annotate picard_MarkDuplicates.xml @ 2:801f5e934011 draft default tip

Uploaded
author devteam
date Thu, 23 Oct 2014 11:40:52 -0400
parents b76a4f17bbbb
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
1 <tool name="MarkDuplicates" id="picard_MarkDuplicates" version="1.122.0">
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
2 <description>examine aligned records in BAM datasets to locate duplicate molecules</description>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
3 <requirements>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
4 <requirement type="package" version="1.122.0">picard</requirement>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
5 </requirements>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
6
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
7 <macros>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
8 <import>picard_macros.xml</import>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
9 </macros>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
10
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
11 <command>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
12 @java_options@
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
13
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
14 java -jar \$JAVA_JAR_PATH/MarkDuplicates.jar
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
15
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
16 INPUT="${inputFile}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
17 OUTPUT="${outFile}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
18
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
19 METRICS_FILE="${metrics_file}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
20 #for $element in $comments:
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
21 COMMENT="${element.comment}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
22 #end for
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
23 REMOVE_DUPLICATES="${remove_duplicates}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
24 ASSUME_SORTED="${assume_sorted}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
25
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
26 DUPLICATE_SCORING_STRATEGY="${duplicate_scoring_strategy}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
27
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
28 READ_NAME_REGEX="${read_name_regex}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
29 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
30
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
31 VALIDATION_STRINGENCY="${validation_stringency}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
32 QUIET=true
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
33 VERBOSITY=ERROR
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
34
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
35 </command>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
36 <inputs>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
37 <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"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
38 <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments">
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
39 <param name="comment" type="text" size="50" label="Add this comment to BAM dataset"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
40 </repeat>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
41 <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"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
42 <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"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
43
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
44 <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">
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
45 <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
46 <option value="TOTAL_MAPPED_REFERENCE_LENGTH">TOTAL_MAPPED_REFERENCE_LENGTH</option>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
47 </param>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
48
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
49
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
50 <param name="read_name_regex" type="text" size="40" 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]+).*.">
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
51 <sanitizer>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
52 <valid initial="string.printable">
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
53 </valid>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
54 </sanitizer>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
55 </param>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
56 <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"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
57
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
58 <expand macro="VS" />
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
59
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
60 </inputs>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
61
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
62 <outputs>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
63 <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: MarkDuplicate metrics"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
64 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: MarkDuplicates BAM output"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
65 </outputs>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
66
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
67 <tests>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
68 <test>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
69 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
70 <param name="comment" value="test-run"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
71 <param name="assume_sorted" value="True"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
72 <param name="remove_duplicates" value="True"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
73 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
74 <param name="optical_duplicate_pixel_distance" value="100"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
75 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
76 <param name="validation_stringency" value="LENIENT"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
77 <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="2"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
78 </test>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
79 </tests>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
80
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
81 <stdio>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
82 <exit_code range="1:" level="fatal"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
83 </stdio>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
84
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
85 <help>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
86
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
87 **Purpose**
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
88
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
89 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.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
90
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
91 @dataset_collections@
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
92
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
93 @description@
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
94
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
95 COMMENT=String
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
96 CO=String Comment(s) to include in the output file's header. This option may be specified 0 or
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
97 more times.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
98
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
99 REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
100 appropriate flags set. Default value: false.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
101
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
102 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
103 names are parsed to extract three variables: tile/region, x coordinate and y coordinate.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
104 These values are used to estimate the rate of optical duplication in order to give a more
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
105 accurate estimated library size. Set this option to null to disable optical duplicate
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
106 detection. The regular expression should contain three capture groups for the three
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
107 variables, in order. It must match the entire read name. Note that if the default regex
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
108 is specified, a regex match is not actually done, but instead the read name is split on
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
109 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
110 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
111 are assumed to be tile, x and y values. Default value:
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
112 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
113
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
114 DUPLICATE_SCORING_STRATEGY=ScoringStrategy
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
115 DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value:
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
116 SUM_OF_BASE_QUALITIES. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH}
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
117
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
118 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
119 The maximum offset between two duplicte clusters in order to consider them optical
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
120 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels)
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
121 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
122 which case 50-100 is more normal. Default value: 100.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
123
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
124 @more_info@
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
125
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
126 </help>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
127 </tool>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
128
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
129