annotate semibin.xml @ 2:99ff9221182c draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/semibin commit 13abac83068b126399ec415141007a48c2efaa84

<tool id="semibin" name="SemiBin" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>
        for Semi-supervised Metagenomic Binning
    </description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="biotools"/>
    <expand macro="requirements"/>
    <expand macro="version"/>
    <command detect_errors="exit_code"><![CDATA[
#import re
@BAM_FILES@
@FASTA_FILES@
SemiBin2
#if $mode.select == 'single' or $mode.select == 'co'
    single_easy_bin
    #if $mode.select == 'single' and str($mode.environment) != ''
    --environment '$mode.environment'
    #end if
    #if $mode.ref.select == "cached"
    --reference-db-data-dir '$mode.ref.cached_db.fields.path'
    #else
    --taxonomy-annotation-table '$mode.ref.taxonomy_annotation_table'
    #end if
#else
    multi_easy_bin
    --separator '$separator'
    #if $mode.ref.select == "cached"
    --reference-db-data-dir '$mode.ref.cached_db.fields.path'
    #else
    --taxonomy-annotation-table 
        #for $e in $mode.ref.taxonomy_annotation_table
            '$e' 
        #end for
    #end if
#end if
    --input-fasta 'contigs.fasta'
    --input-bam *.bam
    --output 'output'
    --cannot-name 'cannot'
    @MIN_LEN@
    --orf-finder '$orf_finder'
    --random-seed $random_seed

#if str($annot.ml_threshold) != ''
    --ml-threshold $annot.ml_threshold
#end if
    --epoches $training.epoches
    --batch-size $training.batch_size
    --max-node $bin.max_node
    --max-edges $bin.max_edges
    --minfasta-kbs $bin.minfasta_kbs
#if ($mode.select == 'single' or $mode.select == 'co') and "pre_reclustering_bins" in $extra_output
    --write-pre-reclustering-bins
#end if
    --compression none
    --threads \${GALAXY_SLOTS:-1}
    --processes \${GALAXY_SLOTS:-1}
&& 
echo "output" &&
ls output
    ]]></command>
    <inputs>
        <conditional name="mode">
            <expand macro="mode_select"/>
            <when value="single">
                <expand macro="input-fasta-single"/>
                <expand macro="input-bam-single"/>
                <expand macro="ref-single"/>
                <expand macro="environment"/>
            </when>
            <when value="co">
                <expand macro="input-fasta-single"/>
                <expand macro="input-bam-multi"/>
                <expand macro="ref-single"/>
            </when>
            <when value="multi">
                <expand macro="input-fasta-multi"/>
                <expand macro="input-bam-multi"/>
                <expand macro="ref-multi"/>
            </when>
        </conditional>
        <expand macro="min_len"/>
        <expand macro="orf-finder"/>
        <expand macro="random-seed"/>
        <section name="annot" title="Contig annotations" expanded="true">
            <expand macro="ml-threshold"/>
        </section>
        <section name="training" title="Training">
            <expand macro="epoches"/>
            <expand macro="batch-size"/>
        </section>
        <section name="bin" title="Binning">
            <expand macro="max-node"/>
            <expand macro="max-edges"/>
            <expand macro="minfasta-kbs"/>
        </section>
        <param name="extra_output" type="select" multiple="true" optional="true" label="Extra outputs" help="In addition to the training data">
            <option value="data">Training data</option>
            <option value="coverage">Coverage files</option>
            <option value="contigs">Contigs (if multiple sample)</option>
            <option value="pre_reclustering_bins">Pre-reclustering bins (only single sample and co-assembly)</option>
        </param>
    </inputs>
    <outputs>
        <collection name="output_pre_recluster_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins before reclustering">
            <filter>mode["select"]!="multi" and extra_output and "pre_reclustering_bins" in extra_output</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_prerecluster_bins"/>
        </collection>
        <collection name="output_after_recluster_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins after reclustering">
            <filter>mode["select"]!="multi" and extra_output and "pre_reclustering_bins" in extra_output</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_recluster_bins"/>
        </collection>
        <collection name="output_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins">
            <filter>mode["select"]!="multi" and not "pre_reclustering_bins" in extra_output</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/output_bins"/>
        </collection>
        <collection name="multi_bins" type="list" label="${tool.name} on ${on_string}: Reconstructed bins before reclustering (multi_bins)">
            <filter>mode["select"]=="multi"</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*).fa" format="fasta" directory="output/bins"/>
        </collection>
        <data name="single_data" format="csv" from_work_dir="output/data.csv" label="${tool.name} on ${on_string}: Training data">
            <filter>(mode["select"]=="single" or mode["select"]=="co") and extra_output and "data" in extra_output</filter>
        </data>
        <data name="single_data_split" format="csv" from_work_dir="output/data_split.csv" label="${tool.name} on ${on_string}: Split training data">
            <filter>(mode["select"]=="single" or mode["select"]=="co") and extra_output and "data" in extra_output</filter>
        </data>
        <collection name="multi_data" type="list" label="${tool.name} on ${on_string}: Training data per sample">
            <filter>mode["select"]=="multi" and extra_output and "data" in extra_output</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
        </collection>
        <collection name="multi_data_split" type="list" label="${tool.name} on ${on_string}: Split training data per sample">
            <filter>mode["select"]=="multi" and extra_output and "data" in extra_output</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)\/data_split.csv" format="csv" directory="output/samples/" recurse="true" match_relative_path="true"/>
        </collection>
        <expand macro="generate_sequence_features_extra_outputs"/>
    </outputs>
    <tests>
        <test expect_num_outputs="5">
            <conditional name="mode">
                <param name="select" value="single"/>
                <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
                <param name="input_bam" ftype="bam" value="input_single.bam"/>
                <conditional name="ref">
                    <param name="select" value="taxonomy"/>
                    <param name="taxonomy_annotation_table" value="taxonomy.tsv"/>
                </conditional>
                <param name="environment" value="human_gut"/>
            </conditional>
            <conditional name="min_len">
                <param name="method" value="min-len"/>
                <param name="min_len" value="0" />
            </conditional>
            <param name="orf_finder" value="prodigal"/>
            <param name="random-seed" value="0"/>
            <section name="annot">
                <param name="ml_threshold" value=""/>
            </section>
            <section name="training">
                <param name="epoches" value="20"/>
                <param name="batch_size" value="2048"/>
            </section>
            <section name="bin">
                <param name="max_node" value="1"/>
                <param name="max_edges" value="200"/>
                <param name="minfasta_kbs" value="200"/>
            </section>
            <param name="extra_output" value="data,coverage,contigs"/>
            <output_collection name="output_bins" count="0"/>
            <output name="single_data" ftype="csv">
                <assert_contents>
                    <has_text text="g1k_0"/>
                    <has_text text="g4k_7"/>
                </assert_contents>
            </output>
            <output name="single_data_split" ftype="csv">
                <assert_contents>
                    <has_text text="g1k_0_1"/>
                    <has_text text="g1k_6_2"/>
                </assert_contents>
            </output>
            <output name="single_cov" ftype="csv">
                <assert_contents>
                    <has_text text="g1k_0"/>
                    <has_text text="0.027"/>
                </assert_contents>
            </output>
            <output name="single_split_cov" ftype="csv">
                <assert_contents>
                    <has_size value="1" delta="1"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="3">
            <conditional name="mode">
                <param name="select" value="co"/>
                <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
                <param name="input_bam" ftype="bam" value="input_coassembly_sorted1.bam,input_coassembly_sorted2.bam,input_coassembly_sorted3.bam,input_coassembly_sorted4.bam,input_coassembly_sorted5.bam"/>
                <conditional name="ref">
                    <param name="select" value="taxonomy"/>
                    <param name="taxonomy_annotation_table" value="taxonomy.tsv"/>
                </conditional>
            </conditional>
            <conditional name="min_len">
                <param name="method" value="ratio"/>
                <param name="ratio" value="0.05"/>
            </conditional>
            <param name="orf_finder" value="fast-naive"/>
            <param name="random-seed" value="0"/>
            <section name="annot">
                <param name="ml_threshold" value=""/>
            </section>
            <section name="training">
                <param name="epoches" value="20"/>
                <param name="batch_size" value="2048"/>
            </section>
            <section name="bin">
                <param name="max_node" value="1"/>
                <param name="max_edges" value="200"/>
                <param name="minfasta_kbs" value="200"/>
            </section>
            <param name="extra_output" value="coverage"/>
            <output_collection name="output_bins" count="0"/>
            <output_collection name="co_cov" count="5">
                <element name="0" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_0"/>
                        <has_text text="g2k_7"/>
                    </assert_contents>
                </element>
                <element name="1" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_0"/>
                        <has_text text="g2k_7"/>
                    </assert_contents>
                </element>
                <element name="4" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_0"/>
                        <has_text text="g2k_7"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="co_split_cov" count="5">
                <element name="0" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_0_1"/>
                        <has_text text="g2k_7_2"/>
                    </assert_contents>
                </element>
                <element name="1" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_0_1"/>
                        <has_text text="g2k_7_2"/>
                    </assert_contents>
                </element>
                <element name="2" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_0_1"/>
                        <has_text text="g2k_7_2"/>
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <test expect_num_outputs="3">
            <conditional name="mode">
                <param name="select" value="co"/>
                <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
                <param name="input_bam" ftype="bam" value="input_coassembly_sorted1.bam,input_coassembly_sorted2.bam,input_coassembly_sorted3.bam,input_coassembly_sorted4.bam,input_coassembly_sorted5.bam"/>
                <conditional name="ref">
                    <param name="select" value="taxonomy"/>
                    <param name="taxonomy_annotation_table" value="taxonomy.tsv"/>
                </conditional>
            </conditional>
            <conditional name="min_len">
                <param name="method" value="ratio"/>
                <param name="ratio" value="0.05"/>
            </conditional>
            <param name="orf_finder" value="fraggenescan"/>
            <param name="random-seed" value="0"/>
            <section name="annot">
                <param name="ml_threshold" value=""/>
            </section>
            <section name="training">
                <param name="epoches" value="20"/>
                <param name="batch_size" value="2048"/>
            </section>
            <section name="bin">
                <param name="max_node" value="1"/>
                <param name="max_edges" value="200"/>
                <param name="minfasta_kbs" value="200"/>
            </section>
            <param name="extra_output" value="coverage"/>
            <output_collection name="output_bins" count="0"/>
            <output_collection name="co_cov" count="5">
                <element name="0" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_0"/>
                        <has_text text="g2k_7"/>
                    </assert_contents>
                </element>
                <element name="1" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_0"/>
                        <has_text text="g2k_7"/>
                    </assert_contents>
                </element>
                <element name="4" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_0"/>
                        <has_text text="g2k_7"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="co_split_cov" count="5">
                <element name="0" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_0_1"/>
                        <has_text text="g2k_7_2"/>
                    </assert_contents>
                </element>
                <element name="1" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_0_1"/>
                        <has_text text="g2k_7_2"/>
                    </assert_contents>
                </element>
                <element name="2" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_0_1"/>
                        <has_text text="g2k_7_2"/>
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <test expect_num_outputs="1">
            <conditional name="mode">
                <param name="select" value="single"/>
                <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
                <param name="input_bam" ftype="bam" value="input_single.bam"/>
                <conditional name="ref">
                    <param name="db_selector" value="cached"/>
                    <param name="cached_db" value="test-db"/>
                </conditional>
            </conditional>
            <conditional name="min_len">
                <param name="method" value="ratio"/>
                <param name="ratio" value="0.05"/>
            </conditional>
            <param name="orf_finder" value="fraggenescan"/>
            <param name="random-seed" value="0"/>
            <section name="annot">
                <param name="ml_threshold" value=""/>
            </section>
            <section name="training">
                <param name="epoches" value="20"/>
                <param name="batch_size" value="2048"/>
            </section>
            <section name="bin">
                <param name="max_node" value="1"/>
                <param name="max_edges" value="200"/>
                <param name="minfasta_kbs" value="200"/>
            </section>
            <param name="extra_output" value=""/>
            <output_collection name="output_bins" count="1">
                <element name="SemiBin_30" ftype="fasta">
                    <assert_contents>
                        <has_text text=">g3k_0"/>
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <test expect_num_outputs="2">
            <conditional name="mode">
                <param name="select" value="single"/>
                <param name="input_fasta" ftype="fasta" value="input_single.fasta"/>
                <param name="input_bam" ftype="bam" value="input_single.bam"/>
                <conditional name="ref">
                    <param name="db_selector" value="cached"/>
                    <param name="cached_db" value="test-db"/>
                </conditional>
            </conditional>
            <conditional name="min_len">
                <param name="method" value="ratio"/>
                <param name="ratio" value="0.05"/>
            </conditional>
            <param name="orf_finder" value="fraggenescan"/>
            <param name="random-seed" value="0"/>
            <section name="annot">
                <param name="ml_threshold" value=""/>
            </section>
            <section name="training">
                <param name="epoches" value="20"/>
                <param name="batch_size" value="2048"/>
            </section>
            <section name="bin">
                <param name="max_node" value="1"/>
                <param name="max_edges" value="200"/>
                <param name="minfasta_kbs" value="200"/>
            </section>
            <param name="extra_output" value="pre_reclustering_bins"/>
            <output_collection name="output_pre_recluster_bins" count="3">
                <element name="SemiBin_0" ftype="fasta">
                    <assert_contents>    
                        <has_text text="g1k_0"/>
                    </assert_contents>
                </element>
                <element name="SemiBin_1" ftype="fasta">
                    <assert_contents>    
                        <has_text text="g2k_0"/>
                    </assert_contents>
                </element>
                <element name="SemiBin_2" ftype="fasta">
                    <assert_contents>    
                        <has_text text="g3k_0"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="output_after_recluster_bins" count="1">
                <element name="SemiBin_30" ftype="fasta">
                    <assert_contents>
                        <has_text text="g3k_0"/>
                    </assert_contents>
                </element>
            </output_collection>
        </test>
        <test expect_num_outputs="8">
            <conditional name="mode">
                <param name="select" value="multi"/>
                <conditional name="multi_fasta">
                    <param name="select" value="concatenated"/>
                    <param name="input_fasta" ftype="fasta" value="input_multi.fasta.gz"/>
                </conditional>
                <param name="input_bam" ftype="bam" value="input_multi_sorted1.bam,input_multi_sorted2.bam,input_multi_sorted3.bam,input_multi_sorted4.bam,input_multi_sorted5.bam,input_multi_sorted6.bam,input_multi_sorted7.bam,input_multi_sorted8.bam,input_multi_sorted9.bam,input_multi_sorted10.bam"/>
                <conditional name="ref">
                    <param name="select" value="taxonomy"/>
                    <param name="taxonomy_annotation_table" value="taxonomy.tsv,taxonomy_2.tsv,taxonomy_3.tsv,taxonomy_4.tsv,taxonomy_5.tsv,taxonomy_6.tsv,taxonomy_7.tsv,taxonomy_8.tsv,taxonomy_9.tsv,taxonomy_10.tsv"/>
                </conditional>
            </conditional>
            <conditional name="min_len">
                <param name="method" value="ratio"/>
                <param name="ratio" value="0.05"/>
            </conditional>
            <param name="orf_finder" value="fraggenescan"/>
            <param name="random_seed" value="0"/>
            <section name="annot">
                <param name="ml_threshold" value=""/>
            </section>
            <section name="training">
                <param name="epoches" value="20"/>
                <param name="batch_size" value="2048"/>
            </section>
            <section name="bin">
                <param name="max_node" value="1"/>
                <param name="max_edges" value="200"/>
                <param name="minfasta_kbs" value="200"/>
            </section>
            <param name="extra_output" value="data,coverage,contigs"/>
            <output_collection name="multi_bins" count="0"/>
            <output_collection name="multi_data" count="10">
                <element name="S8" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_0,"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="multi_data_split" count="10">
                <element name="S8" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_0_1,"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="multi_cov" count="10">
                <element name="8" ftype="csv">
                    <assert_contents>
                        <has_text text="S1:g1k_5,"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="multi_cov_sample" count="10">
                <element name="S8" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_3"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="multi_split_cov" count="10">
                <element name="8" ftype="csv">
                    <assert_contents>
                        <has_text text="S1:g1k_5_1,0."/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="multi_split_cov_sample" count="10">
                <element name="S8" ftype="csv">
                    <assert_contents>
                        <has_text text="g1k_3_1"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output_collection name="multi_contigs" count="10">
                <element name="S8" ftype="fasta">
                    <assert_contents>
                        <has_text text=">g1k_0"/>
                    </assert_contents>
                </element>
            </output_collection>
        </test>
    </tests>
    <help><![CDATA[
@HELP_HEADER@

Inputs
======

@HELP_INPUT_FASTA@
@HELP_INPUT_BAM@

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