annotate taxonomy_wf.xml @ 0:91230b9141c1 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/checkm commit 2a3b068a98bf0e913dc03e0d5c2182cfd102cf27

<tool id="checkm_taxonomy_wf" name="CheckM taxonomy_wf" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>
        Analyze all genome bins with the same marker set
    </description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="biotools"/>
    <expand macro="requirements"/>
    <expand macro="version"/>
    <command detect_errors="exit_code"><![CDATA[
@BIN_INPUTS@

checkm taxonomy_wf
    '$rank_taxon.rank'
    '$rank_taxon.taxon.fields.value'
    'bins'
    'output'
    $analyze.ali
    $analyze.nt
    $analyze.genes
    $qa.individual_markers
    $qa.skip_adj_correction
    $qa.skip_pseudogene_correction
    --aai_strain $qa.aai_strain
    $qa.ignore_thresholds
    --e_value $qa.e_value
    --length $qa.length
    --file '$results'
    --tab_table
    --extension 'fasta'
    --threads \${GALAXY_SLOTS:-1}
    ]]></command>
    <inputs>
        <expand macro="rank_taxon"/>
        <expand macro="bin_inputs"/>
        <section name="analyze" title="Marker gene identification">
            <expand macro="analyze_params" />
        </section>
        <section name="qa" title="Bin assessment">
            <expand macro="qa_params" />
        </section>
        <param name="extra_outputs" type="select" multiple="true" optional="true" label="Extra outputs">
            <option value="marker_file">Marker genes</option>
            <option value="hmmer_analyze">Marker gene HMM hits to each bin</option>
            <option value="bin_stats_analyze">Marker gene bin stats</option>
            <option value="checkm_hmm_info">Marker gene HMM info for each bin</option>
            <expand macro="analyze_extra_output_options" />
            <option value="bin_stats_ext">Marker gene bin extensive stats</option>
            <expand macro="qa_extra_output_options" />
        </param>
    </inputs>
    <outputs>
        <data name="results" format="tabular" label="${tool.name} on ${on_string}: Bin statistics"/>
        <!-- taxon_set outputs -->
        <data name="marker_file" format="tabular" from_work_dir="output/*.ms" label="${tool.name} on ${on_string}: Marker genes">
            <filter>'marker_file' in extra_outputs</filter>
        </data>
        <!--analyze outputs-->
        <collection name="hmmer_analyze" type="list" label="${tool.name} on ${on_string}: Marker gene HMM hits to each bin">
            <filter>'hmmer_analyze' in extra_outputs</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)/hmmer\.analyze\.txt" format="txt" directory="output/bins/" recurse="true" match_relative_path="true"/>
        </collection>
        <data name="bin_stats_analyze" format="tabular" from_work_dir="output/storage/bin_stats.analyze.tsv" label="${tool.name} on ${on_string}: Marker gene bin stats">
            <filter>'bin_stats_analyze' in extra_outputs</filter>
        </data>
        <data name="checkm_hmm_info" format="zip" from_work_dir="output/storage/checkm_hmm_info.pkl.gz" label="${tool.name} on ${on_string}: Marker gene HMM info for each bin" >
            <filter>'checkm_hmm_info' in extra_outputs</filter>
        </data>
        <collection name="hmmer_analyze_ali" type="list" label="${tool.name} on ${on_string}: HMMER alignment file for each bin">
            <filter>analyze['ali'] and 'hmmer_analyze_ali' in extra_outputs</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.*)/hmmer\.analyze\.ali\.txt" format="txt" directory="output/bins/" recurse="true" match_relative_path="true"/>
        </collection>
        <!--qa outputs-->
        <data name="bin_stats_ext" format="tabular" from_work_dir="output/storage/bin_stats_ext.tsv" label="${tool.name} on ${on_string}: Marker gene bin extensive stats">
            <filter>'bin_stats_ext' in extra_outputs</filter>
        </data>
        <expand macro="qa_extra_outputs" />
        <data name="marker_gene_stats" format="tabular" from_work_dir="output/storage/marker_gene_stats.tsv"  label="${tool.name} on ${on_string}: Marker gene statistics">
            <filter>'marker_gene_stats' in extra_outputs</filter>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="1">
            <conditional name="bins">
                <param name="select" value="collection"/>
                <param name="bins_coll">
                    <collection type="list">
                        <element name="637000110" ftype="fasta" value="637000110.fna"/>
                    </collection>
                </param>
            </conditional>
            <conditional name="rank_taxon">
                <param name="rank" value="life"/>
                <param name="taxon" value="Prokaryote"/>
            </conditional>
            <section name="analyze">
                <param name="ali" value="false"/>
                <param name="nt" value="false"/>
                <param name="genes" value="false"/>
            </section>
            <section name="qa">
                <param name="individual_markers" value="false"/>
                <param name="skip_adj_correction" value="false"/>
                <param name="skip_pseudogene_correction" value="false"/>
                <param name="aai_strain" value="0.9"/>
                <param name="ignore_thresholds" value="false"/>
                <param name="e_value" value="1e-10"/>
                <param name="length" value="0.7"/>
            </section>
            <param name="extra_outputs" value=""/>
            <output name="results" ftype="tabular">
                <assert_contents>
                    <has_text text="637000110"/>
                    <has_text text="Marker lineage"/>
                    <has_text text="Prokaryote"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="8">
            <conditional name="bins">
                <param name="select" value="collection"/>
                <param name="bins_coll">
                    <collection type="list">
                        <element name="637000110" ftype="fasta" value="637000110.fna"/>
                    </collection>
                </param>
            </conditional>
            <conditional name="rank_taxon">
                <param name="rank" value="life"/>
                <param name="taxon" value="Prokaryote"/>
            </conditional>
            <section name="analyze">
                <param name="ali" value="true"/>
                <param name="nt" value="false"/>
                <param name="genes" value="false"/>
            </section>
            <section name="qa">
                <param name="individual_markers" value="false"/>
                <param name="skip_adj_correction" value="false"/>
                <param name="skip_pseudogene_correction" value="false"/>
                <param name="aai_strain" value="0.9"/>
                <param name="ignore_thresholds" value="false"/>
                <param name="e_value" value="1e-10"/>
                <param name="length" value="0.7"/>
            </section>
            <param name="extra_outputs" value="marker_file,hmmer_analyze,hmmer_analyze_ali,bin_stats_analyze,bin_stats_ext,checkm_hmm_info,marker_gene_stats"/>
            <output name="results" ftype="tabular">
                <assert_contents>
                    <has_text text="637000110"/>
                    <has_text text="Marker lineage"/>
                    <has_text text="Prokaryote"/>
                </assert_contents>
            </output>
            <output name="marker_file" ftype="tabular">
                <assert_contents>
                    <has_text text="[Taxon Marker File]"/>
                    <has_text text="Prokaryote"/>
                    <has_text text="PF01000.21"/>
                </assert_contents>
            </output>
            <output_collection name="hmmer_analyze" count="1">
                <element name="637000110" ftype="txt">
                    <assert_contents>
                        <has_text text="target name"/>
                        <has_text text="AC_000091_570"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output name="bin_stats_analyze" ftype="tabular">
                <assert_contents>
                    <has_text text="637000110"/>
                    <has_text text="GC"/>
                    <has_text text="GC std"/>
                </assert_contents>
            </output>
            <output name="checkm_hmm_info" ftype="zip">
                <assert_contents>
                    <has_size value="4373" delta="100"/>
                </assert_contents>
            </output>
            <output_collection name="hmmer_analyze_ali" count="1">
                <element name="637000110" ftype="txt">
                    <assert_contents>
                        <has_text text="hmmsearch"/>
                        <has_text text="Query"/>
                        <has_text text="TOBE_2"/>
                    </assert_contents>
                </element>
            </output_collection>
            <output name="bin_stats_ext" ftype="tabular">
                <assert_contents>
                    <has_text text="637000110"/>
                    <has_text text="marker lineage"/>
                </assert_contents>
            </output>
            <output name="marker_gene_stats" ftype="tabular">
                <assert_contents>
                    <has_text text="637000110"/>
                    <has_text text="AC_000091_79"/>
                    <has_text text="PF00318.15"/>
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[
@HELP_HEADER@

This command runs recommended workflow to analyze all genome bins with the same marker set. A common example would be a set of genomes from the same taxonomic group. 

The workflow for using a taxonomic-specific marker set consists of 3 mandatory (M) steps and 1 recommended (R) step:

- (R) The taxon_list command produces a table indicating all taxa for which a marker set can be produced. All support taxa at a given taxonomic rank can be produced by passing taxon_list the --rank flag
- (M) The taxon_set command is used to produce marker sets for a specific taxon:
- (M) The analyze command identifies marker genes within each genome bin and estimate completeness and contamination. All putative genomes to be analyzed must be provided.
- (M) The qa command is used to produce different tables summarizing the quality of each genome bin.

Inputs
======


Outputs
=======

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