Mercurial > repos > devteam > picard

comparison picard_MarkDuplicates.xml @ 18:7615ac66c6e5 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-iuc/tree/master/tools/picard commit 3ce5dea3af8f4816b4a83914b53402aa84e08fca
author iuc
date Sat, 20 Jan 2018 08:28:24 -0500
parents fc288950c3b7
children 5053a18d9bc8
comparison
equal deleted inserted replaced
17:fc288950c3b7 18:7615ac66c6e5
1 <tool name="MarkDuplicates" id="picard_MarkDuplicates" version="@TOOL_VERSION@.1"> 1 <tool name="MarkDuplicates" id="picard_MarkDuplicates" version="@TOOL_VERSION@.2">
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" />
22 ASSUME_SORTED='${assume_sorted}' 22 ASSUME_SORTED='${assume_sorted}'
23 23
24 DUPLICATE_SCORING_STRATEGY='${duplicate_scoring_strategy}' 24 DUPLICATE_SCORING_STRATEGY='${duplicate_scoring_strategy}'
25 25
26 #import pipes 26 #import pipes
27 READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" } 27 #if $read_name_regex:
28 READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) }
29 #end if
28 OPTICAL_DUPLICATE_PIXEL_DISTANCE='${optical_duplicate_pixel_distance}' 30 OPTICAL_DUPLICATE_PIXEL_DISTANCE='${optical_duplicate_pixel_distance}'
29 31
30 # Optional arguments 32 # Optional arguments
31 #if $barcode_tag: 33 #if $barcode_tag:
32 BARCODE_TAG='${barcode_tag}' 34 BARCODE_TAG='${barcode_tag}'
33 #end if 35 #end if
34 36
35 VALIDATION_STRINGENCY='${validation_stringency}' 37 VALIDATION_STRINGENCY='${validation_stringency}'
36 QUIET=true 38 QUIET=true
37 VERBOSITY=ERROR 39 VERBOSITY=ERROR
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">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 </param> 53 </param>
52 54
53 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 <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]+).*."> 56
55 <sanitizer> 57 <sanitizer>
56 <valid initial="string.printable"> 58 <valid initial="string.printable">
57 </valid> 59 </valid>
58 </sanitizer> 60 </sanitizer>
59 </param> 61 </param>
74 <test> 76 <test>
75 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/> 77 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/>
76 <param name="comment" value="test-run"/> 78 <param name="comment" value="test-run"/>
77 <param name="assume_sorted" value="True"/> 79 <param name="assume_sorted" value="True"/>
78 <param name="remove_duplicates" value="True"/> 80 <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]+).*."/> 81 <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"/> 82 <param name="optical_duplicate_pixel_distance" value="100"/>
81 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/> 83 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/>
82 <param name="validation_stringency" value="LENIENT"/> 84 <param name="validation_stringency" value="LENIENT"/>
83 <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="4"/> 85 <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="4"/>
86 </test>
87 <test>
88 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/>
89 <param name="comment" value="test-run"/>
90 <param name="assume_sorted" value="True"/>
91 <param name="remove_duplicates" value="False"/>
92 <param name="read_name_regex" value=""/>
93 <param name="optical_duplicate_pixel_distance" value="100"/>
94 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/>
95 <param name="validation_stringency" value="LENIENT"/>
96 <output name="outFile" file="picard_MarkDuplicates_test2.bam" ftype="bam" lines_diff="4"/>
84 </test> 97 </test>
85 </tests> 98 </tests>
86 99
87 100
88 <help> 101 <help>
100 more times. 113 more times.
101 114
102 REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with 115 REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with
103 appropriate flags set. Default value: false. 116 appropriate flags set. Default value: false.
104 117
105 READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. Read 118 READ_NAME_REGEX=String This option is only needed if your read names do not follow a standard illumina convention
119 of colon separation but do contain tile, x, and y coordinates (unusual).
120 A regular expression that can be used to parse read names in the incoming SAM file. Read
106 names are parsed to extract three variables: tile/region, x coordinate and y coordinate. 121 names are parsed to extract three variables: tile/region, x coordinate and y coordinate.
107 These values are used to estimate the rate of optical duplication in order to give a more 122 These values are used to estimate the rate of optical duplication in order to give a more
108 accurate estimated library size. Set this option to null to disable optical duplicate 123 accurate estimated library size. Set this option to null to disable optical duplicate
109 detection. The regular expression should contain three capture groups for the three 124 detection. The regular expression should contain three capture groups for the three
110 variables, in order. It must match the entire read name. Note that if the default regex 125 variables, in order. It must match the entire read name. Note that if the default regex
111 is specified, a regex match is not actually done, but instead the read name is split on 126 is specified, a regex match is not actually done, but instead the read name is split on
112 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be 127 colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be
113 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements 128 tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements
114 are assumed to be tile, x and y values. Default value: 129 are assumed to be tile, x and y values. Default value: ''
115 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*. 130
116 131
117 DUPLICATE_SCORING_STRATEGY=ScoringStrategy 132 DUPLICATE_SCORING_STRATEGY=ScoringStrategy
118 DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value: 133 DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value:
119 SUM_OF_BASE_QUALITIES. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH} 134 SUM_OF_BASE_QUALITIES. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH}
120 135
121 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer 136 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer
122 The maximum offset between two duplicte clusters in order to consider them optical 137 The maximum offset between two duplicate clusters in order to consider them optical
123 duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels) 138 duplicates. This should be set to 100 for (circa 2011+) read names and typical flowcells.
124 unless using later versions of the Illumina pipeline that multiply pixel values by 10, in 139 Structured flow cells (NovaSeq, HiSeq 4000, X) should use ~2500.
125 which case 50-100 is more normal. Default value: 100. 140 For older conventions, distances could be to some fairly small number (e.g. 5-10 pixels)
141 Default value: 100.
126 142
127 BARCODE_TAG=String Barcode SAM tag (ex. BC for 10X Genomics) Default value: null. 143 BARCODE_TAG=String Barcode SAM tag (ex. BC for 10X Genomics) Default value: null.
128 144
129 @more_info@ 145 @more_info@
130 146