comparison maxbin2.xml @ 2:6a638de7915c draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/maxbin2/ commit 08beeabf7a8e91d0e95f5cdb71249dd6efe2bd46"

1:864279a0d64b

<tool id="maxbin2" name="MaxBin2" version="2.2.4_galaxy1">
    <requirements>
        <requirement type="package" version="2.2.4">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 $intype_cond.intype_select == 'rds':

    #end if
    -thread \${GALAXY_SLOTS:-1}

    && tar -xf out.marker_of_each_bin.tar.gz

    ## redirect the idba out and err file content to stdout and err
    #if $intype_cond.intype_select == 'rds' and $intype_cond.reassembly != ""
        && echo "==== IDBA stdout ===="
        && cat out.idba.out
        && echo "==== IDBA stderr ====" 1>&2
        && cat out.idba.err 1>&2
    #end if
    ]]></command>

              <param name="intype_select" type="select" label="Input type">
                  <option value="rds" selected="true">Sequencing Reads</option>
                  <option value="abdc">Abundances</option>
              </param>
              <when value="rds">
                  <param name="reads" argument="-read/-read2/..." type="data" format="fasta,fastq" multiple="true" label="Reads file(s)"/>
                  <param argument="--reassembly" type="boolean" truevalue="-reassembly" falsevalue="" checked="false" label="" help="Reassembly option is still highly experimental. To use this function, you need to feed MaxBin interleaved paired-end fastq or fasta file." />
              </when>
              <when value="abdc">
                  <param name="abund" argument="-abund/-abund2/..." type="data" format="tabular" multiple="true" label="Abundance file(s)"/>
              </when>
          </conditional>
          <conditional name="adv_cond">
            <param name="adv_select" type="select" label="Advanced options">
                <option value="yes">Yes</option>

            </param>
            <when value="no"/>
            <when value="yes">
                <param argument="-min_contig_length" type="integer" min="0" value="1000" label="minimum contig length" />
                <param argument="-max_iteration" type="integer" min="0" value="50" label="Maximum Expectation-Maximization algorithm iteration number" />
                <param argument="-prob_threshold" type="float" min="0" max="1.0" value="0.9" label="Probability threshold for EM final classification" />
                <param name="plotmarker" type="boolean" truevalue="-plotmarker" falsevalue="" checked="false" label="Generate visualization of the marker gene presence numbers" />
                <param argument="-markerset" type="select" label="Marker gene set">
                    <option value="107" selected="true">107 marker genes present in >95% of bacteria</option>
                    <option value="40">40 marker gene sets that are universal among bacteria and archaea</option>
                </param>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <collection name="bins" type="list" label="${tool.name} on ${on_string} (bins)">
            <discover_datasets pattern="out.(?P&lt;designation&gt;[0-9]+).fasta" format="fasta" visible="false" />
        </collection>
        <data name="summary" format="tabular" label="${tool.name} on ${on_string} (summary)" from_work_dir="out.summary"/>
        <data name="log" format="txt" label="${tool.name} on ${on_string} (log)" from_work_dir="out.log"/>
        <data name="abundout" format="tabular" label="${tool.name} on ${on_string} (abundances)" from_work_dir="out.abund1">
            <filter>intype_cond['intype_select']=='rds'</filter>
        </data>
        <data name="marker" format="tabular" label="${tool.name} on ${on_string} (marker gene presence)" from_work_dir="out.marker"/>
        <data name="plot" format="pdf" label="${tool.name} on ${on_string} (marker gene presence plot)" from_work_dir="out.marker.pdf">
            <filter>adv_cond['adv_select']=='yes' and adv_cond['plotmarker']</filter>
        </data>
        <data name="noclass" format="fasta" label="${tool.name} on ${on_string} (unclassified sequences)" from_work_dir="out.noclass"/>
        <data name="toshort" format="fasta" label="${tool.name} on ${on_string} (to short sequences)" from_work_dir="out.tooshort"/>
        <collection name="markers" type="list" label="${tool.name} on ${on_string} (markers prediced for bins)">
            <discover_datasets pattern="out.(?P&lt;designation&gt;[0-9]+).marker.fasta" format="fasta" visible="false" />
        </collection>
        <!-- additional output in case of reassembly -->
	<collection name="reassembly_bins" type="list" label="${tool.name} on ${on_string} (reassembly bins)">
            <discover_datasets directory="out.reassem" pattern="out.(?P&lt;designation&gt;[0-9]+).fasta" format="fasta" visible="false" />
            <filter>intype_cond['intype_select']=='rds' and intype_cond['reassembly']</filter>
        </collection>
        <collection name="reassembly_reads" type="list" label="${tool.name} on ${on_string} (reassembly reads)">
            <discover_datasets directory="out.reassem" pattern="out.reads.(?P&lt;designation&gt;[0-9]+)" format="fasta" visible="false" />

        <data name="reassembly_n50" format="txt" label="${tool.name} on ${on_string} (reassembly N50)" from_work_dir="out.reassem/N50.txt">
            <filter>intype_cond['intype_select']=='rds' and intype_cond['reassembly']</filter>
        </data>
    </outputs>
    <tests>
        <test><!-- test w contigs and reads as input -->
            <param name="contig" value="Bin_Sample3_contigs.fasta" ftype="fasta" />
            <conditional name="intype_cond">
                <param name="intype_select" value="rds"/>
                <param name="reads" value="interleavedPE_unmapped_Sample3_total.fasta" ftype="fasta"/>
            </conditional>
            <conditional name="adv_cond">
                <param name="adv_select" value="no"/>
            </conditional>
            <output_collection name="bins" type="list" count="2">
                <element name="001" file="1/out.001.fasta" ftype="fasta"/>
                <element name="002" file="1/out.002.fasta" ftype="fasta"/>
            </output_collection>
            <output name="summary" file="1/out.summary" ftype="tabular" />
            <output name="log" file="1/out.log" ftype="txt" compare="diff" lines_diff="17" />
            <output name="abundout" file="1/out.abund1" ftype="tabular" />
            <output name="marker" file="1/out.marker" ftype="tabular" />
            <output name="noclass" file="1/out.noclass" ftype="fasta" />
            <output name="toshort" file="1/out.tooshort" ftype="fasta" />
            <output_collection name="markers" type="list" count="1">
                <element name="001" file="1/out.001.marker.fasta" ftype="fasta"/>
            </output_collection>
        </test>
        <test><!--test w contigs and abundances as input + advanced options -->
            <param name="contig" value="Bin_Sample3_contigs.fasta" ftype="fasta" />
            <conditional name="intype_cond">
                <param name="intype_select" value="abdc"/>
                <param name="abund" value="abundances.tsv" ftype="tabular"/>
            </conditional>

            <output_collection name="bins" type="list" count="2">
                <element name="001" file="2/out.001.fasta" ftype="fasta"/>
                <element name="002" file="2/out.002.fasta" ftype="fasta"/>
            </output_collection>
            <output name="summary" file="2/out.summary" ftype="tabular" />
            <output name="log" file="2/out.log" ftype="txt" compare="diff" lines_diff="17" />
            <output name="marker" file="2/out.marker" ftype="tabular" />
            <output name="plot" file="2/out.marker.pdf" ftype="pdf" compare="sim_size" />
            <output name="noclass" file="2/out.noclass" ftype="fasta" />
            <output name="toshort" file="2/out.tooshort" ftype="fasta" />
            <output_collection name="markers" type="list" count="1">
                <element name="001" file="2/out.001.marker.fasta" ftype="fasta"/>
            </output_collection>
        </test>
        <test><!-- test w contigs and reads as input + reassembly-->
            <param name="contig" value="Bin_Sample3_contigs.fasta" ftype="fasta" />
            <conditional name="intype_cond">
                <param name="intype_select" value="rds"/>
                <param name="reads" value="interleavedPE_unmapped_Sample3_total.fasta" ftype="fasta"/>
                <param name="reassembly" value="-reassembly"/>
            </conditional>
            <conditional name="adv_cond">
                <param name="adv_select" value="no"/>
            </conditional>
            <output_collection name="bins" type="list" count="2">
                <element name="001" file="3/out.001.fasta" ftype="fasta"/>
                <element name="002" file="3/out.002.fasta" ftype="fasta"/>
            </output_collection>
            <output name="summary" file="3/out.summary" ftype="tabular" />
            <output name="log" file="3/out.log" ftype="txt" compare="diff" lines_diff="17" />
            <output name="abundout" file="3/out.abund1" ftype="tabular" />
            <output name="marker" file="3/out.marker" ftype="tabular" />
            <output name="noclass" file="3/out.noclass" ftype="fasta" />
            <output name="toshort" file="3/out.tooshort" ftype="fasta" />
            <output_collection name="markers" type="list" count="1">
                <element name="001" file="3/out.001.marker.fasta" ftype="fasta"/>
            </output_collection>
            <output_collection name="reassembly_bins" type="list" count="2">
                <element name="001" file="3/out.reassem/out.001.fasta" ftype="fasta"/>
                <element name="002" file="3/out.reassem/out.002.fasta" ftype="fasta"/>
            </output_collection>
            <output_collection name="reassembly_reads" type="list" count="2">

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
achieve binning through an Expectation-Maximization algorithm.


**Input**:

MaxBin need the contigs and contig abundance information. The contig abundance
information can be provided in two ways: the user can choose to provide

**Reassembly**

This is an experimental feature of MaxBin. It calls for each read bin IDBA_UD with the pre_correction parameter.  Of course this IDBA_UD call can be done also with the corresponding Galaxy tool

]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btv638</citation>
        <citation type="bibtex">
@misc{renameTODO,
  author = {LastTODO, FirstTODO},
  year = {TODO},
  title = {TODO},
  url = {https://downloads.jbei.org/data/microbial_communities/MaxBin/MaxBin.html},
}</citation>
    </citations>
</tool>

2:6a638de7915c

<tool id="maxbin2" name="MaxBin2" version="@MAXBIN_VERSION@+galaxy1">
    <description>clusters metagenomic contigs into bins</description>
    <macros>
        <token name="@MAXBIN_VERSION@">2.2.7</token>
    </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 $intype_cond.intype_select == 'rds':

    #end if
    -thread \${GALAXY_SLOTS:-1}

    && tar -xf out.marker_of_each_bin.tar.gz

	## redirect the idba out and err file content to stdout and err
	## since this is also wanted in case the error case ';' is used here to 
	## separate commands
    #if $intype_cond.intype_select == 'rds' and $intype_cond.reassembly != ""
        ; echo "==== IDBA stdout ===="
        && cat out.idba.out
        && echo "==== IDBA stderr ====" 1>&2
        && cat out.idba.err 1>&2
    #end if
    ]]></command>

              <param name="intype_select" type="select" label="Input type">
                  <option value="rds" selected="true">Sequencing Reads</option>
                  <option value="abdc">Abundances</option>
              </param>
              <when value="rds">
                  <param name="reads" type="data" format="fasta,fastq" multiple="true" label="Reads file(s)" help="(-read/-read2/...)"/>
                  <param name="output_abundances" type="boolean" truevalue="true" falsevalue="false" 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." />
              </when>
              <when value="abdc">
                  <param name="abund" type="data" format="tabular" multiple="true" label="Abundance file(s)" help="(-abund/-abund2/...)" />
              </when>
          </conditional>
          <conditional name="adv_cond">
            <param name="adv_select" type="select" label="Advanced options">
                <option value="yes">Yes</option>

            </param>
            <when value="no"/>
            <when value="yes">
                <param argument="-min_contig_length" type="integer" min="0" value="1000" label="minimum contig length" />
                <param argument="-max_iteration" type="integer" min="0" value="50" label="Maximum Expectation-Maximization algorithm iteration number" />
                <param argument="-prob_threshold" type="float" min="0" max="1.0" value="0.5" label="Probability threshold for EM final classification" />
                <param argument="-plotmarker" type="boolean" truevalue="-plotmarker" falsevalue="" checked="false" label="Generate visualization of the marker gene presence numbers" />
                <param name="output_marker" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Output marker gene presence for bins table" />
                <param name="output_markers" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Output marker genes for each bin as fasta" />
                <param name="output_log" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Output log" />
                <param argument="-markerset" type="select" label="Marker gene set">
                    <option value="107" selected="true">107 marker genes present in >95% of bacteria</option>
                    <option value="40">40 marker gene sets that are universal among bacteria and archaea</option>
                </param>
            </when>
        </conditional>
    </inputs>
    <outputs>
        <!-- default outputs -->
        <collection name="bins" type="list" label="${tool.name} on ${on_string} (bins)">
            <discover_datasets pattern="out.(?P&lt;designation&gt;[0-9]+).fasta" format="fasta" visible="false" />
        </collection>
        <data name="noclass" format="fasta" label="${tool.name} on ${on_string} (unclassified sequences)" from_work_dir="out.noclass"/>
        <data name="toshort" format="fasta" label="${tool.name} on ${on_string} (to short sequences)" from_work_dir="out.tooshort"/>
        <data name="summary" format="tabular" label="${tool.name} on ${on_string} (summary)" from_work_dir="out.summary"/>

        <!-- optional outputs -->
        <data name="log" format="txt" label="${tool.name} on ${on_string} (log)" from_work_dir="out.log">
            <filter>adv_cond['adv_select']=='yes' and adv_cond['output_log']</filter>
        </data>
        <data name="marker" format="tabular" label="${tool.name} on ${on_string} (marker gene presence)" from_work_dir="out.marker">
            <filter>adv_cond['adv_select']=='yes' and adv_cond['output_marker']</filter>
        </data>
        <data name="abundout" format="tabular" label="${tool.name} on ${on_string} (abundances)" from_work_dir="out.abund1">
            <filter>intype_cond['intype_select']=='rds' and intype_cond['output_abundances']</filter>
        </data>
        <data name="plot" format="pdf" label="${tool.name} on ${on_string} (marker gene presence plot)" from_work_dir="out.marker.pdf">
            <filter>adv_cond['adv_select']=='yes' and adv_cond['plotmarker']</filter>
        </data>
        <collection name="markers" type="list" label="${tool.name} on ${on_string} (markers prediced for bins)">
            <discover_datasets pattern="out.(?P&lt;designation&gt;[0-9]+).marker.fasta" format="fasta" visible="false" />
            <filter>adv_cond['adv_select']=='yes' and adv_cond['output_markers']</filter>
        </collection>

        <!-- additional output in case of reassembly -->
        <collection name="reassembly_bins" type="list" label="${tool.name} on ${on_string} (reassembly bins)">
            <discover_datasets directory="out.reassem" pattern="out.(?P&lt;designation&gt;[0-9]+).fasta" format="fasta" visible="false" />
            <filter>intype_cond['intype_select']=='rds' and intype_cond['reassembly']</filter>
        </collection>
        <collection name="reassembly_reads" type="list" label="${tool.name} on ${on_string} (reassembly reads)">
            <discover_datasets directory="out.reassem" pattern="out.reads.(?P&lt;designation&gt;[0-9]+)" format="fasta" visible="false" />

        <data name="reassembly_n50" format="txt" label="${tool.name} on ${on_string} (reassembly N50)" from_work_dir="out.reassem/N50.txt">
            <filter>intype_cond['intype_select']=='rds' and intype_cond['reassembly']</filter>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="4"><!-- test w contigs and reads as input -->
            <param name="contig" value="Bin_Sample3_contigs.fasta" ftype="fasta" />
            <conditional name="intype_cond">
                <param name="intype_select" value="rds"/>
                <param name="reads" value="interleavedPE_unmapped_Sample3_small.fasta" ftype="fasta"/>
            </conditional>
            <conditional name="adv_cond">
                <param name="adv_select" value="no"/>
            </conditional>
            <output_collection name="bins" type="list" count="2">
                <element name="001" file="1/out.001.fasta" ftype="fasta"/>
                <element name="002" file="1/out.002.fasta" ftype="fasta"/>
            </output_collection>
            <output name="summary" file="1/out.summary" ftype="tabular" />
            <output name="noclass" file="1/out.noclass" ftype="fasta" />
            <output name="toshort" file="1/out.tooshort" ftype="fasta" />
        </test>
        <!-- test w contigs and reads as input test for optional outputs -->
        <test expect_num_outputs="9">
            <param name="contig" value="Bin_Sample3_contigs.fasta" ftype="fasta" />
            <conditional name="intype_cond">
                <param name="intype_select" value="rds"/>
                <param name="reads" value="interleavedPE_unmapped_Sample3_small.fasta" ftype="fasta"/>
                <param name="output_abundances" value="true" />
            </conditional>
            <conditional name="adv_cond">
                <param name="adv_select" value="yes"/>
                <param name="plotmarker" value="true" />
                <param name="output_marker" value="true" />
                <param name="output_markers" value="true" />
                <param name="output_log" value="true" />
            </conditional>
            <output_collection name="bins" type="list" count="2">
                <element name="001" file="1/out.001.fasta" ftype="fasta"/>
                <element name="002" file="1/out.002.fasta" ftype="fasta"/>
            </output_collection>
            <output name="summary" file="1/out.summary" ftype="tabular" />
            <output name="noclass" file="1/out.noclass" ftype="fasta" />
            <output name="toshort" file="1/out.tooshort" ftype="fasta" />
            <output name="log" file="1/out.log" ftype="txt" compare="diff" lines_diff="21" />
            <output name="abundout" file="1/out.abund1" ftype="tabular" />
            <output name="marker" file="1/out.marker" ftype="tabular" />
            <output name="plot" file="1/out.marker.pdf" ftype="pdf" compare="sim_size" />
            <output_collection name="markers" type="list" count="1">
                <element name="001" file="1/out.001.marker.fasta" ftype="fasta"/>
            </output_collection>
        </test>
        <!--test w contigs and abundances as input + advanced options -->
        <test expect_num_outputs="5">
            <param name="contig" value="Bin_Sample3_contigs.fasta" ftype="fasta" />
            <conditional name="intype_cond">
                <param name="intype_select" value="abdc"/>
                <param name="abund" value="abundances.tsv" ftype="tabular"/>
            </conditional>

            <output_collection name="bins" type="list" count="2">
                <element name="001" file="2/out.001.fasta" ftype="fasta"/>
                <element name="002" file="2/out.002.fasta" ftype="fasta"/>
            </output_collection>
            <output name="summary" file="2/out.summary" ftype="tabular" />
            <output name="noclass" file="2/out.noclass" ftype="fasta" />
            <output name="toshort" file="2/out.tooshort" ftype="fasta" />
            <output name="plot" file="2/out.marker.pdf" ftype="pdf" compare="sim_size" />
        </test>
        <!-- test w contigs and reads as input + reassembly-->
        <test expect_num_outputs="8">
            <param name="contig" value="Bin_Sample3_contigs.fasta" ftype="fasta" />
            <conditional name="intype_cond">
                <param name="intype_select" value="rds"/>
                <param name="reads" value="interleavedPE_unmapped_Sample3_small.fasta" ftype="fasta"/>
                <param name="reassembly" value="-reassembly"/>
            </conditional>
            <conditional name="adv_cond">
                <param name="adv_select" value="no"/>
            </conditional>
            <output_collection name="bins" type="list" count="2">
                <element name="001" file="3/out.001.fasta" ftype="fasta"/>
                <element name="002" file="3/out.002.fasta" ftype="fasta"/>
            </output_collection>
            <output name="summary" file="3/out.summary" ftype="tabular" />
            <output name="noclass" file="3/out.noclass" ftype="fasta" />
            <output name="toshort" file="3/out.tooshort" ftype="fasta" />
            <output_collection name="reassembly_bins" type="list" count="2">
                <element name="001" file="3/out.reassem/out.001.fasta" ftype="fasta"/>
                <element name="002" file="3/out.reassem/out.002.fasta" ftype="fasta"/>
            </output_collection>
            <output_collection name="reassembly_reads" type="list" count="2">

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
achieve binning through an Expectation-Maximization algorithm.

**Input**:

MaxBin need the contigs and contig abundance information. The contig abundance
information can be provided in two ways: the user can choose to provide

**Reassembly**

This is an experimental feature of MaxBin. It calls for each read bin IDBA_UD with the pre_correction parameter.  Of course this IDBA_UD call can be done also with the corresponding Galaxy tool


** More information **

https://downloads.jbei.org/data/microbial_communities/MaxBin/MaxBin.html

]]></help>
    <citations>
        <citation type="doi">10.1093/bioinformatics/btv638</citation>
    </citations>
</tool>