annotate picard_MarkDuplicates.xml @ 12:05087b27692a draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
author devteam
date Sun, 27 Nov 2016 15:11:50 -0500
parents 5eaa8a968300
children 7e6fd3d0f16e
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
8
3a3234d7a2e8 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents: 6
diff changeset
1 <tool name="MarkDuplicates" id="picard_MarkDuplicates" version="@TOOL_VERSION@.0">
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
2 <description>examine aligned records in BAM datasets to locate duplicate molecules</description>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
3 <macros>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
4 <import>picard_macros.xml</import>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
5 </macros>
8
3a3234d7a2e8 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents: 6
diff changeset
6 <expand macro="requirements" />
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
7 <command detect_errors="exit_code"><![CDATA[
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
8 @java_options@
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
9
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
10 picard
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
11 MarkDuplicates
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
12
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
13 INPUT="${inputFile}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
14 OUTPUT="${outFile}"
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
15
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
16 METRICS_FILE="${metrics_file}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
17 #for $element in $comments:
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
18 COMMENT="${element.comment}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
19 #end for
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
20 REMOVE_DUPLICATES="${remove_duplicates}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
21 ASSUME_SORTED="${assume_sorted}"
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
22
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
23 DUPLICATE_SCORING_STRATEGY="${duplicate_scoring_strategy}"
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
24
6
4ff1e04010e6 Uploaded
devteam
parents: 5
diff changeset
25 #import pipes
4ff1e04010e6 Uploaded
devteam
parents: 5
diff changeset
26 READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" }
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
27 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}"
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
28
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
29 VALIDATION_STRINGENCY="${validation_stringency}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
30 QUIET=true
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
31 VERBOSITY=ERROR
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
32
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
33 ]]></command>
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
34 <inputs>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
35 <param format="bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
36 <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments">
9
5eaa8a968300 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 1869970193a1878acbc0f8a79b81dd02b37f1dc1
devteam
parents: 8
diff changeset
37 <param name="comment" type="text" label="Add this comment to BAM dataset"/>
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
38 </repeat>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
39 <param name="remove_duplicates" type="boolean" label="If true do not write duplicates to the output file instead of writing them with appropriate flags set" help="REMOVE_DUPLICATES; default=False"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
40 <param name="assume_sorted" type="boolean" label="Assume the input file is already sorted" checked="true" truevalue="true" falsevalue="false" help="ASSUME_SORTED; default=True"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
41
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
42 <param name="duplicate_scoring_strategy" type="select" label="The scoring strategy for choosing the non-duplicate among candidates" help="DUPLICATE_SCORING_STRATEGY; default=SUM_OF_BASE_QUALITIES">
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
43 <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
44 <option value="TOTAL_MAPPED_REFERENCE_LENGTH">TOTAL_MAPPED_REFERENCE_LENGTH</option>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
45 </param>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
46
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
47
9
5eaa8a968300 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 1869970193a1878acbc0f8a79b81dd02b37f1dc1
devteam
parents: 8
diff changeset
48 <param name="read_name_regex" type="text" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*." label="Regular expression that can be used to parse read names in the incoming SAM/BAM dataset" help="READ_NAME_REGEX; Read names are parsed to extract three variables: tile/region, x coordinate and y coordinate. These values are used to estimate the rate of optical duplication in order to give a more accurate estimated library size. See help below for more info; default=[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.">
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
49 <sanitizer>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
50 <valid initial="string.printable">
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
51 </valid>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
52 </sanitizer>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
53 </param>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
54 <param name="optical_duplicate_pixel_distance" type="integer" value="100" min="0" max="500" label="The maximum offset between two duplicte clusters in order to consider them optical duplicates" help="OPTICAL_DUPLICATE_PIXEL_DISTANCE; default=100"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
55
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
56 <expand macro="VS" />
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
57
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
58 </inputs>
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
59
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
60 <outputs>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
61 <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: MarkDuplicate metrics"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
62 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: MarkDuplicates BAM output"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
63 </outputs>
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
64
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
65 <tests>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
66 <test>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
67 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
68 <param name="comment" value="test-run"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
69 <param name="assume_sorted" value="True"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
70 <param name="remove_duplicates" value="True"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
71 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
72 <param name="optical_duplicate_pixel_distance" value="100"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
73 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
74 <param name="validation_stringency" value="LENIENT"/>
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
75 <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="4"/>
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
76 </test>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
77 </tests>
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
78
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
79
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
80 <help>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
81
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
82 **Purpose**
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
83
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
84 Examines aligned records in the supplied SAM or BAM dataset to locate duplicate molecules. All records are then written to the output file with the duplicate records flagged.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
85
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
86 @dataset_collections@
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
87
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
88 @description@
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
89
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
90 COMMENT=String
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
91 CO=String Comment(s) to include in the output file's header. This option may be specified 0 or
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
92 more times.
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
93
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
94 REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
95 appropriate flags set. Default value: false.
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
96
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
97 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
98 names are parsed to extract three variables: tile/region, x coordinate and y coordinate.
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
99 These values are used to estimate the rate of optical duplication in order to give a more
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
100 accurate estimated library size. Set this option to null to disable optical duplicate
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
101 detection. The regular expression should contain three capture groups for the three
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
102 variables, in order. It must match the entire read name. Note that if the default regex
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
103 is specified, a regex match is not actually done, but instead the read name is split on
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
104 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
105 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
106 are assumed to be tile, x and y values. Default value:
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
107 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
108
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
109 DUPLICATE_SCORING_STRATEGY=ScoringStrategy
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
110 DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value:
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
111 SUM_OF_BASE_QUALITIES. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH}
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
112
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
113 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
12
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
114 The maximum offset between two duplicte clusters in order to consider them optical
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
115 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels)
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
116 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in
05087b27692a planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents: 9
diff changeset
117 which case 50-100 is more normal. Default value: 100.
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
118
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
119 @more_info@
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
120
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
121 </help>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
122 </tool>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
123
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
124