comparison picard_SamToFastq.xml @ 0:b76a4f17bbbb draft

Uploaded

0:b76a4f17bbbb

<tool name="SamToFastq" id="picard_SamToFastq" version="1.122.0">
  <description>extract reads and qualities from SAM/BAM dataset and convert to fastq</description>
  <requirements>
    <requirement type="package" version="1.122.0">picard</requirement>
  </requirements>
  
  <macros>
    <import>picard_macros.xml</import>
  </macros>
  
  <command>
     
    echo "BAM" > $report &amp;&amp;    ## This is necessary for output dataset detection (see output tags below)
    
    @java_options@
    
    java -jar \$JAVA_JAR_PATH/SamToFastq.jar
    
    INPUT="${inputFile}"
    
    #if str( $output_per_rg ) == "true":
      OUTPUT_PER_RG=true
      OUTPUT_DIR=.
    #elif str( $output_per_rg ) == "false" and str( $interleave ) == "false":
      FASTQ=READ1.fastq
      SECOND_END_FASTQ=READ2.fastq
      UNPAIRED_FASTQ=UNPAIRED_READS.fastq
    #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"/>
    <param name="interleave" type="boolean" label="Will generate an interleaved fastq if paired, each line will have /1 or /2 to describe which end it came from" help="INTERLEAVE; default=False"/>
    <param name="include_non_pf_reads" type="boolean" label="Include non-PF reads from the SAM/BAM dataset into the output FASTQ" help="INCLUDE_NON_PF_READS; PF means 'passes filtering'. Reads whose 'not passing quality controls' flag is set are non-PF reads; default=False"/>
    <param name="clipping_attribute" type="text" size="4" value="null" label="The attribute that stores the position at which the SAM/BAM record should be clipped" help="CLIPPING_ATTRIBUTE; default=null"/>
    <param name="clipping_action" type="text" size="10" value="null" label="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" help="CLIPPING_ACTION; default=null"/>
    <param name="read1_trim" type="integer" value="0" min="0" label="The number of bases to trim from the beginning of read 1" help="READ1_TRIM; default=0"/>
    <param name="read1_max_bases_to_write" type="integer" value="-1" label="The maximum number of bases to write from read 1 after trimming" help="READ1_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="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> 
  
  <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&lt;designation&gt;.+)\.fastq" ext="fastqsanger" visible="true"/>
    </data>
  </outputs>
  
  <tests>
    <test>
      <param name="inputFile" value="picard_SamToFastq.bam" ftype="bam"/>
      <param name="output_per_rg" value="false"/>
      <param name="re_reverse" value="true"/>
      <param name="interleave" value="true"/>
      <param name="include_non_pf_reads" value="false"/>
      <param name="clipping_attribute" value="null" />
      <param name="clipping_action" value="null" />
      <param name="read1_trim" value="0" />
      <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"/>   
      <output name="report">
        <assert_contents>
          <has_line line="BAM" />
        </assert_contents>
        <discovered_dataset designation="INTERLEAVED" file="picard_SamToFastq_test1.fq" ftype="fastqsanger"/>
      </output>
    </test>
  </tests>
  
  <stdio>
    <exit_code range="1:"  level="fatal"/>
  </stdio>
  
  <help>

**Purpose**

Extracts read sequences and qualities from the input SAM/BAM dataset and outputs them in Sanger fastq format. In the RE_REVERSE=True mode (default behavior), if the read is aligned and the alignment is to the reverse strand on the genome, the read's sequence from input SAM.BAM dataset will be reverse-complemented prior to writing it to fastq in order restore correctly the original read sequence as it was generated by the sequencer.

-----

.. class:: warningmark

**DANGER: Multiple Outputs**

Generating per readgroup fastq (setting **OUTPUT_PER_RG** to True) may produce very large numbers of outputs. Know what you are doing!

@dataset_collections@

@description@

  FASTQ=File
  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.  
                                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 
                                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 
                                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. 
  
  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} 
  
  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} 
  
  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} 
  
  CLIPPING_ATTRIBUTE=String
  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. 
  
  READ1_TRIM=Integer
  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. 
  
  READ2_TRIM=Integer
  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. 
  
  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 
                                there are paired reads with non-primary alignments.  Default value: false.
                                Possible values: {true, false} 
  
@more_info@

  </help>
</tool>