comparison macros.xml @ 5:8ba0c2edf3f3 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/semibin commit ee5d87e278238478c8ecab4a2f73723323f179a7

4:40ffba87bbcf

<?xml version="1.0"?>
<macros>
    <token name="@TOOL_VERSION@">2.0.2</token>
    <token name="@VERSION_SUFFIX@">2</token>
    <token name="@PROFILE@">24.0</token>
    <xml name="biotools">
        <xrefs>
            <xref type="bio.tools">semibin</xref>
        </xrefs>
    </xml>

            <when value="multi">
                <expand macro="input-fasta-multi"/>
            </when>
        </conditional>
    </xml>
    <xml name="mode_select">
        <param name="select" type="select" label="Binning mode">
            <option value="single" selected="true">Single sample binning (each sample is assembled and binned independently)</option>
            <option value="co">Co-assembly binning (samples are co-assembled together and binned together)</option>
            <option value="multi">Multi-sample binning (multiple samples are assembled and binned individually, but information from multiple samples is used together)</option>
        </param>
    </xml>
    <xml name="input-fasta-single">
        <param argument="--input-fasta" type="data" format="fasta,fasta.gz" label="Contig sequences"/>
    </xml>

        <param argument="--input-bam" type="data" format="bam" label="Read mapping to the contigs" help="Sorted BAM files"/>
    </xml>
    <xml name="input-bam-multi">
        <param argument="--input-bam" type="data" format="bam" multiple="true" label="Read mapping to the contigs" help="One file per sample, sorted BAM files"/>
    </xml>
    <token name="@BAM_FILES@"><![CDATA[
#if $mode.select == 'single'
#set $identifier = re.sub('[^\s\w\-\\.]', '_', str($input_bam.element_identifier))
ln -s '$input_bam' '${identifier}.bam' &&
#else
    #for $e in $input_bam
        #set $identifier = re.sub('[^\s\w\-\\.]', '_', str($e.element_identifier))
ln -s '$e' '${identifier}.bam' &&
    #end for
#end if
    ]]></token>
    <xml name="ref_select_cannot">
        <param name="select" type="select" label="Reference database">
            <option value="cached">Cached database</option>
            <option value="taxonomy">Pre-computed taxonomy</option>

    </xml>
    <xml name="orf-finder">
        <param argument="--orf-finder" type="select" label="ORF finder used to estimate the number of bins">
            <option value="fast-naive" selected="true">Fast-Naive</option>
            <option value="prodigal">Prodigal</option>
            <option value="fraggenescan">Fraggenescan</option>
        </param>
    </xml>
    <xml name="max-node">
        <param argument="--max-node" type="float" min="0" max="1" value="1" label="Fraction of contigs that considered to be binned"/>
    </xml>

    <xml name="data">
        <param argument="--data" type="data" format="csv" label="Train data"/>
    </xml>
    <xml name="data_output_single">
        <data name="single_data" format="csv" from_work_dir="output/data.csv" label="${tool.name} on ${on_string}: Training data">
            <filter>mode["select"]=="single" or mode["select"]=="co"</filter>
        </data>
        <data name="single_data_split" format="csv" from_work_dir="output/data_split.csv" label="${tool.name} on ${on_string}: Split training data">
            <filter>mode["select"]=="single" or mode["select"]=="co"</filter>
        </data>
    </xml>
    <xml name="data_output_multi">
        <collection name="multi_data" type="list" label="${tool.name} on ${on_string}: Training data per sample">
            <filter>mode["select"]=="multi"</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
        </collection>
        <collection name="multi_data_split" type="list" label="${tool.name} on ${on_string}: Split training data per sample">
            <filter>mode["select"]=="multi"</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_split.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
        </collection>
    </xml>
    <xml name="generate_sequence_features_extra_outputs">
        <data name="single_cov" format="csv" from_work_dir="output/*_data_cov.csv" label="${tool.name} on ${on_string}: Coverage">
            <filter>mode["select"]=="single" and extra_output and "coverage" in extra_output</filter>
        </data>
        <data name="single_split_cov" format="csv" from_work_dir="output/*_data_split_cov.csv" label="${tool.name} on ${on_string}: Coverage (split data)">
            <filter>mode["select"]=="single" and extra_output and "coverage" in extra_output</filter>
        </data>
        <collection name="co_cov" type="list" label="${tool.name} on ${on_string}: Coverage (co_cov)">
            <filter>mode["select"]=="co" and extra_output and "coverage" in extra_output</filter>
            <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_cov\.csv" format="csv" directory="output/" />
        </collection>
        <collection name="co_split_cov" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample">
            <filter>mode["select"]=="co" and extra_output and "coverage" in extra_output</filter>
            <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_split_cov\.csv" format="csv" directory="output/" />
        </collection>
        <collection name="multi_cov" type="list" label="${tool.name} on ${on_string}: Coverage (multi_cov)">
            <filter>mode["select"]=="multi" and extra_output and "coverage" in extra_output</filter>
            <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_cov.csv" format="csv" directory="output/samples/" />
        </collection>
        <collection name="multi_cov_sample" type="list" label="${tool.name} on ${on_string}: Coverage per sample">
            <filter>mode["select"]=="multi" and extra_output and "coverage" in extra_output</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_cov.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
        </collection>
        <collection name="multi_split_cov" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample (multi_split_cov)">
            <filter>mode["select"]=="multi" and extra_output and "coverage" in extra_output</filter>
            <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_split_cov.csv" format="csv" directory="output/samples/" />
        </collection>
        <collection name="multi_split_cov_sample" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample (multi_split_cov_sample)">
            <filter>mode["select"]=="multi" and extra_output and "coverage" in extra_output</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_split_cov.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
        </collection>
        <collection name="multi_contigs" type="list" label="${tool.name} on ${on_string}: Contigs">
            <filter>mode["select"]=="multi" and extra_output and "contigs" in extra_output</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/samples/" />
        </collection>
        
    </xml>
    <xml name="train_output">
        <data name="model" format="h5" from_work_dir="output/model.h5" label="${tool.name} on ${on_string}: Semi-supervised deep learning model" />
    </xml>
    <xml name="cannot_link_output">
        <data name="cannot" format="txt" from_work_dir="output/cannot/cannot.txt" label="${tool.name} on ${on_string}: Cannot-link constraints" />
    </xml>
    <token name="@HELP_HEADER@"><![CDATA[
What it does
============

SemiBin is a Semi-supervised siamese neural network for metagenomic binning

]]></token>
    <token name="@HELP_INPUT_FASTA@"><![CDATA[
- Contigs in fasta for 1 or several samples from single or co-assembly
]]></token>
    <token name="@HELP_INPUT_BAM@"><![CDATA[
- BAM with reads mapping to the contigs
]]></token>
    <token name="@HELP_CANNOT@"><![CDATA[
- Cannot-link constraints
]]></token>
    <token name="@HELP_DATA@"><![CDATA[
- Training data and split training data for the model
]]></token>
    <token name="@HELP_MODEL@"><![CDATA[
- Semi-supervised deep learning model
]]></token>
    <token name="@HELP_BINS@"><![CDATA[
- Reconstructed bins after reclustering
- Reconstructed bins before reclustering
]]></token>
    <xml name="citations">
        <citations>
            <citation type="doi">10.1038/s41467-022-29843-y</citation>
        </citations>
    </xml>

5:8ba0c2edf3f3

<?xml version="1.0"?>
<macros>
    <token name="@TOOL_VERSION@">2.1.0</token>
    <token name="@VERSION_SUFFIX@">0</token>
    <token name="@PROFILE@">21.01</token>
    <xml name="biotools">
        <xrefs>
            <xref type="bio.tools">semibin</xref>
        </xrefs>
    </xml>

            <when value="multi">
                <expand macro="input-fasta-multi"/>
            </when>
        </conditional>
    </xml>
    <xml name="mode_fasta_strobealign">
        <conditional name="mode">
            <expand macro="mode_select"/>
            <when value="single">
                <expand macro="input-fasta-single"/>
                <expand macro="input-txt"/>
            </when>
            <when value="co">
                <expand macro="input-fasta-single"/>
                <expand macro="input-txt"/>
            </when>
            <when value="multi">
                <expand macro="input-fasta-multi"/>
                <expand macro="input-txt"/>
            </when>
        </conditional>
    </xml>
    <xml name="mode_select">
        <param name="select" type="select" label="Binning mode">
            <option value="single" selected="true">Single sample binning (each sample is assembled and binned independently)</option>
            <option value="co">Co-assembly binning (samples are co-assembled together and binned together)</option>
            <option value="multi">Multi-sample binning (multiple samples are assembled and binned individually, but information from multiple samples is used together)</option>
        </param>
    </xml>
    <xml name="bam_or_strobealign">
        <param name="align_select" type="select" label="Use bam or strobealign abundance files?" help="Strobealign abundance files can only be used when samples used in binning above or equal 5">
            <option value="bam">BAM</option>
            <option value="txt">Strobealign-aemb file(s)</option>
        </param>
    </xml>
    <xml name="input-fasta-single">
        <param argument="--input-fasta" type="data" format="fasta,fasta.gz" label="Contig sequences"/>
    </xml>

        <param argument="--input-bam" type="data" format="bam" label="Read mapping to the contigs" help="Sorted BAM files"/>
    </xml>
    <xml name="input-bam-multi">
        <param argument="--input-bam" type="data" format="bam" multiple="true" label="Read mapping to the contigs" help="One file per sample, sorted BAM files"/>
    </xml>
    <!-- Strobealign files -->
    <xml name="input-txt">
        <param argument="--abundance" type="data" format="txt" label="Read mapping to the contigs" multiple="true" help="Strobealign abundance files"/>
    </xml>
    <token name="@BAM_FILES@"><![CDATA[
#if $mode.select == 'single'
#set $identifier = re.sub('[^\s\w\-\\.]', '_', str($mode.input_bam.element_identifier))
ln -s '$mode.input_bam' '${identifier}.bam' &&
#else
    #for $e in $mode.input_bam
        #set $identifier = re.sub('[^\s\w\-\\.]', '_', str($e.element_identifier))
ln -s '$e' '${identifier}.bam' &&
    #end for
#end if
    ]]></token>
    <token name="@STROBEALIGN_FILES@"><![CDATA[
#for $e in $mode.align_select.abundance
    #set $identifier = re.sub('[^\s\w\-\\.]', '_', str($e.element_identifier))
    ln -s '$e' '${identifier}.txt' &&
#end for
    ]]></token>
    <xml name="ref_select_cannot">
        <param name="select" type="select" label="Reference database">
            <option value="cached">Cached database</option>
            <option value="taxonomy">Pre-computed taxonomy</option>

    </xml>
    <xml name="orf-finder">
        <param argument="--orf-finder" type="select" label="ORF finder used to estimate the number of bins">
            <option value="fast-naive" selected="true">Fast-Naive</option>
            <option value="prodigal">Prodigal</option>
        </param>
    </xml>
    <xml name="max-node">
        <param argument="--max-node" type="float" min="0" max="1" value="1" label="Fraction of contigs that considered to be binned"/>
    </xml>

    <xml name="data">
        <param argument="--data" type="data" format="csv" label="Train data"/>
    </xml>
    <xml name="data_output_single">
        <data name="single_data" format="csv" from_work_dir="output/data.csv" label="${tool.name} on ${on_string}: Training data">
            <filter>input_type_select['mode']['select']=="single" or input_type_select['mode']['select']=="co"</filter>
        </data>
        <data name="single_data_split" format="csv" from_work_dir="output/data_split.csv" label="${tool.name} on ${on_string}: Split training data">
            <filter>input_type_select['mode']['select']=="single" or input_type_select['mode']['select']=="co"</filter>
        </data>
    </xml>
    <xml name="data_output_multi"> 
        <collection name="multi_data" type="list" label="${tool.name} on ${on_string}: Training data per sample">
            <filter>input_type_select['mode']['select']=="multi"</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
        </collection>
        <collection name="multi_data_split" type="list" label="${tool.name} on ${on_string}: Split training data per sample">
            <filter>input_type_select['mode']['select']=="multi"</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_split.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
        </collection>
    </xml>
    <xml name="generate_sequence_features_extra_outputs">
        <data name="single_cov" format="csv" from_work_dir="output/*_data_cov.csv" label="${tool.name} on ${on_string}: Coverage">
            <filter>input_type_select['mode']['select']=="single" and extra_output and "coverage" in extra_output</filter>
            <filter>input_type_select['input_type']=="bam"</filter>
        </data>
        <data name="single_split_cov" format="csv" from_work_dir="output/*_data_split_cov.csv" label="${tool.name} on ${on_string}: Coverage (split data)">
            <filter>input_type_select['mode']['select']=="single" and extra_output and "coverage" in extra_output</filter>
            <filter>input_type_select['input_type']=="bam"</filter>
        </data>
        <collection name="co_cov" type="list" label="${tool.name} on ${on_string}: Coverage (co_cov)">
            <filter>input_type_select['mode']['select']=="co" and extra_output and "coverage" in extra_output</filter>
            <filter>input_type_select['input_type']=="bam"</filter>
            <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_cov\.csv" format="csv" directory="output/" />
        </collection>
        <collection name="co_split_cov" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample">
            <filter>input_type_select['mode']['select']=="co" and extra_output and "coverage" in extra_output</filter>
            <filter>input_type_select['input_type']=="bam"</filter>
            <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_split_cov\.csv" format="csv" directory="output/" />
        </collection>
        <data name="cov_txt" label="${tool.name} on ${on_string}: Coverage (split data) per sample (aemb)" from_work_dir="output/cov_split.csv" format="csv">
            <filter>input_type_select['mode']['select']=="single" or input_type_select['mode']['select']=="co" and extra_output and "coverage" in extra_output</filter>
            <filter>input_type_select['input_type']=="txt"</filter>
        </data>
        <data name="co_cov_txt" label="${tool.name} on ${on_string}: Coverage (aemb)" format="csv" from_work_dir="output/cov.csv">
            <filter>input_type_select['mode']['select']=="single" or input_type_select['mode']['select']=="co" and extra_output and "coverage" in extra_output</filter>
            <filter>input_type_select['input_type']=="txt"</filter>
        </data>
        <collection name="multi_split_cov_txt" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample (multi_split_cov) (aemb)">
            <filter>input_type_select['mode']['select']=="multi" and extra_output and "coverage" in extra_output</filter>
            <filter>input_type_select['input_type']=="txt"</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_split_cov.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
        </collection>
        <collection name="multi_cov" type="list" label="${tool.name} on ${on_string}: Coverage (multi_cov)">
            <filter>input_type_select['mode']['select']=="multi" and extra_output and "coverage" in extra_output</filter>
            <filter>input_type_select['input_type']=="bam"</filter>
            <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_cov.csv" format="csv" directory="output/samples/" recurse="true"/>
        </collection>
        <collection name="multi_cov_sample" type="list" label="${tool.name} on ${on_string}: Coverage per sample">
            <filter>input_type_select['mode']['select']=="multi" and extra_output and "coverage" in extra_output</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_cov.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
        </collection>
        <collection name="multi_split_cov" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample (multi_split_cov)">
            <filter>input_type_select['mode']['select']=="multi" and extra_output and "coverage" in extra_output</filter>
            <filter>input_type_select['input_type']=="bam"</filter>
            <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_split_cov.csv" format="csv" directory="output/samples/" />
        </collection>
        <collection name="multi_split_cov_sample" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample (multi_split_cov_sample)">
            <filter>input_type_select['mode']['select']=="multi" and extra_output and "coverage" in extra_output</filter>
            <filter>input_type_select['input_type']=="bam"</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_split_cov.csv" format="csv" directory="output/samples/" match_relative_path="true" recurse="true"/>
        </collection>
        <collection name="multi_contigs" type="list" label="${tool.name} on ${on_string}: Contigs">
            <filter>input_type_select['mode']['select']=="multi" and extra_output and "contigs" in extra_output</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/samples/" />
        </collection>
    </xml>
    <xml name="generate_sequence_features_extra_outputs_main">
    <!-- Single -->
        <data name="single_cov" format="csv" from_work_dir="output/*_data_cov.csv" label="${tool.name} on ${on_string}: Coverage">
            <filter>mode['select']=="single" and extra_output and "coverage" in extra_output</filter>
        </data>
        <data name="single_split_cov" format="csv" from_work_dir="output/*_data_split_cov.csv" label="${tool.name} on ${on_string}: Coverage (split data)">
            <filter>mode['select']=="single" and extra_output and "coverage" in extra_output</filter>
        </data>
    <!-- Bam co aligned -->
        <collection name="co_cov_bam" type="list" label="${tool.name} on ${on_string}: Coverage (co_cov)">
            <filter>mode['select']=="co" and extra_output and "coverage" in extra_output</filter>
            <filter>mode['align_select']</filter>
            <filter>mode['align_select']['align_select']=="bam"</filter>
            <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_cov\.csv" format="csv" directory="output/" />
        </collection>
        <collection name="co_split_cov_bam" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample">
            <filter>mode['select']=="co" and extra_output and "coverage" in extra_output</filter>
            <filter>mode['align_select']</filter>
            <filter>mode['align_select']['align_select']=="bam"</filter>
            <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_split_cov\.csv" format="csv" directory="output/" />
        </collection>

    <!-- Bam Multi aligned -->
        <collection name="multi_cov_bam" type="list" label="${tool.name} on ${on_string}: Coverage (multi_cov)">
            <filter>mode['select']=="multi" and extra_output and "coverage" in extra_output</filter>
            <filter>mode['align_select']</filter>
            <filter>mode['align_select']['align_select']=="bam"</filter>
            <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_cov.csv" format="csv" directory="output/samples/" />
        </collection>
        <collection name="multi_cov_sample_bam" type="list" label="${tool.name} on ${on_string}: Coverage per sample">
            <filter>mode['select']=="multi" and extra_output and "coverage" in extra_output</filter>
            <filter>mode['align_select']</filter>
            <filter>mode['align_select']['align_select']=="bam"</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_cov.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
        </collection>
        <collection name="multi_split_cov_bam" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample (multi_split_cov)">
            <filter>mode['select']=="multi" and extra_output and "coverage" in extra_output</filter>
            <filter>mode['align_select']</filter>
            <filter>mode['align_select']['align_select']=="bam"</filter>
            <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_split_cov.csv" format="csv" directory="output/samples/" />
        </collection>
        <collection name="multi_split_cov_sample_bam" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample (multi_split_cov_sample)">
            <filter>mode['select']=="multi" and extra_output and "coverage" in extra_output</filter>
            <filter>mode['align_select']</filter>
            <filter>mode['align_select']['align_select']=="bam"</filter>
            <discover_datasets pattern=".*\.bam_(?P&lt;designation&gt;.*)_data_split_cov.csv" format="csv" directory="output/samples/" />
        </collection>
        <collection name="multi_contigs" type="list" label="${tool.name} on ${on_string}: Contigs">
            <filter>mode['select']=="multi" and extra_output and "contigs" in extra_output</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/samples/" />
        </collection>
        <!-- Txt co aligned -->
        <data name="co_split_cov_txt" label="${tool.name} on ${on_string}: Coverage (split data) per sample (aemb)" from_work_dir="output/cov_split.csv" format="csv">
            <filter>mode['select']=="co" and extra_output and "coverage" in extra_output</filter>
            <filter>mode['align_select']</filter>
            <filter>mode['align_select']['align_select']=="txt"</filter>
        </data>
        <data name="co_cov_txt" label="${tool.name} on ${on_string}: Coverage (aemb)" format="csv" from_work_dir="output/cov.csv">
            <filter>mode['select']=="co" and extra_output and "coverage" in extra_output</filter>
            <filter>mode['align_select']</filter>
            <filter>mode['align_select']['align_select']=="txt"</filter>
        </data>
        <!-- Txt multi aligned -->
        <collection name="multi_cov_txt" type="list" label="${tool.name} on ${on_string}: Coverage per sample (aemb)">
            <filter>mode['select']=="multi" and extra_output and "coverage" in extra_output</filter>
            <filter>mode['align_select']</filter>
            <filter>mode['align_select']['align_select'] =="txt"</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_cov.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
        </collection>
        <collection name="multi_split_cov_txt" type="list" label="${tool.name} on ${on_string}: Coverage (split data) per sample (multi_split_cov) (aemb)">
            <filter>mode['select']=="multi" and extra_output and "coverage" in extra_output</filter>
            <filter>mode['align_select']</filter>
            <filter>mode['align_select']['align_select']=="txt"</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_split_cov.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
        </collection>
    </xml>
    <xml name="train_output">
        <data name="model" format="h5" from_work_dir="output/model.h5" label="${tool.name} on ${on_string}: Semi-supervised deep learning model" />
    </xml>
    <xml name="cannot_link_output">
        <data name="cannot" format="txt" from_work_dir="output/cannot/cannot.txt" label="${tool.name} on ${on_string}: Cannot-link constraints" />
    </xml>
    <token name="@HELP_HEADER@"><![CDATA[

What it does
============

SemiBin is a Semi-supervised siamese neural network for metagenomic binning
    ]]></token>
    <token name="@HELP_INPUT_FASTA@"><![CDATA[
- Contigs in fasta for 1 or several samples from single or co-assembly
    ]]></token>
    <token name="@HELP_INPUT_BAM@"><![CDATA[
- BAM with reads mapping to the contigs
    ]]></token>
    <token name="@HELP_INPUT_STROBEALIGN@"><![CDATA[
- TXT alignment files that are the output of strobealign-aemb
    ]]></token>
    <token name="@HELP_CANNOT@"><![CDATA[
- Cannot-link constraints
    ]]></token>
    <token name="@HELP_DATA@"><![CDATA[
- Training data and split training data for the model
    ]]></token>
    <token name="@HELP_MODEL@"><![CDATA[
- Semi-supervised deep learning model
    ]]></token>
    <token name="@HELP_BINS@"><![CDATA[
- Reconstructed bins after reclustering
- Reconstructed bins before reclustering
    ]]></token>
    <xml name="citations">
        <citations>
            <citation type="doi">10.1038/s41467-022-29843-y</citation>
        </citations>
    </xml>