annotate picard_MarkDuplicatesWithMateCigar.xml @ 0:b76a4f17bbbb draft

Uploaded
author devteam
date Thu, 23 Oct 2014 11:31:30 -0400
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
1 <tool name="MarkDuplicatesWithMateCigar" id="picard_MarkDuplicatesWithMateCigar" 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/MarkDuplicatesWithMateCigar.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
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
24 MINIMUM_DISTANCE="${minimum_distance}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
25 SKIP_PAIRS_WITH_NO_MATE_CIGAR="${skip_pairs_with_no_mate_cigar}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
26
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
27
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
28 REMOVE_DUPLICATES="${remove_duplicates}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
29 ASSUME_SORTED="${assume_sorted}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
30
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
31 DUPLICATE_SCORING_STRATEGY="${duplicate_scoring_strategy}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
32
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
33 READ_NAME_REGEX="${read_name_regex}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
34 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
35
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
36
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
37 BLOCK_SIZE=100000
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
38 VALIDATION_STRINGENCY="${validation_stringency}"
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
39 QUIET=true
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
40 VERBOSITY=ERROR
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
41
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
42 </command>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
43 <inputs>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
44 <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
45 <param name="comment" type="text" size="50" label="Add this comment to BAM dataset"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
46 </repeat>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
47
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
48 <param name="minimum_distance" type="integer" value="-1" label="The minimum distance to buffer records to account for clipping on the 5' end of the records" help="MINIMUM_DISTANCE; Set this number to -1 to use twice the first read's read length (or 100, whichever is smaller); default=-1"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
49 <param name="skip_pairs_with_no_mate_cigar" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Skip record pairs with no mate cigar and include them in the output" help="SKIP_PAIRS_WITH_NO_MATE_CIGAR; default=True"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
50 <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
51 <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
52
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
53 <param name="duplicate_scoring_strategy" type="select" label="The scoring strategy for choosing the non-duplicate among candidates" help="DUPLICATE_SCORING_STRATEGY; default=TOTAL_MAPPED_REFERENCE_LENGTH">
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
54 <option value="TOTAL_MAPPED_REFERENCE_LENGTH" select="True">TOTAL_MAPPED_REFERENCE_LENGTH</option>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
55 <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
56 </param>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
57
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
58
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
59 <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
60 <sanitizer>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
61 <valid initial="string.printable">
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
62 </valid>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
63 </sanitizer>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
64 </param>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
65 <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
66
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
67 <expand macro="VS" />
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
68
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
69 </inputs>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
70
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
71 <outputs>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
72 <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: MarkDuplicate metrics"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
73 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: MarkDuplicates BAM output"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
74 </outputs>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
75
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
76 <tests>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
77 <test>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
78 <param name="inputFile" value="picard_MarkDuplicatesWithMateCigar.bam" ftype="bam"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
79 <param name="minimum_distance" value="-1"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
80 <param name="skip_pairs_with_no_mate_cigar" value="True"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
81 <param name="comment" value="test-run"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
82 <param name="assume_sorted" value="True"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
83 <param name="remove_duplicates" value="False"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
84 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
85 <param name="optical_duplicate_pixel_distance" value="100"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
86 <param name="duplicate_scoring_strategy" value="TOTAL_MAPPED_REFERENCE_LENGTH"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
87 <param name="validation_stringency" value="LENIENT"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
88 <output name="outFile" file="picard_MarkDuplicatesWithMateCigar_test1.bam" ftype="bam" lines_diff="4"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
89 </test>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
90 </tests>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
91
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
92 <stdio>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
93 <exit_code range="1:" level="fatal"/>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
94 </stdio>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
95
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
96 <help>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
97
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
98 **Purpose**
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
99
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
100 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
101
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
102 ------
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
103
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
104 .. class:: warningmark
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
105
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
106 On the difference between **MarkDuplicates** and **picard_MarkDuplicatesWithMateCigar**
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
107
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
108 From Samtools Announce MailingList_:
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
109
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
110 This tool can replace MarkDuplicates if the input SAM/BAM has Mate CIGAR (MC) optional tags pre-computed
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
111 (see the tools RevertOriginalBaseQualitiesAndAddMateCigar and FixMateInformation). This allows the new tool
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
112 to perform a streaming duplicate marking routine (i.e. a single-pass). This tool cannot be used with
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
113 alignments that have large gaps or reference skips, which happens frequently in RNA-seq data.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
114
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
115 .. _MailingList: http://sourceforge.net/p/samtools/mailman/message/32910359/
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
116
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
117 @dataset_collections@
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
118
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
119 @description@
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
120
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
121 MINIMUM_DISTANCE=Integer The minimum distance to buffer records to account for clipping on the 5' end of the
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
122 records.Set this number to -1 to use twice the first read's read length (or 100,
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
123 whichever is smaller). Default value: -1. This option can be set to 'null' to clear the
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
124 default value.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
125
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
126 SKIP_PAIRS_WITH_NO_MATE_CIGAR=Boolean
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
127 Skip record pairs with no mate cigar and include them in the output. Default value:
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
128 true. This option can be set to 'null' to clear the default value. Possible values:
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
129 {true, false}
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
130
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
131 COMMENT=String
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
132 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
133 more times.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
134
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
135 REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
136 appropriate flags set. Default value: false.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
137
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
138 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
139 names are parsed to extract three variables: tile/region, x coordinate and y coordinate.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
140 These values are used to estimate the rate of optical duplication in order to give a more
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
141 accurate estimated library size. Set this option to null to disable optical duplicate
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
142 detection. The regular expression should contain three capture groups for the three
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
143 variables, in order. It must match the entire read name. Note that if the default regex
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
144 is specified, a regex match is not actually done, but instead the read name is split on
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
145 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
146 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
147 are assumed to be tile, x and y values. Default value:
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
148 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
149
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
150 DUPLICATE_SCORING_STRATEGY=ScoringStrategy
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
151 DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value:
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
152 TOTAL_MAPPED_REFERENCE_LENGTH. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH}
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
153
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
154 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
155 The maximum offset between two duplicte clusters in order to consider them optical
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
156 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels)
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
157 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
158 which case 50-100 is more normal. Default value: 100.
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
159
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
160 @more_info@
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
161
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
162 </help>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
163 </tool>
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
164
b76a4f17bbbb Uploaded
devteam
parents:
diff changeset
165