comparison lastz.xml @ 8:e7f19d6a9af8 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/lastz commit a7e9d5b3906b7ebb35b1c29c3a8e8203b2cefccd

7:10aca14c2332

<tool id="lastz_wrapper_2" name="LASTZ" version="1.3.1">
    <description>: align long sequences</description>
    <macros>
        <import>lastz_macros.xml</import>
    </macros>
    <requirements>

        #if $interpolation.inner:
            '--inner=${interpolation.inner}'
        #end if

## OUTPUT FORMATS --------------------------------

        #if str( $output_format.out.format ) == "bam":
            '--format=${output_format.out.bam_options}'
        #elif str( $output_format.out.format ) == "general_def":

            --format=BLASTN-
        #elif str( $output_format.out.format ) == "general_full":
            '--format=general-:${output_format.out.fields}'
        #end if
        --action:target=multiple
        --rdotplot=plot.r
        #if str( $output_format.out.format ) == "bam":
            | samtools sort -@\${GALAXY_SLOTS:-2} -O bam -o '${output}' &&
        #else:
            > '${output}' &&
        #end if
        Rscript $r_plot > /dev/null 2>&1

        ]]>
    </command>
    <configfiles>
        <configfile name="r_plot">

                <when value="no">
                    <!-- Do nothing -->
                </when>
            </conditional>
            <param name="ambigN" type="boolean" truevalue="--ambiguous=n" checked="false" label="Treat each N in the input sequences as an ambiguous nucleotide" argument="--ambiguous=n" help="Substitutions with N are scored as zero, instead of using the fill_score value from the scoring file (which is -100 by default)."/>
            <param name="ambigIUPAC" type="boolean" truevalue="--ambiguous=iupac" checked="false" label="Treat each of the IUPAC-IUB ambiguity codes (B, D, H, K, M, R, S, V, W, and Y, as well as N) in the input sequences as a completely ambiguous nucleotide." argument="--ambiguous=iupac" help="Substitutions with these characters are scored as zero, instead of using the fill_score value from the scoring file (which is -100 by default)."/>
        </section>
        <section name="seeding" expanded="false" title="Seeding">
            <conditional name="seed">
                <param name="seed_selector" type="select" display="radio" label="Select seed type">
                    <option value="defaults" selected="true">Use defaults</option>

                </when>
                <when value="blastn">
                    <!-- Do nothing -->
                </when>
            </conditional>
        </section>
    </inputs>
    <outputs>
        <data format="tabular" name="output" label="${tool.name} on ${on_string}: mapped reads">
            <change_format>
                 <when input="output_format.out.format" value="bam" format="bam" />
                  <when input="output_format.out.format" value="maf" format="maf" />
            </change_format>
        </data>
        <data format="png" name="out_plot" label="${tool.name} on ${on_string}: dot plot"/>
    </outputs>
    <tests>
        <test>
            <param name="ref_source" value="cached" />
            <param name="target_2bit" value="phiX174" />

        </test>
        <test>
            <param name="ref_source" value="history" />
            <param name="target" ftype="fasta.gz" value="chrM_human.fa.gz" />
            <param name="query" ftype="fastq.bz2" value="chrM_mouse.fq.bz2" />
            <param name="strand" value="--strand=both" />
            <param name="format" value="blastn" />
            <output name="output" value="test5.out" />
        </test>
        <test>

        </test>
    </tests>

    <help><![CDATA[

        **What is does**

        LASTZ is designed to preprocess one sequence or set of sequences (which we collectively call the *TARGET*) and then align several *QUERY* sequences to it. It was developed by `Bob Harris <http://www.bx.psu.edu/~rsharris/>`_ in the lab of Webb Miller at Penn State.

        .. class:: warningmark

        **Read documentation** before proceeding. LASTZ is a complex tool with many parameter options. Fortunately, there is a `great manual <https://lastz.github.io/lastz/>`_ maintained by its author. Default parameters may be sufficient to obtain the initial idea about how similar your sequences are, but to produce reliable alignments you may need to tweak the parameters. So RTFM!

        **About LASTZ parameters**

        Galaxy's version of LASTZ has nine parameter sections (*Where to look*, *Scoring*, *Seeding*, *HSPs*, *Chaining*, *Gapped extension*, *Filtering*, *Interpolation*, and *Output*). These sections closely follow parameter description in the `manual <https://lastz.github.io/lastz/#syntax>`_.

        **Defaults**

        here are defaults for some of the most important parameters::

            --seed=<pattern>       set seed pattern (12of19, 14of22, or general pattern)
                                   (default is 1110100110010101111)
                                   SEE "Seeding" SECTION -> "Select seed type"

            --[no]transition       allow (or don't) one transition in a seed hit
                                   (by default a transition is allowed)
                                   SEE "Seeding" SECTION -> "Allow transitions"

            --[no]chain            perform chaining
                                   (by default no chaining is performed)
                                   SEE "Chaining" SECTION

            --[no]gapped           perform gapped alignment (instead of gap-free)
                                   (by default gapped alignment is performed)
                                   SEE "Gapped extension" SECTION

            --strand=both          search both strands
            --strand=plus          search + strand only (matching strand of query spec)
                                   (by default both strands are searched)
                                   SEE "Where to look" SECTION

            --scores=<file>        read substitution and gap scores from a file
                                   SEE "Scoring" SECTION

            --xdrop=<score>        set x-drop threshold (default is 10sub[A][A])
                                   SEE "HSPs" SECTION

            --ydrop=<score>        set y-drop threshold (default is open+300extend)
                                   SEE "Gapped extension" SECTION

            --hspthresh=<score>    set threshold for high scoring pairs (default is 3000)
                                   ungapped extensions scoring lower are discarded
                                   <score> can also be a percentage or base count
                                   SEE "HSPs" SECTION

            --gappedthresh=<score> set threshold for gapped alignments
                                   gapped extensions scoring lower are discarded
                                   <score> can also be a percentage or base count
                                   (default is to use same value as --hspthresh)
                                   SEE "Gapped extension" SECTION


        **Substitution matrix**

        By default the HOXD70 substitution scores are used (from `Chiaromonte et al. 2002 <https://www.ncbi.nlm.nih.gov/pubmed/11928468>`_)::

            bad_score          = X:-1000  # used for sub['X'][*] and sub[*]['X']
            fill_score         = -100     # used when sub[*][*] is not defined
            gap_open_penalty   =  400
            gap_extend_penalty =   30

                 A     C     G     T
            A   91  -114   -31  -123
            C -114   100  -125   -31
            G  -31  -125   100  -114
            T -123   -31  -114    91

        Matrix can be supplied as an input to **Read the substitution scores** parameter in *Scoring* section. Substitution matrix can be inferred from your data using another LASTZ-based tool (LASTZ_D: Infer substitution scores).

        **Output**

        This version of LASTZ produces two outputs by default: a BAM alignment file and a dot-plot in PNG format. Other formats can be configured in *Output* section. This incarnation of LASTZ produces outputs without comment line starting with '#'. To learn identity of each column, consult `formats section of LASTZ manual <https://lastz.github.io/lastz/#formats>`_.

        ]]>
    </help>
    <expand macro="citations"/>
</tool>

8:e7f19d6a9af8

<tool id="lastz_wrapper_2" name="LASTZ" version="1.3.2">
    <description>: align long sequences</description>
    <macros>
        <import>lastz_macros.xml</import>
    </macros>
    <requirements>

        #if $interpolation.inner:
            '--inner=${interpolation.inner}'
        #end if

## HOUSEKEEPING ----------------------------------

        --traceback=160M


## OUTPUT FORMATS --------------------------------

        #if str( $output_format.out.format ) == "bam":
            '--format=${output_format.out.bam_options}'
        #elif str( $output_format.out.format ) == "general_def":

            --format=BLASTN-
        #elif str( $output_format.out.format ) == "general_full":
            '--format=general-:${output_format.out.fields}'
        #end if
        --action:target=multiple
        $output_format.rplot
        #if str( $output_format.out.format ) == "bam":
            | samtools sort -@\${GALAXY_SLOTS:-2} -O bam -o '${output}'
        #else:
            > '${output}'
        #end if
        #if $output_format.rplot:
            &&
            Rscript $r_plot > /dev/null 2>&1
        #end if

        ]]>
    </command>
    <configfiles>
        <configfile name="r_plot">

                <when value="no">
                    <!-- Do nothing -->
                </when>
            </conditional>
            <param name="ambigN" type="boolean" truevalue="--ambiguous=n" checked="false" label="Treat each N in the input sequences as an ambiguous nucleotide" argument="--ambiguous=n" help="Substitutions with N are scored as zero, instead of using the fill_score value from the scoring file (which is -100 by default)."/>
            <param name="ambigIUPAC" type="boolean" truevalue="--ambiguous=iupac" checked="true" label="Treat each of the IUPAC-IUB ambiguity codes (B, D, H, K, M, R, S, V, W, and Y, as well as N) in the input sequences as a completely ambiguous nucleotide." argument="--ambiguous=iupac" help="Substitutions with these characters are scored as zero, instead of using the fill_score value from the scoring file (which is -100 by default)."/>
        </section>
        <section name="seeding" expanded="false" title="Seeding">
            <conditional name="seed">
                <param name="seed_selector" type="select" display="radio" label="Select seed type">
                    <option value="defaults" selected="true">Use defaults</option>

                </when>
                <when value="blastn">
                    <!-- Do nothing -->
                </when>
            </conditional>
            <param name="rplot" type="boolean" truevalue="--rdotplot=plot.r" falsevalue="" checked="false" argument="--rdotplot" label="Create a dotplot representation of alignments?" help="The dotplot is only useful if query and target contain exactly one sequence each"/>
        </section>
    </inputs>
    <outputs>
        <data format="tabular" name="output" label="${tool.name} on ${on_string}: mapped reads">
            <change_format>
                 <when input="output_format.out.format" value="bam" format="bam" />
                  <when input="output_format.out.format" value="maf" format="maf" />
            </change_format>
        </data>
        <data format="png" name="out_plot" label="${tool.name} on ${on_string}: dot plot">
            <filter>output_format['rplot']</filter>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="ref_source" value="cached" />
            <param name="target_2bit" value="phiX174" />

        </test>
        <test>
            <param name="ref_source" value="history" />
            <param name="target" ftype="fasta.gz" value="chrM_human.fa.gz" />
            <param name="query" ftype="fastq.bz2" value="chrM_mouse.fq.bz2" />
            <param name="traceback" value="83886080" />
            <param name="word" value="28" />
            <param name="strand" value="--strand=both" />
            <param name="format" value="blastn" />
            <output name="output" value="test5.out" />
        </test>
        <test>

        </test>
    </tests>

    <help><![CDATA[

**What is does**

LASTZ is designed to preprocess one sequence or set of sequences (which we collectively call the *TARGET*) and then align several *QUERY* sequences to it. It was developed by `Bob Harris <http://www.bx.psu.edu/~rsharris/>`_ in the lab of Webb Miller at Penn State.

.. class:: infomark

**Read documentation** before proceeding. LASTZ is a complex tool with many parameter options. Fortunately, there is a `great manual <https://lastz.github.io/lastz/>`_ maintained by its author. Default parameters may be sufficient to obtain the initial idea about how similar your sequences are, but to produce reliable alignments you may need to tweak the parameters. So RTFM!

.. class:: warningmark

Galaxy version of LASTZ sets **--ambiguous=iupac** as default (see **Scoring** section). This prevents LASTZ from erroring out if one of the DNA inputrs contains "non-strandard" nucleotides.  

**About LASTZ parameters**

Galaxy's version of LASTZ has nine parameter sections (*Where to look*, *Scoring*, *Seeding*, *HSPs*, *Chaining*, *Gapped extension*, *Filtering*, *Interpolation*, and *Output*). These sections closely follow parameter description in the `manual <https://lastz.github.io/lastz/#syntax>`_.

**Defaults**

here are defaults for some of the most important parameters::

    --seed=<pattern>       set seed pattern (12of19, 14of22, or general pattern)
                           (default is 1110100110010101111)
                           SEE "Seeding" SECTION -> "Select seed type"

    --[no]transition       allow (or don't) one transition in a seed hit
                           (by default a transition is allowed)
                           SEE "Seeding" SECTION -> "Allow transitions"

    --[no]chain            perform chaining
                           (by default no chaining is performed)
                           SEE "Chaining" SECTION

    --[no]gapped           perform gapped alignment (instead of gap-free)
                           (by default gapped alignment is performed)
                           SEE "Gapped extension" SECTION

    --strand=both          search both strands
    --strand=plus          search + strand only (matching strand of query spec)
                           (by default both strands are searched)
                           SEE "Where to look" SECTION

    --scores=<file>        read substitution and gap scores from a file
                           SEE "Scoring" SECTION

    --xdrop=<score>        set x-drop threshold (default is 10sub[A][A])
                           SEE "HSPs" SECTION

    --ydrop=<score>        set y-drop threshold (default is open+300extend)
                           SEE "Gapped extension" SECTION

    --hspthresh=<score>    set threshold for high scoring pairs (default is 3000)
                           ungapped extensions scoring lower are discarded
                           <score> can also be a percentage or base count
                           SEE "HSPs" SECTION

    --gappedthresh=<score> set threshold for gapped alignments
                           gapped extensions scoring lower are discarded
                           <score> can also be a percentage or base count
                           (default is to use same value as --hspthresh)
                           SEE "Gapped extension" SECTION


**Substitution matrix**

By default the HOXD70 substitution scores are used (from `Chiaromonte et al. 2002 <https://www.ncbi.nlm.nih.gov/pubmed/11928468>`_)::

    bad_score          = X:-1000  # used for sub['X'][*] and sub[*]['X']
    fill_score         = -100     # used when sub[*][*] is not defined
    gap_open_penalty   =  400
    gap_extend_penalty =   30

         A     C     G     T
    A   91  -114   -31  -123
    C -114   100  -125   -31
    G  -31  -125   100  -114
    T -123   -31  -114    91

Matrix can be supplied as an input to **Read the substitution scores** parameter in *Scoring* section. Substitution matrix can be inferred from your data using another LASTZ-based tool (LASTZ_D: Infer substitution scores).

**Output**

This version of LASTZ produces one output by default: a BAM alignment file. Other formats as well as a Dot Plot can be configured in *Output* section. This incarnation of LASTZ produces outputs without comment line starting with '#'. To learn identity of each column, consult `formats section of LASTZ manual <https://lastz.github.io/lastz/#formats>`_.

        ]]>
    </help>
    <expand macro="citations"/>
</tool>