annotate picard_MarkDuplicates.xml @ 2:4aa5b444fd42 draft default tip

Deleted selected files
author devteam
date Tue, 16 Dec 2014 16:50:01 -0500
parents 4419e9980172
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
4419e9980172 Uploaded
devteam
parents:
diff changeset
1 <tool name="MarkDuplicates" id="picard_MarkDuplicates" version="1.122.0">
4419e9980172 Uploaded
devteam
parents:
diff changeset
2 <description>examine aligned records in BAM datasets to locate duplicate molecules</description>
4419e9980172 Uploaded
devteam
parents:
diff changeset
3 <requirements>
4419e9980172 Uploaded
devteam
parents:
diff changeset
4 <requirement type="package" version="1.122.0">picard</requirement>
4419e9980172 Uploaded
devteam
parents:
diff changeset
5 </requirements>
4419e9980172 Uploaded
devteam
parents:
diff changeset
6
4419e9980172 Uploaded
devteam
parents:
diff changeset
7 <macros>
4419e9980172 Uploaded
devteam
parents:
diff changeset
8 <import>picard_macros.xml</import>
4419e9980172 Uploaded
devteam
parents:
diff changeset
9 </macros>
4419e9980172 Uploaded
devteam
parents:
diff changeset
10
4419e9980172 Uploaded
devteam
parents:
diff changeset
11 <command>
4419e9980172 Uploaded
devteam
parents:
diff changeset
12 @java_options@
4419e9980172 Uploaded
devteam
parents:
diff changeset
13
4419e9980172 Uploaded
devteam
parents:
diff changeset
14 java -jar \$JAVA_JAR_PATH/MarkDuplicates.jar
4419e9980172 Uploaded
devteam
parents:
diff changeset
15
4419e9980172 Uploaded
devteam
parents:
diff changeset
16 INPUT="${inputFile}"
4419e9980172 Uploaded
devteam
parents:
diff changeset
17 OUTPUT="${outFile}"
4419e9980172 Uploaded
devteam
parents:
diff changeset
18
4419e9980172 Uploaded
devteam
parents:
diff changeset
19 METRICS_FILE="${metrics_file}"
4419e9980172 Uploaded
devteam
parents:
diff changeset
20 #for $element in $comments:
4419e9980172 Uploaded
devteam
parents:
diff changeset
21 COMMENT="${element.comment}"
4419e9980172 Uploaded
devteam
parents:
diff changeset
22 #end for
4419e9980172 Uploaded
devteam
parents:
diff changeset
23 REMOVE_DUPLICATES="${remove_duplicates}"
4419e9980172 Uploaded
devteam
parents:
diff changeset
24 ASSUME_SORTED="${assume_sorted}"
4419e9980172 Uploaded
devteam
parents:
diff changeset
25
4419e9980172 Uploaded
devteam
parents:
diff changeset
26 DUPLICATE_SCORING_STRATEGY="${duplicate_scoring_strategy}"
4419e9980172 Uploaded
devteam
parents:
diff changeset
27
4419e9980172 Uploaded
devteam
parents:
diff changeset
28 READ_NAME_REGEX="${read_name_regex}"
4419e9980172 Uploaded
devteam
parents:
diff changeset
29 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}"
4419e9980172 Uploaded
devteam
parents:
diff changeset
30
4419e9980172 Uploaded
devteam
parents:
diff changeset
31 VALIDATION_STRINGENCY="${validation_stringency}"
4419e9980172 Uploaded
devteam
parents:
diff changeset
32 QUIET=true
4419e9980172 Uploaded
devteam
parents:
diff changeset
33 VERBOSITY=ERROR
4419e9980172 Uploaded
devteam
parents:
diff changeset
34
4419e9980172 Uploaded
devteam
parents:
diff changeset
35 </command>
4419e9980172 Uploaded
devteam
parents:
diff changeset
36 <inputs>
4419e9980172 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"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
38 <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments">
4419e9980172 Uploaded
devteam
parents:
diff changeset
39 <param name="comment" type="text" size="50" label="Add this comment to BAM dataset"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
40 </repeat>
4419e9980172 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"/>
4419e9980172 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"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
43
4419e9980172 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">
4419e9980172 Uploaded
devteam
parents:
diff changeset
45 <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option>
4419e9980172 Uploaded
devteam
parents:
diff changeset
46 <option value="TOTAL_MAPPED_REFERENCE_LENGTH">TOTAL_MAPPED_REFERENCE_LENGTH</option>
4419e9980172 Uploaded
devteam
parents:
diff changeset
47 </param>
4419e9980172 Uploaded
devteam
parents:
diff changeset
48
4419e9980172 Uploaded
devteam
parents:
diff changeset
49
4419e9980172 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]+).*.">
4419e9980172 Uploaded
devteam
parents:
diff changeset
51 <sanitizer>
4419e9980172 Uploaded
devteam
parents:
diff changeset
52 <valid initial="string.printable">
4419e9980172 Uploaded
devteam
parents:
diff changeset
53 </valid>
4419e9980172 Uploaded
devteam
parents:
diff changeset
54 </sanitizer>
4419e9980172 Uploaded
devteam
parents:
diff changeset
55 </param>
4419e9980172 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"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
57
4419e9980172 Uploaded
devteam
parents:
diff changeset
58 <expand macro="VS" />
4419e9980172 Uploaded
devteam
parents:
diff changeset
59
4419e9980172 Uploaded
devteam
parents:
diff changeset
60 </inputs>
4419e9980172 Uploaded
devteam
parents:
diff changeset
61
4419e9980172 Uploaded
devteam
parents:
diff changeset
62 <outputs>
4419e9980172 Uploaded
devteam
parents:
diff changeset
63 <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: MarkDuplicate metrics"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
64 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: MarkDuplicates BAM output"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
65 </outputs>
4419e9980172 Uploaded
devteam
parents:
diff changeset
66
4419e9980172 Uploaded
devteam
parents:
diff changeset
67 <tests>
4419e9980172 Uploaded
devteam
parents:
diff changeset
68 <test>
4419e9980172 Uploaded
devteam
parents:
diff changeset
69 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
70 <param name="comment" value="test-run"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
71 <param name="assume_sorted" value="True"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
72 <param name="remove_duplicates" value="True"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
73 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
74 <param name="optical_duplicate_pixel_distance" value="100"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
75 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
76 <param name="validation_stringency" value="LENIENT"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
77 <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="2"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
78 </test>
4419e9980172 Uploaded
devteam
parents:
diff changeset
79 </tests>
4419e9980172 Uploaded
devteam
parents:
diff changeset
80
4419e9980172 Uploaded
devteam
parents:
diff changeset
81 <stdio>
4419e9980172 Uploaded
devteam
parents:
diff changeset
82 <exit_code range="1:" level="fatal"/>
4419e9980172 Uploaded
devteam
parents:
diff changeset
83 </stdio>
4419e9980172 Uploaded
devteam
parents:
diff changeset
84
4419e9980172 Uploaded
devteam
parents:
diff changeset
85 <help>
4419e9980172 Uploaded
devteam
parents:
diff changeset
86
4419e9980172 Uploaded
devteam
parents:
diff changeset
87 **Purpose**
4419e9980172 Uploaded
devteam
parents:
diff changeset
88
4419e9980172 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.
4419e9980172 Uploaded
devteam
parents:
diff changeset
90
4419e9980172 Uploaded
devteam
parents:
diff changeset
91 @dataset_collections@
4419e9980172 Uploaded
devteam
parents:
diff changeset
92
4419e9980172 Uploaded
devteam
parents:
diff changeset
93 @description@
4419e9980172 Uploaded
devteam
parents:
diff changeset
94
4419e9980172 Uploaded
devteam
parents:
diff changeset
95 COMMENT=String
4419e9980172 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
4419e9980172 Uploaded
devteam
parents:
diff changeset
97 more times.
4419e9980172 Uploaded
devteam
parents:
diff changeset
98
4419e9980172 Uploaded
devteam
parents:
diff changeset
99 REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with
4419e9980172 Uploaded
devteam
parents:
diff changeset
100 appropriate flags set. Default value: false.
4419e9980172 Uploaded
devteam
parents:
diff changeset
101
4419e9980172 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
4419e9980172 Uploaded
devteam
parents:
diff changeset
103 names are parsed to extract three variables: tile/region, x coordinate and y coordinate.
4419e9980172 Uploaded
devteam
parents:
diff changeset
104 These values are used to estimate the rate of optical duplication in order to give a more
4419e9980172 Uploaded
devteam
parents:
diff changeset
105 accurate estimated library size. Set this option to null to disable optical duplicate
4419e9980172 Uploaded
devteam
parents:
diff changeset
106 detection. The regular expression should contain three capture groups for the three
4419e9980172 Uploaded
devteam
parents:
diff changeset
107 variables, in order. It must match the entire read name. Note that if the default regex
4419e9980172 Uploaded
devteam
parents:
diff changeset
108 is specified, a regex match is not actually done, but instead the read name is split on
4419e9980172 Uploaded
devteam
parents:
diff changeset
109 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
4419e9980172 Uploaded
devteam
parents:
diff changeset
110 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
4419e9980172 Uploaded
devteam
parents:
diff changeset
111 are assumed to be tile, x and y values. Default value:
4419e9980172 Uploaded
devteam
parents:
diff changeset
112 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.
4419e9980172 Uploaded
devteam
parents:
diff changeset
113
4419e9980172 Uploaded
devteam
parents:
diff changeset
114 DUPLICATE_SCORING_STRATEGY=ScoringStrategy
4419e9980172 Uploaded
devteam
parents:
diff changeset
115 DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value:
4419e9980172 Uploaded
devteam
parents:
diff changeset
116 SUM_OF_BASE_QUALITIES. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH}
4419e9980172 Uploaded
devteam
parents:
diff changeset
117
4419e9980172 Uploaded
devteam
parents:
diff changeset
118 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
4419e9980172 Uploaded
devteam
parents:
diff changeset
119 The maximum offset between two duplicte clusters in order to consider them optical
4419e9980172 Uploaded
devteam
parents:
diff changeset
120 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels)
4419e9980172 Uploaded
devteam
parents:
diff changeset
121 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in
4419e9980172 Uploaded
devteam
parents:
diff changeset
122 which case 50-100 is more normal. Default value: 100.
4419e9980172 Uploaded
devteam
parents:
diff changeset
123
4419e9980172 Uploaded
devteam
parents:
diff changeset
124 @more_info@
4419e9980172 Uploaded
devteam
parents:
diff changeset
125
4419e9980172 Uploaded
devteam
parents:
diff changeset
126 </help>
4419e9980172 Uploaded
devteam
parents:
diff changeset
127 </tool>
4419e9980172 Uploaded
devteam
parents:
diff changeset
128
4419e9980172 Uploaded
devteam
parents:
diff changeset
129