annotate datasets_gene.xml @ 11:ac24fff14f23 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ncbi_datasets commit 4d7d3a56084e140f4fa63fb0e04a08b732f247f2

<tool id="datasets_download_gene" name="NCBI Datasets Gene" profile="@PROFILE@" license="@LICENSE@" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
    <description>download gene sequences and metadata</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"></expand>
    <command><![CDATA[
#import re
@SETUP_CERTIFICATES@
datasets download gene $query.subcommand.download_by
#if $query.subcommand.download_by == 'taxon':
    '$query.subcommand.taxon_positional'
#else:
    #if $query.subcommand.text_or_file.text_or_file == 'text':
        #echo " ".join(f"'{x}'" for x in re.split(" |,", str($query.subcommand.text_or_file.accession)) if x)
    #else
        --inputfile '$query.subcommand.text_or_file.inputfile'
    #end if
#end if

#if $query.subcommand.download_by != 'taxon' and $query.subcommand.ortholog:
    --ortholog '$query.subcommand.ortholog'
#end if

#if $query.subcommand.download_by == 'symbol':
    #if $query.subcommand.taxon
        --taxon '$query.subcommand.taxon'
    #end if
#end if

#if $query.subcommand.download_by == 'accession':
    #if $query.subcommand.taxon_filter
        --taxon-filter '$query.subcommand.taxon_filter'
    #end if
    #if str($query.subcommand.include_flanks_bp)
        --include-flanks-bp $query.subcommand.include_flanks_bp
    #end if
#end if

#if $filters.fasta_filter_cond.fasta_filter_select
    #if $filters.fasta_filter_cond.fasta_filter_select == 'text'
        --fasta-filter #echo ",".join(f"'{x}'" for x in $filters.fasta_filter_cond.fasta_filter.split(',') if x)
    #else
        --fasta-filter-file '$filters.fasta_filter_cond.fasta_filter_file'
    #end if
#end if

--include
#if $file_choices.kingdom_cond.include
    #echo ",".join($file_choices.kingdom_cond.include)
#else
    none
#end if

--no-progressbar

## produce TSV report file (either gene or prok-gene)
&& 
dataformat
    tsv
    $file_choices.kingdom_cond.kingdom_sel
    --package ncbi_dataset.zip
    --fields #echo ",".join($file_choices.kingdom_cond.report_columns)
    > gene_data_report.tsv
## if ! dataformat tsv gene --package ncbi_dataset.zip > gene_data_report.tsv 2> dataformat.log; then
##     dataformat tsv prok-gene --package ncbi_dataset.zip > gene_data_report.tsv 2>> dataformat.log;
## fi

#if $file_choices.kingdom_cond.include and "product-report" in $file_choices.kingdom_cond.include
    && dataformat tsv gene-product --package ncbi_dataset.zip > gene_product_report.tsv
#end if

## unzip and rehydrate if any data is to be downloaded (include is not None)
#if $file_choices.kingdom_cond.include
    ## unzip
    && 7z x -y ncbi_dataset.zip > 7z.log
#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 genes to download">
                    <option value="gene-id">By NCBI Gene ID</option>
                    <option value="symbol">By Gene symbol</option>
                    <option value="accession">By RefSeq nucleotide or protein accession</option>
                    <option value="taxon">By taxon (NCBI Taxonomy ID, scientific or common name at any tax rank)</option>
                </param>
                <when value="gene-id">
                    <expand macro="text_or_file" what="Gene ID" what_extended="NCBI Gene ID" help=""/>
                    <expand macro="ortholog"/>
                </when>
                <when value="symbol">
                    <expand macro="text_or_file" what="Gene Symbol" what_extended="NCBI Gene Symbol" help=""/>
                    <expand macro="ortholog"/>
                    <param argument="--taxon" type="text" value="human" label="Species for gene symbol" help="NCBI taxid, common or scientific name">
                        <sanitizer invalid_char="">
                            <valid initial="string.letters">
                                <add value=" " />
                                <add value="-" />
                            </valid>
                        </sanitizer>
                    </param>
                </when>
                <when value="accession">
                    <expand macro="text_or_file" what="Gene Accession" what_extended="NCBI Gene Accession" help=""/>
                    <expand macro="ortholog"/>
                    <param argument="--taxon-filter" type="text" value="" label="Limit gene sequences and annotation report file to specified taxon" help="any rank, only available for WP accessions">
                        <sanitizer invalid_char="">
                            <valid initial="string.letters">
                                <add value=" " />
                                <add value="-" />
                            </valid>
                        </sanitizer>
                    </param>
                    <param argument="--include-flanks-bp" type="integer" optional="true" min="0" label="Length of flanking nucleotides" help="WP accessions only"/>
                </when>
                <when value="taxon">
                    <expand macro="taxon_positional"/>
                </when>
            </conditional>
        </section>
        <section name="filters" title="Filters and Limit">
            <conditional name="fasta_filter_cond" label="Filter protein and RNA sequences by RefSeq nucleotide and protein accessions">
                <param name="fasta_filter_select" type="select" label="Apply filter">
                    <option value="">No</option>
                    <option value="text">Enter accessions</option>
                    <option value="file">Read a list of accessions from a dataset</option>
                </param>
                <when value=""/>
                <when value="text">
                    <param argument="--fasta-filter" type="text" label="RefSeq nucleotide and protein accessions" help="Comma separated">
                        <sanitizer invalid_char="">
                            <valid initial="string.letters,string.digits">
                                <add value="," />
                            </valid>
                        </sanitizer>
                    </param>
                </when>
                <when value="file">
                    <param argument="--fasta-filter-file" type="data" format="txt" label="Dataset with list of RefSeq nucleotide and protein accessions" help=""/>
                </when>
            </conditional>
        </section>
        <section name="file_choices" title="Output options" expanded="true">
            <conditional name="kingdom_cond">
                <param name="kingdom_sel" type="select" label="Kingdom" help="Prokaryotic: Accessions starting with WP_. Data report has a different format and the rna, cds, 3/5' UTR and gene-product report are not suported. ">
                    <option value="gene">Eukaryote</option>
                    <option value="prok-gene">Prokaryote</option>
                </param>
                <when value="gene">
                    <expand macro="gene_tsv_report_columns">
                        <option value="gene-id" selected="true">NCBI GeneID</option>
                        <option value="gene-type" selected="true">Gene Type</option>
                        <option value="common-name" selected="true">Common Name</option>
                        <option value="description" selected="true">Description</option>
                        <option value="symbol" selected="true">Symbol</option>
                        <option value="synonyms" selected="true">Synonyms</option>
                        <option value="tax-id" selected="true">Taxonomic ID</option>
                        <option value="tax-name" selected="true">Taxonomic Name</option>
                    </expand>
                    <expand macro="include">
                        <expand macro="gene_includes">
                            <option value="rna" selected="true">transcript (rna)</option>
                            <option value="cds">nucleotide coding sequences (cds)</option>
                            <option value="5p-utr">5'-UTR (5p-utr)</option>
                            <option value="3p-utr">3'-UTR (3p-utr)</option>
                            <option value="product-report"> (product-report)</option>
                        </expand>
                    </expand>
                </when>
                <when value="prok-gene">
                    <expand macro="prok_gene_tsv_report_columns">
                        <option value="accession" selected="true">Accession</option>
                        <option value="description" selected="true">Description</option>
                        <option value="ec-number" selected="true">EC Number</option>
                        <option value="gene-symbol" selected="true">Gene Symbol</option>
                        <option value="mapping-count" selected="true">Number of Genome Mappings</option>
                        <option value="protein-length" selected="true">Protein Length</option>
                        <option value="protein-name" selected="true">Protein Name</option>
                    </expand>
                    <expand macro="include">
                        <expand macro="gene_includes"/>
                    </expand>
                </when>
            </conditional>
            <param name="decompress" type="boolean" label="Decompress FASTA" help="By default FASTA files are provided zipped (fasta.gz) if this is checked the data will be decompressed"/>
        </section>
    </inputs>
    <outputs>
        <data name="gene_data_report" format="tabular" label="NCBI Gene Datasets: Data Report" from_work_dir="gene_data_report.tsv"/>
        <data name="gene_product_report" format="tabular" label="NCBI Gene Datasets: Product Report" from_work_dir="gene_product_report.tsv">
            <filter>file_choices['kingdom_cond']['include'] and "product-report" in file_choices['kingdom_cond']['include']</filter>
        </data>
        <data name="gene_fasta" label="NCBI Gene Datasets: Gene fasta" format="fasta" from_work_dir="ncbi_dataset/data/gene.fna">
            <filter>file_choices['kingdom_cond']['include'] and "gene" in file_choices['kingdom_cond']['include']</filter>
        </data>
        <data name="rna_fasta" label="NCBI Gene Datasets: RNA fasta" format="fasta" from_work_dir="ncbi_dataset/data/rna.fna">
            <filter>file_choices['kingdom_cond']['include'] and "rna" in file_choices['kingdom_cond']['include']</filter>
        </data>
        <data name="protein_fasta" label="NCBI Gene Datasets: protein fasta" format="fasta" from_work_dir="ncbi_dataset/data/protein.faa">
            <filter>file_choices['kingdom_cond']['include'] and "protein" in file_choices['kingdom_cond']['include']</filter>
        </data>
        <data name="cds_fasta" label="NCBI Gene Datasets: CDS fasta" format="fasta" from_work_dir="ncbi_dataset/data/cds.fna">
            <filter>file_choices['kingdom_cond']['include'] and "cds" in file_choices['kingdom_cond']['include']</filter>
        </data>
        <data name="threep_utr_fasta" label="NCBI Gene Datasets: 3' UTR fasta" format="fasta" from_work_dir="ncbi_dataset/data/3p_utr.fna">
            <filter>file_choices['kingdom_cond']['include'] and "5p-utr" in file_choices['kingdom_cond']['include']</filter>
        </data>
        <data name="fivep_utr_fasta" label="NCBI Gene Datasets: 5' UTR fasta" format="fasta" from_work_dir="ncbi_dataset/data/5p_utr.fna">
            <filter>file_choices['kingdom_cond']['include'] and "5p-utr" in file_choices['kingdom_cond']['include']</filter>
        </data>
    </outputs>
    <tests>
        <!-- 1: datasets download gene gene-id 672 -->
        <test expect_num_outputs="3">
            <conditional name="query|subcommand">
                <param name="download_by" value="gene-id"/>
                <conditional name="text_or_file">
                    <param name="text_or_file" value="text"/>
                    <param name="accession" value="672"/>
                </conditional>
            </conditional>
            <output name="gene_data_report">
                <assert_contents>
                    <has_text text="human"/>
                    <has_text text="BRCA1"/>
                    <has_n_lines n="2"/>
                    <has_n_columns n="8"/>
                </assert_contents>
            </output>
            <output name="rna_fasta">
                <assert_contents>
                    <has_text text=">"/>
                </assert_contents>
            </output>
            <output name="protein_fasta">
                <assert_contents>
                    <has_text text=">"/>
                </assert_contents>
            </output>
        </test>
        <!-- 2: datasets download gene gene-id 2597 14433 -->
        <test expect_num_outputs="3">
            <conditional name="query|subcommand">
                <param name="download_by" value="gene-id"/>
                <conditional name="text_or_file">
                    <param name="text_or_file" value="text"/>
                    <param name="accession" value="2597,14433"/>
                </conditional>
            </conditional>
            <output name="gene_data_report">
                <assert_contents>
                    <has_text text="house mouse"/>
                    <has_text text="glyceraldehyde-3-phosphate dehydrogenase"/>
                    <has_n_lines n="3"/>
                    <has_n_columns n="8"/>
                </assert_contents>
            </output>
            <output name="rna_fasta">
                <assert_contents>
                    <has_text text=">"/>
                </assert_contents>
            </output>
            <output name="protein_fasta">
                <assert_contents>
                    <has_text text=">"/>
                </assert_contents>
            </output>
        </test>
        <!-- 3: same as above + give accessions by file, 2 different outputs and ortholog-->
        <test expect_num_outputs="3">
            <conditional name="query|subcommand">
                <param name="download_by" value="gene-id"/>
                <conditional name="text_or_file">
                    <param name="text_or_file" value="file"/>
                    <param name="inputfile" value="geneids.txt"/>
                </conditional>
                <param name="ortholog" value="Haplorrhini,Strepsirrhini"/>
            </conditional>
            <section name="file_choices">
                <conditional name="kingdom_cond">
                    <param name="include" value="gene,cds"/>
                </conditional>
            </section>
            <output name="gene_data_report">
                <assert_contents>
                    <has_text text="baboon"/>
                    <has_text text="glyceraldehyde-3-phosphate dehydrogenase"/>
                    <has_n_lines n="31"/>
                    <has_n_columns n="8"/>
                </assert_contents>
            </output>
            <output name="gene_fasta">
                <assert_contents>
                    <has_text text=">"/>
                </assert_contents>
            </output>
            <output name="cds_fasta">
                <assert_contents>
                    <has_text text=">"/>
                </assert_contents>
            </output>
        </test>
        <!-- 4: datasets download gene symbol tp53 -->
        <test expect_num_outputs="1">
            <conditional name="query|subcommand">
                <param name="download_by" value="symbol"/>
                <conditional name="text_or_file">
                    <param name="text_or_file" value="text"/>
                    <param name="accession" value="tp53"/>
                </conditional>
            </conditional>
            <section name="file_choices">
                <conditional name="kingdom_cond">
                    <param name="include" value=""/>
                </conditional>
            </section>
            <output name="gene_data_report">
                <assert_contents>
                    <has_text text="human"/>
                    <has_n_lines n="2"/>
                    <has_n_columns n="8"/>
                </assert_contents>
            </output>
        </test>
        <!-- 5: datasets download gene symbol brca1 \-\-taxon mouse -->
        <test expect_num_outputs="4">
            <conditional name="query|subcommand">
                <param name="download_by" value="symbol"/>
                <conditional name="text_or_file">
                    <param name="text_or_file" value="text"/>
                    <param name="accession" value="brca1"/>
                </conditional>
                <param name="taxon" value="mouse"/>
            </conditional>
            <section name="file_choices">
                <conditional name="kingdom_cond">
                    <param name="include" value="3p-utr,5p-utr,product-report"/>
                </conditional>
            </section>
            <output name="gene_data_report">
                <assert_contents>
                    <has_text text="house mouse"/>
                    <has_text text="Brca1"/>
                    <has_n_lines n="2"/>
                    <has_n_columns n="8"/>
                </assert_contents>
            </output>
            <output name="gene_product_report">
                <assert_contents>
                    <has_text text="house mouse"/>
                    <has_text text="XR_004936704.1"/>
                    <has_n_lines n="137"/>
                    <has_n_columns n="38"/>
                </assert_contents>
            </output>
            <output name="threep_utr_fasta">
                <assert_contents>
                    <has_text text=">"/>
                </assert_contents>
            </output>
            <output name="fivep_utr_fasta">
                <assert_contents>
                    <has_text text=">"/>
                </assert_contents>
            </output>
        </test>
        <!-- 6: datasets download gene symbol brca1 \-\-ortholog -->
        <test expect_num_outputs="1">
            <conditional name="query|subcommand">
                <param name="download_by" value="symbol"/>
                <conditional name="text_or_file">
                    <param name="text_or_file" value="text"/>
                    <param name="accession" value="brca1"/>
                </conditional>
                <param name="ortholog" value="rodentia"/>
            </conditional>
            <section name="file_choices">
                <conditional name="kingdom_cond">
                    <param name="include" value=""/>
                </conditional>
            </section>
            <output name="gene_data_report">
                <assert_contents>
                    <has_text text="rat"/>
                    <has_text text="Brca1"/>
                    <has_n_lines n="38"/>
                    <has_n_columns n="8"/>
                </assert_contents>
            </output>
        </test>

        <!-- 7: datasets download gene accession NP_000483.3 -->
        <test expect_num_outputs="1">
            <conditional name="query|subcommand">
                <param name="download_by" value="accession"/>
                <conditional name="text_or_file">
                    <param name="text_or_file" value="text"/>
                    <param name="accession" value="NP_000483.3"/>
                </conditional>
            </conditional>
            <section name="file_choices">
                <conditional name="kingdom_cond">
                    <param name="include" value=""/>
                </conditional>
            </section>
            <output name="gene_data_report">
                <assert_contents>
                    <has_text text="human"/>
                    <has_n_lines n="2"/>
                    <has_n_columns n="8"/>
                </assert_contents>
            </output>
        </test>
        <!-- 8: datasets download gene accession NM_000546.6 NM_000492.4 + ortholog-->
        <test expect_num_outputs="1">
            <conditional name="query|subcommand">
                <param name="download_by" value="accession"/>
                <conditional name="text_or_file">
                    <param name="text_or_file" value="text"/>
                    <param name="accession" value="NM_000546.6 NM_000492.4"/>
                </conditional>
                <param name="ortholog" value="true"/>
            </conditional>
            <section name="file_choices">
                <conditional name="kingdom_cond">
                    <param name="include" value=""/>
                </conditional>
            </section>
            <output name="gene_data_report">
                <assert_contents>
                    <has_text text="human"/>
                    <has_n_lines n="823"/>
                    <has_n_columns n="8"/>
                </assert_contents>
            </output>
        </test>

        <!-- 9: datasets download gene accession WP_004675351.1 + include_flanks_bp -->
        <test expect_num_outputs="3">
            <conditional name="query|subcommand">
                <param name="download_by" value="accession"/>
                <conditional name="text_or_file">
                    <param name="text_or_file" value="text"/>
                    <param name="accession" value="WP_004675351.1"/>
                </conditional>
                <param name="include_flanks_bp" value="100"/>
            </conditional>
            <section name="file_choices">
                <conditional name="kingdom_cond">
                    <param name="kingdom_sel" value="prok-gene"/>
                    <param name="include" value="gene,protein"/>
                </conditional>
            </section>
            <output name="gene_data_report">
                <assert_contents>
                    <has_text text="glcE"/>
                    <has_n_lines n="2"/>
                    <has_n_columns n="7"/>
                </assert_contents>
            </output>
            <output name="gene_fasta">
                <assert_contents>
                    <has_text text=">"/>
                </assert_contents>
            </output>
            <output name="protein_fasta">
                <assert_contents>
                    <has_text text=">"/>
                </assert_contents>
            </output>
            <assert_command>
                <has_text text="include-flanks-bp 100"/>
            </assert_command>
        </test> 

        <!-- 10: datasets download gene taxon human   -->
        <test expect_num_outputs="1">
            <conditional name="query|subcommand">
                <param name="download_by" value="taxon"/>
                <param name="taxon_positional" value="human"/>
            </conditional>
            <section name="file_choices">
                <conditional name="kingdom_cond">
                    <param name="include" value=""/>
                </conditional>
            </section>
            <output name="gene_data_report">
                <assert_contents>
                    <has_text text="human"/>
                    <has_n_lines n="72533"/>
                    <has_n_columns n="8"/>
                </assert_contents>
            </output>
        </test> 
        <!-- 11: datasets download gene taxon human + \-\-fasta-filter  -->
        <test expect_num_outputs="2">
            <conditional name="query|subcommand">
                <param name="download_by" value="taxon"/>
                <param name="taxon_positional" value="human"/>
            </conditional>
            <section name="file_choices">
                <conditional name="kingdom_cond">
                    <param name="include" value="protein"/>
                </conditional>
            </section>
            <section name="filters">
                <conditional name="fasta_filter_cond">
                    <param name="fasta_filter_select" value="text"/>
                    <param name="fasta_filter" value="NP_542432.2"/>
                </conditional>
            </section>
            <output name="gene_data_report">
                <assert_contents>
                    <has_text text="human"/>
                    <has_n_lines n="72533"/>
                    <has_n_columns n="8"/>
                </assert_contents>
            </output>
            <output name="protein_fasta">
                <assert_contents>
                    <has_text text=">" n="1" />
                </assert_contents>
            </output></test>
    </tests>
    <help>
<![CDATA[
**Download Gene Datasets from NCBI**

Download a gene dataset (gene sequence, transcipt, amino acid sequences, 
nucleotide coding sequences, 5'-UTR, 3'-UTR) as well as gene and gene
product reports. Genes can be referred by gene id, symbol, accession,
or taxon.
]]>
    </help>
</tool>