Mercurial > repos > devteam > picard
annotate picard_MarkDuplicates.xml @ 11:efc56ee1ade4 draft
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit a1517c9d22029095120643bbe2c8fa53754dd2b7
| author | devteam |
|---|---|
| date | Wed, 11 Nov 2015 12:23:17 -0500 |
| parents | 5eaa8a968300 |
| children | 05087b27692a |
| 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="MarkDuplicates" id="picard_MarkDuplicates" 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" /> |
| 5 | 7 <command> |
| 8 @java_options@ | |
| 9 | |
| 10 java -jar \$JAVA_JAR_PATH/picard.jar | |
| 11 MarkDuplicates | |
| 12 | |
| 13 INPUT="${inputFile}" | |
| 14 OUTPUT="${outFile}" | |
| 15 | |
| 16 METRICS_FILE="${metrics_file}" | |
| 17 #for $element in $comments: | |
| 18 COMMENT="${element.comment}" | |
| 19 #end for | |
| 20 REMOVE_DUPLICATES="${remove_duplicates}" | |
| 21 ASSUME_SORTED="${assume_sorted}" | |
| 22 | |
| 23 DUPLICATE_SCORING_STRATEGY="${duplicate_scoring_strategy}" | |
| 24 | |
| 6 | 25 #import pipes |
| 26 READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" } | |
| 5 | 27 OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}" |
| 28 | |
| 29 VALIDATION_STRINGENCY="${validation_stringency}" | |
| 30 QUIET=true | |
| 31 VERBOSITY=ERROR | |
| 32 | |
| 33 </command> | |
| 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"/> | |
| 36 <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
|
37 <param name="comment" type="text" label="Add this comment to BAM dataset"/> |
| 5 | 38 </repeat> |
| 39 <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"/> | |
| 40 <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"/> | |
| 41 | |
| 42 <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"> | |
| 43 <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option> | |
| 44 <option value="TOTAL_MAPPED_REFERENCE_LENGTH">TOTAL_MAPPED_REFERENCE_LENGTH</option> | |
| 45 </param> | |
| 46 | |
| 47 | |
|
9
5eaa8a968300
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit 1869970193a1878acbc0f8a79b81dd02b37f1dc1
devteam
parents:
8
diff
changeset
|
48 <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 | 49 <sanitizer> |
| 50 <valid initial="string.printable"> | |
| 51 </valid> | |
| 52 </sanitizer> | |
| 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"/> | |
| 55 | |
| 56 <expand macro="VS" /> | |
| 57 | |
| 58 </inputs> | |
| 59 | |
| 60 <outputs> | |
| 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"/> | |
| 63 </outputs> | |
| 64 | |
| 65 <tests> | |
| 66 <test> | |
| 67 <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/> | |
| 68 <param name="comment" value="test-run"/> | |
| 69 <param name="assume_sorted" 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]+).*."/> | |
| 72 <param name="optical_duplicate_pixel_distance" value="100"/> | |
| 73 <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/> | |
| 74 <param name="validation_stringency" value="LENIENT"/> | |
| 75 <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="2"/> | |
| 76 </test> | |
| 77 </tests> | |
| 78 | |
| 79 <stdio> | |
| 80 <exit_code range="1:" level="fatal"/> | |
| 81 </stdio> | |
| 82 | |
| 83 <help> | |
| 84 | |
| 85 **Purpose** | |
| 86 | |
| 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. | |
| 88 | |
| 89 @dataset_collections@ | |
| 90 | |
| 91 @description@ | |
| 92 | |
| 93 COMMENT=String | |
| 94 CO=String Comment(s) to include in the output file's header. This option may be specified 0 or | |
| 95 more times. | |
| 96 | |
| 97 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. | |
| 99 | |
| 100 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. | |
| 102 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 | |
| 104 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 | |
| 106 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 | |
| 108 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: | |
| 110 [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*. | |
| 111 | |
| 112 DUPLICATE_SCORING_STRATEGY=ScoringStrategy | |
| 113 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} | |
| 115 | |
| 116 OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer | |
| 117 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) | |
| 119 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. | |
| 121 | |
| 122 @more_info@ | |
| 123 | |
| 124 </help> | |
| 125 </tool> | |
| 126 | |
| 127 |