annotate picard_MarkDuplicatesWithMateCigar.xml @ 8:3a3234d7a2e8 draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
author devteam
date Thu, 16 Jul 2015 15:53:10 -0400
parents 4ff1e04010e6
children 5eaa8a968300
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
8
3a3234d7a2e8 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents: 6
diff changeset
1 <tool name="MarkDuplicatesWithMateCigar" id="picard_MarkDuplicatesWithMateCigar" version="@TOOL_VERSION@.0">
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
2 <description>examine aligned records in BAM datasets to locate duplicate molecules</description>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
3 <macros>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
4 <import>picard_macros.xml</import>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
5 </macros>
8
3a3234d7a2e8 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents: 6
diff changeset
6 <expand macro="requirements" />
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
7 <command>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
8 @java_options@
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
9
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
10 java -jar \$JAVA_JAR_PATH/picard.jar
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
11 MarkDuplicatesWithMateCigar
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
12
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
13 INPUT="${inputFile}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
14 OUTPUT="${outFile}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
15
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
16 METRICS_FILE="${metrics_file}"
8
3a3234d7a2e8 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents: 6
diff changeset
17 COMMENT="${comment}"
3a3234d7a2e8 planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 00a7926c285bc4a339bd7deebf40b28f39c7d947-dirty
devteam
parents: 6
diff changeset
18
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
19 MINIMUM_DISTANCE="${minimum_distance}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
20 SKIP_PAIRS_WITH_NO_MATE_CIGAR="${skip_pairs_with_no_mate_cigar}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
21
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
22
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
23 REMOVE_DUPLICATES="${remove_duplicates}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
24 ASSUME_SORTED="${assume_sorted}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
25
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
26 DUPLICATE_SCORING_STRATEGY="${duplicate_scoring_strategy}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
27
6
4ff1e04010e6 Uploaded
devteam
parents: 5
diff changeset
28 #import pipes
4ff1e04010e6 Uploaded
devteam
parents: 5
diff changeset
29 READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" }
5
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
30 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
31
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
32
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
33 BLOCK_SIZE=100000
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
34 VALIDATION_STRINGENCY="${validation_stringency}"
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
35 QUIET=true
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
36 VERBOSITY=ERROR
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
37
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
38 </command>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
39 <inputs>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
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"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
41 <param name="comment" type="text" size="50" label="Add this comment to BAM dataset"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
42
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
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"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
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"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
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"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
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"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
47
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
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">
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
49 <option value="TOTAL_MAPPED_REFERENCE_LENGTH" select="True">TOTAL_MAPPED_REFERENCE_LENGTH</option>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
50 <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
51 </param>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
52
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
53
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
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]+).*.">
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
55 <sanitizer>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
56 <valid initial="string.printable">
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
57 </valid>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
58 </sanitizer>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
59 </param>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
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"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
61
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
62 <expand macro="VS" />
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
63
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
64 </inputs>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
65
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
66 <outputs>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
67 <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: MarkDuplicate metrics"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
68 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: MarkDuplicates BAM output"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
69 </outputs>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
70
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
71 <tests>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
72 <test>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
73 <param name="inputFile" value="picard_MarkDuplicatesWithMateCigar.bam" ftype="bam"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
74 <param name="minimum_distance" value="-1"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
75 <param name="skip_pairs_with_no_mate_cigar" value="True"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
76 <param name="comment" value="test-run"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
77 <param name="assume_sorted" value="True"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
78 <param name="remove_duplicates" value="False"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
79 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
80 <param name="optical_duplicate_pixel_distance" value="100"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
81 <param name="duplicate_scoring_strategy" value="TOTAL_MAPPED_REFERENCE_LENGTH"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
82 <param name="validation_stringency" value="LENIENT"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
83 <output name="outFile" file="picard_MarkDuplicatesWithMateCigar_test1.bam" ftype="bam" lines_diff="4"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
84 </test>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
85 </tests>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
86
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
87 <stdio>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
88 <exit_code range="1:" level="fatal"/>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
89 </stdio>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
90
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
91 <help>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
92
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
93 **Purpose**
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
94
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
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.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
96
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
97 ------
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
98
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
99 .. class:: warningmark
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
100
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
101 On the difference between **MarkDuplicates** and **picard_MarkDuplicatesWithMateCigar**
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
102
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
103 From Samtools Announce MailingList_:
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
104
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
105 This tool can replace MarkDuplicates if the input SAM/BAM has Mate CIGAR (MC) optional tags pre-computed
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
106 (see the tools RevertOriginalBaseQualitiesAndAddMateCigar and FixMateInformation). This allows the new tool
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
107 to perform a streaming duplicate marking routine (i.e. a single-pass). This tool cannot be used with
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
108 alignments that have large gaps or reference skips, which happens frequently in RNA-seq data.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
109
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
110 .. _MailingList: http://sourceforge.net/p/samtools/mailman/message/32910359/
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
111
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
112 @dataset_collections@
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
113
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
114 @description@
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
115
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
116 MINIMUM_DISTANCE=Integer The minimum distance to buffer records to account for clipping on the 5' end of the
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
117 records.Set this number to -1 to use twice the first read's read length (or 100,
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
118 whichever is smaller). Default value: -1. This option can be set to 'null' to clear the
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
119 default value.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
120
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
121 SKIP_PAIRS_WITH_NO_MATE_CIGAR=Boolean
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
122 Skip record pairs with no mate cigar and include them in the output. Default value:
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
123 true. This option can be set to 'null' to clear the default value. Possible values:
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
124 {true, false}
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
125
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
126 COMMENT=String
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
127 CO=String Comment(s) to include in the output file's header. This option may be specified 0 or
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
128 more times.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
129
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
130 REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
131 appropriate flags set. Default value: false.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
132
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
133 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
134 names are parsed to extract three variables: tile/region, x coordinate and y coordinate.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
135 These values are used to estimate the rate of optical duplication in order to give a more
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
136 accurate estimated library size. Set this option to null to disable optical duplicate
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
137 detection. The regular expression should contain three capture groups for the three
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
138 variables, in order. It must match the entire read name. Note that if the default regex
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
139 is specified, a regex match is not actually done, but instead the read name is split on
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
140 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
141 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
142 are assumed to be tile, x and y values. Default value:
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
143 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
144
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
145 DUPLICATE_SCORING_STRATEGY=ScoringStrategy
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
146 DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value:
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
147 TOTAL_MAPPED_REFERENCE_LENGTH. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH}
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
148
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
149 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
150 The maximum offset between two duplicte clusters in order to consider them optical
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
151 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels)
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
152 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
153 which case 50-100 is more normal. Default value: 100.
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
154
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
155 @more_info@
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
156
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
157 </help>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
158 </tool>
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
159
3d4f1fa26f0e Uploaded
devteam
parents:
diff changeset
160