comparison bismark_bowtie2_wrapper.xml @ 4:243e8f9fb75b draft

Uploaded

3:91f07ff056ca

    <requirements>
        <requirement type="set_environment">SCRIPT_PATH</requirement>
        <requirement type="package" version="0.1.19">samtools</requirement>
        <requirement type="package" version="2.1.0">bowtie2</requirement>
    </requirements>
    <parallelism method="basic"></parallelism>
    <command interpreter="python">
        bismark_wrapper.py
        
        ## Change this to accommodate the number of threads you have available.
        --num-threads "\${GALAXY_SLOTS:-24}"

        --bismark_path \$SCRIPT_PATH

        --bowtie2

        ##
        ## Bismark Genome Preparation, if desired.

        ##
        ##  Input parameters
        ##


        #if $singlePaired.sPaired == "single":
            --single-paired $singlePaired.input_singles

            #if $singlePaired.input_singles.ext == "fastqillumina":

            #end for

            --mate1 #echo ','.join($mate1)
            --mate2 #echo ','.join($mate2)

            #if $singlePaired.mate_list[0].input_mate1.ext == "fastqillumina":
                --phred64-quals
                --fastq
            #elif $singlePaired.mate_list[0].input_mate1.ext == "fastqsanger":
                --fastq
            #elif $singlePaired.mate_list[0].input_mate1.ext == "fasta":
                --fasta
            #end if

            -I $singlePaired.minInsert
            -X $singlePaired.maxInsert
        #end if

            --seed-mismatches $params.seed_mismatches
            ## default 15
            --seed-extention-attempts $params.seed_extention_attempts
            ## default 2
            --max-reseed $params.max_reseed
            
            ## default 70
            ##--maqerr $params.maqerr

            ## default unlimited
            #if $params.qupto != 0:

          --output-suppressed-reads-l $output_suppressed_reads_l
          --output-suppressed-reads-r $output_suppressed_reads_r
        #end if
      #end if

    </command>
    <inputs>
        <conditional name="refGenomeSource">
          <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
            <option value="indexed">Use a built-in index</option>

                <param name="unmapped_read_file" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Write all reads that could not be aligned to a file" />
                <!-- output Options -->
                <param name="bismark_stdout" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Write the bismark output and summary information to an extra file" />
                <param name="isReportOutput" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Offer all report files concatenated in one file" />

                <!--end output options --> 
            </when>  <!-- full -->
      </conditional>  <!-- params -->
      <!--
      <param name="suppress_header" type="boolean" truevalue="..suppress-header" falsevalue="" checked="false" label="Suppress the header in the output SAM file" help="Bowtie produces SAM with several lines of header information by default." />
        -->

            <action type="format">
              <option type="from_param" name="singlePaired.input_singles" param_attribute="ext" />
            </action>
          </when>
          <when value="paired">
            <action type="format">
              <option type="from_param" name="singlePaired.mate_list[0].input_mate1" param_attribute="ext" />
            </action>
          </when>
        </conditional>
      </actions>
    </data>

    <data format="fastq" name="output_suppressed_reads_r" label="${tool.name} on ${on_string}: suppressed reads (R)">
      <filter>singlePaired['sPaired'] == "paired"</filter>
      <filter>params['settingsType'] == "custom"</filter>
      <filter>params['supressed_read_file'] is True</filter>
      <actions>
        <conditional name="singlePaired.sPaired">
          <when value="single">
            <action type="format">
              <option type="from_param" name="singlePaired.input_singles" param_attribute="ext" />
            </action>
          </when>
          <when value="paired">
            <action type="format">
              <option type="from_param" name="singlePaired.mate_list[0].input_mate1" param_attribute="ext" />
            </action>
          </when>
        </conditional>
      </actions>
    </data>

            <action type="format">
              <option type="from_param" name="singlePaired.input_singles" param_attribute="ext" />
            </action>
          </when>
          <when value="paired">
            <action type="format">
              <option type="from_param" name="singlePaired.mate_list[0].input_mate1" param_attribute="ext" />
            </action>
          </when>
        </conditional>
      </actions>
    </data>

    <data format="fastq" name="output_unmapped_reads_r" label="${tool.name} on ${on_string}: unmapped reads (R)">
      <filter>singlePaired['sPaired'] == "paired"</filter>
      <filter>params['settingsType'] == "custom"</filter>
      <filter>params['unmapped_read_file'] is True</filter>
      <actions>
        <conditional name="singlePaired.sPaired">
          <when value="single">
            <action type="format">
              <option type="from_param" name="singlePaired.input_singles" param_attribute="ext" />
            </action>
          </when>
          <when value="paired">
            <action type="format">
              <option type="from_param" name="singlePaired.mate_list[0].input_mate1" param_attribute="ext" />
            </action>
          </when>
        </conditional>
      </actions>
    </data>
    </outputs>

    <tests>
    </tests>

    <help>

**What it does**

Bismark_ is a bisulfite mapper and methylation caller. Bismark takes in FastA or FastQ files and aligns the
reads to a specified bisulfite genome. Sequence reads are transformed into a bisulfite converted forward strand

The output is in SAM format, and has the following columns::

    Column  Description
  --------  --------------------------------------------------------
  1  QNAME  seq-ID
  2  FLAG   this flag tries to take the strand a bisulfite read 
            originated from into account 
            (this is different from ordinary DNA alignment flags!)
  3  RNAME  chromosome
  4  POS    start position
  5  MAPQ   always 255
  6  CIGAR  extended CIGAR string

  8  MPOS   1-based Mate POSition
  9  ISIZE  Inferred insert SIZE
  10 SEQ    query SEQuence on the same strand as the reference
  11 QUAL   Phred33 scale
  12 NM-tag edit distance to the reference)
  13 XX-tag base-by-base mismatches to the reference. 
            This does not include indels.
  14 XM-tag methylation call string
  15 XR-tag read conversion state for the alignment
  16 XG-tag genome conversion state for the alignment
  

Each read of paired-end alignments is written out in a separate line in the above format.


It looks like this (scroll sideways to see the entire example)::

  --phred33-quals        FASTQ qualities are ASCII chars equal to the Phred quality plus 33. Default: on.

  --phred64-quals        FASTQ qualities are ASCII chars equal to the Phred quality plus 64. Default: off.

  --solexa-quals         Convert FASTQ qualities from solexa-scaled (which can be negative) to phred-scaled
                         (which can't). The formula for conversion is: 
                         phred-qual = 10 * log(1 + 10 ** (solexa-qual/10.0)) / log(10). Used with -q. This
                         is usually the right option for use with (unconverted) reads emitted by the GA
                         Pipeline versions prior to 1.3. Works only for Bowtie 1. Default: off.

  --solexa1.3-quals      Same as --phred64-quals. This is usually the right option for use with (unconverted)

Alignment::

  -n/--seedmms INT       The maximum number of mismatches permitted in the "seed", i.e. the first L base pairs
                         of the read (where L is set with -l/--seedlen). This may be 0, 1, 2 or 3 and the 
                         default is 1. This option is only available for Bowtie 1 (for Bowtie 2 see -N).

  -l/--seedlen           The "seed length"; i.e., the number of bases of the high quality end of the read to
                         which the -n ceiling applies. The default is 28. Bowtie (and thus Bismark) is faster for
                         larger values of -l. This option is only available for Bowtie 1 (for Bowtie 2 see -L).

                         For reference, this used to be the old (now deprecated) description of -M:
                         Bowtie 2 searches for at most INT+1 distinct, valid alignments for each read. The search terminates when it
                         can't find more distinct valid alignments, or when it finds INT+1 distinct alignments, whichever
                         happens first. Only the best alignment is reported. Information from the other alignments is used to
                         estimate mapping quality and to set SAM optional fields, such as AS:i and XS:i. Increasing -M makes 
                         Bowtie 2 slower, but increases the likelihood that it will pick the correct alignment for a read that
                         aligns many places. For reads that have more than INT+1 distinct, valid alignments, Bowtie 2 does not
                         guarantee that the alignment reported is the best possible in terms of alignment score. -M is
                         always used and its default value is set to 10.

  </help>
</tool>

4:243e8f9fb75b

    <requirements>
        <requirement type="set_environment">SCRIPT_PATH</requirement>
        <requirement type="package" version="0.1.19">samtools</requirement>
        <requirement type="package" version="2.1.0">bowtie2</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
        <exit_code range=":-1" />
        <regex match="Error:" />
        <regex match="Exception:" />
    </stdio>
    <command interpreter="python">
<![CDATA[
        bismark_wrapper.py

        ## Change this to accommodate the number of threads you have available.
        --num-threads "\${GALAXY_SLOTS:-24}"

        ##--bismark_path \$SCRIPT_PATH

        --bowtie2

        ##
        ## Bismark Genome Preparation, if desired.

        ##
        ##  Input parameters
        ##

        #if $singlePaired.sPaired == "single":
            --single-paired $singlePaired.input_singles

            #if $singlePaired.input_singles.ext == "fastqillumina":

            #end for

            --mate1 #echo ','.join($mate1)
            --mate2 #echo ','.join($mate2)

            #for $mate_pair in $singlePaired.mate_list:
                #if $mate_pair.input_mate1.ext == "fastqillumina":
                    --phred64-quals
                    --fastq
                #elif $mate_pair.input_mate1.ext == "fastqsanger":
                    --fastq
                #elif $mate_pair.input_mate1.ext == "fasta":
                    --fasta
                #end if
                #break
            #end for

            -I $singlePaired.minInsert
            -X $singlePaired.maxInsert
        #end if

            --seed-mismatches $params.seed_mismatches
            ## default 15
            --seed-extention-attempts $params.seed_extention_attempts
            ## default 2
            --max-reseed $params.max_reseed

            ## default 70
            ##--maqerr $params.maqerr

            ## default unlimited
            #if $params.qupto != 0:

          --output-suppressed-reads-l $output_suppressed_reads_l
          --output-suppressed-reads-r $output_suppressed_reads_r
        #end if
      #end if

]]>
    </command>
    <inputs>
        <conditional name="refGenomeSource">
          <param name="genomeSource" type="select" label="Will you select a reference genome from your history or use a built-in index?" help="Built-ins were indexed using default options">
            <option value="indexed">Use a built-in index</option>

                <param name="unmapped_read_file" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Write all reads that could not be aligned to a file" />
                <!-- output Options -->
                <param name="bismark_stdout" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Write the bismark output and summary information to an extra file" />
                <param name="isReportOutput" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Offer all report files concatenated in one file" />

                <!--end output options -->
            </when>  <!-- full -->
      </conditional>  <!-- params -->
      <!--
      <param name="suppress_header" type="boolean" truevalue="..suppress-header" falsevalue="" checked="false" label="Suppress the header in the output SAM file" help="Bowtie produces SAM with several lines of header information by default." />
        -->

            <action type="format">
              <option type="from_param" name="singlePaired.input_singles" param_attribute="ext" />
            </action>
          </when>
          <when value="paired">
            <!--action type="format">
              <option type="from_param" name="singlePaired.mate_list[0].input_mate1" param_attribute="ext" />
            </action-->
          </when>
        </conditional>
      </actions>
    </data>

    <data format="fastq" name="output_suppressed_reads_r" label="${tool.name} on ${on_string}: suppressed reads (R)">
      <filter>
        ((
            singlePaired['sPaired'] == "paired" and
          params['settingsType'] == "custom" and
          params['suppressed_read_file'] is True
        ))
      </filter>
      <actions>
        <conditional name="singlePaired.sPaired">
          <when value="single">
            <action type="format">
              <option type="from_param" name="singlePaired.input_singles" param_attribute="ext" />
            </action>
          </when>
          <when value="paired">
            <!--action type="format">
              <option type="from_param" name="singlePaired.mate_list[0].input_mate1" param_attribute="ext" />
            </action-->
          </when>
        </conditional>
      </actions>
    </data>

            <action type="format">
              <option type="from_param" name="singlePaired.input_singles" param_attribute="ext" />
            </action>
          </when>
          <when value="paired">
            <!--action type="format">
              <option type="from_param" name="singlePaired.mate_list[0].input_mate1" param_attribute="ext" />
            </action-->
          </when>
        </conditional>
      </actions>
    </data>

    <data format="fastq" name="output_unmapped_reads_r" label="${tool.name} on ${on_string}: unmapped reads (R)">
      <filter>
        ((
            singlePaired['sPaired'] == "paired" and
          params['settingsType'] == "custom" and
          params['unmapped_read_file'] is True
        ))
      </filter>
      <actions>
        <conditional name="singlePaired.sPaired">
          <when value="single">
            <action type="format">
              <option type="from_param" name="singlePaired.input_singles" param_attribute="ext" />
            </action>
          </when>
          <when value="paired">
            <!--action type="format">
              <option type="from_param" name="singlePaired.mate_list[0].input_mate1" param_attribute="ext" />
            </action-->
          </when>
        </conditional>
      </actions>
    </data>
    </outputs>

    <tests>
    </tests>

    <help>
<![CDATA[

**What it does**

Bismark_ is a bisulfite mapper and methylation caller. Bismark takes in FastA or FastQ files and aligns the
reads to a specified bisulfite genome. Sequence reads are transformed into a bisulfite converted forward strand

The output is in SAM format, and has the following columns::

    Column  Description
  --------  --------------------------------------------------------
  1  QNAME  seq-ID
  2  FLAG   this flag tries to take the strand a bisulfite read
            originated from into account
            (this is different from ordinary DNA alignment flags!)
  3  RNAME  chromosome
  4  POS    start position
  5  MAPQ   always 255
  6  CIGAR  extended CIGAR string

  8  MPOS   1-based Mate POSition
  9  ISIZE  Inferred insert SIZE
  10 SEQ    query SEQuence on the same strand as the reference
  11 QUAL   Phred33 scale
  12 NM-tag edit distance to the reference)
  13 XX-tag base-by-base mismatches to the reference.
            This does not include indels.
  14 XM-tag methylation call string
  15 XR-tag read conversion state for the alignment
  16 XG-tag genome conversion state for the alignment


Each read of paired-end alignments is written out in a separate line in the above format.


It looks like this (scroll sideways to see the entire example)::

  --phred33-quals        FASTQ qualities are ASCII chars equal to the Phred quality plus 33. Default: on.

  --phred64-quals        FASTQ qualities are ASCII chars equal to the Phred quality plus 64. Default: off.

  --solexa-quals         Convert FASTQ qualities from solexa-scaled (which can be negative) to phred-scaled
                         (which can't). The formula for conversion is:
                         phred-qual = 10 * log(1 + 10 ** (solexa-qual/10.0)) / log(10). Used with -q. This
                         is usually the right option for use with (unconverted) reads emitted by the GA
                         Pipeline versions prior to 1.3. Works only for Bowtie 1. Default: off.

  --solexa1.3-quals      Same as --phred64-quals. This is usually the right option for use with (unconverted)

Alignment::

  -n/--seedmms INT       The maximum number of mismatches permitted in the "seed", i.e. the first L base pairs
                         of the read (where L is set with -l/--seedlen). This may be 0, 1, 2 or 3 and the
                         default is 1. This option is only available for Bowtie 1 (for Bowtie 2 see -N).

  -l/--seedlen           The "seed length"; i.e., the number of bases of the high quality end of the read to
                         which the -n ceiling applies. The default is 28. Bowtie (and thus Bismark) is faster for
                         larger values of -l. This option is only available for Bowtie 1 (for Bowtie 2 see -L).

                         For reference, this used to be the old (now deprecated) description of -M:
                         Bowtie 2 searches for at most INT+1 distinct, valid alignments for each read. The search terminates when it
                         can't find more distinct valid alignments, or when it finds INT+1 distinct alignments, whichever
                         happens first. Only the best alignment is reported. Information from the other alignments is used to
                         estimate mapping quality and to set SAM optional fields, such as AS:i and XS:i. Increasing -M makes
                         Bowtie 2 slower, but increases the likelihood that it will pick the correct alignment for a read that
                         aligns many places. For reads that have more than INT+1 distinct, valid alignments, Bowtie 2 does not
                         guarantee that the alignment reported is the best possible in terms of alignment score. -M is
                         always used and its default value is set to 10.

]]>
  </help>
  <citations>
      <citation type="doi">10.1093/bioinformatics/btr167</citation>
  </citations>
</tool>