Mercurial > repos > devteam > picard

comparison picard_MarkDuplicates.xml @ 5:3d4f1fa26f0e draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author devteam
date Tue, 16 Dec 2014 19:03:21 -0500
parents
children 4ff1e04010e6
comparison
equal deleted inserted replaced
4:ab1f60c26526 5:3d4f1fa26f0e
1 <tool name="MarkDuplicates" id="picard_MarkDuplicates" version="1.126.0">
2 <description>examine aligned records in BAM datasets to locate duplicate molecules</description>
3 <requirements>
4 <requirement type="package" version="1.126.0">picard</requirement>
5 </requirements>
6
7 <macros>
8 <import>picard_macros.xml</import>
9 </macros>
10
11 <command>
12 @java_options@
13
14 java -jar \$JAVA_JAR_PATH/picard.jar
15 MarkDuplicates
16
17 INPUT="${inputFile}"
18 OUTPUT="${outFile}"
19
20 METRICS_FILE="${metrics_file}"
21 #for $element in $comments:
22 COMMENT="${element.comment}"
23 #end for
24 REMOVE_DUPLICATES="${remove_duplicates}"
25 ASSUME_SORTED="${assume_sorted}"
26
27 DUPLICATE_SCORING_STRATEGY="${duplicate_scoring_strategy}"
28
29 READ_NAME_REGEX="${read_name_regex}"
30 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}"
31
32 VALIDATION_STRINGENCY="${validation_stringency}"
33 QUIET=true
34 VERBOSITY=ERROR
35
36 </command>
37 <inputs>
38 <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"/>
39 <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments">
40 <param name="comment" type="text" size="50" label="Add this comment to BAM dataset"/>
41 </repeat>
42 <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"/>
43 <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"/>
44
45 <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">
46 <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option>
47 <option value="TOTAL_MAPPED_REFERENCE_LENGTH">TOTAL_MAPPED_REFERENCE_LENGTH</option>
48 </param>
49
50
51 <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]+).*.">
52 <sanitizer>
53 <valid initial="string.printable">
54 </valid>
55 </sanitizer>
56 </param>
57 <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"/>
58
59 <expand macro="VS" />
60
61 </inputs>
62
63 <outputs>
64 <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: MarkDuplicate metrics"/>
65 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: MarkDuplicates BAM output"/>
66 </outputs>
67
68 <tests>
69 <test>
70 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/>
71 <param name="comment" value="test-run"/>
72 <param name="assume_sorted" value="True"/>
73 <param name="remove_duplicates" value="True"/>
74 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/>
75 <param name="optical_duplicate_pixel_distance" value="100"/>
76 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/>
77 <param name="validation_stringency" value="LENIENT"/>
78 <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="2"/>
79 </test>
80 </tests>
81
82 <stdio>
83 <exit_code range="1:" level="fatal"/>
84 </stdio>
85
86 <help>
87
88 **Purpose**
89
90 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.
91
92 @dataset_collections@
93
94 @description@
95
96 COMMENT=String
97 CO=String Comment(s) to include in the output file's header. This option may be specified 0 or
98 more times.
99
100 REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with
101 appropriate flags set. Default value: false.
102
103 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read
104 names are parsed to extract three variables: tile/region, x coordinate and y coordinate.
105 These values are used to estimate the rate of optical duplication in order to give a more
106 accurate estimated library size. Set this option to null to disable optical duplicate
107 detection. The regular expression should contain three capture groups for the three
108 variables, in order. It must match the entire read name. Note that if the default regex
109 is specified, a regex match is not actually done, but instead the read name is split on
110 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
111 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
112 are assumed to be tile, x and y values. Default value:
113 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.
114
115 DUPLICATE_SCORING_STRATEGY=ScoringStrategy
116 DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value:
117 SUM_OF_BASE_QUALITIES. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH}
118
119 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
120 The maximum offset between two duplicte clusters in order to consider them optical
121 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels)
122 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in
123 which case 50-100 is more normal. Default value: 100.
124
125 @more_info@
126
127 </help>
128 </tool>
129
130