|
0
|
1 <tool name="MarkDuplicatesWithMateCigar" id="picard_MarkDuplicatesWithMateCigar" version="1.135">
|
|
|
2 <description>examine aligned records in BAM datasets to locate duplicate molecules</description>
|
|
|
3 <macros>
|
|
|
4 <import>picard_macros.xml</import>
|
|
|
5 </macros>
|
|
|
6 <expand macro="requirements" />
|
|
|
7 <command>
|
|
|
8 @java_options@
|
|
|
9
|
|
|
10 java -jar \$JAVA_JAR_PATH/picard.jar
|
|
|
11 MarkDuplicatesWithMateCigar
|
|
|
12
|
|
|
13 INPUT="${inputFile}"
|
|
|
14 OUTPUT="${outFile}"
|
|
|
15
|
|
|
16 METRICS_FILE="${metrics_file}"
|
|
|
17 COMMENT="${comment}"
|
|
|
18
|
|
|
19 MINIMUM_DISTANCE="${minimum_distance}"
|
|
|
20 SKIP_PAIRS_WITH_NO_MATE_CIGAR="${skip_pairs_with_no_mate_cigar}"
|
|
|
21
|
|
|
22
|
|
|
23 REMOVE_DUPLICATES="${remove_duplicates}"
|
|
|
24 ASSUME_SORTED="${assume_sorted}"
|
|
|
25
|
|
|
26 DUPLICATE_SCORING_STRATEGY="${duplicate_scoring_strategy}"
|
|
|
27
|
|
|
28 #import pipes
|
|
|
29 READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" }
|
|
|
30 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}"
|
|
|
31
|
|
|
32
|
|
|
33 BLOCK_SIZE=100000
|
|
|
34 VALIDATION_STRINGENCY="${validation_stringency}"
|
|
|
35 QUIET=true
|
|
|
36 VERBOSITY=ERROR
|
|
|
37
|
|
|
38 </command>
|
|
|
39 <inputs>
|
|
|
40 <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"/>
|
|
|
41 <param name="comment" type="text" size="50" label="Add this comment to BAM dataset"/>
|
|
|
42
|
|
|
43 <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"/>
|
|
|
44 <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"/>
|
|
|
45 <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"/>
|
|
|
46 <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"/>
|
|
|
47
|
|
|
48 <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">
|
|
|
49 <option value="TOTAL_MAPPED_REFERENCE_LENGTH" select="True">TOTAL_MAPPED_REFERENCE_LENGTH</option>
|
|
|
50 <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option>
|
|
|
51 </param>
|
|
|
52
|
|
|
53
|
|
|
54 <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]+).*.">
|
|
|
55 <sanitizer>
|
|
|
56 <valid initial="string.printable">
|
|
|
57 </valid>
|
|
|
58 </sanitizer>
|
|
|
59 </param>
|
|
|
60 <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"/>
|
|
|
61
|
|
|
62 <expand macro="VS" />
|
|
|
63
|
|
|
64 </inputs>
|
|
|
65
|
|
|
66 <outputs>
|
|
|
67 <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: MarkDuplicate metrics"/>
|
|
|
68 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: MarkDuplicates BAM output"/>
|
|
|
69 </outputs>
|
|
|
70
|
|
|
71 <tests>
|
|
|
72 <test>
|
|
|
73 <param name="inputFile" value="picard_MarkDuplicatesWithMateCigar.bam" ftype="bam"/>
|
|
|
74 <param name="minimum_distance" value="-1"/>
|
|
|
75 <param name="skip_pairs_with_no_mate_cigar" value="True"/>
|
|
|
76 <param name="comment" value="test-run"/>
|
|
|
77 <param name="assume_sorted" value="True"/>
|
|
|
78 <param name="remove_duplicates" value="False"/>
|
|
|
79 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/>
|
|
|
80 <param name="optical_duplicate_pixel_distance" value="100"/>
|
|
|
81 <param name="duplicate_scoring_strategy" value="TOTAL_MAPPED_REFERENCE_LENGTH"/>
|
|
|
82 <param name="validation_stringency" value="LENIENT"/>
|
|
|
83 <output name="outFile" file="picard_MarkDuplicatesWithMateCigar_test1.bam" ftype="bam" lines_diff="4"/>
|
|
|
84 </test>
|
|
|
85 </tests>
|
|
|
86
|
|
|
87 <stdio>
|
|
|
88 <exit_code range="1:" level="fatal"/>
|
|
|
89 </stdio>
|
|
|
90
|
|
|
91 <help>
|
|
|
92
|
|
|
93 **Purpose**
|
|
|
94
|
|
|
95 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.
|
|
|
96
|
|
|
97 ------
|
|
|
98
|
|
|
99 .. class:: warningmark
|
|
|
100
|
|
|
101 On the difference between **MarkDuplicates** and **picard_MarkDuplicatesWithMateCigar**
|
|
|
102
|
|
|
103 From Samtools Announce MailingList_:
|
|
|
104
|
|
|
105 This tool can replace MarkDuplicates if the input SAM/BAM has Mate CIGAR (MC) optional tags pre-computed
|
|
|
106 (see the tools RevertOriginalBaseQualitiesAndAddMateCigar and FixMateInformation). This allows the new tool
|
|
|
107 to perform a streaming duplicate marking routine (i.e. a single-pass). This tool cannot be used with
|
|
|
108 alignments that have large gaps or reference skips, which happens frequently in RNA-seq data.
|
|
|
109
|
|
|
110 .. _MailingList: http://sourceforge.net/p/samtools/mailman/message/32910359/
|
|
|
111
|
|
|
112 @dataset_collections@
|
|
|
113
|
|
|
114 @description@
|
|
|
115
|
|
|
116 MINIMUM_DISTANCE=Integer The minimum distance to buffer records to account for clipping on the 5' end of the
|
|
|
117 records.Set this number to -1 to use twice the first read's read length (or 100,
|
|
|
118 whichever is smaller). Default value: -1. This option can be set to 'null' to clear the
|
|
|
119 default value.
|
|
|
120
|
|
|
121 SKIP_PAIRS_WITH_NO_MATE_CIGAR=Boolean
|
|
|
122 Skip record pairs with no mate cigar and include them in the output. Default value:
|
|
|
123 true. This option can be set to 'null' to clear the default value. Possible values:
|
|
|
124 {true, false}
|
|
|
125
|
|
|
126 COMMENT=String
|
|
|
127 CO=String Comment(s) to include in the output file's header. This option may be specified 0 or
|
|
|
128 more times.
|
|
|
129
|
|
|
130 REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with
|
|
|
131 appropriate flags set. Default value: false.
|
|
|
132
|
|
|
133 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read
|
|
|
134 names are parsed to extract three variables: tile/region, x coordinate and y coordinate.
|
|
|
135 These values are used to estimate the rate of optical duplication in order to give a more
|
|
|
136 accurate estimated library size. Set this option to null to disable optical duplicate
|
|
|
137 detection. The regular expression should contain three capture groups for the three
|
|
|
138 variables, in order. It must match the entire read name. Note that if the default regex
|
|
|
139 is specified, a regex match is not actually done, but instead the read name is split on
|
|
|
140 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
|
|
|
141 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
|
|
|
142 are assumed to be tile, x and y values. Default value:
|
|
|
143 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.
|
|
|
144
|
|
|
145 DUPLICATE_SCORING_STRATEGY=ScoringStrategy
|
|
|
146 DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value:
|
|
|
147 TOTAL_MAPPED_REFERENCE_LENGTH. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH}
|
|
|
148
|
|
|
149 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
|
|
|
150 The maximum offset between two duplicte clusters in order to consider them optical
|
|
|
151 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels)
|
|
|
152 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in
|
|
|
153 which case 50-100 is more normal. Default value: 100.
|
|
|
154
|
|
|
155 @more_info@
|
|
|
156
|
|
|
157 </help>
|
|
|
158 </tool>
|
|
|
159
|
|
|
160
|
