Mercurial > repos > devteam > picard
changeset 13:7e6fd3d0f16e draft
planemo upload for repository https://github.com/galaxyproject/tools-devteam/tree/master/tools/picard commit bf94a1505c131fb3f67c867b6e1d886780efa42e
line wrap: on
line diff
--- a/picard_AddCommentsToBam.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_AddCommentsToBam.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,9 +6,10 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ + @symlink_element_identifier@ picard AddCommentsToBam - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" #for $element in $comments: COMMENT="${element.comment}"
--- a/picard_AddOrReplaceReadGroups.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_AddOrReplaceReadGroups.xml Tue Dec 06 10:04:41 2016 -0500 @@ -10,9 +10,10 @@ #set $rg_auto_name = $read_group_name_default($inputFile) @set_read_group_vars@ @java_options@ + @symlink_element_identifier@ picard AddOrReplaceReadGroups - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' $format_read_group("RGLB=", $rg_lb, '"') $format_read_group("RGPL=", $rg_pl, '"') $format_read_group("RGPU=", $rg_pu, '"') @@ -25,21 +26,21 @@ QUIET=true VERBOSITY=ERROR OUTPUT="${outFile}" - + </command> - + <inputs> <param format="bam,sam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset" /> <expand macro="read_group_inputs_picard" /> <expand macro="VS" /> - + </inputs> - + <outputs> <data name="outFile" format="bam" label="${tool.name} on ${on_string}: BAM with replaced/modified readgroups"/> </outputs> - - + + <tests> <test> <param name="inputFile" value="picard_ARRG.bam" /> @@ -66,42 +67,42 @@ @description@ INPUT=File - I=File Input file (bam or sam). Required. + I=File Input file (bam or sam). Required. OUTPUT=File - O=File Output file (bam or sam). Required. + O=File Output file (bam or sam). Required. SORT_ORDER=SortOrder - SO=SortOrder Optional sort order to output in. If not supplied OUTPUT is in the same order as INPUT. - Default value: null. Possible values: {unsorted, queryname, coordinate} + SO=SortOrder Optional sort order to output in. If not supplied OUTPUT is in the same order as INPUT. + Default value: null. Possible values: {unsorted, queryname, coordinate} RGID=String - ID=String Read Group ID Default value: 1. This option can be set to 'null' to clear the default - value. + ID=String Read Group ID Default value: 1. This option can be set to 'null' to clear the default + value. RGLB=String - LB=String Read Group Library Required. - + LB=String Read Group Library Required. + RGPL=String - PL=String Read Group platform (e.g. illumina, solid) Required. + PL=String Read Group platform (e.g. illumina, solid) Required. RGPU=String - PU=String Read Group platform unit (eg. run barcode) Required. + PU=String Read Group platform unit (eg. run barcode) Required. RGSM=String - SM=String Read Group sample name Required. + SM=String Read Group sample name Required. RGCN=String - CN=String Read Group sequencing center name Default value: null. + CN=String Read Group sequencing center name Default value: null. RGDS=String - DS=String Read Group description Default value: null. + DS=String Read Group description Default value: null. RGDT=Iso8601Date - DT=Iso8601Date Read Group run date Default value: null. + DT=Iso8601Date Read Group run date Default value: null. RGPI=Integer - PI=Integer Read Group predicted insert size Default value: null. + PI=Integer Read Group predicted insert size Default value: null. @more_info@ </help>
--- a/picard_BedToIntervalList.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_BedToIntervalList.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,40 +6,40 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ - + @symlink_element_identifier@ #set $picard_dict = "localref.dict" #set $ref_fasta = "localref.fa" ## This is done because picards "likes" .fa extension - + ln -s "${reference_source.ref_file}" "${ref_fasta}" && - + #if str( $reference_source.reference_source_selector ) == "history": - + picard CreateSequenceDictionary REFERENCE="${ref_fasta}" OUTPUT="${picard_dict}" QUIET=true VERBOSITY=ERROR - + && - + #else: - + #set $ref_fasta = str( $reference_source.ref_file.fields.path ) ## getting path of reference fasta file (must end with .fa) #set $picard_dict=$ref_fasta[:-2]+"dict" ## replacing .fa with .dict - - #end if - + + #end if + picard BedToIntervalList - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" - + SEQUENCE_DICTIONARY="${picard_dict}" QUIET=true VERBOSITY=ERROR - + ]]></command> - + <inputs> - + <conditional name="reference_source"> <param name="reference_source_selector" type="select" label="Load picard dictionary file from"> <option value="cached">Local cache</option> @@ -54,11 +54,11 @@ <validator type="no_options" message="A built-in dictionary is not available for the build associated with the selected input file"/> </param> </when> - <when value="history"> + <when value="history"> <param name="ref_file" type="data" format="fasta" label="Use the following dataset to create dictionary" help="You can upload a FASTA sequence to the history from which Picard will automatically generate dictionary using CreateSequenceDictionary command" /> </when> </conditional> - + <param format="bed" name="inputFile" type="data" label="Select coordinate dataset or dataset collection" help="This can be a bed or interval dataset" /> </inputs> @@ -74,8 +74,8 @@ <output name="outFile" file="picard_BedToIntervalList_test1.pif" ftype="picard_interval_list" lines_diff="8" /> </test> </tests> - - + + <help> .. class:: infomark
--- a/picard_CleanSam.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_CleanSam.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,35 +6,36 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ + @symlink_element_identifier@ picard CleanSam - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" QUIET=true VERBOSITY=ERROR VALIDATION_STRINGENCY=${validation_stringency} ]]></command> - + <inputs> <param name="inputFile" type="data" format="sam,bam" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/> - + <expand macro="VS" /> - + </inputs> - + <outputs> <data name="outFile" format="bam" label="${tool.name} on ${on_string}: cleaned BAM dataset"> </data> </outputs> - - + + <tests> <test> <param name="inputFile" ftype="bam" value="picard_CleanSam.bam" /> - <output name="outFile" file="picard_CleanSam_test1.bam" ftype="bam" /> + <output name="outFile" file="picard_CleanSam_test1.bam" ftype="bam" lines_diff="4"/> </test> </tests> - + <help> .. class:: infomark @@ -45,9 +46,9 @@ 1. to soft-clip an alignment that hangs off the end of its reference sequence. 2. to set MAPQ to 0 if a read is unmapped. - + @dataset_collections@ - + @more_info@ </help>
--- a/picard_CollectAlignmentSummaryMetrics.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_CollectAlignmentSummaryMetrics.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,6 +6,7 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ + @symlink_element_identifier@ ##set up input files #set $reference_fasta_filename = "localref.fa" @@ -18,7 +19,7 @@ picard CollectAlignmentSummaryMetrics - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" MAX_INSERT_SIZE=${maxinsert} #for $sequence in $adapters: @@ -36,7 +37,7 @@ VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param format="sam,bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset."/> @@ -98,25 +99,25 @@ @description@ - MAX_INSERT_SIZE=Integer Paired end reads above this insert size will be considered chimeric along with - inter-chromosomal pairs. Default value: 100000. + MAX_INSERT_SIZE=Integer Paired end reads above this insert size will be considered chimeric along with + inter-chromosomal pairs. Default value: 100000. - ADAPTER_SEQUENCE=String List of adapter sequences to use when processing the alignment metrics This option may - be specified 0 or more times. + ADAPTER_SEQUENCE=String List of adapter sequences to use when processing the alignment metrics This option may + be specified 0 or more times. METRIC_ACCUMULATION_LEVEL=MetricAccumulationLevel - LEVEL=MetricAccumulationLevel The level(s) at which to accumulate metrics. Possible values: {ALL_READS, SAMPLE, - LIBRARY, READ_GROUP} This option may be specified 0 or more times. + LEVEL=MetricAccumulationLevel The level(s) at which to accumulate metrics. Possible values: {ALL_READS, SAMPLE, + LIBRARY, READ_GROUP} This option may be specified 0 or more times. IS_BISULFITE_SEQUENCED=Boolean - BS=Boolean Whether the SAM or BAM file consists of bisulfite sequenced reads. + BS=Boolean Whether the SAM or BAM file consists of bisulfite sequenced reads. REFERENCE_SEQUENCE=File - R=File Reference sequence fasta Default value: null. + R=File Reference sequence fasta Default value: null. ASSUME_SORTED=Boolean - AS=Boolean If true (default), then the sort order in the header file will be ignored. + AS=Boolean If true (default), then the sort order in the header file will be ignored. @more_info@
--- a/picard_CollectBaseDistributionByCycle.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_CollectBaseDistributionByCycle.xml Tue Dec 06 10:04:41 2016 -0500 @@ -8,30 +8,31 @@ </expand> <command detect_errors="exit_code"><![CDATA[ @java_options@ + @symlink_element_identifier@ ##set up input files #set $reference_fasta_filename = "localref.fa" - + #if str( $reference_source.reference_source_selector ) == "history": ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" && #else: #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path ) #end if - + picard CollectBaseDistributionByCycle - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" CHART_OUTPUT="${pdfFile}" ALIGNED_READS_ONLY="${aligned_reads_only}" PF_READS_ONLY="${pf_reads_only}" REFERENCE_SEQUENCE="${reference_fasta_filename}" ASSUME_SORTED="${assume_sorted}" - + VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param format="sam,bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset."/> @@ -51,19 +52,19 @@ <param name="ref_file" type="data" format="fasta" label="Use the folloing dataset as the reference sequence" help="REFERENCE_SEQUENCE; You can upload a FASTA sequence to the history and use it as reference" /> </when> </conditional> - <param name="aligned_reads_only" type="boolean" label="Calculate the base distribution over aligned reads only" checked="true" truevalue="true" falsevalue="false" help="ALIGNED_READS_ONLY"/> - <param name="pf_reads_only" type="boolean" label="Calculate the base distribution over PF (passing filtering) reads only" checked="true" truevalue="true" falsevalue="false" help="PF_READS_ONLY"/> - <param name="assume_sorted" type="boolean" label="Assume the input file is already sorted" checked="true" truevalue="true" falsevalue="false" help="ASSUME_SORTED"/> - + <param name="aligned_reads_only" type="boolean" label="Calculate the base distribution over aligned reads only" checked="true" truevalue="true" falsevalue="false" help="ALIGNED_READS_ONLY"/> + <param name="pf_reads_only" type="boolean" label="Calculate the base distribution over PF (passing filtering) reads only" checked="true" truevalue="true" falsevalue="false" help="PF_READS_ONLY"/> + <param name="assume_sorted" type="boolean" label="Assume the input file is already sorted" checked="true" truevalue="true" falsevalue="false" help="ASSUME_SORTED"/> + <expand macro="VS" /> - + </inputs> - + <outputs> <data format="tabular" name="outFile"/> <data format="pdf" name="pdfFile"/> </outputs> - + <tests> <test> <param name="aligned_reads_only" value="true" /> @@ -75,8 +76,8 @@ <output name="outFile" file="picard_CollectBaseDistributionByCycle_test1.tab" ftype="tabular" lines_diff="4"/> </test> </tests> - - + + <help> .. class:: infomark @@ -89,19 +90,19 @@ @description@ - ALIGNED_READS_ONLY=Boolean If set to true, calculate the base distribution over aligned reads only. Default value: - false. This option can be set to 'null' to clear the default value. Possible values: - {true, false} + ALIGNED_READS_ONLY=Boolean If set to true, calculate the base distribution over aligned reads only. Default value: + false. This option can be set to 'null' to clear the default value. Possible values: + {true, false} - PF_READS_ONLY=Boolean If set to true calculate the base distribution over PF reads only. Default value: false. - This option can be set to 'null' to clear the default value. Possible values: {true, - false} + PF_READS_ONLY=Boolean If set to true calculate the base distribution over PF reads only. Default value: false. + This option can be set to 'null' to clear the default value. Possible values: {true, + false} REFERENCE_SEQUENCE=File - R=File Reference sequence fasta Default value: null. + R=File Reference sequence fasta Default value: null. ASSUME_SORTED=Boolean - AS=Boolean If true (default), then the sort order in the header file will be ignored. Default + AS=Boolean If true (default), then the sort order in the header file will be ignored. Default @more_info@
--- a/picard_CollectGcBiasMetrics.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_CollectGcBiasMetrics.xml Tue Dec 06 10:04:41 2016 -0500 @@ -8,6 +8,7 @@ </expand> <command detect_errors="exit_code"><![CDATA[ @java_options@ + @symlink_element_identifier@ ##set up input files #set $reference_fasta_filename = "localref.fa" @@ -20,7 +21,7 @@ picard CollectGcBiasMetrics - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" CHART_OUTPUT="${pdfFile}" SUMMARY_OUTPUT="${summaryFile}"
--- a/picard_CollectInsertSizeMetrics.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_CollectInsertSizeMetrics.xml Tue Dec 06 10:04:41 2016 -0500 @@ -8,27 +8,28 @@ </expand> <command detect_errors="exit_code"><![CDATA[ @java_options@ + @symlink_element_identifier@ ##set up input files #set $reference_fasta_filename = "localref.fa" - + #if str( $reference_source.reference_source_selector ) == "history": ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" && #else: #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path ) #end if - + picard CollectInsertSizeMetrics - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" HISTOGRAM_FILE="${histFile}" DEVIATIONS="${deviations}" - + #if str( $hist_width ): HISTOGRAM_WIDTH="${hist_width}" #end if - + MINIMUM_PCT="${min_pct}" REFERENCE_SEQUENCE="${reference_fasta_filename}" ASSUME_SORTED="${assume_sorted}" @@ -37,7 +38,7 @@ VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param format="sam,bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset."/> @@ -67,16 +68,16 @@ <option value="LIBRARY">Library</option> <option value="READ_GROUP">Read group</option> </param> - + <expand macro="VS" /> - + </inputs> - + <outputs> <data format="tabular" name="outFile"/> <data format="pdf" name="histFile"/> </outputs> - + <tests> <test> <param name="metric_accumulation_level" value="ALL_READS"/> @@ -90,8 +91,8 @@ <output name="outFile" file="picard_CollectInsertSizeMetrics_test1.tab" ftype="tabular" lines_diff="4"/> </test> </tests> - - + + <help> .. class:: infomark @@ -104,30 +105,30 @@ @description@ - - DEVIATIONS=Double Generate mean, sd and plots by trimming the data down to MEDIAN + - DEVIATIONS*MEDIAN_ABSOLUTE_DEVIATION. This is done because insert size data typically - includes enough anomalous values from chimeras and other artifacts to make the mean and - sd grossly misleading regarding the real distribution. Default value: 10.0. + + DEVIATIONS=Double Generate mean, sd and plots by trimming the data down to MEDIAN + + DEVIATIONS*MEDIAN_ABSOLUTE_DEVIATION. This is done because insert size data typically + includes enough anomalous values from chimeras and other artifacts to make the mean and + sd grossly misleading regarding the real distribution. Default value: 10.0. HISTOGRAM_WIDTH=Integer - W=Integer Explicitly sets the Histogram width, overriding automatic truncation of Histogram tail. - Also, when calculating mean and standard deviation, only bins <= Histogram_WIDTH will be - included. Default value: not set. + W=Integer Explicitly sets the Histogram width, overriding automatic truncation of Histogram tail. + Also, when calculating mean and standard deviation, only bins <= Histogram_WIDTH will be + included. Default value: not set. MINIMUM_PCT=Float - M=Float When generating the Histogram, discard any data categories (out of FR, TANDEM, RF) that - have fewer than this percentage of overall reads. (Range: 0 to 1). Default value: 0.05. + M=Float When generating the Histogram, discard any data categories (out of FR, TANDEM, RF) that + have fewer than this percentage of overall reads. (Range: 0 to 1). Default value: 0.05. METRIC_ACCUMULATION_LEVEL=MetricAccumulationLevel - LEVEL=MetricAccumulationLevel The level(s) at which to accumulate metrics. Possible values: {ALL_READS, SAMPLE, - LIBRARY, READ_GROUP} This option may be specified 0 or more times. - + LEVEL=MetricAccumulationLevel The level(s) at which to accumulate metrics. Possible values: {ALL_READS, SAMPLE, + LIBRARY, READ_GROUP} This option may be specified 0 or more times. + ASSUME_SORTED=Boolean - AS=Boolean If true (default), then the sort order in the header file will be ignored. Default - value: true. This option can be set to 'null' to clear the default value. Possible + AS=Boolean If true (default), then the sort order in the header file will be ignored. Default + value: true. This option can be set to 'null' to clear the default value. Possible values: {true, false} - + @more_info@ </help>
--- a/picard_CollectRnaSeqMetrics.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_CollectRnaSeqMetrics.xml Tue Dec 06 10:04:41 2016 -0500 @@ -9,33 +9,33 @@ <command detect_errors="exit_code"><![CDATA[ ## Set up input files - + @symlink_element_identifier@ ## Reference sequences #set $reference_fasta_filename = "localref.fa" - + #if str( $reference_source.reference_source_selector ) == "history": ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" && #else: #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path ) #end if - + ## refFlat data ## The awk line below converts a file obtained from UCSC as specified in the tool help to refFlat format - + grep -v '^#' ${refFlat} | awk '{print $11"\t"$1"\t"$2"\t"$3"\t"$4"\t"$5"\t"$6"\t"$7"\t"$8"\t"$9"\t"$10}' > refFlat.tab && - + ## Start picard command - + @java_options@ picard CollectRnaSeqMetrics REF_FLAT=refFlat.tab - + #if str( $ribosomal_intervals ) != "None": RIBOSOMAL_INTERVALS="${ribosomal_intervals}" #end if - + STRAND_SPECIFICITY="${strand_specificity}" MINIMUM_LENGTH="${minimum_length}" CHART_OUTPUT="${pdfFile}" @@ -43,20 +43,20 @@ #for $sequence_to_ignore in $ignore_list: IGNORE_SEQUENCE="${sequence_to_ignore.sequence}" #end for - + RRNA_FRAGMENT_PERCENTAGE="${rrna_fragment_percentage}" METRIC_ACCUMULATION_LEVEL="${metric_accumulation_level}" - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" REFERENCE_SEQUENCE="${reference_fasta_filename}" ASSUME_SORTED="${assume_sorted}" - + QUIET=true VERBOSITY=ERROR VALIDATION_STRINGENCY=${validation_stringency} - + ]]></command> - + <inputs> <param format="sam,bam" type="data" name="inputFile" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset" /> <conditional name="reference_source"> @@ -73,7 +73,7 @@ <when value="history"> <param name="ref_file" type="data" format="fasta" label="Use the folloing dataset as the reference sequence" help="REFERENCE_SEQUENCE; You can upload a FASTA sequence to the history and use it as reference" /> </when> - </conditional> + </conditional> <param format="tabular" name="refFlat" type="data" label="Gene annotations in refFlat form" help="See "Obtaining gene annotations in refFlat format" below for help" /> <param name="ribosomal_intervals" format="picard_interval_list" type="data" optional="True" label="Location of rRNA sequences in genome, in interval_list format" help="RIBOSOMAL_INTERVALS; If not specified no bases will be identified as being ribosomal. The list of intervals can be geberated from BED or Interval datasets using Galaxy BedToIntervalList tool"/> <param name="strand_specificity" type="select" label="What is the RNA-seq library strand specificity" help="STRAND_SPECIFICITY; For unpaired reads, use FIRST_READ_TRANSCRIPTION_STRAND if the reads are expected to be on the transcription strand."> @@ -93,7 +93,7 @@ <option value="READ_GROUP">Read group</option> </param> <param name="assume_sorted" type="boolean" label="Assume the input file is already sorted" checked="true" truevalue="true" falsevalue="false" help="ASSUME_SORTED"/> - + <expand macro="VS" /> </inputs> @@ -101,7 +101,7 @@ <data format="pdf" name="pdfFile" label="${tool.name} on ${on_string}: Chart PDF"/> <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Summary stats"/> </outputs> - + <tests> <test> <param name="reference_source_selector" value="history"/> @@ -156,41 +156,41 @@ 8. Click **Send query to Galaxy** 9. A new dataset will appear in the current Galaxy history 10. Use this dataset as the input for **Gene annotations in refFlat form** dropdown of this tool - + .. _refFlat: http://genome.ucsc.edu/goldenPath/gbdDescriptionsOld.html#RefFlat @description@ - REF_FLAT=File Gene annotations in refFlat form. Format described here: - http://genome.ucsc.edu/goldenPath/gbdDescriptionsOld.html#RefFlat Required. + REF_FLAT=File Gene annotations in refFlat form. Format described here: + http://genome.ucsc.edu/goldenPath/gbdDescriptionsOld.html#RefFlat Required. - RIBOSOMAL_INTERVALS=File Location of rRNA sequences in genome, in interval_list format. If not specified no bases - will be identified as being ribosomal. Format described here: + RIBOSOMAL_INTERVALS=File Location of rRNA sequences in genome, in interval_list format. If not specified no bases + will be identified as being ribosomal. Format described here: http://picard.sourceforge.net/javadoc/net/sf/picard/util/IntervalList.html and can be generated from BED datasetes using Galaxy's wrapper for picard_BedToIntervalList tool STRAND_SPECIFICITY=StrandSpecificity - STRAND=StrandSpecificity For strand-specific library prep. For unpaired reads, use FIRST_READ_TRANSCRIPTION_STRAND - if the reads are expected to be on the transcription strand. Required. Possible values: - {NONE, FIRST_READ_TRANSCRIPTION_STRAND, SECOND_READ_TRANSCRIPTION_STRAND} + STRAND=StrandSpecificity For strand-specific library prep. For unpaired reads, use FIRST_READ_TRANSCRIPTION_STRAND + if the reads are expected to be on the transcription strand. Required. Possible values: + {NONE, FIRST_READ_TRANSCRIPTION_STRAND, SECOND_READ_TRANSCRIPTION_STRAND} - MINIMUM_LENGTH=Integer When calculating coverage based values (e.g. CV of coverage) only use transcripts of this + MINIMUM_LENGTH=Integer When calculating coverage based values (e.g. CV of coverage) only use transcripts of this length or greater. Default value: 500. - IGNORE_SEQUENCE=String If a read maps to a sequence specified with this option, all the bases in the read are - counted as ignored bases. + IGNORE_SEQUENCE=String If a read maps to a sequence specified with this option, all the bases in the read are + counted as ignored bases. RRNA_FRAGMENT_PERCENTAGE=Double - This percentage of the length of a fragment must overlap one of the ribosomal intervals - for a read or read pair by this must in order to be considered rRNA. Default value: 0.8. + This percentage of the length of a fragment must overlap one of the ribosomal intervals + for a read or read pair by this must in order to be considered rRNA. Default value: 0.8. METRIC_ACCUMULATION_LEVEL=MetricAccumulationLevel - LEVEL=MetricAccumulationLevel The level(s) at which to accumulate metrics. Possible values: {ALL_READS, SAMPLE, + LEVEL=MetricAccumulationLevel The level(s) at which to accumulate metrics. Possible values: {ALL_READS, SAMPLE, LIBRARY, READ_GROUP} This option may be specified 0 or more times. - + ASSUME_SORTED=Boolean - AS=Boolean If true (default), then the sort order in the header file will be ignored. Default - value: true. Possible values: {true, false} + AS=Boolean If true (default), then the sort order in the header file will be ignored. Default + value: true. Possible values: {true, false} @more_info@
--- a/picard_CollectWgsMetrics.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_CollectWgsMetrics.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,29 +6,30 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ + @symlink_element_identifier@ ##set up input files #set $reference_fasta_filename = "localref.fa" - + #if str( $reference_source.reference_source_selector ) == "history": ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" && #else: #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path ) #end if - + picard CollectWgsMetrics - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" REFERENCE_SEQUENCE="${reference_fasta_filename}" MINIMUM_MAPPING_QUALITY="${minimum_mapping_quality}" MINIMUM_BASE_QUALITY="${minimum_base_quality}" COVERAGE_CAP="${coverage_cap}" - + VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param format="sam,bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/> @@ -52,15 +53,15 @@ <param name="minimum_base_quality" type="integer" value="20" label="Minimum base quality for a base to contribute coverage" help="MINIMUM_BASE_QUALITY; default=20"/> <param name="coverage_cap" type="integer" value="250" label="Treat bases with coverage exceeding this value as if they had coverage at this value" help="COVERAGE_CAP; default=250"/> - + <expand macro="VS" /> - + </inputs> - + <outputs> <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Summary data"/> </outputs> - + <tests> <test> <param name="reference_source_selector" value="history" /> @@ -70,10 +71,10 @@ <param name="ref_file" value="picard_CollectWgsMetrics_ref.fa" /> <param name="inputFile" value="picard_CollectWgsMetrics.bam" ftype="bam" /> <output name="outFile" file="picard_CollectWgsMetrics_test1.tab" ftype="tabular" lines_diff="4"/> - </test> + </test> </tests> - - + + <help> .. class:: infomark @@ -87,14 +88,14 @@ @description@ MINIMUM_MAPPING_QUALITY=Integer - MQ=Integer Minimum mapping quality for a read to contribute coverage. Default value: 20. + MQ=Integer Minimum mapping quality for a read to contribute coverage. Default value: 20. MINIMUM_BASE_QUALITY=Integer - Q=Integer Minimum base quality for a base to contribute coverage. Default value: 20. + Q=Integer Minimum base quality for a base to contribute coverage. Default value: 20. COVERAGE_CAP=Integer - CAP=Integer Treat bases with coverage exceeding this value as if they had coverage at this value. - Default value: 250. + CAP=Integer Treat bases with coverage exceeding this value as if they had coverage at this value. + Default value: 250. @more_info@
--- a/picard_DownsampleSam.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_DownsampleSam.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,9 +6,10 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ + @symlink_element_identifier@ picard DownsampleSam - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" PROBABILITY=${probability} RANDOM_SEED=${seed} @@ -20,16 +21,16 @@ <param format="sam,bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM or BAM dataset" /> <param name="probability" type="float" min="0.0" max="1.0" label="Probability (between 0 and 1) that any given read will be kept" help="PROBABILITY; specify 1 to keep all reads, 0.1 to keep 10% of the reads" value="1" /> <param name="seed" type="integer" label="Random seed value" help="RANDOM_SEED; default=1" value="1" /> - + <expand macro="VS" /> - + </inputs> - - + + <outputs> <data name="outFile" format="bam" label="${tool.name} on ${on_string}: downsampled BAM"/> </outputs> - + <tests> <test> <param name="inputFile" value="picard_DownsampleSam.bam" ftype="bam" /> @@ -52,18 +53,18 @@ @description@ INPUT=File - I=File The input SAM or BAM file to downsample. Required. + I=File The input SAM or BAM file to downsample. Required. OUTPUT=File - O=File The output, downsampled, SAM or BAM file to write. Required. + O=File The output, downsampled, SAM or BAM file to write. Required. RANDOM_SEED=Long R=Long Random seed to use if reproducibilty is desired. Setting to null will cause multiple invocations to produce different results. - + PROBABILITY=Double - P=Double The probability of keeping any individual read, between 0 and 1. - + P=Double The probability of keeping any individual read, between 0 and 1. + @more_info@
--- a/picard_EstimateLibraryComplexity.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_EstimateLibraryComplexity.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,13 +6,13 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ - + @symlink_element_identifier@ picard EstimateLibraryComplexity - - INPUT="${inputFile}" + + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" - + MIN_IDENTICAL_BASES="${min_identical_bases}" MAX_DIFF_RATE="${max_diff_rate}" MIN_MEAN_QUALITY="${min_mean_quality}" @@ -20,11 +20,11 @@ #import pipes READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" } OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}" - + VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param format="bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset" /> @@ -42,13 +42,13 @@ <param name="optical_duplicate_pixel_distance" type="integer" value="100" min="0" max="500" label="The maximum offset between two duplicte clusters in order to consider them optical duplicates" help="OPTICAL_DUPLICATE_PIXEL_DISTANCE; default=100"/> <expand macro="VS" /> - - </inputs> - + + </inputs> + <outputs> <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Library complexity report"/> </outputs> - + <tests> <test> <param name="inputFile" value="picard_EstimateLibraryComplexity.bam" ftype="bam"/> @@ -62,8 +62,8 @@ <output name="outFile" file="picard_EstimateLibraryComplexity_test1.tab" ftype="tabular" lines_diff="4"/> </test> </tests> - - + + <help> **Purpose** @@ -86,40 +86,40 @@ @description@ - MIN_IDENTICAL_BASES=Integer The minimum number of bases at the starts of reads that must be identical for reads to be - grouped together for duplicate detection. In effect total_reads / 4^max_id_bases reads - will be compared at a time, so lower numbers will produce more accurate results but - consume exponentially more memory and CPU. Default value: 5. - - MAX_DIFF_RATE=Double The maximum rate of differences between two reads to call them identical. Default value: + MIN_IDENTICAL_BASES=Integer The minimum number of bases at the starts of reads that must be identical for reads to be + grouped together for duplicate detection. In effect total_reads / 4^max_id_bases reads + will be compared at a time, so lower numbers will produce more accurate results but + consume exponentially more memory and CPU. Default value: 5. + + MAX_DIFF_RATE=Double The maximum rate of differences between two reads to call them identical. Default value: 0.03. - - MIN_MEAN_QUALITY=Integer The minimum mean quality of the bases in a read pair for the read to be analyzed. Reads - with lower average quality are filtered out and not considered in any calculations. + + MIN_MEAN_QUALITY=Integer The minimum mean quality of the bases in a read pair for the read to be analyzed. Reads + with lower average quality are filtered out and not considered in any calculations. Default value: 20. - - MAX_GROUP_RATIO=Integer Do not process self-similar groups that are this many times over the mean expected group - size. I.e. if the input contains 10m read pairs and MIN_IDENTICAL_BASES is set to 5, then + + MAX_GROUP_RATIO=Integer Do not process self-similar groups that are this many times over the mean expected group + size. I.e. if the input contains 10m read pairs and MIN_IDENTICAL_BASES is set to 5, then the mean expected group size would be approximately 10 reads. Default value: 500. - - READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. 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. Set this option to null to disable optical duplicate - detection. The regular expression should contain three capture groups for the three - variables, in order. It must match the entire read name. Note that if the default regex - is specified, a regex match is not actually done, but instead the read name is split on - colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be - tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements - are assumed to be tile, x and y values. Default value: + + READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. 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. Set this option to null to disable optical duplicate + detection. The regular expression should contain three capture groups for the three + variables, in order. It must match the entire read name. Note that if the default regex + is specified, a regex match is not actually done, but instead the read name is split on + colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be + tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements + are assumed to be tile, x and y values. Default value: [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*. - - OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer - The maximum offset between two duplicte clusters in order to consider them optical - duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels) - unless using later versions of the Illumina pipeline that multiply pixel values by 10, in + + OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer + The maximum offset between two duplicte clusters in order to consider them optical + duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels) + unless using later versions of the Illumina pipeline that multiply pixel values by 10, in which case 50-100 is more normal. Default value: 100. - + @more_info@
--- a/picard_FastqToSam.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_FastqToSam.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,10 +6,9 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ - picard FastqToSam - + #if str( $input_type.input_type_selector ) == "se": FASTQ="${input_type.fastq}" #elif str( $input_type.input_type_selector ) == "pe": @@ -19,54 +18,54 @@ FASTQ="${input_type.fastq.forward}" FASTQ2="${input_type.fastq.reverse}" #end if - + QUALITY_FORMAT="${quality_format}" OUTPUT="${outFile}" READ_GROUP_NAME="${read_group_name}" SAMPLE_NAME="${sample_name}" - + #if str( $library_name ): LIBRARY_NAME="${library_name}" #end if - + #if str( $platform_unit ): PLATFORM_UNIT="${platform_unit}" #end if - + #if str( $platform ): PLATFORM="${platform}" #end if - + #if str( $sequencing_center ): SEQUENCING_CENTER="${sequencing_center}" #end if - + #if str( $predicted_insert_size ): PREDICTED_INSERT_SIZE="${predicted_insert_size}" #end if - + #if str( $comment ): COMMENT="${comment}" #end if - + #if str( $description ): DESCRIPTION="${description}" #end if - + #if str( $run_date ): RUN_DATE="${run_date}" #end if - + MIN_Q="${min_q}" MAX_Q="${max_q}" STRIP_UNPAIRED_MATE_NUMBER="${strip_unpairied_mate_number}" ALLOW_AND_IGNORE_EMPTY_LINES="${allow_and_ignore_empty_lines}" - + SORT_ORDER=coordinate VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <conditional name="input_type"> @@ -86,7 +85,7 @@ <param name="fastq" type="data_collection" collection_type="paired" format="fastq" label="FASTQ paired dataset collection" help="FASTQ and FASTQ2; A collection of two datasets with forward and reverse reads. See help below on explanation of dataset collections"/> </when> </conditional> - + <param name="quality_format" type="select" label="Select quality encoding scheme" help="QUALITY_FORMAT"> <option value="Standard" selected="True">Sanger (+33)</option> <option value="Illumina">Illumina (+64)</option> @@ -108,15 +107,15 @@ <param name="max_q" type="integer" value="93" min="0" max="100" label="Minimum quality allowed in the input fastq" help="MAX_Q; An exception will be thrown if a quality is greater than this value; default=93"/> <param name="strip_unpairied_mate_number" type="boolean" truevalue="true" falsevalue="false" label="If true and this is an unpaired fastq any occurance of '/1' will be removed from the end of a read name" help="STRIP_UNPAIRED_MATE_NUMBER; default=false"/> <param name="allow_and_ignore_empty_lines" type="boolean" truevalue="true" falsevalue="false" label="Allow (and ignore) empty lines" help="ALLOW_AND_IGNORE_EMPTY_LINES; default=false"/> - + <expand macro="VS" /> - - </inputs> - + + </inputs> + <outputs> <data format="bam" name="outFile" label="${tool.name} on ${on_string}: reads as unaligned BAM"/> </outputs> - + <tests> <test> <param name="input_type_selector" value="pe" /> @@ -139,9 +138,9 @@ <param name="fastq" value="picard_FastqToSam_read1.fq" ftype="fastq" /> <param name="fastq2" value="picard_FastqToSam_read2.fq" ftype="fastq" /> <output name="outFile" file="picard_FastqToSam_test1.bam" ftype="bam" lines_diff="4"/> - </test> + </test> </tests> - + <help> .. class:: infomark @@ -157,62 +156,62 @@ @description@ FASTQ=File - F1=File Input fastq file for single end data, or first read in paired end + F1=File Input fastq file for single end data, or first read in paired end data. Required. - + FASTQ2=File - F2=File Input fastq file for the second read of paired end data (if used). + F2=File Input fastq file for the second read of paired end data (if used). QUALITY_FORMAT=FastqQualityFormat - V=FastqQualityFormat A value describing how the quality values are encoded in the fastq. Either Solexa for - pre-pipeline 1.3 style scores (solexa scaling + 66), Illumina for pipeline 1.3 and above - (phred scaling + 64) or Standard for phred scaled scores with a character shift of 33. - If this value is not specified, the quality format will be detected automatically. - Default value: null. Possible values: {Solexa, Illumina, Standard} + V=FastqQualityFormat A value describing how the quality values are encoded in the fastq. Either Solexa for + pre-pipeline 1.3 style scores (solexa scaling + 66), Illumina for pipeline 1.3 and above + (phred scaling + 64) or Standard for phred scaled scores with a character shift of 33. + If this value is not specified, the quality format will be detected automatically. + Default value: null. Possible values: {Solexa, Illumina, Standard} READ_GROUP_NAME=String - RG=String Read group name Default value: A. - + RG=String Read group name Default value: A. + SAMPLE_NAME=String - SM=String Sample name to insert into the read group header Required. - + SM=String Sample name to insert into the read group header Required. + LIBRARY_NAME=String LB=String The library name to place into the LB attribute in the read group header. - + PLATFORM_UNIT=String PU=String The platform unit (often run_barcode.lane) to insert into the read group header. - + PLATFORM=String PL=String The platform type (e.g. illumina, solid) to insert into the read group header. - + SEQUENCING_CENTER=String CN=String The sequencing center from which the data originated. - + PREDICTED_INSERT_SIZE=Integer PI=Integer Predicted median insert size, to insert into the read group header. - + COMMENT=String - CO=String Comment to include in the merged output file's header. - + CO=String Comment to include in the merged output file's header. + DESCRIPTION=String - DS=String Inserted into the read group header. - + DS=String Inserted into the read group header. + RUN_DATE=Iso8601Date - DT=Iso8601Date Date the run was produced, to insert into the read group header. - - MIN_Q=Integer Minimum quality allowed in the input fastq. An exception will be thrown if a quality is + DT=Iso8601Date Date the run was produced, to insert into the read group header. + + MIN_Q=Integer Minimum quality allowed in the input fastq. An exception will be thrown if a quality is less than this value. Default value: 0. - - MAX_Q=Integer Maximum quality allowed in the input fastq. An exception will be thrown if a quality is + + MAX_Q=Integer Maximum quality allowed in the input fastq. An exception will be thrown if a quality is greater than this value. Default value: 93. - + STRIP_UNPAIRED_MATE_NUMBER=Boolean - If true and this is an unpaired fastq any occurance of '/1' will be removed from the end - of a read name. Default value: false. Possible values: {true, false} - + If true and this is an unpaired fastq any occurance of '/1' will be removed from the end + of a read name. Default value: false. Possible values: {true, false} + ALLOW_AND_IGNORE_EMPTY_LINES=Boolean - Allow (and ignore) empty lines Default value: false. Possible values: {true, false} - + Allow (and ignore) empty lines Default value: false. Possible values: {true, false} + @more_info@
--- a/picard_FilterSamReads.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_FilterSamReads.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,35 +6,35 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ - + @symlink_element_identifier@ ##Sam Sorting is performed here because FilterSamReads requires input to be in query-sorted order - + picard SortSam - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT=query_sorted_bam.bam SORT_ORDER=queryname VALIDATION_STRINGENCY=LENIENT QUIET=true VERBOSITY=ERROR - + && - + picard FilterSamReads INPUT=query_sorted_bam.bam FILTER="${filter_type.filter}" - + #if ( str( $filter_type.filter ) == "includeReadList" or str( $filter_type.filter ) == "excludeReadList" ): READ_LIST_FILE="${filter_type.read_list_file}" #end if - + OUTPUT="${outFile}" SORT_ORDER=coordinate VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param name="inputFile" type="data" format="sam,bam" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/> @@ -54,15 +54,15 @@ <param name="read_list_file" type="data" format="tabular" label="Dataset containing read names that will be EXCLUDED in the output" help="READ_LIST_FILE"/> </when> </conditional> - + <expand macro="VS" /> - - </inputs> - + + </inputs> + <outputs> <data format="bam" name="outFile" label="${tool.name} on ${on_string}: filtered BAM"/> </outputs> - + <tests> <test> <param name="inputFile" value="picard_FilterSamReads.bam" ftype="bam"/> @@ -79,8 +79,8 @@ <output name="outFile" file="picard_FilterSamReads_exclude_reads_test2.bam" ftype="bam" lines_diff="4"/> </test> </tests> - - + + <help> **Purpose** @@ -93,32 +93,32 @@ **Warning on using this tool on BWA-MEM output** -This tool will likely fail on BAM datasets generated by BWA MEM as it generates partial read alignemnts. +This tool will likely fail on BAM datasets generated by BWA MEM as it generates partial read alignemnts. @dataset_collections@ @description@ FILTER=Filter Filter. Required. Possible values: - includeAligned [OUTPUT SAM/BAM will contain aligned - reads only. (Note that *both* first and + includeAligned [OUTPUT SAM/BAM will contain aligned + reads only. (Note that *both* first and second of paired reads must be aligned to be included - in the OUTPUT SAM or BAM)], - + in the OUTPUT SAM or BAM)], + excludeAligned [OUTPUT SAM/BAM will contain un-mapped reads only. - (Note that *both* first and second of pair must be aligned to be + (Note that *both* first and second of pair must be aligned to be excluded from the OUTPUT SAM or BAM)] - - includeReadList [OUTPUT SAM/BAM will contain reads + + includeReadList [OUTPUT SAM/BAM will contain reads that are supplied in the READ_LIST_FILE file] - - excludeReadList [OUTPUT bam will contain - reads that are *not* supplied in the READ_LIST_FILE file]} + + excludeReadList [OUTPUT bam will contain + reads that are *not* supplied in the READ_LIST_FILE file]} READ_LIST_FILE=File - RLF=File Read List File containing reads that will be included or excluded from the OUTPUT SAM or - BAM file. Default value: null. - + RLF=File Read List File containing reads that will be included or excluded from the OUTPUT SAM or + BAM file. Default value: null. + @more_info@ </help>
--- a/picard_FixMateInformation.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_FixMateInformation.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,33 +6,32 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ - picard FixMateInformation INPUT="${inputFile}" OUTPUT="${outFile}" ASSUME_SORTED=${assume_sorted} ADD_MATE_CIGAR=${add_mate_cigar} - + SORT_ORDER=coordinate VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param name="inputFile" multiple="True" type="data" format="sam,bam" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/> <param name="add_mate_cigar" type="boolean" checked="true" truevalue="True" falsevalue="False" label="Adds the mate CIGAR tag (MC) if true, does not if false" help="ADD_MATE_CIGAR; default=True"/> <param name="assume_sorted" type="boolean" truevalue="True" falsevalue="False" label="Assume that the input file is QUERYNAME sorted" help="ASSUME_SORTED; default=False"/> - + <expand macro="VS" /> - - </inputs> - + + </inputs> + <outputs> <data format="bam" name="outFile" label="${tool.name} on ${on_string}: BAM with fixed mates"/> </outputs> - + <tests> <test> <param name="inputFile" value="picard_FixMateInformation.bam" ftype="bam"/> @@ -42,8 +41,8 @@ <output name="outFile" file="picard_FixMateInformation_test1.bam" ftype="bam" lines_diff="4"/> </test> </tests> - - + + <help> **Purpose** @@ -64,12 +63,12 @@ @description@ ASSUME_SORTED=Boolean - AS=Boolean If true, assume that the input file is queryname sorted, even if the header says - otherwise. Default value: false. - + AS=Boolean If true, assume that the input file is queryname sorted, even if the header says + otherwise. Default value: false. + ADD_MATE_CIGAR=Boolean - MC=Boolean Adds the mate CIGAR tag (MC) if true, does not if false. Default value: true. - + MC=Boolean Adds the mate CIGAR tag (MC) if true, does not if false. Default value: true. + @more_info@ </help>
--- a/picard_MarkDuplicates.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_MarkDuplicates.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,11 +6,11 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ - + @symlink_element_identifier@ picard MarkDuplicates - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" METRICS_FILE="${metrics_file}"
--- a/picard_MarkDuplicatesWithMateCigar.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_MarkDuplicatesWithMateCigar.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,40 +6,40 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ - + @symlink_element_identifier@ picard MarkDuplicatesWithMateCigar - - INPUT="${inputFile}" + + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" - + METRICS_FILE="${metrics_file}" COMMENT="${comment}" MINIMUM_DISTANCE="${minimum_distance}" SKIP_PAIRS_WITH_NO_MATE_CIGAR="${skip_pairs_with_no_mate_cigar}" - - + + REMOVE_DUPLICATES="${remove_duplicates}" ASSUME_SORTED="${assume_sorted}" - + DUPLICATE_SCORING_STRATEGY="${duplicate_scoring_strategy}" - + #import pipes READ_NAME_REGEX=${ pipes.quote( str( $read_name_regex ) ) or "''" } OPTICAL_DUPLICATE_PIXEL_DISTANCE="${optical_duplicate_pixel_distance}" - - + + BLOCK_SIZE=100000 VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param format="bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/> <param name="comment" type="text" label="Add this comment to BAM dataset"/> - + <param name="minimum_distance" type="integer" value="-1" label="The minimum distance to buffer records to account for clipping on the 5' end of the records" help="MINIMUM_DISTANCE; Set this number to -1 to use twice the first read's read length (or 100, whichever is smaller); default=-1"/> <param name="skip_pairs_with_no_mate_cigar" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Skip record pairs with no mate cigar and include them in the output" help="SKIP_PAIRS_WITH_NO_MATE_CIGAR; default=True"/> <param name="remove_duplicates" type="boolean" label="If true do not write duplicates to the output file instead of writing them with appropriate flags set" help="REMOVE_DUPLICATES; default=False"/> @@ -60,14 +60,14 @@ <param name="optical_duplicate_pixel_distance" type="integer" value="100" min="0" max="500" label="The maximum offset between two duplicte clusters in order to consider them optical duplicates" help="OPTICAL_DUPLICATE_PIXEL_DISTANCE; default=100"/> <expand macro="VS" /> - - </inputs> - + + </inputs> + <outputs> <data format="txt" name="metrics_file" label="${tool.name} on ${on_string}: MarkDuplicate metrics"/> <data format="bam" name="outFile" label="${tool.name} on ${on_string}: MarkDuplicates BAM output"/> </outputs> - + <tests> <test> <param name="inputFile" value="picard_MarkDuplicatesWithMateCigar.bam" ftype="bam"/> @@ -83,8 +83,8 @@ <output name="outFile" file="picard_MarkDuplicatesWithMateCigar_test1.bam" ftype="bam" lines_diff="4"/> </test> </tests> - - + + <help> **Purpose** @@ -110,44 +110,44 @@ @description@ - MINIMUM_DISTANCE=Integer The minimum distance to buffer records to account for clipping on the 5' end of the - records.Set this number to -1 to use twice the first read's read length (or 100, - whichever is smaller). Default value: -1. This option can be set to 'null' to clear the - default value. - + MINIMUM_DISTANCE=Integer The minimum distance to buffer records to account for clipping on the 5' end of the + records.Set this number to -1 to use twice the first read's read length (or 100, + whichever is smaller). Default value: -1. This option can be set to 'null' to clear the + default value. + SKIP_PAIRS_WITH_NO_MATE_CIGAR=Boolean - Skip record pairs with no mate cigar and include them in the output. Default value: - true. This option can be set to 'null' to clear the default value. Possible values: - {true, false} + Skip record pairs with no mate cigar and include them in the output. Default value: + true. This option can be set to 'null' to clear the default value. Possible values: + {true, false} - COMMENT=String - CO=String Comment(s) to include in the output file's header. This option may be specified 0 or - more times. + COMMENT=String + CO=String Comment(s) to include in the output file's header. This option may be specified 0 or + more times. + + REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with + appropriate flags set. Default value: false. - REMOVE_DUPLICATES=Boolean If true do not write duplicates to the output file instead of writing them with - appropriate flags set. Default value: false. - - READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. 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. Set this option to null to disable optical duplicate - detection. The regular expression should contain three capture groups for the three - variables, in order. It must match the entire read name. Note that if the default regex - is specified, a regex match is not actually done, but instead the read name is split on - colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be - tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements - are assumed to be tile, x and y values. Default value: + READ_NAME_REGEX=String Regular expression that can be used to parse read names in the incoming SAM file. 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. Set this option to null to disable optical duplicate + detection. The regular expression should contain three capture groups for the three + variables, in order. It must match the entire read name. Note that if the default regex + is specified, a regex match is not actually done, but instead the read name is split on + colon character. For 5 element names, the 3rd, 4th and 5th elements are assumed to be + tile, x and y values. For 7 element names (CASAVA 1.8), the 5th, 6th, and 7th elements + are assumed to be tile, x and y values. Default value: [a-zA-Z0-9]+:[0-9]:([0-9]+):([0-9]+):([0-9]+).*. - + DUPLICATE_SCORING_STRATEGY=ScoringStrategy - DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value: - TOTAL_MAPPED_REFERENCE_LENGTH. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH} - + DS=ScoringStrategy The scoring strategy for choosing the non-duplicate among candidates. Default value: + TOTAL_MAPPED_REFERENCE_LENGTH. Possible values: {SUM_OF_BASE_QUALITIES, TOTAL_MAPPED_REFERENCE_LENGTH} + OPTICAL_DUPLICATE_PIXEL_DISTANCE=Integer - The maximum offset between two duplicte clusters in order to consider them optical - duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels) - unless using later versions of the Illumina pipeline that multiply pixel values by 10, in - which case 50-100 is more normal. Default value: 100. + The maximum offset between two duplicte clusters in order to consider them optical + duplicates. This should usually be set to some fairly small number (e.g. 5-10 pixels) + unless using later versions of the Illumina pipeline that multiply pixel values by 10, in + which case 50-100 is more normal. Default value: 100. @more_info@
--- a/picard_MeanQualityByCycle.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_MeanQualityByCycle.xml Tue Dec 06 10:04:41 2016 -0500 @@ -9,30 +9,30 @@ <command detect_errors="exit_code"><![CDATA[ @java_options@ ##set up input files - + @symlink_element_identifier@ #set $reference_fasta_filename = "localref.fa" - + #if str( $reference_source.reference_source_selector ) == "history": ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" && #else: #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path ) #end if - + picard MeanQualityByCycle - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" CHART_OUTPUT="${pdfFile}" REFERENCE_SEQUENCE="${reference_fasta_filename}" ALIGNED_READS_ONLY="${aligned_reads_only}" PF_READS_ONLY="${pf_reads_only}" - + ASSUME_SORTED="${assume_sorted}" - + VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param format="sam,bam" name="inputFile" type="data" label="SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset."/> @@ -55,16 +55,16 @@ <param name="aligned_reads_only" type="boolean" truevalue="true" falsevalue="false" label="If set to true, calculate mean quality over aligned reads only" help="ALIGNED_READS_ONLY; default=False"/> <param name="pf_reads_only" type="boolean" truevalue="true" falsevalue="false" label="If set to true calculate mean quality over reads passing quality filter" help="PF_READS_ONLY; 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"/> - + <expand macro="VS" /> - + </inputs> - + <outputs> <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Summary data"/> <data format="pdf" name="pdfFile" label="${tool.name} on ${on_string}: Chart PDF"/> </outputs> - + <tests> <test> <param name="assume_sorted" value="true" /> @@ -74,31 +74,31 @@ <param name="ref_file" value="picard_MeanQualityByCycle_ref.fa" /> <param name="inputFile" value="picard_MeanQualityByCycle.bam" ftype="bam" /> <output name="outFile" file="picard_MeanQualityByCycle_test1.tab" ftype="tabular" lines_diff="4"/> - </test> + </test> </tests> - - + + <help> .. class:: infomark **Purpose** -Program to chart the distribution of base qualities by cycle within reads supplied in a SAM or BAM dataset. +Program to chart the distribution of base qualities by cycle within reads supplied in a SAM or BAM dataset. @dataset_collections@ @description@ - ALIGNED_READS_ONLY=Boolean If set to true, calculate the base distribution over aligned reads only. Default value: - false. Possible values: {true, false} + ALIGNED_READS_ONLY=Boolean If set to true, calculate the base distribution over aligned reads only. Default value: + false. Possible values: {true, false} - PF_READS_ONLY=Boolean If set to true calculate the base distribution over PF reads only. Default value: false. - This option can be set to 'null' to clear the default value. Possible values: {true, - false} + PF_READS_ONLY=Boolean If set to true calculate the base distribution over PF reads only. Default value: false. + This option can be set to 'null' to clear the default value. Possible values: {true, + false} ASSUME_SORTED=Boolean - AS=Boolean If true (default), then the sort order in the header file will be ignored. Default: True + AS=Boolean If true (default), then the sort order in the header file will be ignored. Default: True @more_info@
--- a/picard_MergeBamAlignment.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_MergeBamAlignment.xml Tue Dec 06 10:04:41 2016 -0500 @@ -8,29 +8,29 @@ @java_options@ #set $picard_dict = "localref.dict" #set $ref_fasta = "localref.fa" ## This is done because picards "likes" .fa extension - + ln -s "${reference_source.ref_file}" "${ref_fasta}" && - + #if str( $reference_source.reference_source_selector ) == "history": - + picard CreateSequenceDictionary REFERENCE="${ref_fasta}" OUTPUT="${picard_dict}" QUIET=true VERBOSITY=ERROR - + && - + #else: - + #set $ref_fasta = str( $reference_source.ref_file.fields.path ) - + #end if - + picard MergeBamAlignment UNMAPPED_BAM="${unmapped_bam}" - + PAIRED_RUN=true ##This argument is ignored and will be removed. Required. Possible values: {true, false} - + #if str( $aligned_or_read1_and_read2.aligned_or_read1_and_read2_selector ) == "paired_one_file": #for $dataset in $aligned_or_read1_and_read2.aligned_bams: ALIGNED_BAM="${dataset.aligned_bam}" @@ -47,48 +47,48 @@ READ1_ALIGNED_BAM="${dataset.read1_aligned_bam}" #end for #end if - + OUTPUT="${outFile}" REFERENCE_SEQUENCE="${ref_fasta}" - + CLIP_ADAPTERS="${clip_adapters}" IS_BISULFITE_SEQUENCE="${is_bisulfite_sequence}" ALIGNED_READS_ONLY="${aligned_reads_only}" MAX_INSERTIONS_OR_DELETIONS="${max_insertions_or_deletions}" - + #for $attribute in $attributes_to_retain: ATTRIBUTES_TO_RETAIN="${$attribute.attribute}" #end for - + #for $attribute in $attributes_to_remove: ATTRIBUTES_TO_REMOVE="${$attribute.attribute}" #end for - + READ1_TRIM="${read1_trim}" READ2_TRIM="${read2_trim}" - + #if str( $orientations ) != "None": #for $orientation in str( $orientations ).split(','): ## See trello card https://trello.com/c/9nW02Zhd EXPECTED_ORIENTATIONS="${orientation}" #end for #end if - - ALIGNER_PROPER_PAIR_FLAGS="${aligner_proper_pair_flags}" + + ALIGNER_PROPER_PAIR_FLAGS="${aligner_proper_pair_flags}" PRIMARY_ALIGNMENT_STRATEGY="${primary_alignment_strategy}" CLIP_OVERLAPPING_READS="${clip_overlapping_reads}" INCLUDE_SECONDARY_ALIGNMENTS="${include_secondary_alignments}" ADD_MATE_CIGAR="${add_mate_cigar}" - + VALIDATION_STRINGENCY="${validation_stringency}" SORT_ORDER=coordinate QUIET=true VERBOSITY=ERROR - + ]]></command> - + <inputs> - + <conditional name="reference_source"> <param name="reference_source_selector" type="select" label="Load reference genome from"> <option value="cached">Local cache</option> @@ -103,11 +103,11 @@ <validator type="no_options" message="A built-in dictionary is not available for the build associated with the selected input file"/> </param> </when> - <when value="history"> + <when value="history"> <param name="ref_file" type="data" format="fasta" label="Use the following dataset to create dictionary" help="You can upload a FASTA sequence to the history from which Picard will automatically generate dictionary using CreateSequenceDictionary command" /> </when> </conditional> - + <param format="sam,bam" name="unmapped_bam" type="data" label="Selected unaligned SAM or BAM with original reads" help="UNMAPPED_BAM; This dataset must be sorted in queryname order (use picard_SortSam to do this)" /> <conditional name="aligned_or_read1_and_read2"> <param name="aligned_or_read1_and_read2_selector" type="select" label="What type of aligned data do you have?"> @@ -134,39 +134,39 @@ </repeat> </when> </conditional> - + <param name="clip_adapters" type="boolean" checked="true" label="Whether to clip adapters where identified" help="CLIP_ADAPTERS; default=True"/> <param name="is_bisulfite_sequence" type="boolean" label="Whether the data is from bisulfite sequencing (used when caculating the NM tag)" help="IS_BISULFITE_SEQUENCE; default=False"/> <param name="aligned_reads_only" type="boolean" label="Whether to output only aligned reads" help="ALIGNED_READS_ONLY; default=False"/> <param name="max_insertions_or_deletions" type="integer" value="1" label="The maximum number of insertions or deletions permitted for an alignment to be included" help="MAX_INSERTIONS_OR_DELETIONS; Alignments with more than this many insertions or deletions will be ignored. Set to -1 to allow any number of insertions or deletions. default=1"/> - + <repeat name="attributes_to_retain" title="Retain the following alignment attribute" min="0" help="You can provide multiple attributes"> <param name="attribute" type="text" label="Reserved alignment attributes (tags starting with X, Y, or Z) that should be brought over from the alignment data when merging" help="ATTRIBUTES_TO_RETAIN; example: XA"/> </repeat> - + <repeat name="attributes_to_remove" title="Remove the following alignment attribute" min="0" help="You can provide multiple attributes"> <param name="attribute" type="text" label="Attributes from the alignment record that should be removed when merging." help="ATTRIBUTES_TO_REMOVE; This overrides ATTRIBUTES_TO_RETAIN if they share common tags"/> </repeat> - + <param name="read1_trim" type="integer" value="0" label="The number of bases trimmed from the beginning of read 1 prior to alignment" help="READ1_TRIM; default=0"/> <param name="read2_trim" type="integer" value="0" label="The number of bases trimmed from the beginning of read 2 prior to alignment" help="READ2_TRIM; default=0"/> - + <param name="orientations" type="select" multiple="True" display="checkboxes" label="The expected orientation of proper read pairs" help="EXPECTED_ORIENTATIONS; multiple orinetations can be selected"> <option value="FR">Forward/Reverse (FR)</option> <option value="RF">Reverse/Forward (RF)</option> <option value="TANDEM">Tandem</option> </param> - - + + <param name="aligner_proper_pair_flags" type="boolean" label="Use the aligner's idea of what a proper pair is rather than computing in this program" help="ALIGNER_PROPER_PAIR_FLAGS; default=False"/> - + <param name="primary_alignment_strategy" type="select" label="Strategy for selecting primary alignment when the aligner has provided more than one alignment for a pair or fragments" help="PRIMARY_ALIGNMENT_STRATEGY; see help below for more info; default=BestMapq"> <option value="BestMapq" selected="True">BestMapq</option> <option value="EarliestFragment">EarliestFragment</option> <option value="BestEndMapq">BestEndMapq</option> <option value="MostDistant">MostDistant</option> </param> - + <param name="clip_overlapping_reads" type="boolean" checked="True" label="For paired reads, soft clip the 3' end of each read if necessary so that it does not extend past the 5' end of its mate" help="CLIP_OVERLAPPING_READS; default=True"/> <param name="include_secondary_alignments" type="boolean" checked="True" label="If false, do not write secondary alignments to output" help="INCLUDE_SECONDARY_ALIGNMENTS; default=True"/> <param name="add_mate_cigar" type="boolean" checked="True" label="Adds the mate CIGAR tag (MC) if true, does not if false" help="ADD_MATE_CIGAR; default=True"/> @@ -197,8 +197,8 @@ <output name="outFile" file="picard_MergeBamAlignment_test1.bam" ftype="bam" lines_diff="4"/> </test> </tests> - - + + <help> .. class:: infomark @@ -212,96 +212,96 @@ @description@ UNMAPPED_BAM=File - UNMAPPED=File Original SAM or BAM file of unmapped reads, which must be in queryname order. Required. - + UNMAPPED=File Original SAM or BAM file of unmapped reads, which must be in queryname order. Required. + ALIGNED_BAM=File - ALIGNED=File SAM or BAM file(s) with alignment data. This option may be specified 0 or more times. - Cannot be used in conjuction with option(s) READ1_ALIGNED_BAM (R1_ALIGNED) + ALIGNED=File SAM or BAM file(s) with alignment data. This option may be specified 0 or more times. + Cannot be used in conjuction with option(s) READ1_ALIGNED_BAM (R1_ALIGNED) READ2_ALIGNED_BAM (R2_ALIGNED) - + READ1_ALIGNED_BAM=File - R1_ALIGNED=File SAM or BAM file(s) with alignment data from the first read of a pair. This option may be - specified 0 or more times. Cannot be used in conjuction with option(s) ALIGNED_BAM + R1_ALIGNED=File SAM or BAM file(s) with alignment data from the first read of a pair. This option may be + specified 0 or more times. Cannot be used in conjuction with option(s) ALIGNED_BAM (ALIGNED) - + READ2_ALIGNED_BAM=File - R2_ALIGNED=File SAM or BAM file(s) with alignment data from the second read of a pair. This option may - be specified 0 or more times. Cannot be used in conjuction with option(s) ALIGNED_BAM + R2_ALIGNED=File SAM or BAM file(s) with alignment data from the second read of a pair. This option may + be specified 0 or more times. Cannot be used in conjuction with option(s) ALIGNED_BAM (ALIGNED) - + PAIRED_RUN=Boolean - PE=Boolean This argument is ignored and will be removed. Required. Possible values: {true, false} - + PE=Boolean This argument is ignored and will be removed. Required. Possible values: {true, false} + JUMP_SIZE=Integer - JUMP=Integer The expected jump size (required if this is a jumping library). Deprecated. Use - EXPECTED_ORIENTATIONS instead Default value: null. Cannot be used in conjuction with + JUMP=Integer The expected jump size (required if this is a jumping library). Deprecated. Use + EXPECTED_ORIENTATIONS instead Default value: null. Cannot be used in conjuction with option(s) EXPECTED_ORIENTATIONS (ORIENTATIONS) - - CLIP_ADAPTERS=Boolean Whether to clip adapters where identified. Default value: true. Possible values: {true, false} - - IS_BISULFITE_SEQUENCE=Boolean Whether the lane is bisulfite sequence (used when caculating the NM tag). Default value: - false. Possible values: {true, false} - - ALIGNED_READS_ONLY=Boolean Whether to output only aligned reads. Default value: false. Possible values: {true, false} - + + CLIP_ADAPTERS=Boolean Whether to clip adapters where identified. Default value: true. Possible values: {true, false} + + IS_BISULFITE_SEQUENCE=Boolean Whether the lane is bisulfite sequence (used when caculating the NM tag). Default value: + false. Possible values: {true, false} + + ALIGNED_READS_ONLY=Boolean Whether to output only aligned reads. Default value: false. Possible values: {true, false} + MAX_INSERTIONS_OR_DELETIONS=Integer - MAX_GAPS=Integer The maximum number of insertions or deletions permitted for an alignment to be included. - Alignments with more than this many insertions or deletions will be ignored. Set to -1 to + MAX_GAPS=Integer The maximum number of insertions or deletions permitted for an alignment to be included. + Alignments with more than this many insertions or deletions will be ignored. Set to -1 to allow any number of insertions or deletions. Default value: 1. - - ATTRIBUTES_TO_RETAIN=String Reserved alignment attributes (tags starting with X, Y, or Z) that should be brought over - from the alignment data when merging. This option may be specified 0 or more times. - - ATTRIBUTES_TO_REMOVE=String Attributes from the alignment record that should be removed when merging. This overrides - ATTRIBUTES_TO_RETAIN if they share common tags. This option may be specified 0 or more - times. - + + ATTRIBUTES_TO_RETAIN=String Reserved alignment attributes (tags starting with X, Y, or Z) that should be brought over + from the alignment data when merging. This option may be specified 0 or more times. + + ATTRIBUTES_TO_REMOVE=String Attributes from the alignment record that should be removed when merging. This overrides + ATTRIBUTES_TO_RETAIN if they share common tags. This option may be specified 0 or more + times. + READ1_TRIM=Integer - R1_TRIM=Integer The number of bases trimmed from the beginning of read 1 prior to alignment Default - value: 0. - + R1_TRIM=Integer The number of bases trimmed from the beginning of read 1 prior to alignment Default + value: 0. + READ2_TRIM=Integer - R2_TRIM=Integer The number of bases trimmed from the beginning of read 2 prior to alignment Default - value: 0. - + R2_TRIM=Integer The number of bases trimmed from the beginning of read 2 prior to alignment Default + value: 0. + EXPECTED_ORIENTATIONS=PairOrientation - ORIENTATIONS=PairOrientation The expected orientation of proper read pairs. Replaces JUMP_SIZE Possible values: {FR, - RF, TANDEM} This option may be specified 0 or more times. Cannot be used in conjuction + ORIENTATIONS=PairOrientation The expected orientation of proper read pairs. Replaces JUMP_SIZE Possible values: {FR, + RF, TANDEM} This option may be specified 0 or more times. Cannot be used in conjuction with option(s) JUMP_SIZE (JUMP) - + ALIGNER_PROPER_PAIR_FLAGS=Boolean - Use the aligner's idea of what a proper pair is rather than computing in this program. - Default value: false. Possible values: {true, false} - + Use the aligner's idea of what a proper pair is rather than computing in this program. + Default value: false. Possible values: {true, false} + SORT_ORDER=SortOrder SO=SortOrder The order in which the merged reads should be output. Default value: coordinate. - Possible values: {unsorted, queryname, coordinate} - + Possible values: {unsorted, queryname, coordinate} + PRIMARY_ALIGNMENT_STRATEGY=PrimaryAlignmentStrategy - Strategy for selecting primary alignment when the aligner has provided more than one - alignment for a pair or fragment, and none are marked as primary, more than one is marked - as primary, or the primary alignment is filtered out for some reason. BestMapq expects - that multiple alignments will be correlated with HI tag, and prefers the pair of - alignments with the largest MAPQ, in the absence of a primary selected by the aligner. - EarliestFragment prefers the alignment which maps the earliest base in the read. Note - that EarliestFragment may not be used for paired reads. BestEndMapq is appropriate for - cases in which the aligner is not pair-aware, and does not output the HI tag. It simply - picks the alignment for each end with the highest MAPQ, and makes those alignments - primary, regardless of whether the two alignments make sense together.MostDistant is also - for a non-pair-aware aligner, and picks the alignment pair with the largest insert size. - If all alignments would be chimeric, it picks the alignments for each end with the best + Strategy for selecting primary alignment when the aligner has provided more than one + alignment for a pair or fragment, and none are marked as primary, more than one is marked + as primary, or the primary alignment is filtered out for some reason. BestMapq expects + that multiple alignments will be correlated with HI tag, and prefers the pair of + alignments with the largest MAPQ, in the absence of a primary selected by the aligner. + EarliestFragment prefers the alignment which maps the earliest base in the read. Note + that EarliestFragment may not be used for paired reads. BestEndMapq is appropriate for + cases in which the aligner is not pair-aware, and does not output the HI tag. It simply + picks the alignment for each end with the highest MAPQ, and makes those alignments + primary, regardless of whether the two alignments make sense together.MostDistant is also + for a non-pair-aware aligner, and picks the alignment pair with the largest insert size. + If all alignments would be chimeric, it picks the alignments for each end with the best MAPQ. For all algorithms, ties are resolved arbitrarily. Default value: BestMapq. - Possible values: {BestMapq, EarliestFragment, BestEndMapq, MostDistant} - - CLIP_OVERLAPPING_READS=BooleanFor paired reads, soft clip the 3' end of each read if necessary so that it does not - extend past the 5' end of its mate. Default value: true. Possible values: {true, false} - + Possible values: {BestMapq, EarliestFragment, BestEndMapq, MostDistant} + + CLIP_OVERLAPPING_READS=BooleanFor paired reads, soft clip the 3' end of each read if necessary so that it does not + extend past the 5' end of its mate. Default value: true. Possible values: {true, false} + INCLUDE_SECONDARY_ALIGNMENTS=Boolean If false, do not write secondary alignments to output. Default value: true. - Possible values: {true, false} - + Possible values: {true, false} + ADD_MATE_CIGAR=Boolean - MC=Boolean Adds the mate CIGAR tag (MC) if true, does not if false. Possible values: {true, false} + MC=Boolean Adds the mate CIGAR tag (MC) if true, does not if false. Possible values: {true, false}
--- a/picard_MergeSamFiles.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_MergeSamFiles.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,17 +6,16 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ - picard MergeSamFiles - + #for $element in $inputFile: INPUT="${element}" #end for - + OUTPUT="${outFile}" MERGE_SEQUENCE_DICTIONARIES="${merge_sequence_dictionaries}" - + ASSUME_SORTED="${assume_sorted}" #for $element in $comments: COMMENT="${element.comment}" @@ -27,7 +26,7 @@ VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param format="sam,bam" name="inputFile" type="data" multiple="True" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/> @@ -37,15 +36,15 @@ <repeat name="comments" title="Comment" min="0" help="You can provide multiple comments"> <param name="comment" type="text" label="Add this comment to BAM dataset" help="COMMENT"/> </repeat> - + <expand macro="VS" /> - - </inputs> - + + </inputs> + <outputs> <data format="bam" name="outFile" label="${tool.name} on ${on_string}: Merged BAM dataset"/> </outputs> - + <tests> <test> <param name="inputFile" value="picard_MergeSamFiles_input1.bam,picard_MergeSamFiles_input2.bam,picard_MergeSamFiles_input3.bam" ftype="bam"/> @@ -55,8 +54,8 @@ <output name="outFile" file="picard_MergeSamFiles_test1.bam" ftype="bam" lines_diff="4"/> </test> </tests> - - + + <help> **Purpose** @@ -68,17 +67,17 @@ @description@ ASSUME_SORTED=Boolean - AS=Boolean If true, assume that the input files are in the same sort order as the requested output - sort order, even if their headers say otherwise. Default value: false. This option can - be set to 'null' to clear the default value. Possible values: {true, false} - + AS=Boolean If true, assume that the input files are in the same sort order as the requested output + sort order, even if their headers say otherwise. Default value: false. This option can + be set to 'null' to clear the default value. Possible values: {true, false} + MERGE_SEQUENCE_DICTIONARIES=Boolean - MSD=Boolean Merge the sequence dictionaries Default value: false. This option can be set to 'null' - to clear the default value. Possible values: {true, false} - + MSD=Boolean Merge the sequence dictionaries Default value: false. This option can be set to 'null' + to clear the default value. Possible values: {true, false} + COMMENT=String - CO=String Comment(s) to include in the merged output file's header. This option may be specified 0 - or more times. + CO=String Comment(s) to include in the merged output file's header. This option may be specified 0 + or more times. @more_info@
--- a/picard_NormalizeFasta.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_NormalizeFasta.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,34 +6,32 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ - - - ## Two lines below are due to the fact that picard likes fasta files to have extension .fa - #set $fasta_file="local_fasta.fa" - ln -s "${inputFile}" "${fasta_file}" && - + + ## Two lines below are due to the fact that picard likes fasta files to have extension .fa + ln -s '$inputFile' '$inputFile.element_identifier'.fa && + picard NormalizeFasta - - INPUT="${fasta_file}" + + INPUT='$inputFile.element_identifier'.fa OUTPUT="${outFile}" LINE_LENGTH="${line_length}" TRUNCATE_SEQUENCE_NAMES_AT_WHITESPACE="${truncate_sequence_names_at_whitespaces}" - + QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param format="fasta" name="inputFile" type="data" label="FASTA dataset or dataset collection" help="If empty, upload or import a FASTA dataset" /> <param name="line_length" type="integer" value="100" min="1" max="200" label="The line length to be used for the output fasta file" help="LINE_LENGTH; default=100"/> <param name="truncate_sequence_names_at_whitespaces" type="boolean" label="Truncate sequence names at first whitespace" help="TRUNCATE_SEQUENCE_NAMES_AT_WHITESPACE; default=False"/> - </inputs> - + </inputs> + <outputs> <data format="fasta" name="outFile" label="${tool.name} on ${on_string}: Normalized FASTA dataset"/> </outputs> - + <tests> <test> <param name="inputFile" value="picard_NormalizeFasta_ref.fa" ftype="fasta"/> @@ -42,8 +40,8 @@ <output name="outFile" file="picard_NormalizeFasta_test1.fa" ftype="fasta"/> </test> </tests> - - + + <help> **Purpose** @@ -54,10 +52,10 @@ @description@ - LINE_LENGTH=Integer The line length to be used for the output fasta file. Default value: 100. - + LINE_LENGTH=Integer The line length to be used for the output fasta file. Default value: 100. + TRUNCATE_SEQUENCE_NAMES_AT_WHITESPACE=Boolean - Truncate sequence names at first whitespace. Default value: false. Possible values: {true, false} + Truncate sequence names at first whitespace. Default value: false. Possible values: {true, false} @more_info@
--- a/picard_QualityScoreDistribution.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_QualityScoreDistribution.xml Tue Dec 06 10:04:41 2016 -0500 @@ -9,31 +9,31 @@ <command detect_errors="exit_code"><![CDATA[ @java_options@ ##set up input files - + @symlink_element_identifier@ #set $reference_fasta_filename = "localref.fa" - + #if str( $reference_source.reference_source_selector ) == "history": ln -s "${reference_source.ref_file}" "${reference_fasta_filename}" && #else: #set $reference_fasta_filename = str( $reference_source.ref_file.fields.path ) #end if - + picard QualityScoreDistribution - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" CHART_OUTPUT="${pdfFile}" REFERENCE_SEQUENCE="${reference_fasta_filename}" ALIGNED_READS_ONLY="${aligned_reads_only}" PF_READS_ONLY="${pf_reads_only}" INCLUDE_NO_CALLS="${include_no_calls}" - + ASSUME_SORTED="${assume_sorted}" - + VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param format="sam,bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/> @@ -57,16 +57,16 @@ <param name="pf_reads_only" type="boolean" truevalue="true" falsevalue="false" label="If set to true calculate mean quality over reads passing quality filter" help="PF_READS_ONLY; default=False"/> <param name="include_no_calls" type="boolean" label="If set to true, include quality for no-call bases in the distribution" help="INCLUDE_NO_CALLS; default=False"/> <param name="assume_sorted" type="boolean" label="Assume the input file is already sorted" checked="true" truevalue="true" falsevalue="false" help="ASSUME_SORTED; default=True"/> - + <expand macro="VS" /> - + </inputs> - + <outputs> <data format="tabular" name="outFile" label="${tool.name} on ${on_string}: Summary data"/> <data format="pdf" name="pdfFile" label="${tool.name} on ${on_string}: Chart PDF"/> </outputs> - + <tests> <test> <param name="assume_sorted" value="true" /> @@ -77,10 +77,10 @@ <param name="ref_file" value="picard_QualityScoreDistribution_ref.fa" /> <param name="inputFile" value="picard_QualityScoreDistribution.bam" ftype="bam" /> <output name="outFile" file="picard_QualityScoreDistribution_test1.tab" ftype="tabular" lines_diff="4"/> - </test> + </test> </tests> - - + + <help> .. class:: infomark @@ -93,17 +93,17 @@ @description@ - ALIGNED_READS_ONLY=Boolean If set to true, calculate the base distribution over aligned reads only. Default value: - false. Possible values: {true, false} + ALIGNED_READS_ONLY=Boolean If set to true, calculate the base distribution over aligned reads only. Default value: + false. Possible values: {true, false} - PF_READS_ONLY=Boolean If set to true calculate the base distribution over PF reads only. Default value: false. + PF_READS_ONLY=Boolean If set to true calculate the base distribution over PF reads only. Default value: false. Possible values: {true, false} - - INCLUDE_NO_CALLS=Boolean If set to true, include quality for no-call bases in the distribution. Default value: - false. Possible values: {true, false} + + INCLUDE_NO_CALLS=Boolean If set to true, include quality for no-call bases in the distribution. Default value: + false. Possible values: {true, false} ASSUME_SORTED=Boolean - AS=Boolean If true (default), then the sort order in the header file will be ignored. Default: True + AS=Boolean If true (default), then the sort order in the header file will be ignored. Default: True @more_info@
--- a/picard_ReorderSam.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_ReorderSam.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,41 +6,42 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ + @symlink_element_identifier@ #set $picard_dict = "localref.dict" #set $ref_fasta = "localref.fa" ## This is done because picards "likes" .fa extension - + ln -s "${reference_source.ref_file}" "${ref_fasta}" && - + #if str( $reference_source.reference_source_selector ) == "history": - + picard CreateSequenceDictionary REFERENCE="${ref_fasta}" OUTPUT="${picard_dict}" QUIET=true VERBOSITY=ERROR - + && - + #else: - + #set $ref_fasta = str( $reference_source.ref_file.fields.path ) - + #end if - + picard ReorderSam - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" REFERENCE="${ref_fasta}" ALLOW_INCOMPLETE_DICT_CONCORDANCE="${allow_incomplete_dict_concordance}" ALLOW_CONTIG_LENGTH_DISCORDANCE="${allow_contig_length_discordance}" - + VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> - + <inputs> - + <conditional name="reference_source"> <param name="reference_source_selector" type="select" label="Load reference genome from"> <option value="cached">Local cache</option> @@ -55,7 +56,7 @@ <validator type="no_options" message="A built-in dictionary is not available for the build associated with the selected input file"/> </param> </when> - <when value="history"> + <when value="history"> <param name="ref_file" type="data" format="fasta" label="Use the following dataset to create dictionary" help="You can upload a FASTA sequence to the history from which Picard will automatically generate dictionary using CreateSequenceDictionary command" /> </when> </conditional> @@ -64,7 +65,7 @@ <param name="allow_incomplete_dict_concordance" type="boolean" label="If true, then allows only a partial overlap of the BAM contigs with the new reference sequence contigs" help="ALLOW_INCOMPLETE_DICT_CONCORDANCE; By default, this tool requires a corresponding contig in the new reference for each read contig; default=False"/> <param name="allow_contig_length_discordance" type="boolean" label="If true, then permits mapping from a read contig to a new reference contig with the same name but a different length" help="ALLOW_CONTIG_LENGTH_DISCORDANCE; HIGHLY DANGEROUS! Only use if you know what you are doing; default=False"/> <expand macro="VS" /> - + </inputs> <outputs> <data name="outFile" format="bam" label="${tool.name} on ${on_string}: Reordered BAM"/> @@ -79,8 +80,8 @@ <output name="outFile" file="picard_ReorderSam_test1.bam" ftype="bam" lines_diff="4"/> </test> </tests> - - + + <help> .. class:: infomark @@ -100,14 +101,14 @@ @description@ ALLOW_INCOMPLETE_DICT_CONCORDANCE=Boolean - S=Boolean If true, then allows only a partial overlap of the BAM contigs with the new reference - sequence contigs. By default, this tool requires a corresponding contig in the new - reference for each read contig Default value: false. Possible values: {true, false} - + S=Boolean If true, then allows only a partial overlap of the BAM contigs with the new reference + sequence contigs. By default, this tool requires a corresponding contig in the new + reference for each read contig Default value: false. Possible values: {true, false} + ALLOW_CONTIG_LENGTH_DISCORDANCE=Boolean - U=Boolean If true, then permits mapping from a read contig to a new reference contig with the same - name but a different length. Highly dangerous, only use if you know what you are doing. - Default value: false. Possible values: {true, false} + U=Boolean If true, then permits mapping from a read contig to a new reference contig with the same + name but a different length. Highly dangerous, only use if you know what you are doing. + Default value: false. Possible values: {true, false} @more_info@ </help>
--- a/picard_ReplaceSamHeader.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_ReplaceSamHeader.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,32 +6,32 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ - - - ## Two lines below are due to the fact that picard likes fasta files to have extension .fa + @symlink_element_identifier@ + + ## Two lines below are due to the fact that picard likes fasta files to have extension .fa #set $fasta_file="local_fasta.fa" - ln -s "${inputFile}" "${fasta_file}" && - + ln -s "${inputFile}" "${fasta_file}" && + picard ReplaceSamHeader - - INPUT="${inputFile}" + + INPUT='$inputFile.element_identifier' HEADER="${header}" OUTPUT="${outFile}" - + QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param format="sam,bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection (header recepient dataset)" help="If empty, upload or import a SAM/BAM dataset"/> <param name="header" type="data" format="sam,bam" label="SAM/BAM dataset from which Header will be read (header source dataset)" help="HEADER; If empty, upload or import a SAM/BAM dataset"/> - </inputs> - + </inputs> + <outputs> <data format="bam" name="outFile" label="${tool.name} on ${on_string}: BAM file with replaced header"/> </outputs> - + <tests> <test> <param name="inputFile" value="picard_ReplaceSamHeader.bam" ftype="bam"/> @@ -39,8 +39,8 @@ <output name="outFile" file="picard_ReplaceSamHeader_test1.bam" ftype="bam"/> </test> </tests> - - + + <help> **Purpose** @@ -50,7 +50,7 @@ @description@ - HEADER=File SAM file from which SAMFileHeader will be read. Required. + HEADER=File SAM file from which SAMFileHeader will be read. Required. @more_info@
--- a/picard_RevertOriginalBaseQualitiesAndAddMateCigar.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_RevertOriginalBaseQualitiesAndAddMateCigar.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,21 +6,20 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ - picard RevertOriginalBaseQualitiesAndAddMateCigar - - INPUT="${inputFile}" + + INPUT='$inputFile' OUTPUT="${outFile}" - + RESTORE_ORIGINAL_QUALITIES="${restore_original_qualities}" MAX_RECORDS_TO_EXAMINE="${max_records_to_examine}" - + SORT_ORDER=coordinate VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param format="sam,bam" name="inputFile" type="data" multiple="True" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/> @@ -28,13 +27,13 @@ <param name="max_records_to_examine" type="integer" value="10000" min="0" label="The maximum number of records to examine to determine if we can exit early and not output, given that there are a no original base qualities (if we are to restore) and mate cigars exist. Set to 0 to never skip the dataset" help="MAX_RECORDS_TO_EXAMINE; default=10,000"/> <expand macro="VS" /> - - </inputs> - + + </inputs> + <outputs> <data format="bam" name="outFile" label="${tool.name} on ${on_string}: Reverted BAM dataset"/> </outputs> - + <tests> <test> <param name="inputFile" value="picard_RevertOriginalBaseQualitiesAndAddMateCigar.bam" ftype="bam"/> @@ -44,8 +43,8 @@ <output name="outFile" file="picard_RevertOriginalBaseQualitiesAndAddMateCigar_test1.bam" ftype="bam" lines_diff="4"/> </test> </tests> - - + + <help> **Purpose** @@ -57,11 +56,11 @@ @description@ RESTORE_ORIGINAL_QUALITIES=Boolean - OQ=Boolean True to restore original qualities from the OQ field to the QUAL field if available. - Default value: true. Possible values: {true, false} - - MAX_RECORDS_TO_EXAMINE=IntegerThe maximum number of records to examine to determine if we can exit early and not - output, given that there are a no original base qualities (if we are to restore) and mate + OQ=Boolean True to restore original qualities from the OQ field to the QUAL field if available. + Default value: true. Possible values: {true, false} + + MAX_RECORDS_TO_EXAMINE=IntegerThe maximum number of records to examine to determine if we can exit early and not + output, given that there are a no original base qualities (if we are to restore) and mate cigars exist. Set to 0 to never skip the file. Default value: 10000. @more_info@
--- a/picard_RevertSam.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_RevertSam.xml Tue Dec 06 10:04:41 2016 -0500 @@ -6,31 +6,30 @@ <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ @java_options@ - picard RevertSam - - INPUT="${inputFile}" + + INPUT='$inputFile' OUTPUT="${outFile}" - + RESTORE_ORIGINAL_QUALITIES="${restore_original_qualities}" REMOVE_DUPLICATE_INFORMATION="${remove_duplicate_information}" REMOVE_ALIGNMENT_INFORMATION="${remove_alignment_information}" - + #for $attribute_to_clear in $attributes_to_clear: ATTRIBUTE_TO_CLEAR="${attribute_to_clear.attribute}" #end for - + SANITIZE="${sanitize}" MAX_DISCARD_FRACTION="${max_discard_fraction}" SAMPLE_ALIAS="${sample_alias}" LIBRARY_NAME="${library_name}" - + SORT_ORDER="${sort_order}" VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> <param format="sam,bam" name="inputFile" type="data" multiple="True" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/> @@ -50,13 +49,13 @@ <option value="unsorted">Unsorted</option> </param> <expand macro="VS" /> - - </inputs> - + + </inputs> + <outputs> <data format="bam" name="outFile" label="${tool.name} on ${on_string}: Reverted BAM dataset"/> </outputs> - + <tests> <test> <param name="inputFile" value="picard_RevertSam.bam" ftype="bam"/> @@ -73,8 +72,8 @@ <output name="outFile" file="picard_RevertSam_test1.bam" ftype="bam" lines_diff="4"/> </test> </tests> - - + + <help> **Purpose** @@ -85,46 +84,46 @@ @description@ - SORT_ORDER=SortOrder + SORT_ORDER=SortOrder SO=SortOrder The sort order to create the reverted output file with. Default value: queryname. - Possible values: {unsorted, queryname, coordinate} - + Possible values: {unsorted, queryname, coordinate} + RESTORE_ORIGINAL_QUALITIES=Boolean - OQ=Boolean True to restore original qualities from the OQ field to the QUAL field if available. - Default value: true. Possible values: {true, false} - + OQ=Boolean True to restore original qualities from the OQ field to the QUAL field if available. + Default value: true. Possible values: {true, false} + REMOVE_DUPLICATE_INFORMATION=Boolean - Remove duplicate read flags from all reads. Note that if this is true and - REMOVE_ALIGNMENT_INFORMATION==false, the output may have the unusual but sometimes - desirable trait of having unmapped reads that are marked as duplicates. Default value: - true. Possible values: {true, false} - + Remove duplicate read flags from all reads. Note that if this is true and + REMOVE_ALIGNMENT_INFORMATION==false, the output may have the unusual but sometimes + desirable trait of having unmapped reads that are marked as duplicates. Default value: + true. Possible values: {true, false} + REMOVE_ALIGNMENT_INFORMATION=Boolean - Remove all alignment information from the file. Default value: true. TPossible values: {true, false} - - ATTRIBUTE_TO_CLEAR=String When removing alignment information, the set of optional tags to remove. This option may - be specified 0 or more times. - - SANITIZE=Boolean WARNING: This option is potentially destructive. If enabled will discard reads in order - to produce a consistent output BAM. Reads discarded include (but are not limited to) - paired reads with missing mates, duplicated records, records with mismatches in length of - bases and qualities. This option can only be enabled if the output sort order is - queryname and will always cause sorting to occur. Possible values: {true, false} - - MAX_DISCARD_FRACTION=Double If SANITIZE=true and higher than MAX_DISCARD_FRACTION reads are discarded due to - sanitization thenthe program will exit with an Exception instead of exiting cleanly. - Output BAM will still be valid. Default value: 0.01. - + Remove all alignment information from the file. Default value: true. TPossible values: {true, false} + + ATTRIBUTE_TO_CLEAR=String When removing alignment information, the set of optional tags to remove. This option may + be specified 0 or more times. + + SANITIZE=Boolean WARNING: This option is potentially destructive. If enabled will discard reads in order + to produce a consistent output BAM. Reads discarded include (but are not limited to) + paired reads with missing mates, duplicated records, records with mismatches in length of + bases and qualities. This option can only be enabled if the output sort order is + queryname and will always cause sorting to occur. Possible values: {true, false} + + MAX_DISCARD_FRACTION=Double If SANITIZE=true and higher than MAX_DISCARD_FRACTION reads are discarded due to + sanitization thenthe program will exit with an Exception instead of exiting cleanly. + Output BAM will still be valid. Default value: 0.01. + SAMPLE_ALIAS=String - ALIAS=String The sample alias to use in the reverted output file. This will override the existing - sample alias in the file and is used only if all the read groups in the input file have - the same sample alias Default value: null. - + ALIAS=String The sample alias to use in the reverted output file. This will override the existing + sample alias in the file and is used only if all the read groups in the input file have + the same sample alias Default value: null. + LIBRARY_NAME=String - LIB=String The library name to use in the reverted output file. This will override the existing - sample alias in the file and is used only if all the read groups in the input file have - the same sample alias Default value: null. - + LIB=String The library name to use in the reverted output file. This will override the existing + sample alias in the file and is used only if all the read groups in the input file have + the same sample alias Default value: null. + @more_info@ </help>
--- a/picard_SamToFastq.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_SamToFastq.xml Tue Dec 06 10:04:41 2016 -0500 @@ -5,16 +5,17 @@ </macros> <expand macro="requirements" /> <command detect_errors="exit_code"><![CDATA[ - + echo "BAM" > $report && ## This is necessary for output dataset detection (see output tags below) - + @java_options@ - + @symlink_element_identifier@ + picard SamToFastq - - INPUT="${inputFile}" - + + INPUT='$inputFile.element_identifier' + #if str( $output_per_rg ) == "true": OUTPUT_PER_RG=true OUTPUT_DIR=. @@ -25,34 +26,34 @@ #elif str( $output_per_rg ) == "false" and str( $interleave ) == "true": FASTQ=INTERLEAVED.fastq #end if - + RE_REVERSE="${re_reverse}" INTERLEAVE="${interleave}" INCLUDE_NON_PF_READS="${include_non_pf_reads}" CLIPPING_ATTRIBUTE="${clipping_attribute}" CLIPPING_ACTION="${clipping_action}" READ1_TRIM="${read1_trim}" - + #if int($read1_max_bases_to_write) > -1: READ1_MAX_BASES_TO_WRITE="${read1_max_bases_to_write}" #end if - + READ2_TRIM="${read2_trim}" - + #if int($read2_max_bases_to_write) > -1: READ2_MAX_BASES_TO_WRITE="${read2_max_bases_to_write}" #end if - + INCLUDE_NON_PRIMARY_ALIGNMENTS="${include_non_primary_alignments}" - - + + VALIDATION_STRINGENCY="${validation_stringency}" QUIET=true VERBOSITY=ERROR - + ]]></command> <inputs> - + <param format="sam,bam" name="inputFile" type="data" label="Select SAM/BAM dataset or dataset collection" help="If empty, upload or import a SAM/BAM dataset"/> <param name="output_per_rg" type="boolean" checked="False" label="Do you want to output a fastq file per read group (two fastq files per read group if the group is paired)" help="OUTPUT_PER_RG; default=False"/> <param name="re_reverse" type="boolean" checked="True" label="Re-reverse bases and qualities of reads with negative strand flag set before writing them to fastq" help="RE_REVERSE; default=True"/> @@ -65,18 +66,18 @@ <param name="read2_trim" type="integer" value="0" min="0" label="The number of bases to trim from the beginning of read 2" help="READ2_TRIM; default=0"/> <param name="read2_max_bases_to_write" type="integer" value="-1" label="The maximum number of bases to write from read 2 after trimming" help="READ2_MAX_BASES_TO_WRITE; If there are fewer than this many bases left after trimming, all will be written. If this value is null then all bases left after trimming will be written; default=null (-1)"/> <param name="include_non_primary_alignments" type="boolean" label="If true, include non-primary alignments in the output" help="INCLUDE_NON_PRIMARY_ALIGNMENTS; Support of non-primary alignments in SamToFastq is not comprehensive, so there may be exceptions if this is set to true and there are paired reads with non-primary alignments; default=False"/> - + <expand macro="VS" /> - - </inputs> - + + </inputs> + <outputs> <!-- here dataset discovery is based on fact that if OUTPUT_PER_RG=true this tool automatically adds .fastq extension to emitted files --> <data format="txt" name="report" label="SamToFastq run" hidden="true"> <discover_datasets pattern="(?P<designation>.+)\.fastq" ext="fastqsanger" visible="true"/> </data> </outputs> - + <tests> <test> <param name="inputFile" value="picard_SamToFastq.bam" ftype="bam"/> @@ -90,7 +91,7 @@ <param name="read1_max_bases_to_write" value="-1"/> <param name="read2_trim" value="0" /> <param name="read2_max_bases_to_write" value="-1"/> - <param name="include_non_primary_alignments" value="false"/> + <param name="include_non_primary_alignments" value="false"/> <output name="report"> <assert_contents> <has_line line="BAM" /> @@ -99,8 +100,8 @@ </output> </test> </tests> - - + + <help> **Purpose** @@ -120,71 +121,71 @@ @description@ FASTQ=File - F=File Output fastq file (single-end fastq or, if paired, first end of the pair fastq). + F=File Output fastq file (single-end fastq or, if paired, first end of the pair fastq). Required. Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG) - + SECOND_END_FASTQ=File - F2=File Output fastq file (if paired, second end of the pair fastq). Default value: null. + F2=File Output fastq file (if paired, second end of the pair fastq). Default value: null. Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG) - + UNPAIRED_FASTQ=File - FU=File Output fastq file for unpaired reads; may only be provided in paired-fastq mode Default + FU=File Output fastq file for unpaired reads; may only be provided in paired-fastq mode Default value: null. Cannot be used in conjuction with option(s) OUTPUT_PER_RG (OPRG) - + OUTPUT_PER_RG=Boolean - OPRG=Boolean Output a fastq file per read group (two fastq files per read group if the group is + OPRG=Boolean Output a fastq file per read group (two fastq files per read group if the group is paired). Default value: false. Possible values: {true, false} Cannot be used in conjuction with option(s) SECOND_END_FASTQ (F2) UNPAIRED_FASTQ (FU) FASTQ (F) - + OUTPUT_DIR=File - ODIR=File Directory in which to output the fastq file(s). Used only when OUTPUT_PER_RG is true. - Default value: null. - + ODIR=File Directory in which to output the fastq file(s). Used only when OUTPUT_PER_RG is true. + Default value: null. + RE_REVERSE=Boolean - RC=Boolean Re-reverse bases and qualities of reads with negative strand flag set before writing them - to fastq Default value: true. Possible values: {true, false} - + RC=Boolean Re-reverse bases and qualities of reads with negative strand flag set before writing them + to fastq Default value: true. Possible values: {true, false} + INTERLEAVE=Boolean - INTER=Boolean Will generate an interleaved fastq if paired, each line will have /1 or /2 to describe - which end it came from Default value: false. Possible values: {true, false} - + INTER=Boolean Will generate an interleaved fastq if paired, each line will have /1 or /2 to describe + which end it came from Default value: false. Possible values: {true, false} + INCLUDE_NON_PF_READS=Boolean - NON_PF=Boolean Include non-PF reads from the SAM file into the output FASTQ files. PF means 'passes - filtering'. Reads whose 'not passing quality controls' flag is set are non-PF reads. - Default value: false. Possible values: {true, false} - + NON_PF=Boolean Include non-PF reads from the SAM file into the output FASTQ files. PF means 'passes + filtering'. Reads whose 'not passing quality controls' flag is set are non-PF reads. + Default value: false. Possible values: {true, false} + CLIPPING_ATTRIBUTE=String - CLIP_ATTR=String The attribute that stores the position at which the SAM record should be clipped Default - value: null. - + CLIP_ATTR=String The attribute that stores the position at which the SAM record should be clipped Default + value: null. + CLIPPING_ACTION=String - CLIP_ACT=String The action that should be taken with clipped reads: 'X' means the reads and qualities - should be trimmed at the clipped position; 'N' means the bases should be changed to Ns in - the clipped region; and any integer means that the base qualities should be set to that - value in the clipped region. Default value: null. - + CLIP_ACT=String The action that should be taken with clipped reads: 'X' means the reads and qualities + should be trimmed at the clipped position; 'N' means the bases should be changed to Ns in + the clipped region; and any integer means that the base qualities should be set to that + value in the clipped region. Default value: null. + READ1_TRIM=Integer - R1_TRIM=Integer The number of bases to trim from the beginning of read 1. Default value: 0. - + R1_TRIM=Integer The number of bases to trim from the beginning of read 1. Default value: 0. + READ1_MAX_BASES_TO_WRITE=Integer - R1_MAX_BASES=Integer The maximum number of bases to write from read 1 after trimming. If there are fewer than - this many bases left after trimming, all will be written. If this value is null then all - bases left after trimming will be written. Default value: null. - + R1_MAX_BASES=Integer The maximum number of bases to write from read 1 after trimming. If there are fewer than + this many bases left after trimming, all will be written. If this value is null then all + bases left after trimming will be written. Default value: null. + READ2_TRIM=Integer - R2_TRIM=Integer The number of bases to trim from the beginning of read 2. Default value: 0. - + R2_TRIM=Integer The number of bases to trim from the beginning of read 2. Default value: 0. + READ2_MAX_BASES_TO_WRITE=Integer - R2_MAX_BASES=Integer The maximum number of bases to write from read 2 after trimming. If there are fewer than - this many bases left after trimming, all will be written. If this value is null then all - bases left after trimming will be written. Default value: null. - + R2_MAX_BASES=Integer The maximum number of bases to write from read 2 after trimming. If there are fewer than + this many bases left after trimming, all will be written. If this value is null then all + bases left after trimming will be written. Default value: null. + INCLUDE_NON_PRIMARY_ALIGNMENTS=Boolean - If true, include non-primary alignments in the output. Support of non-primary alignments - in SamToFastq is not comprehensive, so there may be exceptions if this is set to true and + If true, include non-primary alignments in the output. Support of non-primary alignments + in SamToFastq is not comprehensive, so there may be exceptions if this is set to true and there are paired reads with non-primary alignments. Default value: false. - Possible values: {true, false} - + Possible values: {true, false} + @more_info@ </help>
--- a/picard_SortSam.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_SortSam.xml Tue Dec 06 10:04:41 2016 -0500 @@ -12,9 +12,10 @@ #set $output = $outFile #end if @java_options@ + @symlink_element_identifier@ picard SortSam - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT='${output}' SORT_ORDER="${sort_order}" QUIET=true
--- a/picard_ValidateSamFile.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_ValidateSamFile.xml Tue Dec 06 10:04:41 2016 -0500 @@ -16,7 +16,7 @@ && ##set up input files - + @symlink_element_identifier@ #set $reference_fasta_filename = "localref.fa" #if str( $reference_source.reference_source_selector ) == "history": @@ -30,7 +30,7 @@ picard ValidateSamFile - INPUT="${inputFile}" + INPUT='$inputFile.element_identifier' OUTPUT="${outFile}" MODE="${mode}"
--- a/picard_macros.xml Sun Nov 27 15:11:50 2016 -0500 +++ b/picard_macros.xml Tue Dec 06 10:04:41 2016 -0500 @@ -16,6 +16,10 @@ </requirements> </xml> + <token name="@symlink_element_identifier@"><![CDATA[ + ln -f -s '$inputFile' '$inputFile.element_identifier' && + ]]></token> + <token name="@java_options@"><![CDATA[ _JAVA_OPTIONS=\${_JAVA_OPTIONS:-'-Xmx2048m -Xms256m'} && export _JAVA_OPTIONS &&