata" name="dbkey"> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
62 <option type="from_param" name="reference_source.ref_file" param_attribute="dbkey" /> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
63 </action> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
64 </when> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
65 </conditional> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
66 </actions> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
67 </macro> |
09a7281d24c5
planemo upload commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents:
5
diff
changeset
|
68 |
2 | 69 <token name="@RG@"> |
0 | 70 ----- |
71 | |
72 .. class:: warningmark | |
73 | |
74 **Read Groups are Important!** | |
75 | |
4
ac30bfd3e2a8
planemo upload commit a50a3947aebc8a1d11bac39599f4efd8ed9a3bd5
devteam
parents:
2
diff
changeset
|
76 One of the recommended best practices in NGS analysis is adding read group information to BAM files. You can do this directly in BWA interface using the |
2 | 77 **Specify read group information?** widget. If you are not familiar with read groups you shold know that this is effectively a way to tag reads with an additional ID. |
0 | 78 This allows you to combine BAM files from, for example, multiple BWA runs into a single dataset. This significantly simplifies downstream processing as |
2 | 79 instead of dealing with multiple datasets you only have to handle only one. This is possible because the read group information allows you to identify |
0 | 80 data from different experiments even if they are combined in one file. Many downstream analysis tools such as varinat callers (e.g., FreeBayes or Naive Varinat Caller |
81 present in Galaxy) are aware of readgtroups and will automatically generate calls for each individual sample even if they are combined within a single file. | |
82 | |
83 **Description of read groups fields** | |
84 | |
85 (from GATK FAQ webpage): | |
86 | |
87 .. csv-table:: | |
88 :header-rows: 1 | |
89 | |
90 Tag,Importance,Definition,Meaning | |
91 "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." | |
92 "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)." | |
93 "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." | |
94 "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." | |
95 | |
96 | |
97 **Example of Read Group usage** | |
98 | |
99 Suppose 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:: | |
100 | |
101 Dad's data: | |
102 @RG ID:FLOWCELL1.LANE1 PL:illumina LB:LIB-DAD-1 SM:DAD PI:200 | |
103 @RG ID:FLOWCELL1.LANE2 PL:illumina LB:LIB-DAD-1 SM:DAD PI:200 | |
104 @RG ID:FLOWCELL1.LANE3 PL:illumina LB:LIB-DAD-2 SM:DAD PI:400 | |
105 @RG ID:FLOWCELL1.LANE4 PL:illumina LB:LIB-DAD-2 SM:DAD PI:400 | |
106 | |
107 Mom's data: | |
108 @RG ID:FLOWCELL1.LANE5 PL:illumina LB:LIB-MOM-1 SM:MOM PI:200 | |
109 @RG ID:FLOWCELL1.LANE6 PL:illumina LB:LIB-MOM-1 SM:MOM PI:200 | |
110 @RG ID:FLOWCELL1.LANE7 PL:illumina LB:LIB-MOM-2 SM:MOM PI:400 | |
111 @RG ID:FLOWCELL1.LANE8 PL:illumina LB:LIB-MOM-2 SM:MOM PI:400 | |
112 | |
113 Kid's data: | |
114 @RG ID:FLOWCELL2.LANE1 PL:illumina LB:LIB-KID-1 SM:KID PI:200 | |
115 @RG ID:FLOWCELL2.LANE2 PL:illumina LB:LIB-KID-1 SM:KID PI:200 | |
116 @RG ID:FLOWCELL2.LANE3 PL:illumina LB:LIB-KID-2 SM:KID PI:400 | |
117 @RG ID:FLOWCELL2.LANE4 PL:illumina LB:LIB-KID-2 SM:KID PI:400 | |
118 | |
119 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). | |
2 | 120 </token> |
121 <token name="@info@"> | |
0 | 122 ----- |
123 | |
124 .. class:: infomark | |
125 | |
126 **More info** | |
127 | |
128 To obtain more information about BWA and ask questions use these resources: | |
129 | |
130 1. https://biostar.usegalaxy.org/ | |
131 2. https://www.biostars.org/ | |
132 3. https://github.com/lh3/bwa | |
133 4. http://bio-bwa.sourceforge.net/ | |
134 | |
2 | 135 </token> |
0 | 136 |
2 | 137 <token name="@dataset_collections@"> |
0 | 138 ------ |
139 | |
140 **Dataset collections - processing large numbers of datasets at once** | |
141 | |
4
ac30bfd3e2a8
planemo upload commit a50a3947aebc8a1d11bac39599f4efd8ed9a3bd5
devteam
parents:
2
diff
changeset
|
142 Dataset collections are in beta-testing. Extensive documentation will be added later this Spring. |
0 | 143 |
144 | |
2 | 145 </token> |
0 | 146 |
147 </macros> |