view sRbowtie.xml @ 8:8157d59a8190 draft default tip

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/sr_bowtie commit 269546398f6e244a5df4aa2108bb4705fad15f7a

<tool id="bowtieForSmallRNA" name="sR_bowtie" version="2.3.1">
    <description>for small RNA short reads</description>
    <xrefs>
        <xref type="bio.tools">sr_bowtie</xref>
    </xrefs>
    <requirements>
        <requirement type="package" version="1.3.1">bowtie</requirement>
        <requirement type="package" version="1.14">samtools</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        #if $refGenomeSource.genomeSource == "history":
            bowtie-build --threads \${GALAXY_SLOTS:-4} -f $refGenomeSource.ownFile genome 1>/dev/null &&
            ln -s -f '$refGenomeSource.ownFile' genome.fa &&
            #set index_path = 'genome'
        #else:
            #set index_path = $refGenomeSource.index.fields.path
        #end if
        #if $input.is_of_type('fasta'):
            #set format = "-f"
        #elif $input.is_of_type('fastq'):
            #set format = "-q"
        #end if

        ## set the method_prefix
        #if $method == "RNA":
            #set method_prefix = "-v %s -M 1 --best --strata --norc" % str($v_mismatches)
        #elif $method == "unique":
            #set method_prefix = "-v %s -m 1" % str($v_mismatches)
        #elif $method == "multiple":
            #set method_prefix = "-v %s -M 1 --best --strata" % str($v_mismatches)
        #elif $method == "k_option":
            #set method_prefix = "-v %s -k 1 --best" % str($v_mismatches)
        #elif $method == "n_option":
            #set method_prefix = "-n %s -M 1 --best" % str($v_mismatches)
        #elif $method == "a_option":
            #set method_prefix = "-v %s -a --best" % str($v_mismatches)
        #end if
 
        ## set the extra_output
        #if $additional_fasta == "No":
            #set extra_output = ""
        #elif $additional_fasta == "al":
            #set extra_output = " --al %s " % str($aligned)
        #elif $additional_fasta == "unal":
            #set extra_output = " --un %s " % str($unaligned)
        #else:
            #set extra_output = " --al %s --un %s " % (str($aligned), str($unaligned))
        #end if
       
        #set $method_postfix = " %s %s " % ($method_prefix, $extra_output)

        ## run the bowtie alignement
        #if $output_format == "tabular":
            bowtie -p \${GALAXY_SLOTS:-4} $method_postfix --suppress 6,7,8 $index_path $format '$input' 2>&1 > $output
        #elif $output_format == "sam":
            bowtie -p \${GALAXY_SLOTS:-4} $method_postfix -S $index_path $format '$input' 2>&1 > '$output'
        #elif $output_format == "bam":
            bowtie -p \${GALAXY_SLOTS:-4} $method_postfix -S $index_path $format '$input'| samtools view -u - | samtools sort -@ "\${GALAXY_SLOTS:-4}" -T tmp -O bam -o $output 2>&1
        #end if
        ##### | samtools view -uS
        ]]></command>
    <inputs>
        <param format="fasta, fastq" help="Only with clipped, fasta or fastq read files" label="Input fasta or fastq file: reads clipped from their adapter" name="input" type="data" />
        <param help="bowtie parameters adjusted to the type of matching. RNA option match to only one strand" label="What kind of matching do you want to do?" name="method" type="select">
            <option value="RNA">Match on sense strand RNA reference index, multiple mappers randomly matched at a single position</option>
            <option value="unique">Match unique mappers on DNA reference index</option>
            <option selected="true" value="multiple">Match on DNA, multiple mappers randomly matched at a single position</option>
            <option value="k_option">Match on DNA as fast as possible, without taking care of mapping issues (for raw annotation of reads)</option>
            <option value="n_option">Match on DNA - RNAseq mode (-n bowtie option)</option>
            <option value="a_option">Match and report all valid alignments</option>
        </param>
        <param help="specify the -v bowtie option" label="Number of mismatches allowed" name="v_mismatches" type="select">
            <option value="0">0</option>
            <option selected="true" value="1">1</option>
            <option value="2">2</option>
            <option value="3">3</option>
        </param>
        <conditional name="refGenomeSource">
            <param help="Built-ins were indexed using default options" label="Will you select a reference genome from your history or use a built-in index?" name="genomeSource" type="select">
                <option value="indexed">Use a built-in index</option>
                <option value="history">Use one from the history</option>
            </param>
            <when value="indexed">
                <param help="if your genome of interest is not listed - contact instance administrator" label="Select a DNA reference index" name="index" type="select">
                    <options from_data_table="bowtie_indexes">
      
          </options>
                </param>
            </when>
            <when value="history">
                <param format="fasta" label="Select a fasta file, to serve as index reference" name="ownFile" type="data" />
            </when>
        </conditional>
        <param help="Note that the BAM will be viewable in trackster only if you choose a full genome referenced for Trackster usage. see the doc below" label="Select output format" name="output_format" type="select">
            <option selected="true" value="tabular">tabular</option>
            <option value="sam">sam</option>
            <option value="bam">bam</option>
        </param>
        <param help="to get aligned and unaligned reads in fasta format" label="additional fasta output" name="additional_fasta" type="select">
            <option selected="true" value="No">No</option>
            <option value="al">aligned</option>
            <option value="unal">unaligned</option>
            <option value="al_and_unal">both aligned and unaligned</option>
        </param>
    </inputs>
    <outputs>
        <data format="tabular" label="Bowtie Output" name="output">
            <change_format>
                <when format="sam" input="output_format" value="sam" />
                <when format="bam" input="output_format" value="bam" />
            </change_format>
            <actions>
                <conditional name="refGenomeSource.genomeSource">
                    <when value="indexed">
                        <action name="dbkey" type="metadata">
                            <option column="1" name="bowtie_indexes" offset="0" type="from_data_table">
                                <filter column="0" compare="startswith" keep="False" type="param_value" value="#" />
                                <filter column="0" ref="refGenomeSource.index" type="param_value" />
                            </option>
                        </action>
                    </when>
                    <when value="history">
                        <action name="dbkey" type="metadata">
                            <option name="refGenomeSource.ownFile" param_attribute="dbkey" type="from_param" />
                        </action>
                    </when>
                </conditional>
            </actions>
        </data>
        <data format_source="input" label="Matched reads" name="aligned">
            <filter>additional_fasta == "al" or additional_fasta == "al_and_unal"</filter>
        </data>
        <data format_source="input" label="Unmatched reads" name="unaligned">
            <filter>additional_fasta == "unal" or additional_fasta == "al_and_unal"</filter>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="1">
            <param name="genomeSource" value="history" />
            <param ftype="fasta" name="ownFile" value="297_reference.fa" />
            <param name="method" value="unique" />
            <param ftype="fasta" name="input" value="input.fa" />
            <param name="v_mismatches" value="1" />
            <param name="output_format" value="bam" />
            <output file="output.bam" ftype="bam" compare="sim_size" delta="1000" name="output" />
        </test>
        <test expect_num_outputs="1">
            <param name="genomeSource" value="history" />
            <param ftype="fasta" name="ownFile" value="297_reference.fa" />
            <param name="method" value="unique" />
            <param ftype="fastq" name="input" value="input.fastq" />
            <param name="v_mismatches" value="1" />
            <param name="output_format" value="bam" />
            <output file="output2.bam" ftype="bam" compare="sim_size" delta="1000" name="output" />
        </test>
        <test expect_num_outputs="2">
            <param name="genomeSource" value="history" />
            <param ftype="fasta" name="ownFile" value="297_reference.fa" />
            <param name="method" value="unique" />
            <param ftype="fastqsanger" name="input" value="input.fastqsanger" />
            <param name="v_mismatches" value="1" />
            <param name="additional_fasta" value="al" />
            <param name="output_format" value="bam" />
            <output file="output2.bam" ftype="bam" compare="sim_size" delta="1000" name="output" />
            <output file="al.fastqsanger" ftype="fastqsanger" name="aligned" />
        </test>
        <test expect_num_outputs="1">
            <param name="genomeSource" value="history" />
            <param ftype="fasta" name="ownFile" value="297_reference.fa" />
            <param name="method" value="multiple" />
            <param ftype="fasta" name="input" value="input.fa" />
            <param name="v_mismatches" value="1" />
            <param name="output_format" value="tabular" />
            <output file="output.tab" ftype="tabular" name="output" />
        </test>
        <test expect_num_outputs="2">
            <param name="genomeSource" value="history" />
            <param ftype="fasta" name="ownFile" value="297_reference.fa" />
            <param name="method" value="multiple" />
            <param ftype="fasta" name="input" value="input.fa" />
            <param name="v_mismatches" value="1" />
            <param name="additional_fasta" value="al" />
            <param name="output_format" value="tabular" />
            <output file="output.tab" ftype="tabular" name="output" />
            <output file="al.fa" ftype="fasta" name="aligned" />
        </test>
    </tests>
    <help>

**What it does**

Bowtie_ is a short read aligner designed to be ultrafast and memory-efficient. It is developed by Ben Langmead and Cole Trapnell. Please cite: Langmead B, Trapnell C, Pop M, Salzberg SL. Ultrafast and memory-efficient alignment of short DNA sequences to the human genome. Genome Biology 10:R25.

.. _Bowtie: http://bowtie-bio.sourceforge.net/index.shtml

A generic "Map with Bowtie for Illumina" Galaxy tool is available in the main Galaxy distribution.

However, this Bowtie wrapper tool only takes FASTQ files as inputs.

The sRbowtie wrapper works with short (-v bowtie mode) reads inputs, in fasta or fastq format, and proposes a simplified set of configurations suited to small RNA analysis.

------

**OPTIONS**

.. class:: infomark

This script uses Bowtie to match reads on a reference index.

Depending on the type of matching, different bowtie options are used:

**Match on sense strand RNA reference index, multiple mappers randomly matched at a single position**

Align on RNA reference, SENSE strand, randomly attributing multiple mapper to target with least mismatches:

*-v [0,1,2,3] -M 1 --best --strata -p 12 --norc*

**Match unique mappers on DNA reference index**

Align ONLY unique mappers on DNA reference index

*-v [0,1,2,3] -m 1 -p 12*

Note that using this option with -v values other than 0 is questionnable...

**Match on DNA, multiple mappers randomly matched at a single position**

Align multiple mappers, randomly attributing multiple mapper to target with least mismatches, number of mismatch allowed specified by -v option:

*-v [0,1,2,3] -M 1 --best --strata -p 12*

**Match on DNA as fast as possible, without taking care of mapping issues (for raw annotation of reads)**

Align with highest speed, not guaranteeing best hit for speed gain:

*-v [0,1,2,3] -k 1 --best -p 12*

**Match on DNA - RNAseq mode (-n bowtie option)**

Align reads in as for RNAseq data alignment

*-n [0,1,2,3] -M 1 --best -p 12*

**Match and report all valid alignments**

Align reads and report all valid alignments

*-v [0,1,2,3] -a --best -p 12*



-----

**Input formats**

.. class:: warningmark

*Lists of reads, in fasta or fastq format, clipped from their adapter sequence*

-----

**OUTPUTS**

If you choose tabular as the output format, you will obtain the matched reads in tabular bowtie output format (--suppress 6,7,8), having the following columns::

    Column    Description
  --------    --------------------------------------------------------
   1 FastaID  fasta identifier
   2 polarity + or - depending whether the match was reported on the forward or reverse strand
   3 target     name of the matched target
   4 Offset   O-based coordinate of the miR on the miRBase pre-miR sequence
   5 Seq      sequence of the matched Read

If you choose SAM, you will get the output in unordered SAM format.

.. class:: warningmark

if you choose BAM, the output will be in sorted BAM format.
To be viewable in Trackster, several condition must be fulfilled:

.. class:: infomark

Reads must have been matched to a genome whose chromosome names are compatible with Trackster genome indexes

.. class:: infomark

the database/Build (dbkey) which is indicated for the dataset (Pencil - Database/Build field) must match a Trackster genome index.

Please contact the Galaxy instance administrator if your genome is not referenced

**Matched and unmatched fasta reads can be retrieved, for further analyses**

  </help>
    <citations>
        <citation type="doi">10.1186/gb-2009-10-3-r25</citation>
    </citations>
</tool>