Mercurial > repos > devteam > picard
annotate picard_MarkDuplicatesWithMateCigar.xml @ 17:fc288950c3b7 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
author | iuc |
---|---|
date | Thu, 13 Apr 2017 19:09:24 -0400 |
parents | 465cbb0cf2eb |
children | 5053a18d9bc8 |
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 | 2 <description>examine aligned records in BAM datasets to locate duplicate molecules</description> |
3 <macros> | |
4 <import>picard_macros.xml</import> | |
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" /> |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
7 <command detect_errors="exit_code"><![CDATA[ |
5 | 8 @java_options@ |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
9 @symlink_element_identifier@ |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
10 picard |
5 | 11 MarkDuplicatesWithMateCigar |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
12 |
14
465cbb0cf2eb
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 74ee0f0b594075fab7f707aaffb4a7f9dac35f2f
devteam
parents:
13
diff
changeset
|
13 INPUT='$escaped_element_identifier' |
5 | 14 OUTPUT="${outFile}" |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
15 |
5 | 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 | 19 MINIMUM_DISTANCE="${minimum_distance}" |
20 SKIP_PAIRS_WITH_NO_MATE_CIGAR="${skip_pairs_with_no_mate_cigar}" | |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
21 |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
22 |
5 | 23 REMOVE_DUPLICATES="${remove_duplicates}" |
24 ASSUME_SORTED="${assume_sorted}" | |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
25 |
5 | 26 DUPLICATE_SCORING_STRATEGY="${duplicate_scoring_strategy}" |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
27 |
6 | 28 #import pipes |
29 READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" } | |
5 | 30 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}" |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
31 |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
32 |
5 | 33 BLOCK_SIZE=100000 |
34 VALIDATION_STRINGENCY="${validation_stringency}" | |
35 QUIET=true | |
36 VERBOSITY=ERROR | |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
37 |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
38 ]]></command> |
5 | 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"/> | |
9
5eaa8a968300
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 1869970193a1878acbc0f8a79b81dd02b37f1dc1
devteam
parents:
8
diff
changeset
|
41 <param name="comment" type="text" label="Add this comment to BAM dataset"/> |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
42 |
5 | 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"> | |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
49 <option value="TOTAL_MAPPED_REFERENCE_LENGTH" selected="True">TOTAL_MAPPED_REFERENCE_LENGTH</option> |
5 | 50 <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option> |
51 </param> | |
52 | |
53 | |
9
5eaa8a968300
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 1869970193a1878acbc0f8a79b81dd02b37f1dc1
devteam
parents:
8
diff
changeset
|
54 <param name="read_name_regex" type="text" 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]+).*."> |
5 | 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" /> | |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
63 |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
64 </inputs> |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
65 |
5 | 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> | |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
70 |
5 | 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> | |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
86 |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
87 |
5 | 88 <help> |
89 | |
90 **Purpose** | |
91 | |
92 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. | |
93 | |
94 ------ | |
95 | |
96 .. class:: warningmark | |
97 | |
98 On the difference between **MarkDuplicates** and **picard_MarkDuplicatesWithMateCigar** | |
99 | |
100 From Samtools Announce MailingList_: | |
101 | |
102 This tool can replace MarkDuplicates if the input SAM/BAM has Mate CIGAR (MC) optional tags pre-computed | |
103 (see the tools RevertOriginalBaseQualitiesAndAddMateCigar and FixMateInformation). This allows the new tool | |
104 to perform a streaming duplicate marking routine (i.e. a single-pass). This tool cannot be used with | |
105 alignments that have large gaps or reference skips, which happens frequently in RNA-seq data. | |
106 | |
107 .. _MailingList: http://sourceforge.net/p/samtools/mailman/message/32910359/ | |
108 | |
109 @dataset_collections@ | |
110 | |
111 @description@ | |
112 | |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
113 MINIMUM_DISTANCE=Integer The minimum distance to buffer records to account for clipping on the 5' end of the |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
114 records.Set this number to -1 to use twice the first read's read length (or 100, |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
115 whichever is smaller). Default value: -1. This option can be set to 'null' to clear the |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
116 default value. |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
117 |
5 | 118 SKIP_PAIRS_WITH_NO_MATE_CIGAR=Boolean |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
119 Skip record pairs with no mate cigar and include them in the output. Default value: |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
120 true. This option can be set to 'null' to clear the default value. Possible values: |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
121 {true, false} |
5 | 122 |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
123 COMMENT=String |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
124 CO=String Comment(s) to include in the output file's header. This option may be specified 0 or |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
125 more times. |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
126 |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
127 REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
128 appropriate flags set. Default value: false. |
5 | 129 |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
130 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
131 names are parsed to extract three variables: tile/region, x coordinate and y coordinate. |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
132 These values are used to estimate the rate of optical duplication in order to give a more |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
133 accurate estimated library size. Set this option to null to disable optical duplicate |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
134 detection. The regular expression should contain three capture groups for the three |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
135 variables, in order. It must match the entire read name. Note that if the default regex |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
136 is specified, a regex match is not actually done, but instead the read name is split on |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
137 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
138 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
139 are assumed to be tile, x and y values. Default value: |
5 | 140 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*. |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
141 |
5 | 142 DUPLICATE_SCORING_STRATEGY=ScoringStrategy |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
143 DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value: |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
144 TOTAL_MAPPED_REFERENCE_LENGTH. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH} |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
145 |
5 | 146 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer |
13
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
147 The maximum offset between two duplicte clusters in order to consider them optical |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
148 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels) |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
149 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in |
7e6fd3d0f16e
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
devteam
parents:
12
diff
changeset
|
150 which case 50-100 is more normal. Default value: 100. |
5 | 151 |
152 @more_info@ | |
153 | |
154 </help> | |
155 </tool> | |
156 | |
157 |