comparison bismark_bowtie_wrapper.xml @ 18:862fb59a9a25 draft

Uploaded

17:73508c5b4273

<tool id="bismark_bowtie" name="Bismark" version="0.7.7.3">
    <!-- Wrapper compatible with Bismark version 0.7.7 -->
    <description>bisulfite mapper (bowtie)</description>
    <!--<version_command>bismark version</version_command>-->
    <requirements>
        <requirement type="set_environment">SCRIPT_PATH</requirement>
        <requirement type="package" version="0.12.8">bowtie</requirement>
        <requirement type="package" version="2.0.0-beta7">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 4

        --bismark_path \$SCRIPT_PATH

        ##
        ## Bismark Genome Preparation, if desired.

                --fastq
            #elif $singlePaired.input_singles.ext == "fasta":
                --fasta
            #end if
        #else:
            --mate-paired 
            --mate1 $singlePaired.input_mate1
            --mate2 $singlePaired.input_mate2

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

            -I $singlePaired.minInsert
            -X $singlePaired.maxInsert

            #end if
            #if $params.skip_reads != 0:
                --skip-reads $params.skip_reads
            #end if

            ###if str($params.isReportOutput) == "yes":
            ##    --output-report-file $report_file
            ###end if

        #end if

        ##
        ## Output parameters.
        ##
        --output $output
        $suppress_header

      #if str( $singlePaired.sPaired ) == "single"
        #if $output_unmapped_reads_l
          --output-unmapped-reads $output_unmapped_reads_l
        #end if

          <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>
            <option value="history">Use one from the history</option>
          </param>
          <when value="indexed">
            <param name="index" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact your Galaxy admin">
              <options from_data_table="bowtie_indexes">
                <filter type="sort_by" column="2"/>
                <validator type="no_options" message="No indexes are available for the selected input dataset"/>
              </options>
            </param>

            </param>
            <when value="single">
                <param name="input_singles" type="data" format="fastqsanger,fastqillumina,fastq,fasta" label="FASTQ/FASTA file" help="FASTQ or FASTA files." />
            </when>
            <when value="paired">
                <param name="input_mate1" type="data" format="fastqsanger,fastqillumina,fastq,fasta" label="FASTQ/FASTA file" help="FASTQ or FASTA files." />
                <param name="input_mate2" type="data" format="fastqsanger,fastqillumina,fastq,fasta" label="FASTQ/FASTA file" help="FASTQ or FASTA files." />
                <param name="minInsert" type="integer" value="0" label="Minimum insert size for valid paired-end alignments" />
                <param name="maxInsert" type="integer" value="250" label="Maximum insert size for valid paired-end alignments" />
            </when>
        </conditional>


        <conditional name="params">

            </param>
            <when value="default" />
            <!-- Full/advanced params. -->
            <when value="custom">
                <!-- -n -->
                <param name="seed_mismatches" type="select" label="The maximum number of mismatches permitted in the 'seed'.">
                    <option value="0">0</option>
                    <option value="1">1</option>
                    <option value="2" selected="true">2</option>
                    <option value="3">3</option>
                </param>
                <!-- -l -->
                <param name="seed_len" type="integer" value="28" label="The 'seed length'; The number of bases of the high quality end of the read to which the maximum number of mismatches applies." />
                <!--
                <param name="maqerr" type="integer" value="70" label="Maximum permitted total of quality values at all mismatched read positions throughout the entire alignment, not just in the 'seed'." />
                -->
                <param name="qupto" type="integer" value="0" label="Only aligns the first N reads or read pairs from the input" help="Default is 0 and means 'no-limit'." />
                <param name="skip_reads" type="integer" value="0" label="Skip (i.e. do not align) the first N reads or read pairs from the input" />

                <param name="suppressed_read_file" type="boolean" truevalue="true" falsevalue="false" checked="False" label="Write ambiguous reads to an extra output file." help="Write all reads which produce more than one valid alignment with the same number of lowest mismatches or other reads that fail to align uniquely." />
                <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="isReportOutput" type="select" label="Offer all report files concatenated in one file.">
                    <option value="yes">yes</option>
                    <option value="no">no</option>
                </param>
                -->
                <!--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" />
    </inputs>
    <outputs>
        <!-- that does not work
        <data format="txt" name="report_file" label="${tool.name} on ${on_string}: Report">
            <filter>str($params.isReportOutput) == "yes"</filter>
        </data>
        -->
        <data format="sam" name="output" label="${tool.name} on ${on_string}: mapped reads">
          <actions>
            <conditional name="refGenomeSource.genomeSource">
              <when value="indexed">
                <action type="metadata" name="dbkey">
                  <option type="from_data_table" name="bowtie2_indexes" column="1" offset="0">

              <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.input_mate1" param_attribute="ext" />
            </action>
          </when>
        </conditional>
      </actions>
    </data>

              <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.input_mate1" param_attribute="ext" />
            </action>
          </when>
        </conditional>
      </actions>
    </data>

              <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.input_mate1" param_attribute="ext" />
            </action>
          </when>
        </conditional>
      </actions>
    </data>

              <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.input_mate1" param_attribute="ext" />
            </action>
          </when>
        </conditional>
      </actions>
    </data>

.. class:: warningmark

There is no such thing (yet) as an automated gearshift in short read mapping. It is all like stick-shift driving in San Francisco. In other words = running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy.

 .. __: http://www.bioinformatics.babraham.ac.uk/projects/bismark/

------

**Input formats**

------

**Bismark parameter list**

This is an exhaustive list of Bismark options:

------

**OPTIONS**


Input::

  --singles              A comma- or space-separated list of files containing the reads to be aligned (e.g.
                         lane1.fq,lane2.fq lane3.fq). Reads may be a mix of different lengths. Bismark will

  --temp_dir DIR          Write temporary files to this directory instead of into the same directory as the input files. If
                         the specified folder does not exist, Bismark will attempt to create it first. The path to the
                         temporary folder can be either relative or absolute.

------

Bowtie 2 alignment options::

  -N INT                 Sets the number of mismatches to allowed in a seed alignment during multiseed alignment.
                         Can be set to 0 or 1. Setting this higher makes alignment slower (often much slower)
                         but increases sensitivity. Default: 0. This option is only available for Bowtie 2 (for
                         Bowtie 1 see -n).

  -L INT                   Sets the length of the seed substrings to align during multiseed alignment. Smaller values
                         make alignment slower but more senstive. Default: the --sensitive preset of Bowtie 2 is
                         used by default, which sets -L to 20. This option is only available for Bowtie 2 (for
                         Bowtie 1 see -l).

  --ignore-quals         When calculating a mismatch penalty, always consider the quality value at the mismatched
                         position to be the highest possible, regardless of the actual value. I.e. input is treated
                         as though all quality values are high. This is also the default behavior when the input
                         doesn't specify quality values (e.g. in -f mode). This option is invariable and on by default.


Bowtie 2 paired-end options::

  --no-mixed             This option disables Bowtie 2's behavior to try to find alignments for the individual mates if
                         it cannot find a concordant or discordant alignment for a pair. This option is invariable and
                         and on by default.

  --no-discordant        Normally, Bowtie 2 looks for discordant alignments if it cannot find any concordant alignments.
                         A discordant alignment is an alignment where both mates align uniquely, but that does not
                         satisfy the paired-end constraints (--fr/--rf/--ff, -I, -X). This option disables that behavior
                         and it is on by default.


Bowtie 2 effort options::

  -D INT                 Up to INT consecutive seed extension attempts can "fail" before Bowtie 2 moves on, using
                         the alignments found so far. A seed extension "fails" if it does not yield a new best or a
                         new second-best alignment. Default: 15.

  -R INT                 INT is the maximum number of times Bowtie 2 will "re-seed" reads with repetitive seeds.
                         When "re-seeding," Bowtie 2 simply chooses a new set of reads (same length, same number of
                         mismatches allowed) at different offsets and searches for more alignments. A read is considered
                         to have repetitive seeds if the total number of seed hits divided by the number of seeds
                         that aligned at least once is greater than 300. Default: 2.


Bowtie 2 Scoring options::

  --score_min "func"     Sets a function governing the minimum alignment score needed for an alignment to be considered
                         "valid" (i.e. good enough to report). This is a function of read length. For instance, specifying
                         L,0,-0.2 sets the minimum-score function f to f(x) = 0 + -0.2 * x, where x is the read length.
                         See also: setting function options at http://bowtie-bio.sourceforge.net/bowtie2. The default is
                         L,0,-0.2.


Bowtie 2 Reporting options::

 --most_valid_alignments INT This used to be the Bowtie 2 parameter -M. As of Bowtie 2 version 2.0.0 beta7 the option -M is
                         deprecated. It will be removed in subsequent versions. What used to be called -M mode is still the
                         default mode, but adjusting the -M setting is deprecated.  Use the -D and -R options to adjust the
                         effort expended to find valid alignments.

                         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>

18:862fb59a9a25

<tool id="bismark_bowtie" name="Bismark" version="0.10.0">
    <!-- Wrapper compatible with Bismark version 0.10 -->
    <description>bisulfite mapper (bowtie)</description>
    <!--<version_command>bismark version</version_command>-->
    <requirements>
        <requirement type="set_environment">SCRIPT_PATH</requirement>
        <requirement type="package" version="0.1.19">samtools</requirement>
        <requirement type="package" version="0.12.8">bowtie</requirement>
    </requirements>
    <parallelism method="basic"></parallelism>
    <command interpreter="python">
        bismark_wrapper.py

        --bismark_path \$SCRIPT_PATH

        ##
        ## Bismark Genome Preparation, if desired.

                --fastq
            #elif $singlePaired.input_singles.ext == "fasta":
                --fasta
            #end if
        #else:
            --mate-paired
            #set $mate1 = list()
            #set $mate2 = list()
            #for $mate_pair in $singlePaired.mate_list
                $mate1.append( str($mate_pair.input_mate1) )
                $mate2.append( str($mate_pair.input_mate2) )
            #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
            #if $params.skip_reads != 0:
                --skip-reads $params.skip_reads
            #end if

            #if $params.bismark_stdout:
                --stdout $output_stdout
            #end if

            #if $params.isReportOutput:
                --output-report-file $report_file
            #end if

        #end if

        ##
        ## Output parameters.
        ##
        --output $output
        ##$suppress_header

      #if str( $singlePaired.sPaired ) == "single"
        #if $output_unmapped_reads_l
          --output-unmapped-reads $output_unmapped_reads_l
        #end if

          <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>
            <option value="history">Use one from the history</option>
          </param>
          <when value="indexed">
            <param name="index" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact your Galaxy admin.">
              <options from_data_table="bowtie_indexes">
                <filter type="sort_by" column="2"/>
                <validator type="no_options" message="No indexes are available for the selected input dataset"/>
              </options>
            </param>

            </param>
            <when value="single">
                <param name="input_singles" type="data" format="fastqsanger,fastqillumina,fastq,fasta" label="FASTQ/FASTA file" help="FASTQ or FASTA files." />
            </when>
            <when value="paired">
                <repeat name="mate_list" title="Paired End Pairs" min="1">
                    <param name="input_mate1" type="data" format="fastqsanger,fastqillumina,fastq,fasta" label="Mate pair 1" help="FASTQ or FASTA files." />
                    <param name="input_mate2" type="data" format="fastqsanger,fastqillumina,fastq,fasta" label="Mate pair 2" help="FASTQ or FASTA files." />
                </repeat>
                <param name="minInsert" type="integer" value="0" label="Minimum insert size for valid paired-end alignments" />
                <param name="maxInsert" type="integer" value="500" label="Maximum insert size for valid paired-end alignments" />
            </when>
        </conditional>


        <conditional name="params">

            </param>
            <when value="default" />
            <!-- Full/advanced params. -->
            <when value="custom">
                <!-- -n -->
                <param name="seed_mismatches" type="select" label="The maximum number of mismatches permitted in the 'seed'">
                    <option value="0">0</option>
                    <option value="1">1</option>
                    <option value="2" selected="true">2</option>
                    <option value="3">3</option>
                </param>
                <!-- -l -->
                <param name="seed_len" type="integer" value="28" label="The 'seed length'; The number of bases of the high quality end of the read to which the maximum number of mismatches applies" />
                <!--
                <param name="maqerr" type="integer" value="70" label="Maximum permitted total of quality values at all mismatched read positions throughout the entire alignment, not just in the 'seed'." />
                -->
                <param name="qupto" type="integer" value="0" label="Only aligns the first N reads or read pairs from the input" help="Default is 0 and means 'no-limit'." />
                <param name="skip_reads" type="integer" value="0" label="Skip (i.e. do not align) the first N reads or read pairs from the input" />

                <param name="suppressed_read_file" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Write ambiguous reads to an extra output file" help="Write all reads which produce more than one valid alignment with the same number of lowest mismatches or other reads that fail to align uniquely." />
                <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." />
     -->
    </inputs>
    <outputs>
        <data format="txt" name="report_file" label="${tool.name} on ${on_string}: Report">
            <filter>
            ((
                params['settingsType'] == "custom" and
                params['isReportOutput'] is True
            ))
            </filter>
        </data>
        <data format="txt" name="output_stdout" label="${tool.name} on ${on_string}: Summary">
            <filter>
            ((
                params['settingsType'] == "custom" and
                params['bismark_stdout'] is True
            ))
            </filter>
        </data>

        <data format="bam" name="output" label="${tool.name} on ${on_string}: mapped reads">
          <actions>
            <conditional name="refGenomeSource.genomeSource">
              <when value="indexed">
                <action type="metadata" name="dbkey">
                  <option type="from_data_table" name="bowtie2_indexes" column="1" offset="0">

              <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>

              <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>

              <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>

              <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>

.. class:: warningmark

There is no such thing (yet) as an automated gearshift in short read mapping. It is all like stick-shift driving in San Francisco. In other words = running this tool with default parameters will probably not give you meaningful results. A way to deal with this is to **understand** the parameters by carefully reading the `documentation`__ and experimenting. Fortunately, Galaxy makes experimenting easy.

 .. __: http://www.bioinformatics.babraham.ac.uk/projects/bismark/


.. class:: warningmark

Make sure all your input reads are in the correct and same format. If thats not the case please adjust/convert the filetype with galaxy's build-in converters.

------

**Input formats**

------

**Bismark parameter list**

This is an exhaustive list of Bismark options.

Input::

  --singles              A comma- or space-separated list of files containing the reads to be aligned (e.g.
                         lane1.fq,lane2.fq lane3.fq). Reads may be a mix of different lengths. Bismark will

  --temp_dir DIR          Write temporary files to this directory instead of into the same directory as the input files. If
                         the specified folder does not exist, Bismark will attempt to create it first. The path to the
                         temporary folder can be either relative or absolute.

  </help>
</tool>