comparison sickle.xml @ 0:15cb7dc0ed41 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/sickle commit 128d3f255f00c47fa2b16d9b7432d48a089660c1

0:15cb7dc0ed41

<tool id="sickle" name="Sickle" version="1.33">
    <description>windowed adaptive trimming of FASTQ data</description>
    <requirements>
        <requirement type="package" version="1.33">sickle</requirement>
    </requirements>
    <version_command>sickle --version | head -n 1</version_command>
    <command>
        sickle

        #if str($readtype.single_or_paired) == "se":
            se -f "${readtype.input_single}" -o "$output_single"

            #if $readtype.input_single.ext in ("fastq", "fastqsanger"):
                -t sanger
            #else if $readtype.input_single.ext == "fastqillumina":
                -t illumina
            #else if $readtype.input_single.ext == "fastqsolexa":
                -t solexa
            #end if
        #end if

        #if str($readtype.single_or_paired) == "pe_combo":
            #if $readtype.output_n:
                pe -c "${readtype.input_combo}" -M "$output_combo"
            #else
                pe -c "${readtype.input_combo}" -m "$output_combo" -s "$output_combo_single"
            #end if

            #if $readtype.input_combo.ext in ("fastq", "fastqsanger"):
                -t sanger
            #else if $readtype.input_combo.ext == "fastqillumina":
                -t illumina
            #else if $readtype.input_combo.ext == "fastqsolexa":
                -t solexa
            #end if
        #end if

        #if str($readtype.single_or_paired) == "pe_sep":
            pe -f "${readtype.input_paired1}" -r "${readtype.input_paired2}" -o "$output_paired1" -p "$output_paired2" -s "$output_paired_single"

            #if $readtype.input_paired1.ext in ("fastq", "fastqsanger"):
                -t sanger
            #else if $readtype.input_paired1.ext == "fastqillumina":
                -t illumina
            #else if $readtype.input_paired1.ext == "fastqsolexa":
                -t solexa
            #end if
        #end if

        #if str($qual_threshold) != "":
            -q $qual_threshold
        #end if

        #if str($length_threshold) != "":
            -l $length_threshold
        #end if

        #if $no_five_prime:
            -x
        #end if

        #if $trunc_n:
            -n
        #end if
    </command>

    <inputs>
        <conditional name="readtype">
            <param name="single_or_paired" type="select" label="Single-end or paired-end reads?" help="Note: Sickle will infer the quality type of the file from its datatype.  I.e., if the datatype is fastqsanger, then the quality type is sanger. The default is fastqsanger.">
                <option value="se" selected="true">Single-end</option>
                <option value="pe_combo">Paired-end (one interleaved input file)</option>
                <option value="pe_sep">Paired-end (two separate input files)</option>
            </param>

            <when value="se">
                <param format="fastq" name="input_single" type="data" label="Single-end FASTQ reads" help="(-f)" />
            </when>

            <when value="pe_combo">
                <param format="fastq" name="input_combo" type="data" label="Paired-end interleaved FASTQ reads" help="(-c)" />
                <param name="output_n" type="boolean" label="Output only one file with all reads" help="This will output only one file with all the reads, where the reads that did not pass filter will be replaced with a single 'N', rather than discarded."/>
            </when>

            <when value="pe_sep">
                <param format="fastq" name="input_paired1" type="data" label="Paired-end forward strand FASTQ reads" help="(-f)" />
                <param format="fastq" name="input_paired2" type="data" label="Paired-end reverse strand FASTQ reads" help="(-r)" />
            </when>
        </conditional>

        <param name="qual_threshold" value="20" min="0" type="integer" optional="true" label="Quality threshold" help="Threshold for trimming based on average quality in a window (-q)" />

        <param name="length_threshold" value="20" min="0" type="integer" optional="true" label="Length threshold" help="Threshold to keep a read based on length after trimming (-l)" />

        <param name="no_five_prime" type="boolean" label="Don't do 5' trimming" help="(-x)" />
        <param name="trunc_n" type="boolean" label="Truncate sequences with Ns at first N position" help="(-n)" />
    </inputs>

    <outputs>
        <data name="output_single" format_source="input_single" label="Single-end output of ${tool.name} on ${on_string}">
            <filter>readtype['single_or_paired'] == 'se'</filter>
        </data>

        <data name="output_combo" format_source="input_combo" label="Paired-end interleaved output of ${tool.name} on ${on_string}">
            <filter>readtype['single_or_paired'] == 'pe_combo'</filter>
        </data>

        <data name="output_combo_single" format_source="input_combo" label="Singletons from paired-end interleaved output of ${tool.name} on ${on_string}">
            <filter>readtype['single_or_paired'] == 'pe_combo' and not readtype['output_n']</filter>
        </data>

        <data name="output_paired1" format_source="input_paired1" label="Paired-end forward strand output of ${tool.name} on ${on_string}">
            <filter>readtype['single_or_paired'] == 'pe_sep'</filter>
        </data>

        <data name="output_paired2" format_source="input_paired2" label="Paired-end reverse strand output of ${tool.name} on ${on_string}">
            <filter>readtype['single_or_paired'] == 'pe_sep'</filter>
        </data>

        <data name="output_paired_single" format_source="input_paired1" label="Singletons from paired-end output of ${tool.name} on ${on_string}">
            <filter>readtype['single_or_paired'] == 'pe_sep'</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="single_or_paired" value="pe_combo" />
            <param name="input_combo" value="test.fastq" />
            <param name="qual_threshold" value="34" />
            <output name="output_combo" file="output.c1.fastq" />
            <output name="output_combo_single" file="output.s.fastq" />
        </test>
        <test>
            <param name="single_or_paired" value="pe_combo" />
            <param name="input_combo" value="test.fastq" />
            <param name="qual_threshold" value="34" />
            <param name="output_n" value="true" />
            <output name="output_combo" file="output.c2.fastq" />
        </test>
        <test>
            <param name="single_or_paired" value="pe_sep" />
            <param name="input_paired1" value="test.f.fastq" />
            <param name="input_paired2" value="test.r.fastq" />
            <param name="qual_threshold" value="34" />
            <output name="output_paired1" file="output.f.fastq" />
            <output name="output_paired2" file="output.r.fastq" />
            <output name="output_paired_single" file="output.s.fastq" />
        </test>
    </tests>
    <help>
**What it does**

Most modern sequencing technologies produce reads that have
deteriorating quality towards the 3'-end and some towards the 5'-end
as well. Incorrectly called bases in both regions negatively impact
assembles, mapping, and downstream bioinformatics analyses.

Sickle is a tool that uses sliding windows along with quality and
length thresholds to determine when quality is sufficiently low to
trim the 3'-end of reads and also determines when the quality is
sufficiently high enough to trim the 5'-end of reads.  It will also
discard reads based upon the length threshold.  It takes the quality
values and slides a window across them whose length is 0.1 times the
length of the read.  If this length is less than 1, then the window is
set to be equal to the length of the read.  Otherwise, the window
slides along the quality values until the average quality in the
window rises above the threshold, at which point the algorithm
determines where within the window the rise occurs and cuts the read
and quality there for the 5'-end cut.  Then when the average quality
in the window drops below the threshold, the algorithm determines
where in the window the drop occurs and cuts both the read and quality
strings there for the 3'-end cut.  However, if the length of the
remaining sequence is less than the minimum length threshold, then the
read is discarded entirely (or replaced with an "N" record). 5'-end
trimming can be disabled. Sickle also has an option to truncate reads
with Ns at the first N position.

Sickle supports three types of quality values: Illumina, Solexa, and
Sanger. Note that the Solexa quality setting is an approximation (the
actual conversion is a non-linear transformation). The end
approximation is close. Illumina quality refers to qualities encoded
with the CASAVA pipeline between versions 1.3 and 1.7.  Illumina
quality using CASAVA >= 1.8 is Sanger encoded. The quality value will
be determined from the datatype of the data, i.e. a fastqsanger datatype
is assumed to be Sanger encoded.

Note that Sickle will remove the 2nd FASTQ record header (on the "+"
line) and replace it with simply a "+". This is the default format for
CASAVA >= 1.8.

-----

**Options**

**Single-end**

This option takes one single-end input file and outputs one single-end
output file of reads that passed the filters.

**Paired-End (one interleaved input file)**

This option takes as input one interleaved paired-end file. If you then
check the "Output only one file with all reads" checkbox, it will output
one interleaved file where any read that did not pass filter will be replaced
with a FASTQ record where the sequence is a single "N" and the quality is the
lowest quality possible for that quality type. This will preserve the paired
nature of the data. If you leave the checkbox unchecked, it will output two files,
one interleaved file with all the passed pairs and one singletons file where only
one of the pair passed filter.

**Paired-End (two separate input files)**

This option takes two separate (forward and reverse) paired-end files as input.
The output is three files: Two paired-end files with pairs that passed filter and
a singletons file where only one of the pair passed filter.

**Quality threshold**

Input your desired quality threshold. This threshold is phred-scaled, which is typically
values between 0-41 for FASTQ data.

**Length threshold**

Input your desired length threshold. This is the threshold to determine if a read is kept
after all the trimming steps are done.

**Disable 5-prime trimming**

An option to disable trimming the read on the 5-prime end. This trimming trims the read
if the average quality values dip below the quality threshold at the 5-prime end.

**Truncate sequences with Ns**

This option will trim a read at the first "N" base in the read after doing quality trimming.
It is then still subject to the length threshold.

-----

Copyright: Nikhil Joshi

http://bioinformatics.ucdavis.edu

http://github.com/najoshi/sickle
    </help>
    <citations>
        <citation type="bibtex">
            @unpublished{sickle_link,
                author = {Joshi, Nikhil A. and Fass, Joseph N.},
                title = {Sickle: A windowed adaptive trimming tool for FASTQ files using quality},
                year = 2011,
                url = { https://github.com/najoshi/sickle }
            }
        </citation>
    </citations>
</tool>