annotate pangolin.xml @ 8:3a656a4a43ed draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/pangolin commit 5a3f70ab430c70b260dd6e0f5b6c53aed2ca5520"

<tool id="pangolin" name="Pangolin" version="@TOOL_VERSION@+galaxy0" profile="20.01">
    <description>Phylogenetic Assignment of Outbreak Lineages</description>
    <macros>
        <token name="@TOOL_VERSION@">3.1.11</token>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">pangolin</requirement>
        <requirement type="package" version="0.23.0">csvtk</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        #if str($db.source) == "download"
            pangolin --update-data --datadir datadir &&
        #else if str($db.source) == "builtin"
            ln -s $db.db_release.fields.path datadir &&
        #end if
        pangolin
        --threads \${GALAXY_SLOTS:-1}
        #if str($db.source) == "download" or str($db.source) == "builtin"
            --datadir 'datadir'
        #end if
        $usher
        $alignment
        --outfile report.csv 
        --max-ambig $max_ambig
        --min-length $min_length
        '$input1'
        && csvtk csv2tab report.csv
        #if not $include_header:
            | tail -n+2 
        #end if
        > '$output1'
        #if $alignment
            && mv sequences.aln.fasta '$align1'
        #end if 
    ]]></command>
    <inputs>
        <param type="data" name="input1" format="fasta" label="Input FASTA File(s)" /> 
        <param argument="--usher" type="boolean" label="Use UShER model" truevalue="--usher" falsevalue="" help="Use UShER model instead of default pangoLEARN model" />
        <param argument="--alignment" type="boolean" label="Generate output alignment" 
            truevalue="--alignment" falsevalue="" /> 
        <param argument="--max-ambig" type="float" label="Maximum proportion of Ns allowed" 
            value="0.5" min="0" max="1" help="Maximum proportion of Ns allowed for pangolin to attempt assignment" />
        <param argument="--min-length" type="integer" label="Minimum query length allowed" 
            value="10000" min="0" help="Minimum query length allowed for pangolin to attempt assignment"/>
        <param name="include_header" type="boolean" label="Include header line in output file" 
            truevalue="true" falsevalue="false" />
        <conditional name="db">
            <param type="select" name="source" label="pangoLEARN source" help="Where to find the pangoLEARN database">
                <option value="download">Download latest from web</option>
                <option value="builtin">Use database from Galaxy server</option>
                <option value="default">Use default database built in to pangolin (not recommended)</option>
            </param>
            <when value="download">
                <!-- these are currently not supported by the pangolin downloader -->
                <!-- <param name="max_retries" label="Max download retries" help="How many times to retry downloading the pangoLEARN database" type="integer" value="5" /> -->
                <!-- <param name="timeout" label="Download timeout" help="How many seconds to wait when downloading the pangoLEARN database" type="float" value="60.0" /> -->
            </when>
            <when value="builtin">
                <param name="db_release" label="pangoLEARN release" type="select">
                    <options from_data_table="pangolearn">
                        <column name="value" index="0" />
                        <column name="name" index="1" />
                        <column name="path" index="3" />
                        <filter type="sort_by" column="0" />
                        <filter type="static_value" column="2" value="3.0" />
                    </options>
                </param>
            </when>
            <when value="default">
            </when>
      </conditional>
    </inputs>
    <outputs>
        <data name="output1" format="tabular" label="pangolin on ${on_string}">
            <actions>
                <action name="column_names" type="metadata" default="taxon,lineage,conflict,ambiguity_score,scorpio_call,scorpio_support,scorpio_conflict,version,pangolin_version,pangoLEARN_version,pango_version,status,note" />
            </actions>
        </data>
        <data name="align1" format="fasta" label="pangolin alignment on ${on_string}">
            <filter>alignment</filter>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="1">
            <param name="input1" value="test1.fasta"/>
            <conditional name="db">
                <param name="source" value="download" />
            </conditional>
            <output name="output1" ftype="tabular">
                <assert_contents>
                    <has_text_matching expression="B.1.1\t0.0" />
                    <has_text text="passed_qc" />
                    <has_n_lines n="1" />
                </assert_contents>
            </output>
        </test>
        <!-- test UShER mode -->
        <test expect_num_outputs="1">
            <param name="input1" value="test1.fasta"/>
            <param name="usher" value="true" />
            <conditional name="db">
                <param name="source" value="download" />
            </conditional>
            <output name="output1" ftype="tabular">
                <assert_contents>
                    <has_text_matching expression="B.1.1\t0.0\t*PUSHER" />
                    <has_text text="passed_qc" />
                    <has_n_lines n="1" />
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="2">
            <param name="alignment" value="--alignment" />
            <param name="input1" value="test1.fasta" />
            <conditional name="db">
                <param name="source" value="download" />
            </conditional>
            <output name="output1" ftype="tabular">
                <assert_contents>
                    <has_text_matching expression="B.1.1\t0.0" />
                    <has_text text="passed_qc" />
                    <has_n_lines n="1" />
                </assert_contents>
            </output>
            <output name="align1" file="aln1.fasta" ftype="fasta">
                <assert_contents>
                    <has_text text="Consensus_EB232-crude-prep_S297" />
                    <has_n_lines n="2" />
                </assert_contents>
            </output>
        </test>
        <!-- testing with builtin data is too large -->
        <!-- <test expect_num_outputs="1">
            <param name="input1" value="test1.fasta"/>
            <conditional name="db">
                <param name="source" value="builtin" />
            </conditional>
            <output name="output1" ftype="tabular">
                <assert_contents>
                    <has_text text="Consensus_EB232-crude-prep_S297" />
                    <has_n_lines n="1" />
                </assert_contents>
            </output>
        </test> 
        <test expect_num_outputs="1">
            <param name="input1" value="multiple_alignment.fasta.gz"/>
            <conditional name="db">
                <param name="source" value="builtin" />
            </conditional>
            <output name="output1" ftype="tabular">
                <assert_contents>
                    <has_text text="Serbia" />
                    <has_text text="Poland" />
                    <has_text text="USA" />
                    <has_n_lines n="34" />
                </assert_contents>
            </output>
        </test> -->
        <!-- test include-header option -->
        <test expect_num_outputs="1">
            <param name="input1" value="multiple_alignment.fasta.gz"/>
            <param name="include_header" value="true" />
            <conditional name="db">
                <param name="source" value="download" />
            </conditional>
            <output name="output1" ftype="tabular">
                <assert_contents>
                    <has_text text="pangoLEARN_version" />
                    <has_text text="lineage" />
                    <has_text text="Serbia" />
                    <has_text text="Poland" />
                    <has_text text="USA" />
                    <has_n_lines n="35" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

`Pangolin <https://cov-lineages.org/pangolin.html>`_ (Phylogenetic Assignment of Named Global Outbreak LINeages) 
is used to assign a SARS-CoV-2 genome sequence the most likely lineage based on the PANGO nomenclature system.

Pangolin uses the `pangoLEARN <https://github.com/cov-lineages/pangoLEARN>`_ stored model for lineage assignment. This
model is updated more frequently than the pangolin tool is. In general one should use the most recent model for lineage
assignment, and the default option for this tool is to download the latest version of the model before the pangolin
tool runs. A pangoLEARN data manager exists so that the Galaxy admin can download specific versions of the pangoLEARN
model as required. Finally the pangolin tool can use its default built-in model, but this is **not recommended** as the
default model rapidly becomes out of date.

    ]]></help>
    <citations>
      <citation type="doi">10.1093/ve/veab064</citation>
    </citations>
</tool>