Mercurial > repos > devteam > picard
diff picard_MarkDuplicates.xml @ 33:3f254c5ced1d draft default tip
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 |
line wrap: on
line diff
--- a/picard_MarkDuplicates.xml Mon Sep 25 08:32:17 2023 +0000 +++ b/picard_MarkDuplicates.xml Sun Mar 03 16:06:11 2024 +0000 @@ -1,112 +1,103 @@ -<tool name="MarkDuplicates" id="picard_MarkDuplicates" version="@TOOL_VERSION@.@WRAPPER_VERSION@"> - <description>examine aligned records in BAM datasets to locate duplicate molecules</description> - <macros> - <import>picard_macros.xml</import> - <token name="@WRAPPER_VERSION@">4</token> - </macros> - <expand macro="requirements" /> - <command detect_errors="exit_code"><![CDATA[ +<tool name="MarkDuplicates" id="picard_MarkDuplicates" version="@TOOL_VERSION@.@WRAPPER_VERSION@" profile="@PROFILE@"> + <description>examine aligned records in BAM datasets to locate duplicate molecules</description> + <macros> + <import>picard_macros.xml</import> + <token name="@WRAPPER_VERSION@">0</token> + </macros> + <expand macro="requirements"/> + <command detect_errors="exit_code"><![CDATA[ @java_options@ @symlink_element_identifier@ - picard - MarkDuplicates + picard MarkDuplicates - INPUT='$escaped_element_identifier' - OUTPUT='${outFile}' + --INPUT '$escaped_element_identifier' + --OUTPUT '${outFile}' - METRICS_FILE='${metrics_file}' + --METRICS_FILE '${metrics_file}' #for $element in $comments: - COMMENT='${element.comment}' + --COMMENT '${element.comment}' #end for - REMOVE_DUPLICATES='${remove_duplicates}' - ASSUME_SORTED='${assume_sorted}' + --REMOVE_DUPLICATES '${remove_duplicates}' + --ASSUME_SORTED '${assume_sorted}' - DUPLICATE_SCORING_STRATEGY='${duplicate_scoring_strategy}' + --DUPLICATE_SCORING_STRATEGY ${duplicate_scoring_strategy} #if $read_name_regex: - READ_NAME_REGEX='${ str( $read_name_regex ) }' + --READ_NAME_REGEX '${ str( $read_name_regex ) }' #end if - OPTICAL_DUPLICATE_PIXEL_DISTANCE='${optical_duplicate_pixel_distance}' + --OPTICAL_DUPLICATE_PIXEL_DISTANCE '${optical_duplicate_pixel_distance}' #if $barcode_tag: - BARCODE_TAG='${barcode_tag}' + --BARCODE_TAG '${barcode_tag}' #end if - VALIDATION_STRINGENCY='${validation_stringency}' - TAGGING_POLICY=All - QUIET=true - VERBOSITY=ERROR + --VALIDATION_STRINGENCY '${validation_stringency}' + --TAGGING_POLICY All + --QUIET true + --VERBOSITY ERROR ]]></command> - <inputs> - <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"/> - <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments"> - <param name="comment" type="text" label="Add this comment to BAM dataset"/> - </repeat> - <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"/> - <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"/> - - <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"> - <option value="SUM_OF_BASE_QUALITIES">SUM_OF_BASE_QUALITIES</option> - <option value="TOTAL_MAPPED_REFERENCE_LENGTH">TOTAL_MAPPED_REFERENCE_LENGTH</option> - </param> - - <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)"> - <expand macro="sanitize_query" /> - </param> - <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"/> - - <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' "/> - - <expand macro="VS" /> - - </inputs> - - <outputs> - <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: tabular"/> - <data format="bam" name="outFile" label="${tool.name} on ${on_string}: BAM"/> - </outputs> - - <tests> - <test> - <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/> - <param name="comment" value="test-run"/> - <param name="assume_sorted" value="True"/> - <param name="remove_duplicates" value="True"/> - <param name="read_name_regex" value=".*[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*"/> - <param name="optical_duplicate_pixel_distance" value="100"/> - <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/> - <param name="validation_stringency" value="LENIENT"/> - <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="4"/> - </test> - <test> - <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/> - <param name="comment" value="test-run"/> - <param name="assume_sorted" value="True"/> - <param name="remove_duplicates" value="False"/> - <param name="read_name_regex" value=""/> - <param name="optical_duplicate_pixel_distance" value="100"/> - <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/> - <param name="validation_stringency" value="LENIENT"/> - <output name="outFile" file="picard_MarkDuplicates_test2.bam" ftype="bam" lines_diff="4"/> - </test> - <test> - <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/> - <param name="comment" value="test-run"/> - <param name="assume_sorted" value="True"/> - <param name="remove_duplicates" value="False"/> - <param name="read_name_regex" value=""/> - <param name="optical_duplicate_pixel_distance" value="100"/> - <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/> - <param name="validation_stringency" value="LENIENT"/> - <param name='barcode_tag' value="RX"/> - <output name="outFile" file="picard_MarkDuplicates_test2.bam" ftype="bam" lines_diff="4"/> - </test> - </tests> - - - <help> + <inputs> + <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"/> + <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments"> + <param name="comment" type="text" label="Add this comment to BAM dataset"/> + </repeat> + <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"/> + <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"/> + <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"> + <option value="SUM_OF_BASE_QUALITIES" selected="true">SUM_OF_BASE_QUALITIES</option> + <option value="TOTAL_MAPPED_REFERENCE_LENGTH">TOTAL_MAPPED_REFERENCE_LENGTH</option> + <option value="RANDOM">RANDOM</option> + </param> + <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)"> + <expand macro="sanitize_query"/> + </param> + <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"/> + <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' "/> + <expand macro="VS"/> + </inputs> + <outputs> + <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: tabular"/> + <data format="bam" name="outFile" label="${tool.name} on ${on_string}: BAM"/> + </outputs> + <tests> + <test> + <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/> + <param name="comment" value="test-run"/> + <param name="assume_sorted" value="True"/> + <param name="remove_duplicates" value="True"/> + <param name="read_name_regex" value=".*[a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*"/> + <param name="optical_duplicate_pixel_distance" value="100"/> + <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/> + <param name="validation_stringency" value="LENIENT"/> + <output name="outFile" file="picard_MarkDuplicates_test1.bam" ftype="bam" lines_diff="4"/> + </test> + <test> + <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/> + <param name="comment" value="test-run"/> + <param name="assume_sorted" value="True"/> + <param name="remove_duplicates" value="False"/> + <param name="read_name_regex" value=""/> + <param name="optical_duplicate_pixel_distance" value="100"/> + <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/> + <param name="validation_stringency" value="LENIENT"/> + <output name="outFile" file="picard_MarkDuplicates_test2.bam" ftype="bam" lines_diff="4"/> + </test> + <test> + <param name="inputFile" value="picard_MarkDuplicates.bam" ftype="bam"/> + <param name="comment" value="test-run"/> + <param name="assume_sorted" value="True"/> + <param name="remove_duplicates" value="False"/> + <param name="read_name_regex" value=""/> + <param name="optical_duplicate_pixel_distance" value="100"/> + <param name="duplicate_scoring_strategy" value="SUM_OF_BASE_QUALITIES"/> + <param name="validation_stringency" value="LENIENT"/> + <param name="barcode_tag" value="RX"/> + <output name="outFile" file="picard_MarkDuplicates_test2.bam" ftype="bam" lines_diff="4"/> + </test> + </tests> + <help> **Purpose** @@ -153,5 +144,5 @@ @more_info@ </help> - <expand macro="citations" /> + <expand macro="citations"/> </tool>