view datasets_genome.xml @ 5:6c829a430475 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ncbi_datasets commit a58a3198ea1b60b6aa9567c6c65f00f8361794f6"
author iuc
date Wed, 04 May 2022 13:15:43 +0000
parents 1a7773882d2c
children 5a2656cc84cb
line wrap: on
line source

<tool id="datasets_download_genome" name="NCBI Datasets Genomes" profile="@PROFILE@" license="@LICENSE" version="@TOOL_VERSION@">
    <description>download genome sequence, annotation and metadata</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"></expand>
    <command><![CDATA[
@SETUP_CERTIFICATES@
datasets download genome $query.subcommand.download_by
#if $query.subcommand.download_by == 'accession':
    #if $query.subcommand.text_or_file.text_or_file == 'text':
        #echo " ".join(f"'{x}'" for x in $query.subcommand.text_or_file.accession.split(' ') if x)
    #else
        --inputfile '$query.subcommand.text_or_file.inputfile'
    #end if
#else:
    '$query.subcommand.taxon'
#end if
$filters.reference
$filters.annotated
#if $filters.assembly_level:
--assembly-level $filters.assembly_level
#end if
#if $filters.assembly_source:
--assembly-source $filters.assembly_source
#end if
#if $filters.chromosomes:
--chromosomes '$filters.chromosomes'
#end if
@EXCLUDES_GENOME@
@INCLUDES_GENOME@
@RELEASED_BEFORE@
@RELEASED_SINCE@
#for search_term in $filters.search:
    --search '$filters.search_term'
#end for
#if $uncompressed
&& unzip ncbi_dataset.zip
#else
&& unzip -l ncbi_dataset.zip > ncbi_dataset.txt
#end if
]]></command>
    <inputs>
        <section name="query" title="Query" expanded="true">
            <conditional name="subcommand">
                <param name="download_by" type="select" label="Choose how to find genomes to download">
                    <option value="accession">Download by NCBI assembly or BioProject accession</option>
                    <option value="taxon">Download by taxon</option>
                </param>
                <when value="accession">
                    <expand macro="text_or_file"/>
                </when>
                <when value="taxon">
                    <param name="taxon" type="text" label="Enter taxon" help="e.g. human, mouse, bos taurus, etc."></param>
                </when>
            </conditional>
        </section>
        <section name="filters" title="Filters and Limit">
            <param argument="--reference" type="boolean" truevalue="--reference" falsevalue="" label="Limit to reference and representative (GCF_ and GCA_) assemblies"/>            
            <expand macro="annotation"></expand>
            <expand macro="assembly_level"></expand>
            <expand macro="assembly_source"></expand>
            <expand macro="chromosomes"></expand>
            <expand macro="released_options"></expand>
            <expand macro="released_options" before_or_after="since"></expand>

            <repeat name="search" title="Add search terms">
                <param argument="--search" type="text" label="Only include genomes that have the specified text in the searchable fields" help="Searchable fields are species and infraspecies, assembly name and submitter"/>
            </repeat>
        </section>
        <section name="file_choices" title="File Choices" expanded="true">
            <expand macro="excludes_genome"></expand>
            <expand macro="includes_genome"></expand>
        </section>
        <param name="uncompressed" type="boolean" label="Uncompress the dataset archive" checked="true"/>
    </inputs>
    <outputs>
        <data name="compressed_archive" format="zip" label="Compressed Archive" from_work_dir="ncbi_dataset.zip">
            <filter>not uncompressed</filter>
        </data>
        <data name="archive_contents" format="txt" label="Archive Contents" from_work_dir="ncbi_dataset.txt">
            <filter>not uncompressed</filter>
        </data>
        <data name="genome_data_report" format="json" label="NCBI Genome Datasets: Data Report" from_work_dir="ncbi_dataset/data/assembly_data_report.jsonl">
            <filter>uncompressed</filter>
        </data>
        <collection name="sequence_report" label="NCBI Genome Datasets: Sequence Data Report" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/sequence_report.jsonl" ext="json" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
            <filter>uncompressed</filter>
        </collection>
        <collection name="genome_fasta" label="NCBI Genome Datasets: genome fasta" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/.*(?&lt;!cds_from)(chr|unplaced|_genomic)*fna" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
            <filter>uncompressed and not file_choices['exclude_seq']</filter>
        </collection>
        <collection name="genomic_cds" label="NCBI Genome Datasets: genomic cds fasta" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/cds_from_genomic\.fna" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
            <filter>uncompressed and not file_choices['exclude_genomic_cds']</filter>
        </collection>
        <collection name="genomic_gff" label="NCBI Genome Datasets: genomic gff3" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/genomic\.gff" ext="gff3" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
            <filter>uncompressed and not file_choices['exclude_gff3']</filter>
        </collection>
        <collection name="rna_fasta" label="NCBI Genome Datasets: RNA fasta" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/rna\.fna" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
            <filter>uncompressed and not file_choices['exclude_rna']</filter>
        </collection>
        <collection name="protein_fasta" label="NCBI Genome Datasets: protein fasta" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/protein\.faa" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
            <filter>uncompressed and not file_choices['exclude_protein']</filter>
        </collection>
        <collection name="genomic_gbff" label="NCBI Genome Datasets: GenBank flatfile" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/genomic\.gbff" ext="txt" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
            <filter>uncompressed and file_choices['include_gbff']</filter>
        </collection>
        <collection name="genomic_gtf" label="NCBI Genome Datasets: gtf" type="list">
            <discover_datasets pattern="(?P&lt;identifier_0&gt;.*?)\/genomic\.gtf" ext="gtf" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"></discover_datasets>
            <filter>uncompressed and file_choices['include_gtf']</filter>
        </collection>
    </outputs>
    <tests>
        <test expect_num_outputs="2">
            <conditional name="query|subcommand">
                <param name="download_by" value="taxon"></param>
                <param name="text_or_file" value="text"></param>
                <param name="taxon" value="human"></param>
            </conditional>
            <param name="chromosomes" value="21"></param>
            <param name="exclude_protein" value="true"/>
            <param name="exclude_rna" value="true"/>
            <param name="exclude_seq" value="true"/>
            <param name="exclude_genomic_cds" value="true"/>
            <param name="exclude_gff3" value="true"/>
            <param name="uncompressed" value="false"/>
            <param name="released_before" value="01/01/2018"></param>
            <output name="archive_contents">
                <assert_contents>
                    <has_text text="ncbi_dataset/data/dataset_catalog.json"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="2">
            <conditional name="query|subcommand">
                <param name="download_by" value="taxon"></param>
                <param name="text_or_file" value="text"></param>
                <param name="taxon" value="human"></param>
            </conditional>
            <param name="chromosomes" value="21"></param>
            <param name="uncompressed" value="false"/>
            <param name="exclude_protein" value="true"/>
            <param name="exclude_rna" value="true"/>
            <param name="exclude_seq" value="true"/>
            <param name="exclude_genomic_cds" value="true"/>
            <param name="exclude_gff3" value="true"/>
            <param name="assembly_level" value="chromosome"/>
            <param name="released_before" value="01/01/2018"></param>
            <output name="archive_contents">
                <assert_contents>
                    <has_text text="ncbi_dataset/data/dataset_catalog.json"/>
                </assert_contents>
            </output>
        </test>
        <test expect_num_outputs="4">
            <conditional name="query|subcommand">
                <param name="download_by" value="accession"></param>
                <conditional name="text_or_file">
                    <param name="text_or_file" value="text"></param>
                    <param name="accession" value="GCF_000013305.1 GCF_000007445.1"></param>
                </conditional>
            </conditional>
            <param name="uncompressed" value="true"/>
            <param name="released_before" value="01/01/2007"></param>
            <param name="exclude_protein" value="true"/>
            <param name="exclude_rna" value="true"/>
            <param name="exclude_seq" value="true"/>
            <param name="exclude_gff3" value="true"/>
            <param name="include_gtf" value="true"/>
            <output name="genome_data_report">
                <assert_contents>
                    <has_text text="GCF_000013305.1"/>
                </assert_contents>
            </output>
            <output_collection name="genomic_gtf" type="list">
                <element name="GCF_000013305.1" file="genome.2.GCF_000013305.1.genomic.gtf" compare="contains"/>
                <element name="GCF_000007445.1" file="GCF_000007445.1.genomic.gtf" compare="contains"/>
            </output_collection>
            <output_collection name="genomic_cds" type="list">
                <element name="GCF_000013305.1" file="genome.2.GCF_000013305.1.genomic.cds" compare="contains"/>
                <element name="GCF_000007445.1" file="genome.2.GCF_000007445.1.genomic.cds" compare="contains"/>
            </output_collection>
        </test>
        <test expect_num_outputs="4">
            <conditional name="query|subcommand">
                <param name="download_by" value="accession"></param>
                <conditional name="text_or_file">
                    <param name="text_or_file" value="file"></param>
                    <param name="inputfile" value="accessions.txt"></param>
                </conditional>
            </conditional>
            <param name="include_gbff" value="true"/>
            <param name="exclude_protein" value="true"/>
            <param name="exclude_rna" value="true"/>
            <param name="exclude_seq" value="true"/>
            <param name="exclude_genomic_cds" value="true"/>
            <param name="uncompressed" value="true"/>
            <param name="released_before" value="01/02/2007"></param>
            <output name="genome_data_report">
                <assert_contents>
                   <has_text text="SAMN02604181"/>
                </assert_contents>
            </output>
            <output_collection name="genomic_gff" type="list">
                <element name="GCF_000013305.1" file="genome.3.GCF_000013305.1.genomic.gff" compare="contains"/>
                <element name="GCF_000007445.1" file="genome.3.GCF_000007445.1.genomic.gff" compare="contains"/>
            </output_collection>
            <output_collection name="genomic_gbff" type="list">
                <element name="GCF_000013305.1" file="genome.3.GCF_000013305.1.genomic.gbff" compare="contains"/>
                <element name="GCF_000007445.1" file="genome.3.GCF_000007445.1.genomic.gbff" compare="contains"/>
            </output_collection>
        </test>
        <test expect_num_outputs="2">
            <conditional name="query|subcommand">
                <param name="download_by" value="accession"></param>
                <conditional name="text_or_file">
                    <param name="text_or_file" value="text"></param>
                    <param name="accession" value="GCF_000001405.40"></param>
                </conditional>
            </conditional>
            <param name="exclude_protein" value="true"/>
            <param name="exclude_rna" value="true"/>
            <param name="exclude_seq" value="true"/>
            <param name="exclude_genomic_cds" value="true"/>
            <param name="exclude_gff3" value="true"/>
            <param name="uncompressed" value="true"/>
            <param name="released_before" value="01/02/2007"></param>
            <output_collection name="sequence_report">
                <element name="GCF_000001405.40" file="GCF_000001405.40.seq.rpt.jsonl" compare="contains"/>
            </output_collection>
        </test>
    </tests>
    <help>
<![CDATA[
**Download Genome Datasets from NCBI**

Download a genome dataset including genome, transcript and protein sequence, annotation and a detailed data report.
Genome datasets can be specified by NCBI Assembly or BioProject accession or taxon. Datasets are downloaded as a zip file.

Tthe default genome dataset includes the following files (if available):
 * data_report.jsonl (genome assembly and annotation metadata, not always available)
 * genomic.fna (genomic sequences)
 * rna.fna (transcript sequences)
 * protein.faa (protein sequences)
 * genomic.gff (genome annotation in gff3 format)
 * dataset_catalog.json (a list of files and file types included in the dataset)
]]>
    </help>

</tool>