comparison maxbin2.xml @ 5:7160fa1ecb30 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/maxbin2/ commit 5efe64a2c3cb7495d708f539d341fa53fba07fe4

4:9d11c2c0ff24

<tool id="maxbin2" name="MaxBin2" version="@MAXBIN_VERSION@+galaxy3">
    <description>clusters metagenomic contigs into bins</description>
    <xrefs>
        <xref type="bio.tools">masigpro</xref>
    </xrefs>
    <macros>
        <token name="@MAXBIN_VERSION@">2.2.7</token>
        <xml name="contig">
            <param argument="-contig" type="data" format="fasta,fasta.gz" label="Contig file"/>
        </xml>

        <xml name="reads_extra_params">
            <param name="output_abundances" type="boolean" checked="false" label="Output abundances" help="" />
            <param argument="--reassembly" type="boolean" truevalue="-reassembly" falsevalue="" checked="false" label="Reassembly" help="Reassembly option is still highly experimental. To use this function, you need to feed MaxBin interleaved paired-end fastq or fasta file." />
        </xml>
    </macros>
    <requirements>
        <requirement type="package" version="@MAXBIN_VERSION@">maxbin2</requirement>
    </requirements>
    <version_command><![CDATA[run_MaxBin.pl -version | head -n 1]]></version_command>
    <command detect_errors="exit_code"><![CDATA[
## generate read or abundance files
#if $assembly.inputs.type == 'reads'
    #if $assembly.type == 'individual'
echo '$assembly.inputs.reads' >> reads_list &&
    #else
        #for $r in $assembly.inputs.reads
            #if $r
echo '$r' >> reads_list &&
            #end if
        #end for
    #end if
#else if $assembly.inputs.type == 'abund'
    #if $assembly.type == 'individual'

            </param>
            <when value="individual">
                <conditional name="inputs">
                    <expand macro="input_type"/>
                    <when value="reads">
                        <param argument="-reads" type="data" format="fasta,fastq" label="Reads file"/>
                        <expand macro="reads_extra_params"/>
                    </when>
                    <when value="abund">
                        <param argument="-abund" type="data" format="tabular" label="Abundance file"/>
                    </when>

                    <has_text text="out.002.fasta"/>
                    <has_text text="2878"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
MaxBin is a software that clusters metagenomic contigs into different bins,
each consists (hopefully) of contigs from one species. MaxBin uses the
nucleotide composition information and contig abundance information to do

The abundance information can be provided as tabular file:

For example, assume I have three contigs named A0001, A0002, and A0003, then my abundance file will look like

A0001	30.89
A0002	20.02
A0003	78.93

Reads/Abundundance files can be given in multiple files.

By default MaxBin will look for 107 marker genes present in >95% of bacteria.
Alternatively you can also choose 40 marker gene sets that are universal among

5:7160fa1ecb30

<tool id="maxbin2" name="MaxBin2" version="@MAXBIN_VERSION@+galaxy6">
    <description>clusters metagenomic contigs into bins</description>
    <macros>
        <token name="@MAXBIN_VERSION@">2.2.7</token>
        <xml name="contig">
            <param argument="-contig" type="data" format="fasta,fasta.gz" label="Contig file"/>
        </xml>

        <xml name="reads_extra_params">
            <param name="output_abundances" type="boolean" checked="false" label="Output abundances" help="" />
            <param argument="--reassembly" type="boolean" truevalue="-reassembly" falsevalue="" checked="false" label="Reassembly" help="Reassembly option is still highly experimental. To use this function, you need to feed MaxBin interleaved paired-end fastq or fasta file." />
        </xml>
    </macros>
    <xrefs>
        <xref type="bio.tools">maxbin</xref>
    </xrefs>
    <requirements>
        <requirement type="package" version="@MAXBIN_VERSION@">maxbin2</requirement>
    </requirements>
    <version_command><![CDATA[run_MaxBin.pl -version | head -n 1]]></version_command>
    <command detect_errors="exit_code"><![CDATA[
## generate read or abundance files
#import re
#if $assembly.inputs.type == 'reads'
    #if $assembly.type == 'individual'
        ## uncompress .gz reads files if necessary
        #set $e = $assembly.inputs.reads
        #set $identifier = re.sub('[^\w\-\\.]', '_', str($e.element_identifier))
        #if $e.ext.endswith(".gz")
gunzip -c '$e' > '$identifier' &&
echo '$identifier' >> reads_list &&
        #else 
ln -s '$e' '$identifier' &&
echo '$identifier' >> reads_list &&
        #end if
    #else
        #for $i, $r in enumerate($assembly.inputs.reads)
            #if $r
                #set $identifier = re.sub('[^\w\-\\.]', '_', str($r.element_identifier))
                #set $newid = $identifier +  '_'  + str($i)
                #if $r.ext.endswith(".gz")
gunzip -c '$r' > '$newid' &&                        
echo '$newid' >> reads_list &&
                #else
ln -s '$r' '$newid' &&
echo '$newid' >> reads_list &&
                #end if
            #end if
        #end for
    #end if
#else if $assembly.inputs.type == 'abund'
    #if $assembly.type == 'individual'

            </param>
            <when value="individual">
                <conditional name="inputs">
                    <expand macro="input_type"/>
                    <when value="reads">
                        <param argument="-reads" type="data" format="fasta,fastq,fastq.gz,fasta.gz" label="Reads file"/>
                        <expand macro="reads_extra_params"/>
                    </when>
                    <when value="abund">
                        <param argument="-abund" type="data" format="tabular" label="Abundance file"/>
                    </when>

                    <has_text text="out.002.fasta"/>
                    <has_text text="2878"/>
                </assert_contents>
            </output>
        </test>
        <!-- test w contigs and reads in fastqsanger format as input -->
        <test expect_num_outputs="4">
            <param name="contig" value="test4_contigs.fasta" ftype="fasta" />
            <conditional name="assembly">
                <param name="type" value="individual"/>
                <conditional name="inputs">
                    <param name="type" value="reads"/>
                    <param name="reads" value="test4_reads.fastqsanger" ftype="fastqsanger"/>
                    <param name="output_abundances" value="false"/>
                    <param name="reassembly" value=""/>
                </conditional>
            </conditional>
            <section name="adv">
                <param name="min_contig_length" value="1000"/>
                <param name="max_iteration" value="50"/>
                <param name="prob_threshold" value="0.5"/>
            </section>
            <section name="output">
                <param name="plotmarker" value=""/>
                <param name="marker" value="false"/>
                <param name="markers" value="false" />
                <param name="log" value="false"/>
                <param name="markerset" value="107"/>
            </section>
            <output_collection name="bins" type="list" count="2">
                <element name="001" file="4/out.001.fasta" ftype="fasta"/>
                <element name="002" file="4/out.002.fasta" ftype="fasta"/>
            </output_collection>
            <output name="summary" file="4/out.summary" ftype="tabular" />
            <output name="noclass" file="4/out.noclass" ftype="fasta" />
            <output name="toshort" file="4/out.tooshort" ftype="fasta" />
        </test>
        <!-- test w contigs and reads in fastqsanger format as input (and whitespace in reads filename)-->
        <test expect_num_outputs="4">
            <param name="contig" value="test4_contigs.fasta" ftype="fasta" />
            <conditional name="assembly">
                <param name="type" value="individual"/>
                <conditional name="inputs">
                    <param name="type" value="reads"/>
                    <param name="reads" value="test4_reads 2.fastqsanger" ftype="fastqsanger"/>
                    <param name="output_abundances" value="false"/>
                    <param name="reassembly" value=""/>
                </conditional>
            </conditional>
            <section name="adv">
                <param name="min_contig_length" value="1000"/>
                <param name="max_iteration" value="50"/>
                <param name="prob_threshold" value="0.5"/>
            </section>
            <section name="output">
                <param name="plotmarker" value=""/>
                <param name="marker" value="false"/>
                <param name="markers" value="false" />
                <param name="log" value="false"/>
                <param name="markerset" value="107"/>
            </section>
            <output_collection name="bins" type="list" count="2">
                <element name="001" file="4/out.001.fasta" ftype="fasta"/>
                <element name="002" file="4/out.002.fasta" ftype="fasta"/>
            </output_collection>
            <output name="summary" file="4/out.summary" ftype="tabular" />
            <output name="noclass" file="4/out.noclass" ftype="fasta" />
            <output name="toshort" file="4/out.tooshort" ftype="fasta" />
        </test>
        <!-- test w contigs and reads in fastqsanger.gz format as input -->
        <test expect_num_outputs="4">
            <param name="contig" value="test4_contigs.fasta" ftype="fasta" />
            <conditional name="assembly">
                <param name="type" value="individual"/>
                <conditional name="inputs">
                    <param name="type" value="reads"/>
                    <param name="reads" value="test4_reads.fastqsanger.gz" ftype="fastqsanger.gz"/>
                    <param name="output_abundances" value="false"/>
                    <param name="reassembly" value=""/>
                </conditional>
            </conditional>
            <section name="adv">
                <param name="min_contig_length" value="1000"/>
                <param name="max_iteration" value="50"/>
                <param name="prob_threshold" value="0.5"/>
            </section>
            <section name="output">
                <param name="plotmarker" value=""/>
                <param name="marker" value="false"/>
                <param name="markers" value="false" />
                <param name="log" value="false"/>
                <param name="markerset" value="107"/>
            </section>
            <output_collection name="bins" type="list" count="2">
                <element name="001" file="4/out.001.fasta" ftype="fasta"/>
                <element name="002" file="4/out.002.fasta" ftype="fasta"/>
            </output_collection>
            <output name="summary" file="4/out.summary" ftype="tabular" />
            <output name="noclass" file="4/out.noclass" ftype="fasta" />
            <output name="toshort" file="4/out.tooshort" ftype="fasta" />
        </test>
        <!-- test w co-assembled contigs and multiple reads as .gz and optional outputs -->
        <test expect_num_outputs="9">
            <param name="contig" value="test4_contigs.fasta" ftype="fasta" />
            <conditional name="assembly">
                <param name="type" value="coassembly"/>
                <conditional name="inputs">
                    <param name="type" value="reads"/>
                    <param name="reads" value="test4_reads.fastqsanger.gz,test4_reads.fastqsanger.gz" ftype="fasta"/>
                    <param name="output_abundances" value="true"/>
                    <param name="reassembly" value=""/>
                </conditional>
            </conditional>
            <section name="adv">
                <param name="min_contig_length" value="1000"/>
                <param name="max_iteration" value="50"/>
                <param name="prob_threshold" value="0.5"/>
            </section>
            <section name="output">
                <param name="plotmarker" value="true"/>
                <param name="marker" value="true"/>
                <param name="markers" value="true" />
                <param name="log" value="true"/>
                <param name="markerset" value="107"/>
            </section>
            <output_collection name="bins" type="list" count="2">
                <element name="001" file="4/out.001.fasta" ftype="fasta"/>
                <element name="002" file="4/out.002.fasta" ftype="fasta"/>
            </output_collection>
            <output name="summary" ftype="tabular">
                <assert_contents>
                    <has_text text="Completeness"/>
                    <has_text text="out.001.fasta"/>
                </assert_contents>
            </output>
            <output name="noclass" file="4/out.noclass" ftype="fasta" />
            <output name="toshort" file="4/out.tooshort" ftype="fasta" />
            <output name="log" ftype="txt" >
                <assert_contents>
                    <has_text text="Input contig"/>
                    <has_text text="Elapsed time"/>
                    <has_text text="Yielded 2 bins for contig (scaffold) file"/>
                </assert_contents>
            </output>
            <output name="abundout" file="4/out.abund1" ftype="tabular" />
            <output name="marker" file="4/out.marker" ftype="tabular" />
            <output name="plot" file="4/out.marker.pdf" ftype="pdf" compare="sim_size" />
            <output_collection name="markers" type="list" count="2">
                <element name="001" ftype="fasta">
                    <assert_contents>
                        <has_text text=">out.001.Methyltransf_5"/>
                    </assert_contents>
                </element>
                <element name="002" ftype="fasta">
                    <assert_contents>
                        <has_text text=">out.002.Methyltransf_5"/>
                    </assert_contents>
                </element>
            </output_collection>
        </test>
    </tests>
    <help><![CDATA[
MaxBin is a software that clusters metagenomic contigs into different bins,
each consists (hopefully) of contigs from one species. MaxBin uses the
nucleotide composition information and contig abundance information to do

The abundance information can be provided as tabular file:

For example, assume I have three contigs named A0001, A0002, and A0003, then my abundance file will look like

    ===== =====
    A0001 30.89
    A0002 20.02
    A0003 78.93
    ===== =====


Reads/Abundundance files can be given in multiple files.

By default MaxBin will look for 107 marker genes present in >95% of bacteria.
Alternatively you can also choose 40 marker gene sets that are universal among