annotate rgi.xml @ 1:f96cbb663aa9 draft

planemo upload for repository https://github.com/arpcard/rgi commit 09a75bd2d655c05892acf7585a7ed08548f1c86d

<tool id="rgi" name="Resistance Gene Identifier (RGI)" version="5.1.0">
    <description>This tool predicts resistome(s) from protein or nucleotide data based on homology and SNP models.</description>
    <requirements>
        <requirement type="package" version="5.1.0">rgi</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <command detect_errors="aggressive"><![CDATA[
#if $db_opts.db_opts_selector != "default":
    rgi load
        #if $db_opts.db_opts_selector == "local":
            -i "${__tool_data_path__}/rgi_databases/$db_opts.rgi_db_local/card.json" 
        #else:
            -i "$db_opts.rgi_db_hist"
        #end if
        --local
    &&
#end if

rgi main
    -i '$input_sequence'
    -o out
    -t $input_type
    -a $alignment_tool
    -n "\${GALAXY_SLOTS:-1}"
    $include_loose
    $low_quality
    -d $data

#if $db_opts.db_opts_selector != "default":
    --local
#end if
       ]]></command>
    <inputs>
        <param argument="--input_sequence" type="data" format="fastq,fasta" label="Input sequence" help="input file must be in either FASTA (contig and protein) or gzip format e.g myFile.fasta, myFasta.fasta.gz"/>
        <param argument="--input_type" type="select" multiple="false" label="Input type" help="specify data input type (default = contig)">
            <option value="contig" selected="true">CONTIG (Nucleotide Sequence)</option>
            <option value="protein">PROTEIN (Protein Sequence)</option>
        </param>
        <param argument="--alignment_tool" type="select" label="Alignment tool" help="specify alignment tool (default = BLAST)">
            <option value="blast" selected="true">BLAST</option>
            <option value="diamond">DIAMOND</option>
        </param>
        <param argument="--include_loose" type="boolean" checked="false" truevalue="--include_loose" falsevalue="" label="Include loose hits" help="include loose hits in addition to strict and perfect hits"/>
        <param argument="--low_quality" type="boolean" checked="false" truevalue="--low_quality" falsevalue="" label="Low quality" help="use for short contigs to predict partial genes"/>
        <param argument="--data" type="select" multiple="false" label="Data type" help="specify a data-type (default = NA)">
            <option value="wgs">WGS</option>
            <option value="plasmid">PLASMID</option>
            <option value="chromosome">CHROMOSOME</option>
            <option value="NA" selected="true">NA</option>
        </param>
        <conditional name="db_opts">
            <param name="db_opts_selector" type="select" label="Select an RGI database">
                <option value="default" selected="true">Default RGI database</option>
                <option value="local">Locally installed RGI database</option>
                <option value="hist">RGI database from your history</option>
            </param>
            <when value="default">
                <param name="rgi_db_local" type="hidden" value="" /> 
                <param name="rgi_db_hist" type="hidden" value="" />
            </when>
            <when value="local">
                <param name="rgi_db_local" type="select" multiple="false" label="Locally installed RGI database">
                    <options from_data_table="rgi_databases">
                        <validator type="no_options" message="No databases are available built-in"/>
                    </options>
                </param>
                <param name="rgi_db_hist" type="hidden" value="" />
            </when>
            <when value="hist">
                <param name="rgi_db_local" type="hidden" value="" />
                <param name="rgi_db_hist" type="data" format="json" label="RGI database from your history" />
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="report" format="json" from_work_dir="out.json" label="${tool.name} on ${on_string}: report.json"/>
        <data name="summary" format="tabular" from_work_dir="out.txt" label="${tool.name} on ${on_string}: summary.txt"/>
    </outputs>
    <tests>
        <test>
            <param name="input_sequence" value="test1.fasta" />
            <param name="input_type" value="contig" />
            <param name="alignment_tool" value="blast" />
            <param name="include_loose" value="false" />
            <param name="low_quality" value="false" />
            <param name="data" value="NA" />
            <conditional name="db_opts">
                <param name="db_opts_selector" value="default" />
            </conditional>
            <output name="summary">
                <assert_contents>
                    <has_text text="AY123251" />
                </assert_contents>
            </output>
        </test>
    </tests>
    <help>
    <![CDATA[
Resistance Gene Identifier (RGI)
================================

RGI is used to predict resistome(s) from protein or nucleotide data based on homology and SNP models. The tool uses data from the CARD database.

Usage
-----

1. Select your input sequence (in FASTA format).
2. Select your input type (CONTIG or PROTEIN).
3. Select your alignment tool (DIAMOND or BLAST).  
4. Specify if you want to include loose hits (YES or NO).
5. Specify if you want to remove temporary files (YES or NO).
6. Specify if you want to low quality predictions (YES or NO).
7. Select your data type (WGS, PLASMID, CHROMOSOME or NA). 
8. Run the tool.

Output
------

There are 2 different output files produced by `rgi`.

summary.txt
^^^^^^^^^^^

A tabular file of all detected resistance genes, one gene per line.

+--------------------------------------------------------------------------------------------------------------------------+---------------+-------+------+-------------+----------+----------------+---------------------+----------------+------------------+----------+-----------------------+--------------------------+-------------+------------+-------------------------+----------------------+---------------------------+------------------------+---------------------------+-----------------------------------------+--------------------------------+-----------+
| ORF_ID                                                                                                                   | Contig        | Start | Stop | Orientation | Cut_Off  | Pass_Bitscore  | Best_Hit_Bitscore   | Best_Hit_ARO   | Best_Identities  | ARO      | Model_type            | SNPs_in_Best_Hit_ARO     | Other_SNPs  | Drug Class | Resistance Mechanism    | AMR Gene Family      | Predicted_DNA             | Predicted_Protein      | CARD_Protein_Sequence     | Percentage Length of Reference Sequence | ID                             | Model_ID  |
+==========================================================================================================================+===============+=======+======+=============+==========+================+=====================+================+==================+==========+=======================+==========================+=============+============+=========================+======================+===========================+========================+===========================+=========================================+================================+===========+
| AY123251.1_6 # 3575 # 4489 # 1 # ID=1_6;partial=00;start_type=ATG;rbs_motif=None;rbs_spacer=None;gc_cont=0.399           | AY123251.1_6  | 3575  | 4489 | \+          | Strict   | 500            | 506.908             | CARB-7         | 83.68            | 3002246  | protein homolog model | n/a                      | n/a         | penam      | antibiotic inactivation | CARB beta-lactamase  | ATGC                      | MLLYKMCDNQNYGVTYMKFLLV | MKSLLVFALLMPSVVFASSSKFQSV | 105.56                                  | gnl|BL_ORD_ID|589|hsp_num:0    | 1443      |
+--------------------------------------------------------------------------------------------------------------------------+---------------+-------+------+-------------+----------+----------------+---------------------+----------------+------------------+----------+-----------------------+--------------------------+-------------+------------+-------------------------+----------------------+---------------------------+------------------------+---------------------------+-----------------------------------------+--------------------------------+-----------+

report.json
^^^^^^^^^^^

A json version of summary.txt.

Help
----

**usage:**
    ``rgi main [-h] -i INPUT_SEQUENCE -o OUTPUT_FILE [-t {read,contig,protein,wgs}] [-a {DIAMOND,BLAST}] [-n THREADS] [--include_loose] [--local] [--clean] [--debug] [--low_quality] [-d {wgs,plasmid,chromosome,NA}] [-v]``

**optional arguments:**

- ``-h, --help``
    show this help message and exit
- ``-i INPUT_SEQUENCE, --input_sequence INPUT_SEQUENCE``
    input file must be in either FASTA (contig and protein) or gzip format e.g myFile.fasta, myFasta.fasta.gz
- ``-o OUTPUT_FILE, --output_file OUTPUT_FILE``
    output folder and base filename
- ``-t {read,contig,protein,wgs}, --input_type {read,contig,protein,wgs}``
    specify data input type (default = contig)
- ``-a {DIAMOND,BLAST}, --alignment_tool {DIAMOND,BLAST}``
    specify alignment tool (default = BLAST)
- ``-n THREADS, --num_threads THREADS``
    number of threads (CPUs) to use in the BLAST search (default=8)
- ``--include_loose``
    include loose hits in addition to strict and perfect hits
- ``--local``
    use local database (default: uses database in executable directory)
- ``--clean``
    removes temporary files
- ``--debug``
    debug mode
- ``--low_quality``
    use for short contigs to predict partial genes
- ``-d {wgs,plasmid,chromosome,NA}, --data {wgs,plasmid,chromosome,NA}``
    specify a data-type (default = NA)
- ``-v, --version``
    prints software version number

Links
-----

RGI: https://card.mcmaster.ca/analyze/rgi

Github: https://github.com/arpcard/rgi

CARD database: https://card.mcmaster.ca
     ]]>
    </help>
    <citations>
        <citation type="doi">10.1093/nar/gkw1004</citation>
    </citations>
</tool>