annotate pangolin.xml @ 5:e2497d4385e2 draft default tip

"planemo upload for repository https://github.com/hCoV-2019/pangolin commit 9e569ed56e07b5d2d3fb8a72ddc477d34570f081"

<tool id="pangolin" name="Pangolin" version="@VERSION@+galaxy0">
    <description> CoV-2019 Phylogenetic Assignment of Named Global Outbreak LINeages</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[

pangolin '$input1' -t "\${GALAXY_SLOTS:-1}" --max-ambig '$additional.max_ambig' --min-length '$additional.min_length' $additional.write_tree $additional.include_putative &&

sed 's/,/\t/g' lineage_report.csv > lineage_report.tsv
    ]]></command>
    <inputs>
        <param name="input1" type="data" format="fasta"
            label="Input multi-sequence fasta file"
            />
        <section name="additional" title="Additional Parameters" expanded="false">
            <param name="max_ambig" type="float" value="0.5" min="0" max="1.0"
                label="Maximum proportion of Ns allowed to attempt assignment"
                argument="--max-ambig"
                />
            <param name="min_length" type="integer" value="10000" min="0"
                label="Minimum query length to attempt assignment"
                argument="--min-length"
                />
            <param name="include_putative" type="boolean" checked="false" argument="-p"
                truevalue="-p"
                falsevalue=""
                label="Include putative lineages"
                help="Putative lineages fit the criteria required for lineage designation but have not got recall values suitable for lineage assignment.
                If left as 'No', only lineages with >95% recall rate will be used."
            />
            <param name="write_tree" type="boolean" checked="false"
                truevalue="--write-tree"
                falsevalue=""
                label="Write guide trees"
                help="Output a collection of trees with each query sequence placed in the guide tree"
                />
        </section>
    </inputs>
    <outputs>
        <data format="tabular" from_work_dir="lineage_report.tsv" name="lineage_report" label="${input1.name}_lineage_report" />
        <collection name="pangolin_trees" type="list" label="${tool.name} Trees">
            <filter>additional['write_tree']</filter>
            <discover_datasets pattern="(?P&lt;designation&gt;.+)\.tree" directory="pangolin_trees/" format="iqtree" />
        </collection>
    </outputs>
    <tests>
        <test>
            <param name="input1" value="test_seqs.fasta" />
            <output name="lineage_report" >
                <assert_contents>
                    <has_text text="Japan/DP0779/2020|EPI_ISL_416626||Japan|unknown||2020-02-17" />
                    <has_text text="USA/NY-NYUMC7/2020|EPI_ISL_418192||USA|New_York|Manhattan|2020-03-16" />
                    <has_text text="This_seq_is_too_short" />
                    <has_text text="lineage" />
                </assert_contents>
            </output>
        </test>
        <test>
            <param name="input1" value="test_seqs.fasta" />
            <section name="additional">
                <param name="write_tree" value="true" />
                <param name="include_putative" value="true" />
            </section>
            <output name="lineage_report" >
                <assert_contents>
                    <has_text text="Japan/DP0779/2020|EPI_ISL_416626||Japan|unknown||2020-02-17" />
                    <has_text text="USA/NY-NYUMC7/2020|EPI_ISL_418192||USA|New_York|Manhattan|2020-03-16" />
                    <has_text text="This_seq_is_too_short" />
                    <has_text text="lineage" />
                </assert_contents>
            </output>
            <output_collection name="pangolin_trees" type="list">
                <element name="USA_NY-NYUMC7_2020_EPI_ISL_418192__USA_New_York_Manhattan_2020-03-16" ftype="iqtree">
                    <assert_contents>
                        <has_text text="USA/NY-NYUMC7/2020|EPI_ISL_418192||USA|New_York|Manhattan|2020-03-16" />
                    </assert_contents>
                </element>
                <element name="Japan_DP0779_2020_EPI_ISL_416626__Japan_unknown__2020-02-17" ftype="iqtree">
                    <assert_contents>
                        <has_text text="Japan/DP0779/2020|EPI_ISL_416626||Japan|unknown||2020-02-17" />
                    </assert_contents>
                </element>
            </output_collection>
        </test>
    </tests>
    <help><![CDATA[
    
Pangolin
--------

Pangolin assigns SARS-CoV-2 genome sequences in fasta format to global lineages from `Rambaut et al. <https://doi.org/10.1101/2020.04.17.046086>`_.
To do this, Pangolin employs the use of external programs including: `iqtree <http://www.iqtree.org/#download>`_, `mafft <https://mafft.cbrc.jp/alignment/software/>`_,
and `snakemake <https://snakemake.readthedocs.io/en/stable/index.html>`_.

More information can be obtained from the authors github site: https://github.com/hCoV-2019/pangolin

You may also wish to visit the authors website at https://pangolin.cog-uk.io/

--------------

**Input** - Multi sequence fasta file or individual fasta files


**Output** - lineage report:

+---------+---------+------+-------------+------------------+-----------+-----------+
| Taxon   | Lineage | aLRT | UFbootstrap | lineages_version | status    | note      |
+=========+=========+======+=============+==================+===========+===========+
| Sample1 | A.1     | 100  | 60          | 2020-04-27       | passed_qc |           |
+---------+---------+------+-------------+------------------+-----------+-----------+
| Sample2 | B.1     | 80   | 80          | 2020-04-27       | passed_qc |           |
+---------+---------+------+-------------+------------------+-----------+-----------+
| Sample3 | B.1.4   | 60   | 100         | 2020-04-27       | fail      | seq_len:0 |
+---------+---------+------+-------------+------------------+-----------+-----------+


Resources for interpreting aLRT and UFbootstrap values:

- `IQ_TREE: Assessing branch supports with single branch tests <http://www.iqtree.org/doc/Tutorial#assessing-branch-supports-with-single-branch-tests>`_

- `IQ_TREE: Command Reference <http://www.iqtree.org/doc/Command-Reference>`_

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