Mercurial > repos > devteam > picard

comparison picard_MarkDuplicates.xml @ 7:08f69add4d06 draft

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-devteam/tree/master/tools/picard commit 7491208ca0c917a053798a48c3e54c3e30e95d92
author devteam
date Sun, 27 Nov 2016 15:11:36 -0500
parents 2589e6207cb4
children e417b1d6288d
comparison
equal deleted inserted replaced
6:961236c5ec73 7:08f69add4d06
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 </macros> 5 </macros>
6 <expand macro="requirements" /> 6 <expand macro="requirements" />
7 <command> 7 <command detect_errors="exit_code"><![CDATA[
8 @java_options@ 8 @java_options@
9 9
10 java -jar \$JAVA_JAR_PATH/picard.jar 10 picard
11 MarkDuplicates 11 MarkDuplicates
12 12
13 INPUT="${inputFile}" 13 INPUT="${inputFile}"
14 OUTPUT="${outFile}" 14 OUTPUT="${outFile}"
15 15
16 METRICS_FILE="${metrics_file}" 16 METRICS_FILE="${metrics_file}"
17 #for $element in $comments: 17 #for $element in $comments:
18 COMMENT="${element.comment}" 18 COMMENT="${element.comment}"
19 #end for 19 #end for
20 REMOVE_DUPLICATES="${remove_duplicates}" 20 REMOVE_DUPLICATES="${remove_duplicates}"
21 ASSUME_SORTED="${assume_sorted}" 21 ASSUME_SORTED="${assume_sorted}"
22 22
23 DUPLICATE_SCORING_STRATEGY="${duplicate_scoring_strategy}" 23 DUPLICATE_SCORING_STRATEGY="${duplicate_scoring_strategy}"
24 24
25 #import pipes 25 #import pipes
26 READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" } 26 READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" }
27 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}" 27 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}"
28 28
29 VALIDATION_STRINGENCY="${validation_stringency}" 29 VALIDATION_STRINGENCY="${validation_stringency}"
30 QUIET=true 30 QUIET=true
31 VERBOSITY=ERROR 31 VERBOSITY=ERROR
32 32
33 </command> 33 ]]></command>
34 <inputs> 34 <inputs>
35 <param format="bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/> 35 <param format="bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/>
36 <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments"> 36 <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments">
37 <param name="comment" type="text" label="Add this comment to BAM dataset"/> 37 <param name="comment" type="text" label="Add this comment to BAM dataset"/>
38 </repeat> 38 </repeat>
52 </sanitizer> 52 </sanitizer>
53 </param> 53 </param>
54 <param name="optical_duplicate_pixel_distance" type="integer" value="100" min="0" max="500" label="The maximum offset between two duplicte clusters in order to consider them optical duplicates" help="OPTICAL_DUPLICATE_PIXEL_DISTANCE; default=100"/> 54 <param name="optical_duplicate_pixel_distance" type="integer" value="100" min="0" max="500" label="The maximum offset between two duplicte clusters in order to consider them optical duplicates" help="OPTICAL_DUPLICATE_PIXEL_DISTANCE; default=100"/>
55 55
56 <expand macro="VS" /> 56 <expand macro="VS" />
57 57
58 </inputs> 58 </inputs>
59 59
60 <outputs> 60 <outputs>
61 <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: MarkDuplicate metrics"/> 61 <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: MarkDuplicate metrics"/>
62 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: MarkDuplicates BAM output"/> 62 <data format="bam" name="outFile" label="${tool.name} on ${on_string}: MarkDuplicates BAM output"/>
63 </outputs> 63 </outputs>
64 64
65 <tests> 65 <tests>
66 <test> 66 <test>
67 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/> 67 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/>
68 <param name="comment" value="test-run"/> 68 <param name="comment" value="test-run"/>
69 <param name="assume_sorted" value="True"/> 69 <param name="assume_sorted" value="True"/>
70 <param name="remove_duplicates" value="True"/> 70 <param name="remove_duplicates" value="True"/>
71 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/> 71 <param name="read_name_regex" value="[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*."/>
72 <param name="optical_duplicate_pixel_distance" value="100"/> 72 <param name="optical_duplicate_pixel_distance" value="100"/>
73 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/> 73 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/>
74 <param name="validation_stringency" value="LENIENT"/> 74 <param name="validation_stringency" value="LENIENT"/>
75 <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="2"/> 75 <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="4"/>
76 </test> 76 </test>
77 </tests> 77 </tests>
78 78
79 <stdio> 79
80 <exit_code range="1:" level="fatal"/>
81 </stdio>
82
83 <help> 80 <help>
84 81
85 **Purpose** 82 **Purpose**
86 83
87 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. 84 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.
88 85
89 @dataset_collections@ 86 @dataset_collections@
90 87
91 @description@ 88 @description@
92 89
93 COMMENT=String 90 COMMENT=String
94 CO=String Comment(s) to include in the output file's header. This option may be specified 0 or 91 CO=String Comment(s) to include in the output file's header. This option may be specified 0 or
95 more times. 92 more times.
96 93
97 REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with 94 REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with
98 appropriate flags set. Default value: false. 95 appropriate flags set. Default value: false.
99 96
100 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read 97 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read
101 names are parsed to extract three variables: tile/region, x coordinate and y coordinate. 98 names are parsed to extract three variables: tile/region, x coordinate and y coordinate.
102 These values are used to estimate the rate of optical duplication in order to give a more 99 These values are used to estimate the rate of optical duplication in order to give a more
103 accurate estimated library size. Set this option to null to disable optical duplicate 100 accurate estimated library size. Set this option to null to disable optical duplicate
104 detection. The regular expression should contain three capture groups for the three 101 detection. The regular expression should contain three capture groups for the three
105 variables, in order. It must match the entire read name. Note that if the default regex 102 variables, in order. It must match the entire read name. Note that if the default regex
106 is specified, a regex match is not actually done, but instead the read name is split on 103 is specified, a regex match is not actually done, but instead the read name is split on
107 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be 104 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
108 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements 105 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
109 are assumed to be tile, x and y values. Default value: 106 are assumed to be tile, x and y values. Default value:
110 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*. 107 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*.
111 108
112 DUPLICATE_SCORING_STRATEGY=ScoringStrategy 109 DUPLICATE_SCORING_STRATEGY=ScoringStrategy
113 DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value: 110 DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value:
114 SUM_OF_BASE_QUALITIES. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH} 111 SUM_OF_BASE_QUALITIES. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH}
115 112
116 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer 113 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
117 The maximum offset between two duplicte clusters in order to consider them optical 114 The maximum offset between two duplicte clusters in order to consider them optical
118 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels) 115 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels)
119 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in 116 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in
120 which case 50-100 is more normal. Default value: 100. 117 which case 50-100 is more normal. Default value: 100.
121 118
122 @more_info@ 119 @more_info@
123 120
124 </help> 121 </help>
125 </tool> 122 </tool>