Mercurial > repos > devteam > picard

comparison picard_MarkDuplicates.xml @ 33:3f254c5ced1d draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/picard commit 9ecbbb878d68a980ba35a90865e524c723ca3ed8
author iuc
date Sun, 03 Mar 2024 16:06:11 +0000
parents f9242e01365a
children
comparison
equal deleted inserted replaced
32:f9242e01365a 33:3f254c5ced1d
1 <tool name="MarkDuplicates" id="picard_MarkDuplicates" version="@TOOL_VERSION@.@WRAPPER_VERSION@"> 1 <tool name="MarkDuplicates" id="picard_MarkDuplicates" version="@TOOL_VERSION@.@WRAPPER_VERSION@" profile="@PROFILE@">
2 <description>examine aligned records in BAM datasets to locate duplicate molecules</description> 2 <description>examine aligned records in BAM datasets to locate duplicate molecules</description>
3 <macros> 3 <macros>
4 <import>picard_macros.xml</import> 4 <import>picard_macros.xml</import>
5 <token name="@WRAPPER_VERSION@">4</token> 5 <token name="@WRAPPER_VERSION@">0</token>
6 </macros> 6 </macros>
7 <expand macro="requirements" /> 7 <expand macro="requirements"/>
8 <command detect_errors="exit_code"><![CDATA[ 8 <command detect_errors="exit_code"><![CDATA[
9 @java_options@ 9 @java_options@
10 @symlink_element_identifier@ 10 @symlink_element_identifier@
11 picard 11 picard MarkDuplicates
12 MarkDuplicates
13 12
14 INPUT='$escaped_element_identifier' 13 --INPUT '$escaped_element_identifier'
15 OUTPUT='${outFile}' 14 --OUTPUT '${outFile}'
16 15
17 METRICS_FILE='${metrics_file}' 16 --METRICS_FILE '${metrics_file}'
18 #for $element in $comments: 17 #for $element in $comments:
19 COMMENT='${element.comment}' 18 --COMMENT '${element.comment}'
20 #end for 19 #end for
21 20
22 REMOVE_DUPLICATES='${remove_duplicates}' 21 --REMOVE_DUPLICATES '${remove_duplicates}'
23 ASSUME_SORTED='${assume_sorted}' 22 --ASSUME_SORTED '${assume_sorted}'
24 23
25 DUPLICATE_SCORING_STRATEGY='${duplicate_scoring_strategy}' 24 --DUPLICATE_SCORING_STRATEGY ${duplicate_scoring_strategy}
26 25
27 #if $read_name_regex: 26 #if $read_name_regex:
28 READ_NAME_REGEX='${ str( $read_name_regex ) }' 27 --READ_NAME_REGEX '${ str( $read_name_regex ) }'
29 #end if 28 #end if
30 OPTICAL_DUPLICATE_PIXEL_DISTANCE='${optical_duplicate_pixel_distance}' 29 --OPTICAL_DUPLICATE_PIXEL_DISTANCE '${optical_duplicate_pixel_distance}'
31 30
32 #if $barcode_tag: 31 #if $barcode_tag:
33 BARCODE_TAG='${barcode_tag}' 32 --BARCODE_TAG '${barcode_tag}'
34 #end if 33 #end if
35 34
36 VALIDATION_STRINGENCY='${validation_stringency}' 35 --VALIDATION_STRINGENCY '${validation_stringency}'
37 TAGGING_POLICY=All 36 --TAGGING_POLICY All
38 QUIET=true 37 --QUIET true
39 VERBOSITY=ERROR 38 --VERBOSITY ERROR
40 39
41 ]]></command> 40 ]]></command>
42 <inputs> 41 <inputs>
43 <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 <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"/>
44 <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments"> 43 <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments">
45 <param name="comment" type="text" label="Add this comment to BAM dataset"/> 44 <param name="comment" type="text" label="Add this comment to BAM dataset"/>
46 </repeat> 45 </repeat>
47 <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="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"/>
48 <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 <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"/>
49 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">
50 <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" selected="true">SUM_OF_BASE_QUALITIES</option>
51 <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option> 50 <option value="TOTAL_MAPPED_REFERENCE_LENGTH">TOTAL_MAPPED_REFERENCE_LENGTH</option>
52 <option value="TOTAL_MAPPED_REFERENCE_LENGTH">TOTAL_MAPPED_REFERENCE_LENGTH</option> 51 <option value="RANDOM">RANDOM</option>
53 </param> 52 </param>
54 53 <param name="read_name_regex" type="text" value="" label="Regular expression that can be used in unusual situations to parse non-standard 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='' (uses : separation)">
55 <param name="read_name_regex" type="text" value="" label="Regular expression that can be used in unusual situations to parse non-standard 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='' (uses : separation)"> 54 <expand macro="sanitize_query"/>
56 <expand macro="sanitize_query" /> 55 </param>
57 </param> 56 <param name="optical_duplicate_pixel_distance" type="integer" value="100" min="0" max="5000" label="The maximum offset between two duplicte clusters in order to consider them optical duplicates" help="OPTICAL_DUPLICATE_PIXEL_DISTANCE; default=100"/>
58 <param name="optical_duplicate_pixel_distance" type="integer" value="100" min="0" max="5000" label="The maximum offset between two duplicte clusters in order to consider them optical duplicates" help="OPTICAL_DUPLICATE_PIXEL_DISTANCE; default=100"/> 57 <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. Typically 'RX' "/>
59 58 <expand macro="VS"/>
60 <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. Typically 'RX' "/> 59 </inputs>
61 60 <outputs>
62 <expand macro="VS" /> 61 <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: tabular"/>
63 62 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: BAM"/>
64 </inputs> 63 </outputs>
65 64 <tests>
66 <outputs> 65 <test>
67 <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: tabular"/> 66 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/>
68 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: BAM"/> 67 <param name="comment" value="test-run"/>
69 </outputs> 68 <param name="assume_sorted" value="True"/>
70 69 <param name="remove_duplicates" value="True"/>
71 <tests> 70 <param name="read_name_regex" value=".*[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*"/>
72 <test> 71 <param name="optical_duplicate_pixel_distance" value="100"/>
73 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/> 72 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/>
74 <param name="comment" value="test-run"/> 73 <param name="validation_stringency" value="LENIENT"/>
75 <param name="assume_sorted" value="True"/> 74 <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="4"/>
76 <param name="remove_duplicates" value="True"/> 75 </test>
77 <param name="read_name_regex" value=".*[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*"/> 76 <test>
78 <param name="optical_duplicate_pixel_distance" value="100"/> 77 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/>
79 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/> 78 <param name="comment" value="test-run"/>
80 <param name="validation_stringency" value="LENIENT"/> 79 <param name="assume_sorted" value="True"/>
81 <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="4"/> 80 <param name="remove_duplicates" value="False"/>
82 </test> 81 <param name="read_name_regex" value=""/>
83 <test> 82 <param name="optical_duplicate_pixel_distance" value="100"/>
84 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/> 83 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/>
85 <param name="comment" value="test-run"/> 84 <param name="validation_stringency" value="LENIENT"/>
86 <param name="assume_sorted" value="True"/> 85 <output name="outFile" file="picard_MarkDuplicates_test2.bam" ftype="bam" lines_diff="4"/>
87 <param name="remove_duplicates" value="False"/> 86 </test>
88 <param name="read_name_regex" value=""/> 87 <test>
89 <param name="optical_duplicate_pixel_distance" value="100"/> 88 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/>
90 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/> 89 <param name="comment" value="test-run"/>
91 <param name="validation_stringency" value="LENIENT"/> 90 <param name="assume_sorted" value="True"/>
92 <output name="outFile" file="picard_MarkDuplicates_test2.bam" ftype="bam" lines_diff="4"/> 91 <param name="remove_duplicates" value="False"/>
93 </test> 92 <param name="read_name_regex" value=""/>
94 <test> 93 <param name="optical_duplicate_pixel_distance" value="100"/>
95 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/> 94 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/>
96 <param name="comment" value="test-run"/> 95 <param name="validation_stringency" value="LENIENT"/>
97 <param name="assume_sorted" value="True"/> 96 <param name="barcode_tag" value="RX"/>
98 <param name="remove_duplicates" value="False"/> 97 <output name="outFile" file="picard_MarkDuplicates_test2.bam" ftype="bam" lines_diff="4"/>
99 <param name="read_name_regex" value=""/> 98 </test>
100 <param name="optical_duplicate_pixel_distance" value="100"/> 99 </tests>
101 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/> 100 <help>
102 <param name="validation_stringency" value="LENIENT"/>
103 <param name='barcode_tag' value="RX"/>
104 <output name="outFile" file="picard_MarkDuplicates_test2.bam" ftype="bam" lines_diff="4"/>
105 </test>
106 </tests>
107
108
109 <help>
110 101
111 **Purpose** 102 **Purpose**
112 103
113 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. 104 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.
114 105
151 BARCODE_TAG=String Barcode SAM tag (ex. BC for 10X Genomics) Default value: null. 142 BARCODE_TAG=String Barcode SAM tag (ex. BC for 10X Genomics) Default value: null.
152 143
153 @more_info@ 144 @more_info@
154 145
155 </help> 146 </help>
156 <expand macro="citations" /> 147 <expand macro="citations"/>
157 </tool> 148 </tool>