Mercurial > repos > devteam > picard
annotate picard_MarkDuplicates.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 | 7615ac66c6e5 |
rev | line source |
---|---|
17
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
1 <tool name="MarkDuplicates" id="picard_MarkDuplicates" version="@TOOL_VERSION@.1"> |
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 MarkDuplicates |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
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='$escaped_element_identifier' |
17
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
14 OUTPUT='${outFile}' |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
15 |
17
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
16 METRICS_FILE='${metrics_file}' |
5 | 17 #for $element in $comments: |
17
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
18 COMMENT='${element.comment}' |
5 | 19 #end for |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
20 |
17
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
21 REMOVE_DUPLICATES='${remove_duplicates}' |
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
22 ASSUME_SORTED='${assume_sorted}' |
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
23 |
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
24 DUPLICATE_SCORING_STRATEGY='${duplicate_scoring_strategy}' |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
25 |
6 | 26 #import pipes |
27 READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" } | |
17
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
28 OPTICAL_DUPLICATE_PIXEL_DISTANCE='${optical_duplicate_pixel_distance}' |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
29 |
17
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
30 # Optional arguments |
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
31 #if $barcode_tag: |
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
32 BARCODE_TAG='${barcode_tag}' |
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
33 #end if |
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
34 |
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
35 VALIDATION_STRINGENCY='${validation_stringency}' |
5 | 36 QUIET=true |
37 VERBOSITY=ERROR | |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
38 |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
39 ]]></command> |
5 | 40 <inputs> |
41 <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"/> | |
42 <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments"> | |
9
5eaa8a968300
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 1869970193a1878acbc0f8a79b81dd02b37f1dc1
devteam
parents:
8
diff
changeset
|
43 <param name="comment" type="text" label="Add this comment to BAM dataset"/> |
5 | 44 </repeat> |
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=SUM_OF_BASE_QUALITIES"> | |
49 <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option> | |
50 <option value="TOTAL_MAPPED_REFERENCE_LENGTH">TOTAL_MAPPED_REFERENCE_LENGTH</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 | |
17
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
62 <param name="barcode_tag" type="text" optional="True" label="Barcode Tag" help="Barcode SAM tag. This tag can be utilized when you have data from an assay that includes Unique Molecular Indices."/> |
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
63 |
5 | 64 <expand macro="VS" /> |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
65 |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
66 </inputs> |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
67 |
5 | 68 <outputs> |
69 <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: MarkDuplicate metrics"/> | |
70 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: MarkDuplicates BAM output"/> | |
71 </outputs> | |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
72 |
5 | 73 <tests> |
74 <test> | |
75 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/> | |
76 <param name="comment" value="test-run"/> | |
77 <param name="assume_sorted" value="True"/> | |
78 <param name="remove_duplicates" value="True"/> | |
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="SUM_OF_BASE_QUALITIES"/> | |
82 <param name="validation_stringency" value="LENIENT"/> | |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
83 <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="4"/> |
5 | 84 </test> |
85 </tests> | |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
86 |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
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 @dataset_collections@ | |
95 | |
96 @description@ | |
97 | |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
98 COMMENT=String |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
99 CO=String Comment(s) to include in the output file's header. This option may be specified 0 or |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
100 more times. |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
101 |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
102 REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
103 appropriate flags set. Default value: false. |
5 | 104 |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
105 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
106 names are parsed to extract three variables: tile/region, x coordinate and y coordinate. |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
107 These values are used to estimate the rate of optical duplication in order to give a more |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
108 accurate estimated library size. Set this option to null to disable optical duplicate |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
109 detection. The regular expression should contain three capture groups for the three |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
110 variables, in order. It must match the entire read name. Note that if the default regex |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
111 is specified, a regex match is not actually done, but instead the read name is split on |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
112 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
113 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
114 are assumed to be tile, x and y values. Default value: |
5 | 115 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*. |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
116 |
5 | 117 DUPLICATE_SCORING_STRATEGY=ScoringStrategy |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
118 DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value: |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
119 SUM_OF_BASE_QUALITIES. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH} |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
120 |
5 | 121 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer |
12
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
122 The maximum offset between two duplicte clusters in order to consider them optical |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
123 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels) |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
124 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in |
05087b27692a
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
devteam
parents:
9
diff
changeset
|
125 which case 50-100 is more normal. Default value: 100. |
5 | 126 |
17
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
127 BARCODE_TAG=String Barcode SAM tag (ex. BC for 10X Genomics) Default value: null. |
fc288950c3b7
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit a55cff7dfc145ed17ec2ee9f6a70d51c6f9d74b6
iuc
parents:
14
diff
changeset
|
128 |
5 | 129 @more_info@ |
130 | |
131 </help> | |
132 </tool> | |
133 | |
134 |