annotate staramr_search.xml @ 4:1e8ec0f861ff draft

planemo upload for repository https://github.com/phac-nml/staramr commit fd6c4338e65d6a33900da6fe7ae6f507105d3446

<tool id="staramr_search" name="staramr" version="0.3.0">
    <description>Scans genome assemblies against the ResFinder and PointFinder databases searching for AMR genes.</description>
    <requirements>
        <requirement type="package" version="0.3.0">staramr</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        #import re

        #set $named_genomes = ''
        #for $genome in $genomes
            #set $_named_genome = re.sub(r'(\s|\(|\))', '_', '"{}.fasta"'.format($genome.element_identifier))
            ln -s "$genome" $_named_genome &&
            #set $named_genomes = $named_genomes + ' ' + $_named_genome
        #end for

        #set $excel_proper_extension = '"{}.xlsx"'.format($excel)
        ln -s "$excel" $excel_proper_extension &&

        staramr search

        --nprocs "\${GALAXY_SLOTS:-1}"

        --pid-threshold $advanced.pid_threshold
        --percent-length-overlap-resfinder $advanced.plength_resfinder
        --percent-length-overlap-pointfinder $advanced.plength_pointfinder

        $advanced.report_all_blast
        $advanced.exclude_negatives
        $advanced.exclude_resistance_phenotypes

        #if str($advanced.exclude_genes.exclude_genes_condition) == 'custom'
            --exclude-genes-file '${advanced.exclude_genes.exclude_genes_file}'
        #elif str($advanced.exclude_genes.exclude_genes_condition) == 'none'
            --no-exclude-genes
        #end if

        --output-summary $summary
        --output-resfinder $resfinder
        #if $use_pointfinder.enable
            --output-pointfinder $pointfinder
        #end if
        --output-settings $settings
        --output-excel $excel_proper_extension

        --output-hits-dir staramr_hits

        #if $use_pointfinder.enable
            --pointfinder-organism $use_pointfinder.organism
        #end if

        $named_genomes
    ]]></command>
    <inputs>
        <param type="data" name="genomes" format="fasta" multiple="true"/>
        <conditional name="use_pointfinder">
            <param name="enable" type="boolean" label="Enable scanning for point mutations using the PointFinder database" />
            <when value="true">
                <param name="organism" type="select" label="Select a pointfinder organism">
                    <option value="salmonella" selected="true">Salmonella</option>
                </param>
            </when>
            <when value="false" />
        </conditional>
        <section name="advanced" title="Advanced options" expanded="false">
            <param name="pid_threshold" type="float" label="Percent identity threshold for BLAST" value="98.0"
                   min="0" max="100" help="(--pid-threshold)" />
            <param name="plength_resfinder" type="float" label="Percent length overlap of BLAST hit for ResFinder database" value="60.0"
                   min="0" max="100" help="(--percent-length-overlap-resfinder)" />
            <param name="plength_pointfinder" type="float" label="Percent length overlap of BLAST hit for PointFinder database" value="95.0"
                   min="0" max="100" help="(--percent-length-overlap-pointfinder)" />
            <param name="report_all_blast" type="boolean" label="Report all BLAST results" truevalue="--report-all-blast" falsevalue=""
                   help="Report all BLAST results (includes overlapping hits, mainly for debugging)" />
            <param name="exclude_negatives" type="boolean" label="Exclude negative (non-resistant) results" truevalue="--exclude-negatives" falsevalue="" />
            <param name="exclude_resistance_phenotypes" type="boolean" label="Exclude resistance phenotypes" truevalue="--exclude-resistance-phenotypes" falsevalue="" />
            <conditional name="exclude_genes">
                <param name="exclude_genes_condition" type="select" label="Exclude certain AMR genes from the results">
                    <option value="default" selected="true">Exclude default list of AMR genes</option>
                    <option value="custom">Provide a custom list of AMR genes to exclude</option>
                    <option value="none">Do not exclude any AMR genes</option>
                </param>
                <when value="default" />
                <when value="custom">
                    <param type="data" name="exclude_genes_file" format="txt,tabular" label="Exclude genes file" help="Pass a file containing a list of genes to exclude from the ResFinder/PointFinder results" />
                </when>
                <when value="none" />
            </conditional>
        </section>
    </inputs>
    <outputs>
        <data format="tabular" name="summary" label="${tool.name} on ${on_string}: summary.tsv" />
        <data format="tabular" name="resfinder" label="${tool.name} on ${on_string}: resfinder.tsv" />
        <data format="tabular" name="pointfinder" label="${tool.name} on ${on_string}: pointfinder.tsv">
            <filter>use_pointfinder['enable']</filter>
        </data>
        <data format="txt" name="settings" label="${tool.name} on ${on_string}: settings.txt" />
        <data format="xlsx" name="excel" label="${tool.name} on ${on_string}: results.xlsx" />
        <collection name="blast_hits" type="list" label="${tool.name} on ${on_string}: hits">
            <discover_datasets pattern="__name_and_ext__" directory="staramr_hits" />
        </collection>
    </outputs>
    <tests>
        <test>
            <param name="genomes" value="16S-rc_gyrA-rc_beta-lactam.fsa" />
            <conditional name="use_pointfinder">
                <param name="enable" value="true" />
                <param name="organism" value="salmonella" />
            </conditional>

            <output name="summary" file="test1-summary.tsv" ftype="tabular" />
            <output name="resfinder" file="test1-resfinder.tsv" ftype="tabular" />
            <output name="pointfinder" file="test1-pointfinder.tsv" ftype="tabular" />
            <output_collection name="blast_hits" type="list">
                <element name="resfinder_16S-rc_gyrA-rc_beta-lactam.fsa" file="test1-hits/resfinder_16S-rc_gyrA-rc_beta-lactam.fsa" />
                <element name="pointfinder_16S-rc_gyrA-rc_beta-lactam.fsa" file="test1-hits/pointfinder_16S-rc_gyrA-rc_beta-lactam.fsa" />
            </output_collection>
        </test>
        <test>
            <param name="genomes" value="16S-rc_gyrA-rc_beta-lactam.fsa" />

            <output name="summary" file="test2-summary.tsv" ftype="tabular" />
            <output name="resfinder" file="test2-resfinder.tsv" ftype="tabular" />
            <output_collection name="blast_hits" type="list">
                <element name="resfinder_16S-rc_gyrA-rc_beta-lactam.fsa" file="test2-hits/resfinder_16S-rc_gyrA-rc_beta-lactam.fsa" />
            </output_collection>
        </test>
        <test>
            <param name="genomes" value="16S-rc_gyrA-rc_beta-lactam.fsa" />
            <param name="pid_threshold" value="99.8" />

            <output name="summary" file="test3-summary.tsv" ftype="tabular" />
        </test>
        <test>
            <param name="genomes" value="16S rc_gyrA rc_beta-lactam spaces (extra:characters).fsa" />
            <param name="pid_threshold" value="99.8" />

            <output name="summary" file="test4-summary.tsv" ftype="tabular" />
        </test>
        <test>
            <param name="genomes" value="test-aminoglycoside.fsa" />

            <output name="summary" file="test5-summary.tsv" ftype="tabular" />
        </test>
        <test>
            <param name="genomes" value="test-aminoglycoside.fsa" />
            <param name="exclude_genes_condition" value="none" />

            <output name="summary" file="test6-summary.tsv" ftype="tabular" />
        </test>
        <test>
            <param name="genomes" value="test-aminoglycoside.fsa" />
            <param name="exclude_genes_condition" value="custom" />
            <param name="exclude_genes_file" value="genes_to_exclude.tsv" />

            <output name="summary" file="test5-summary.tsv" ftype="tabular" />
        </test>
    </tests>
    <help><![CDATA[
staramr
=======

staramr_ scans bacterial genome contigs against both the ResFinder_ and PointFinder_ databases (used by the ResFinder webservice_) and compiles a summary report of detected antimicrobial resistance genes.

Usage
-----

1. Select your genome contigs (in FASTA format).
2. Select whether or not you wish to scan your genome for point mutations giving antimicrobial resistance using the PointFinder database. This requires you to specify the specific organism you are scanning (currently only *salmonella* is supported).
3. Run the tool.

Input
-----

Genomes
```````

staramr_ takes as input one or more assembled genomes (in FASTA format) to search for AMR genes.

Exclude genes file
``````````````````

Setting **Provide a custom list of AMR genes to exclude** in the **Advanced options** allows you to pass a file containing a list of genes to exclude from the results. The file must start with a line **#gene_id** and the gene names must correspond to the sequence IDs in the ResFinder/PointFinder databases.  For example:

::

    #gene_id
    aac(6')-Iaa_1_NC_003197

Output
------

There are 5 different output files produced by `staramr` as well as a collection of additional files.

summary.tsv
```````````

A summary of all detected AMR genes/mutations in each genome, one genome per line.

+------------+-----------------------------------------------------------+-----------------------------------------------------------------------------------------------------------+
| Isolate ID | Genotype                                                  | Predicted Phenotype                                                                                       |
+============+===========================================================+===========================================================================================================+
| SRR1952908 | aadA1, aadA2, blaTEM-57, cmlA1, gyrA (S83Y), sul3, tet(A) | streptomycin, ampicillin, chloramphenicol, ciprofloxacin I/R, nalidixic acid, sulfisoxazole, tetracycline |
+------------+-----------------------------------------------------------+-----------------------------------------------------------------------------------------------------------+
| SRR1952926 | blaTEM-57, gyrA (S83Y), tet(A)                            | ampicillin, ciprofloxacin I/R, nalidixic acid, tetracycline                                               |
+------------+-----------------------------------------------------------+-----------------------------------------------------------------------------------------------------------+

resfinder.tsv
`````````````

A tabular file of each AMR gene and additional BLAST information from the **ResFinder** database, one gene per line.

+------------+------------+----------------------+------------+-----------+--------------------------+--------------+--------+-------+-----------+
| Isolate ID | Gene       | Predicted Phenotype  | %Identity  | %Overlap  | HSP Length/Total Length  | Contig       | Start  | End   | Accession |
+============+============+======================+============+===========+==========================+==============+========+=======+===========+
| SRR1952908 | sul3       | sulfisoxazole        | 100.00     | 100.00    | 792/792                  | contig00030  | 2091   | 2882  | AJ459418  |
+------------+------------+----------------------+------------+-----------+--------------------------+--------------+--------+-------+-----------+
| SRR1952908 | tet(A)     | tetracycline         | 99.92      | 100.00    | 1200/1200                | contig00032  | 1551   | 2750  | AJ517790  |
+------------+------------+----------------------+------------+-----------+--------------------------+--------------+--------+-------+-----------+
| SRR1952908 | cmlA1      | chloramphenicol      | 99.92      | 100.00    | 1260/1260                | contig00030  | 6707   | 5448  | M64556    |
+------------+------------+----------------------+------------+-----------+--------------------------+--------------+--------+-------+-----------+
| SRR1952908 | aadA1      | streptomycin         | 100.00     | 100.00    | 792/792                  | contig00030  | 5355   | 4564  | JQ414041  |
+------------+------------+----------------------+------------+-----------+--------------------------+--------------+--------+-------+-----------+
| SRR1952908 | aadA2      | streptomycin         | 99.75      | 100.00    | 792/792                  | contig00030  | 7760   | 6969  | JQ364967  |
+------------+------------+----------------------+------------+-----------+--------------------------+--------------+--------+-------+-----------+
| SRR1952908 | blaTEM-57  | ampicillin           | 99.88      | 100.00    | 861/861                  | contig00032  | 6247   | 5387  | FJ405211  |
+------------+------------+----------------------+------------+-----------+--------------------------+--------------+--------+-------+-----------+
| SRR1952926 | tet(A)     | tetracycline         | 99.92      | 100.00    | 1200/1200                | contig00027  | 1480   | 2679  | AJ517790  |
+------------+------------+----------------------+------------+-----------+--------------------------+--------------+--------+-------+-----------+
| SRR1952926 | blaTEM-57  | ampicillin           | 99.88      | 100.00    | 861/861                  | contig00027  | 6176   | 5316  | FJ405211  |
+------------+------------+----------------------+------------+-----------+--------------------------+--------------+--------+-------+-----------+

pointfinder.tsv
```````````````

A tabular file of each AMR point mutation and additional BLAST information from the **PointFinder** database, one gene per line.

+-------------+--------------+------------------------------------+--------+-----------+----------------------+------------+-----------+--------------------------+--------------+---------+--------+
| Isolate ID  | Gene         | Predicted Phenotype                | Type   | Position  | Mutation             | %Identity  | %Overlap  | HSP Length/Total Length  | Contig       | Start   | End    |
+=============+==============+====================================+========+===========+======================+============+===========+==========================+==============+=========+========+
| SRR1952908  | gyrA (S83Y)  | ciprofloxacin I/R, nalidixic acid  | codon  | 83        | TCC -> TAC (S -> Y)  | 99.96      | 100.00    | 2637/2637                | contig00008  | 22801   | 20165  |
+-------------+--------------+------------------------------------+--------+-----------+----------------------+------------+-----------+--------------------------+--------------+---------+--------+
| SRR1952926  | gyrA (S83Y)  | ciprofloxacin I/R, nalidixic acid  | codon  | 83        | TCC -> TAC (S -> Y)  | 99.96      | 100.00    | 2637/2637                | contig00011  | 157768  | 160404 |
+-------------+--------------+------------------------------------+--------+-----------+----------------------+------------+-----------+--------------------------+--------------+---------+--------+

settings.txt
````````````

The command-line, database versions, and other settings used to run `staramr`.

::

    command_line                  = staramr search -o out --pointfinder-organism salmonella SRR1952908.fasta SRR1952926.fasta
    version                       = 0.2.0
    start_time                    = 2018-06-05 14:41:44
    end_time                      = 2018-06-05 14:41:47
    total_minutes                 = 0.05
    resfinder_db_dir              = staramr/databases/data/dist/resfinder
    resfinder_db_url              = https://bitbucket.org/genomicepidemiology/resfinder_db.git
    resfinder_db_commit           = dc33e2f9ec2c420f99f77c5c33ae3faa79c999f2
    resfinder_db_date             = Tue, 20 Mar 2018 16:49
    pointfinder_db_dir            = staramr/databases/data/dist/pointfinder
    pointfinder_db_url            = https://bitbucket.org/genomicepidemiology/pointfinder_db.git
    pointfinder_db_commit         = ba65c4d175decdc841a0bef9f9be1c1589c0070a
    pointfinder_db_date           = Fri, 06 Apr 2018 09:02
    pointfinder_gene_drug_version = 050218
    resfinder_gene_drug_version   = 050218 

results.xlsx
````````````

An Excel spreadsheet containing the previous 4 files as separate worksheets.

BLAST Hits
``````````

The dataset collection  **hits** stores fasta files of the specific blast hits. 

Galaxy wrapper written by Aaron Petkau at the National Microbiology Laboratory, Public Health Agency of Canada.

.. _staramr: https://github.com/phac-nml/staramr
.. _ResFinder: https://bitbucket.org/genomicepidemiology/resfinder_db
.. _PointFinder: https://bitbucket.org/genomicepidemiology/pointfinder_db
.. _webservice: https://cge.cbs.dtu.dk/services/ResFinder/
    ]]></help>
    <citations>
        <citation type="bibtex">
            @misc{githubstaramr,
              author = {Petkau, Aaron},
              year = {2018},
              title = {staramr},
              publisher = {GitHub},
              journal = {GitHub repository},
              url = {https://github.com/phac-nml/staramr},
       }</citation>
    </citations>
</tool>