Mercurial > repos > devteam > picard

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