Mercurial > repos > iuc > ncbi_datasets
changeset 11:ac24fff14f23 draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/ncbi_datasets commit 4d7d3a56084e140f4fa63fb0e04a08b732f247f2
| author | iuc |
|---|---|
| date | Fri, 02 Dec 2022 10:52:48 +0000 |
| parents | a3395b1d871b |
| children | d78faac2c6ef |
| files | datasets_gene.xml datasets_genome.xml macros.xml test-data/geneids.txt |
| diffstat | 4 files changed, 973 insertions(+), 113 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/datasets_gene.xml Fri Dec 02 10:52:48 2022 +0000 @@ -0,0 +1,536 @@ +<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>
--- a/datasets_genome.xml Mon Nov 21 11:40:05 2022 +0000 +++ b/datasets_genome.xml Fri Dec 02 10:52:48 2022 +0000 @@ -5,16 +5,17 @@ </macros> <expand macro="requirements"></expand> <command><![CDATA[ +#import re @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 $query.subcommand.text_or_file.accession.split(' ') if x) + #echo " ".join(f"'{x}'" for x in re.split(" |,", str($query.subcommand.text_or_file.accession)) if x) #else --inputfile '$query.subcommand.text_or_file.inputfile' #end if #else: - '$query.subcommand.taxon' + '$query.subcommand.taxon_positional' $query.subcommand.tax_exact_match #end if $filters.reference @@ -37,24 +38,55 @@ --search '$filters.search_term' #end for --no-progressbar -#if $uncompressed -&& 7z x -y ncbi_dataset.zip -#else -&& 7z l ncbi_dataset.zip > ncbi_dataset.txt +--dehydrated + +## produce TSV report file +&& dataformat tsv genome + --package ncbi_dataset.zip + --fields #echo ",".join($file_choices.report_columns) + > genome_data_report.tsv + +## unzip and rehydrate if any data is to be downloaded (include is not None) +#if $file_choices.include + ## unzip + && 7z x -y ncbi_dataset.zip > 7z.log + + ## rehydrate + && datasets rehydrate + --directory ./ + #if not $file_choices.decompress + --gzip + #end if + --max-workers \${NCBI_DATASETS_MAX_WORKERS:-10} + + ## rename all faa, fna (resp faa.gz, fna.gz) to fasta (resp fasta.gz) to allow discovery + && find ncbi_dataset \( -name "*.faa" -o -name "*.fna" -o -name "*.faa.gz" -o -name "*.fna.gz" \) -exec sh -c 'mv {} \$(echo {} | sed "s/.f[an]a\(.gz\)\?\$/.fasta\1/")' \; + + ## unzip all compressed (non-fasta) files (jsonl files are just named .gz) + && find ncbi_dataset -name "*.jsonl.gz" -exec sh -c 'mv {} \$(dirname {})/\$(basename {} .gz)' \; + #if $file_choices.decompress + && find ncbi_dataset \( -name "*.gz" ! -name "*fasta.gz" \) -exec gunzip {} \; + #end if + + #if "seq-report" in $file_choices.include + && find ncbi_dataset -name sequence_report.jsonl -exec sh -c 'dataformat tsv genome-seq --inputfile {} > \$(dirname {})/\$(basename {} .jsonl).tsv' \; + #end if + + && true ## because Galaxy removes trailing ; from command #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> + <option value="accession">By NCBI assembly or BioProject accession</option> + <option value="taxon">By taxon (NCBI Taxonomy ID, scientific or common name at any tax rank)</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."/> + <expand macro="taxon_positional"/> <param argument="--tax-exact-match" type="boolean" truevalue="--tax-exact-match" falsevalue="" label="Exclude sub-species when a species-level taxon is specified"/> </when> </conditional> @@ -67,7 +99,6 @@ <option value="latest">Latest</option> <option value="all">All</option> </param> - <!-- TODO add test for assembly source: according to CLI doc args are RefSeq, GenBank, All and not refseq / genbank--> <expand macro="assembly_source"/> <expand macro="chromosomes"/> <param argument="--exclude-atypical" type="boolean" truevalue="--exclude-atypical" falsevalue="" label="Exclude atypical assemblies"/> @@ -78,82 +109,93 @@ <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="include"/> + <section name="file_choices" title="Output options" expanded="true"> + <expand macro="tsv_report_columns"> + <option value="accession" selected="true">accession</option> + <option value="organism-name" selected="true">organism-name</option> + <option value="assminfo-submitter" selected="true">assminfo-submitter</option> + <option value="assminfo-name" selected="true">assminfo-name</option> + </expand> + <expand macro="include"> + <expand macro="genome_includes"/> + </expand> + <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> - <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> + <data name="genome_data_report" format="tabular" label="NCBI Genome Datasets: Data Report" from_work_dir="genome_data_report.tsv"/> <collection name="sequence_report" label="NCBI Genome Datasets: Sequence Data Report" type="list"> - <discover_datasets pattern="(?P<identifier_0>.*?)\/sequence_report.jsonl" ext="json" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/> - <filter>uncompressed and file_choices['include'] and "seq-report" in file_choices['include']</filter> + <discover_datasets pattern="(?P<identifier_0>.*?)\/sequence_report.tsv" ext="tabular" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/> + <filter>file_choices['include'] and "seq-report" in file_choices['include']</filter> </collection> <collection name="genome_fasta" label="NCBI Genome Datasets: genome fasta" type="list:list"> - <discover_datasets pattern="(?P<identifier_0>.*?)/(?!rna|cds_from)(?P<identifier_1>.*?)(_genomic)?.fna" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/> - <filter>uncompressed and file_choices['include'] and "genome" in file_choices['include']</filter> + <discover_datasets pattern="(?P<identifier_0>.*?)/(?!rna|cds_from)(?P<identifier_1>.*?)(_genomic)?\.(?P<ext>fasta(\.gz)?)" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/> + <filter>file_choices['include'] and "genome" in file_choices['include']</filter> </collection> <collection name="rna_fasta" label="NCBI Genome Datasets: RNA fasta" type="list"> - <discover_datasets pattern="(?P<identifier_0>.*?)\/rna\.fna" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/> - <filter>uncompressed and file_choices['include'] and "rna" in file_choices['include']</filter> + <discover_datasets pattern="(?P<identifier_0>.*?)\/rna\.(?P<ext>fasta(\.gz)?)$" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/> + <filter>file_choices['include'] and "rna" in file_choices['include']</filter> </collection> <collection name="protein_fasta" label="NCBI Genome Datasets: protein fasta" type="list"> - <discover_datasets pattern="(?P<identifier_0>.*?)\/protein\.faa" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/> - <filter>uncompressed and file_choices['include'] and "protein" in file_choices['include']</filter> + <discover_datasets pattern="(?P<identifier_0>.*?)\/protein\.(?P<ext>fasta(\.gz)?)$" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/> + <filter>file_choices['include'] and "protein" in file_choices['include']</filter> </collection> <collection name="genomic_cds" label="NCBI Genome Datasets: genomic cds fasta" type="list"> - <discover_datasets pattern="(?P<identifier_0>.*?)\/cds_from_genomic\.fna" ext="fasta" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/> - <filter>uncompressed and file_choices['include'] and "cds" in file_choices['include']</filter> + <discover_datasets pattern="(?P<identifier_0>.*?)\/cds_from_genomic\.(?P<ext>fasta(\.gz)?)$" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/> + <filter>file_choices['include'] and "cds" in file_choices['include']</filter> </collection> <collection name="genomic_gff" label="NCBI Genome Datasets: genomic gff3" type="list"> <discover_datasets pattern="(?P<identifier_0>.*?)\/genomic\.gff" ext="gff3" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/> - <filter>uncompressed and file_choices['include'] and "gff3" in file_choices['include']</filter> + <filter>file_choices['include'] and "gff3" in file_choices['include']</filter> </collection> <collection name="genomic_gtf" label="NCBI Genome Datasets: gtf" type="list"> <discover_datasets pattern="(?P<identifier_0>.*?)\/genomic\.gtf" ext="gtf" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/> - <filter>uncompressed and file_choices['include'] and "gtf" in file_choices['include']</filter> + <filter>file_choices['include'] and "gtf" in file_choices['include']</filter> </collection> <collection name="genomic_gbff" label="NCBI Genome Datasets: GenBank flatfile" type="list"> <discover_datasets pattern="(?P<identifier_0>.*?)\/genomic\.gbff" ext="txt" directory="ncbi_dataset/data" recurse="true" match_relative_path="true"/> - <filter>uncompressed and file_choices['include'] and "gbff" in file_choices['include']</filter> + <filter>file_choices['include'] and "gbff" in file_choices['include']</filter> </collection> </outputs> <tests> - <test expect_num_outputs="2"> + <!-- Note: All but one test use the non-default decompress="true" + + this is because (at 11/22) Galaxy can not apply text assertions on the content + of compressed files https://github.com/galaxyproject/galaxy/pull/15085 + + So with decompress="true" more powerfull assertions are powerful. + A single test checks the default, ie decompress="false". + --> + <test expect_num_outputs="1"> <conditional name="query|subcommand"> <param name="download_by" value="taxon"/> - <param name="text_or_file" value="text"/> - <param name="taxon" value="human"/> + <param name="taxon_positional" value="human"/> </conditional> <param name="chromosomes" value="21"/> - <param name="include" value=""/> - <param name="uncompressed" value="false"/> <param name="released_before" value="01/01/2018"/> - <output name="archive_contents"> + <section name="file_choices"> + <param name="include" value=""/> + </section> + <output name="genome_data_report"> <assert_contents> - <has_text text="ncbi_dataset/data/dataset_catalog.json"/> + <has_text text="Assembly Accession	Assembly Name	Assembly Submitter	Organism Name"/> + <has_n_lines n="144"/> + <has_n_columns n="4"/> </assert_contents> </output> </test> <test expect_num_outputs="2"> <conditional name="query|subcommand"> <param name="download_by" value="taxon"/> - <param name="text_or_file" value="text"/> - <param name="taxon" value="human"/> + <param name="taxon_positional" value="human"/> </conditional> <param name="chromosomes" value="21"/> - <param name="include" value="genome"/> - <param name="uncompressed" value="true"/> <param name="assembly_level" value="chromosome,complete"/> <param name="released_before" value="01/01/2018"/> + <section name="file_choices"> + <param name="include" value="genome"/> + <param name="decompress" value="true"/> + </section> <output_collection name="genome_fasta" type="list:list" count="14"> <expand macro="genome_fasta_assert" el1="GCA_000002115.2" el2="chr21" expression=">"/> <expand macro="genome_fasta_assert" el1="GCA_000002125.2" el2="chr21" expression=">"/> @@ -174,22 +216,24 @@ <output name="genome_data_report"> <assert_contents> <has_text text="Homo sapiens"/> + <has_n_columns n="4"/> </assert_contents> </output> </test> - <!-- same as precious test but assembly_source (refseq which removes some of the genomes) --> + <!-- same as previous test but assembly_source (refseq which removes some of the genomes) --> <test expect_num_outputs="2"> <conditional name="query|subcommand"> <param name="download_by" value="taxon"/> - <param name="text_or_file" value="text"/> - <param name="taxon" value="human"/> + <param name="taxon_positional" value="human"/> </conditional> <param name="chromosomes" value="21"/> - <param name="include" value="genome"/> - <param name="uncompressed" value="true"/> <param name="assembly_level" value="chromosome,complete"/> <param name="assembly_source" value="refseq"/> <param name="released_before" value="01/01/2018"/> + <section name="file_choices"> + <param name="include" value="genome"/> + <param name="decompress" value="true"/> + </section> <output_collection name="genome_fasta" type="list:list" count="2"> <expand macro="genome_fasta_assert" el1="GCF_000002125.1" el2="chr21" expression=">"/> <expand macro="genome_fasta_assert" el1="GCF_000306695.2" el2="chr21" expression=">"/> @@ -197,6 +241,8 @@ <output name="genome_data_report"> <assert_contents> <has_text text="Homo sapiens"/> + <has_n_lines n="5"/> + <has_n_columns n="4"/> </assert_contents> </output> </test> @@ -208,21 +254,41 @@ <param name="accession" value="GCF_000013305.1 GCF_000007445.1"/> </conditional> </conditional> - <param name="include" value="seq-report,gtf,cds"/> - <param name="uncompressed" value="true"/> <param name="released_before" value="01/01/2007"/> + <section name="file_choices"> + <param name="include" value="seq-report,gtf,cds"/> + <param name="decompress" value="true"/> + </section> <output name="genome_data_report"> <assert_contents> <has_text text="GCF_000013305.1"/> + <has_n_lines n="3"/> + <has_n_columns n="4"/> </assert_contents> </output> + <output_collection name="sequence_report" type="list" count="2" > + <element name="GCF_000007445.1"> + <assert_contents> + <has_text text="GCF_000007445.1"/> + <has_n_lines n="2"/> + <has_n_columns n="14"/> + </assert_contents> + </element> + <element name="GCF_000013305.1"> + <assert_contents> + <has_text text="GCF_000013305.1"/> + <has_n_lines n="2"/> + <has_n_columns n="14"/> + </assert_contents> + </element> + </output_collection> <output_collection name="genomic_gtf" type="list"> <element name="GCF_000007445.1" file="GCF_000007445.1.genomic.gtf" compare="contains"/> <element name="GCF_000013305.1" file="genome.2.GCF_000013305.1.genomic.gtf" compare="contains"/> </output_collection> <output_collection name="genomic_cds" type="list"> - <element name="GCF_000007445.1" file="genome.2.GCF_000007445.1.genomic.cds" compare="contains"/> - <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" decompress="true"/> + <element name="GCF_000013305.1" file="genome.2.GCF_000013305.1.genomic.cds" compare="contains" decompress="true"/> </output_collection> </test> <test expect_num_outputs="4"> @@ -233,12 +299,17 @@ <param name="inputfile" value="accessions.txt"/> </conditional> </conditional> - <param name="include" value="seq-report,gbff,gff3"/> - <param name="uncompressed" value="true"/> <param name="released_before" value="01/01/2007"/> + <section name="file_choices"> + <param name="include" value="seq-report,gff3,gbff"/> + <param name="decompress" value="true"/> + </section> <output name="genome_data_report"> <assert_contents> - <has_text text="SAMN02604181"/> + <has_text text="GCF_000013305.1"/> + <has_text text="GCF_000007445.1"/> + <has_n_lines n="3"/> + <has_n_columns n="4"/> </assert_contents> </output> <output_collection name="genomic_gff" type="list"> @@ -250,7 +321,9 @@ <element name="GCF_000013305.1" file="genome.3.GCF_000013305.1.genomic.gbff" compare="contains"/> </output_collection> </test> - <test expect_num_outputs="2"> + + <!-- should not fail https://github.com/ncbi/datasets/issues/194 --> + <test expect_num_outputs="2" expect_failure="true"> <conditional name="query|subcommand"> <param name="download_by" value="accession"/> <conditional name="text_or_file"> @@ -258,32 +331,14 @@ <param name="accession" value="GCF_000001405"/> </conditional> </conditional> - <param name="include" value="seq-report"/> - <param name="uncompressed" value="true"/> <param name="released_before" value="01/01/2015"/> <param name="assembly_version" value="all"/> - <output_collection name="sequence_report" count="4"> - <element name="GCF_000001405.25"> - <assert_contents> - <has_text text="assignedMoleculeLocationType"/> - </assert_contents> - </element> - <element name="GCF_000001405.26"> - <assert_contents> - <has_text text="assignedMoleculeLocationType"/> - </assert_contents> - </element> - <element name="GCF_000001405.27"> - <assert_contents> - <has_text text="assignedMoleculeLocationType"/> - </assert_contents> - </element> - <element name="GCF_000001405.28"> - <assert_contents> - <has_text text="assignedMoleculeLocationType"/> - </assert_contents> - </element> - </output_collection> + <section name="file_choices"> + <param name="include" value="seq-report"/> + </section> + <!-- + <output_collection name="sequence_report" type="list" count="4" > + --> </test> <test expect_num_outputs="5"> <conditional name="query|subcommand"> @@ -293,11 +348,64 @@ <param name="accession" value="GCF_000146045.2"/> </conditional> </conditional> - <param name="include" value="seq-report,genome,rna,cds"/> - <param name="uncompressed" value="true"/> + <section name="file_choices"> + <param name="include" value="genome,protein,rna,cds"/> + <param name="decompress" value="true"/> + </section> <output_collection name="genome_fasta" type="list:list" count="1"> <expand macro="genome_fasta_assert" el1="GCF_000146045.2" el2="GCF_000146045.2_R64" expression=">NC_[0-9]+\.[0-9]+ Saccharomyces cerevisiae S288[Cc] (mitochondrion|chromosome .*), complete (sequence|genome)" expression_n="17"/> </output_collection> + <output_collection name="protein_fasta" type="list" count="1"> + <element name="GCF_000146045.2" decompress="true"> + <assert_contents> + <has_text text=">"/> + </assert_contents> + </element> + </output_collection> + <output_collection name="rna_fasta" type="list" count="1"> + <element name="GCF_000146045.2" decompress="true"> + <assert_contents> + <has_text text=">"/> + </assert_contents> + </element> + </output_collection> + </test> + <!-- same as the previous test, but use the default value for decompress, + see comment at the beginning of the tests --> + <test expect_num_outputs="5"> + <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="GCF_000146045.2"/> + </conditional> + </conditional> + <section name="file_choices"> + <param name="include" value="genome,protein,rna,cds"/> + </section> + <output_collection name="genome_fasta" type="list:list" count="1"> + <element name="GCF_000146045.2"> + <element name="GCF_000146045.2_R64" ftype="fasta.gz"> + <assert_contents> + <has_size value="3843460"/> + </assert_contents> + </element> + </element> + </output_collection> + <output_collection name="protein_fasta" type="list" count="1"> + <element name="GCF_000146045.2" ftype="fasta.gz"> + <assert_contents> + <has_size value="1844838"/> + </assert_contents> + </element> + </output_collection> + <output_collection name="rna_fasta" type="list" count="1"> + <element name="GCF_000146045.2" ftype="fasta.gz"> + <assert_contents> + <has_size value="2784534"/> + </assert_contents> + </element> + </output_collection> </test> <test expect_num_outputs="3"> <conditional name="query|subcommand"> @@ -307,8 +415,11 @@ <param name="accession" value="GCF_000146045.2 GCF_000002945.1"/> </conditional> </conditional> - <param name="include" value="seq-report,genome"/> - <param name="uncompressed" value="true"/> + <section name="file_choices"> + <param name="include" value="seq-report,genome"/> + <param name="decompress" value="true"/> + </section> + <output_collection name="sequence_report" type="list" count="2"/> <output_collection name="genome_fasta" type="list:list" count="2"> <expand macro="genome_fasta_assert" el1="GCF_000002945.1" el2="GCF_000002945.1_ASM294v2" expression=">NC_[0-9]+\.[0-9]+ Schizosaccharomyces pombe (mitochondrion|chromosome .*), complete (sequence|genome)" expression_n="4"/> <expand macro="genome_fasta_assert" el1="GCF_000146045.2" el2="GCF_000146045.2_R64" expression=">NC_[0-9]+\.[0-9]+ Saccharomyces cerevisiae S288[Cc] (mitochondrion|chromosome .*), complete (sequence|genome)" expression_n="17"/> @@ -320,12 +431,10 @@ <test expect_num_outputs="1" expect_test_failure="true"> <conditional name="query|subcommand"> <param name="download_by" value="taxon"/> - <param name="text_or_file" value="text"/> - <param name="taxon" value="4932"/> + <param name="taxon_positional" value="4932"/> <param name="tax_exact_match" value="true"/> </conditional> <param name="include" value=""/> - <param name="uncompressed" value="true"/> <output name="genome_data_report"> <assert_contents> <has_text text="Saccharomyces cerevisiae ZTW1" negate="true"/> @@ -338,15 +447,18 @@ **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. +Genome datasets can be specified by NCBI Assembly or BioProject accession(s) or by taxon. + +The download is a three step process: -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) +1. A "dehydrated" zip file is downloaded which includes the metadata and the download URL) +2. The metadata is transformed into a tabular (TSV) file +3. The data is hydrated (the actual data is downloaded) + +The 3rd step can be skipped by unselecting all output types in the `Include` parameter. +Thereby its possible to inspect the metadata prior to the actual data download. Also this +allows to use the tool for querying data sets (and their accessions) of interest which +can then be downloaded in a second call using the accessions. ]]> </help>
--- a/macros.xml Mon Nov 21 11:40:05 2022 +0000 +++ b/macros.xml Fri Dec 02 10:52:48 2022 +0000 @@ -1,5 +1,5 @@ <macros> - <token name="@TOOL_VERSION@">14.3</token> + <token name="@TOOL_VERSION@">14.4</token> <token name="@VERSION_SUFFIX@">0</token> <token name="@PROFILE@">21.01</token> <token name="@LICENSE@">MIT</token> @@ -39,8 +39,10 @@ <option value="file">Read a list of @WHAT_EXTENDED@s from a dataset</option> </param> <when value="text"> - <param name="accession" type="text" label="Enter space separated list of @WHAT@s" help="@HELP@"> - <yield/> + <!-- command section also allows spaces as separator for backward compatibility + prefer comma because this is used also in other text params--> + <param name="accession" type="text" label="Enter comma separated list of @WHAT@s" help="@HELP@"> + <validator type="length" min="1" message="Provide at least one @WHAT@"/> </param> </when> <when value="file"> @@ -59,18 +61,45 @@ </sanitizer> </param> </xml> - <xml name="include"> - <param argument="--include" type="select" multiple="true" optional="true"> - <option value="genome" selected="true">genomic sequence (genome)</option> - <option value="rna">transcript (rna)</option> - <option value="protein">amnio acid sequences (protein)</option> - <option value="cds">nucleotide coding sequences (cds)</option> - <option value="gff3">general feature file (gff3)</option> - <option value="gtf">gene transfer format (gtf)</option> - <option value="gbff">GenBank flat file (gbff)</option> - <option value="seq-report">sequence report file (seq-report)</option> + + <xml name="taxon_positional"> + <param name="taxon_positional" type="text" label="Enter taxon" help="e.g. human, mouse, bos taurus, etc."/> + </xml> + + <xml name="ortholog"> + <param argument="--ortholog" type="text" label="Retrieve orthologs for taxa" help="Retrieve data for an ortholog set. Provide one or more comma separated taxa (any rank) to filter results or 'all' for the complete set."> + <sanitizer invalid_char=""> + <valid initial="string.letters,string.digits"> + <add value=" " /> + <add value="," /> + <add value="-" /> + </valid> + </sanitizer> </param> </xml> + + <xml name="include"> + <param argument="--include" type="select" multiple="true" optional="true" label="Include" help="Download the following datasets (if available)"> + <yield/> + </param> + </xml> + <xml name="genome_includes"> + <option value="genome" selected="true">genomic sequence (genome)</option> + <option value="rna">transcript (rna)</option> + <option value="protein">amnio acid sequences (protein)</option> + <option value="cds">nucleotide coding sequences (cds)</option> + <option value="gff3">general feature file (gff3)</option> + <option value="gtf">gene transfer format (gtf)</option> + <option value="gbff">GenBank flat file (gbff)</option> + <option value="seq-report">sequence report file (seq-report)</option> + <yield/> + </xml> + <xml name="gene_includes"> + <option value="gene">gene sequence (gene)</option> + <option value="protein" selected="true">amnio acid sequences (protein)</option> + <yield/> + </xml> + <token name="@INCLUDE@"><![CDATA[ --include #if $file_choices.include @@ -79,6 +108,187 @@ none #end if ]]></token> + <xml name="tsv_report_columns"> + <param name="report_columns" type="select" multiple="true" optional="false" label="Columns in the report"> + <option value="accession">Assembly Accession</option> + <option value="annotinfo-busco-complete">Annotation BUSCO Complete</option> + <option value="annotinfo-busco-duplicated">Annotation BUSCO Duplicated</option> + <option value="annotinfo-busco-fragmented">Annotation BUSCO Fragmented</option> + <option value="annotinfo-busco-lineage">Annotation BUSCO Lineage</option> + <option value="annotinfo-busco-missing">Annotation BUSCO Missing</option> + <option value="annotinfo-busco-singlecopy">Annotation BUSCO Single Copy</option> + <option value="annotinfo-busco-totalcount">Annotation BUSCO Total Count</option> + <option value="annotinfo-busco-ver">Annotation BUSCO Version</option> + <option value="annotinfo-featcount-gene-non-coding">Annotation Count Gene Non-coding</option> + <option value="annotinfo-featcount-gene-other">Annotation Count Gene Other</option> + <option value="annotinfo-featcount-gene-protein-coding">Annotation Count Gene Protein-coding</option> + <option value="annotinfo-featcount-gene-pseudogene">Annotation Count Gene Pseudogene</option> + <option value="annotinfo-featcount-gene-total">Annotation Count Gene Total</option> + <option value="annotinfo-method">Annotation Method</option> + <option value="annotinfo-name">Annotation Name</option> + <option value="annotinfo-pipeline">Annotation Pipeline</option> + <option value="annotinfo-provider">Annotation Provider</option> + <option value="annotinfo-release-date">Annotation Release Date</option> + <option value="annotinfo-release-version">Annotation Release Version</option> + <option value="annotinfo-report-url">Annotation Report URL</option> + <option value="annotinfo-software-version">Annotation Software Version</option> + <option value="annotinfo-status">Annotation Status</option> + <option value="assminfo-atypicalis-atypical">Assembly Atypical Is Atypical</option> + <option value="assminfo-atypicalwarnings">Assembly Atypical Warnings</option> + <option value="assminfo-bioproject-lineage-accession">Assembly BioProject Lineage Accession</option> + <option value="assminfo-bioproject-lineage-parent-accession">Assembly BioProject Lineage Parent Accession</option> + <option value="assminfo-bioproject-lineage-parent-accessions">Assembly BioProject Lineage Parent Accessions</option> + <option value="assminfo-bioproject-lineage-title">Assembly BioProject Lineage Title</option> + <option value="assminfo-biosample-accession">Assembly BioSample Accession</option> + <option value="assminfo-biosample-attribute-name">Assembly BioSample Attribute Name</option> + <option value="assminfo-biosample-attribute-value">Assembly BioSample Attribute Value</option> + <option value="assminfo-biosample-bioproject-accession">Assembly BioSample BioProject Accession</option> + <option value="assminfo-biosample-bioproject-parent-accession">Assembly BioSample BioProject Parent Accession</option> + <option value="assminfo-biosample-bioproject-parent-accessions">Assembly BioSample BioProject Parent Accessions</option> + <option value="assminfo-biosample-bioproject-title">Assembly BioSample BioProject Title</option> + <option value="assminfo-biosample-description-comment">Assembly BioSample Description Comment</option> + <option value="assminfo-biosample-description-organism-common-name">Assembly BioSample Description Organism Common Name</option> + <option value="assminfo-biosample-description-organism-infraspecific-breed">Assembly BioSample Description Organism Infraspecific Names Breed</option> + <option value="assminfo-biosample-description-organism-infraspecific-cultivar">Assembly BioSample Description Organism Infraspecific Names Cultivar</option> + <option value="assminfo-biosample-description-organism-infraspecific-ecotype">Assembly BioSample Description Organism Infraspecific Names Ecotype</option> + <option value="assminfo-biosample-description-organism-infraspecific-isolate">Assembly BioSample Description Organism Infraspecific Names Isolate</option> + <option value="assminfo-biosample-description-organism-infraspecific-sex">Assembly BioSample Description Organism Infraspecific Names Sex</option> + <option value="assminfo-biosample-description-organism-infraspecific-strain">Assembly BioSample Description Organism Infraspecific Names Strain</option> + <option value="assminfo-biosample-description-organism-name">Assembly BioSample Description Organism Name</option> + <option value="assminfo-biosample-description-organism-pangolin">Assembly BioSample Description Organism Pangolin Classification</option> + <option value="assminfo-biosample-description-organism-tax-id">Assembly BioSample Description Organism Taxonomic ID</option> + <option value="assminfo-biosample-description-title">Assembly BioSample Description Title</option> + <option value="assminfo-biosample-ids-db">Assembly BioSample Sample Identifiers Database</option> + <option value="assminfo-biosample-ids-label">Assembly BioSample Sample Identifiers Label</option> + <option value="assminfo-biosample-ids-value">Assembly BioSample Sample Identifiers Value</option> + <option value="assminfo-biosample-last-updated">Assembly BioSample Last updated</option> + <option value="assminfo-biosample-models">Assembly BioSample Models</option> + <option value="assminfo-biosample-owner-contact-lab">Assembly BioSample Owner Contact Lab</option> + <option value="assminfo-biosample-owner-name">Assembly BioSample Owner Name</option> + <option value="assminfo-biosample-package">Assembly BioSample Package</option> + <option value="assminfo-biosample-publication-date">Assembly BioSample Publication date</option> + <option value="assminfo-biosample-status-status">Assembly BioSample Status Status</option> + <option value="assminfo-biosample-status-when">Assembly BioSample Status When</option> + <option value="assminfo-biosample-submission-date">Assembly BioSample Submission date</option> + <option value="assminfo-blast-url">Assembly Blast URL</option> + <option value="assminfo-description">Assembly Description</option> + <option value="assminfo-level">Assembly Level</option> + <option value="assminfo-linked-assmaccession">Assembly Linked Assembly Accession</option> + <option value="assminfo-linked-assmtype">Assembly Linked Assembly Type</option> + <option value="assminfo-name">Assembly Name</option> + <option value="assminfo-paired-assmaccession">Assembly Paired Assembly Accession</option> + <option value="assminfo-paired-assmname">Assembly Paired Assembly Name</option> + <option value="assminfo-paired-assmstatus">Assembly Paired Assembly Status</option> + <option value="assminfo-refseq-category">Assembly Refseq Category</option> + <option value="assminfo-sequencing-tech">Assembly Sequencing Tech</option> + <option value="assminfo-status">Assembly Status</option> + <option value="assminfo-submission-date">Assembly Submission Date</option> + <option value="assminfo-submitter">Assembly Submitter</option> + <option value="assminfo-synonym">Assembly Synonym</option> + <option value="assminfo-type">Assembly Type</option> + <option value="assmstats-contig-l50">Assembly Stats Contig L50</option> + <option value="assmstats-contig-n50">Assembly Stats Contig N50</option> + <option value="assmstats-gaps-between-scaffolds-count">Assembly Stats Gaps Between Scaffolds Count</option> + <option value="assmstats-gc-count">Assembly Stats GC Count</option> + <option value="assmstats-gc-percent">Assembly Stats GC Percent</option> + <option value="assmstats-number-of-component-sequences">Assembly Stats Number of Component Sequences</option> + <option value="assmstats-number-of-contigs">Assembly Stats Number of Contigs</option> + <option value="assmstats-number-of-scaffolds">Assembly Stats Number of Scaffolds</option> + <option value="assmstats-scaffold-l50">Assembly Stats Scaffold L50</option> + <option value="assmstats-scaffold-n50">Assembly Stats Scaffold N50</option> + <option value="assmstats-total-number-of-chromosomes">Assembly Stats Total Number of Chromosomes</option> + <option value="assmstats-total-sequence-len">Assembly Stats Total Sequence Length</option> + <option value="assmstats-total-ungapped-len">Assembly Stats Total Ungapped Length</option> + <option value="current-accession">Current Accession</option> + <option value="organelle-assembly-name">Organelle Assembly Name</option> + <option value="organelle-bioproject-accessions">Organelle BioProject Accessions</option> + <option value="organelle-description">Organelle Description</option> + <option value="organelle-infraspecific-name">Organelle Infraspecific Name</option> + <option value="organelle-submitter">Organelle Submitter</option> + <option value="organelle-total-seq-length">Organelle Total Seq Length</option> + <option value="organism-common-name">Organism Common Name</option> + <option value="organism-infraspecific-breed">Organism Infraspecific Names Breed</option> + <option value="organism-infraspecific-cultivar">Organism Infraspecific Names Cultivar</option> + <option value="organism-infraspecific-ecotype">Organism Infraspecific Names Ecotype</option> + <option value="organism-infraspecific-isolate">Organism Infraspecific Names Isolate</option> + <option value="organism-infraspecific-sex">Organism Infraspecific Names Sex</option> + <option value="organism-infraspecific-strain">Organism Infraspecific Names Strain</option> + <option value="organism-name">Organism Name</option> + <option value="organism-pangolin">Organism Pangolin Classification</option> + <option value="organism-tax-id">Organism Taxonomic ID</option> + <option value="source_database">Source Database</option> + <option value="wgs-contigs-url">WGS contigs URL</option> + <option value="wgs-project-accession">WGS project accession</option> + <option value="wgs-url">WGS URL</option> + <yield/> + </param> + </xml> + + <xml name="gene_tsv_report_columns"> + <param name="report_columns" type="select" multiple="true" optional="false" label="Columns in the report"> + <option value="annotation-assembly-accession">Annotation Assembly Accession</option> + <option value="annotation-assembly-name">Annotation Assembly Name</option> + <option value="annotation-genomic-range-accession">Annotation Genomic Range Accession</option> + <option value="annotation-genomic-range-exon-order">Annotation Genomic Range Exons Order</option> + <option value="annotation-genomic-range-exon-orientation">Annotation Genomic Range Exons Orientation</option> + <option value="annotation-genomic-range-exon-start">Annotation Genomic Range Exons Start</option> + <option value="annotation-genomic-range-exon-stop">Annotation Genomic Range Exons Stop</option> + <option value="annotation-genomic-range-range-order">Annotation Genomic Range Order</option> + <option value="annotation-genomic-range-range-orientation">Annotation Genomic Range Orientation</option> + <option value="annotation-genomic-range-range-start">Annotation Genomic Range Start</option> + <option value="annotation-genomic-range-range-stop">Annotation Genomic Range Stop</option> + <option value="annotation-genomic-range-seq-name">Annotation Genomic Range Seq Name</option> + <option value="annotation-release-date">Annotation Release Date</option> + <option value="annotation-release-name">Annotation Release Name</option> + <option value="chromosomes">Chromosomes</option> + <option value="common-name">Common Name</option> + <option value="description">Description</option> + <option value="ensembl-geneids">Ensembl GeneIDs</option> + <option value="gene-id">NCBI GeneID</option> + <option value="gene-type">Gene Type</option> + <option value="genomic-region-gene-range-accession">Genomic Region Gene Range Sequence Accession</option> + <option value="genomic-region-gene-range-range-order">Genomic Region Gene Range Order</option> + <option value="genomic-region-gene-range-range-orientation">Genomic Region Gene Range Orientation</option> + <option value="genomic-region-gene-range-range-start">Genomic Region Gene Range Start</option> + <option value="genomic-region-gene-range-range-stop">Genomic Region Gene Range Stop</option> + <option value="genomic-region-genomic-region-type">Genomic Region Genomic Region Type</option> + <option value="group-id">Gene Group Identifier</option> + <option value="group-method">Gene Group Method</option> + <option value="name-authority">Nomenclature Authority</option> + <option value="name-id">Nomenclature ID</option> + <option value="omim-ids">OMIM IDs</option> + <option value="orientation">Orientation</option> + <option value="ref-standard-gene-range-accession">Reference Standard Gene Range Sequence Accession</option> + <option value="ref-standard-gene-range-range-order">Reference Standard Gene Range Order</option> + <option value="ref-standard-gene-range-range-orientation">Reference Standard Gene Range Orientation</option> + <option value="ref-standard-gene-range-range-start">Reference Standard Gene Range Start</option> + <option value="ref-standard-gene-range-range-stop">Reference Standard Gene Range Stop</option> + <option value="ref-standard-genomic-region-type">Reference Standard Genomic Region Type</option> + <option value="replaced-gene-id">Replaced NCBI GeneID</option> + <option value="rna-type">RNA Type</option> + <option value="swissprot-accessions">SwissProt Accessions</option> + <option value="symbol">Symbol</option> + <option value="synonyms">Synonyms</option> + <option value="tax-id">Taxonomic ID</option> + <option value="tax-name">Taxonomic Name</option> + <yield/> + </param> + </xml> + <xml name="prok_gene_tsv_report_columns"> + <param name="report_columns" type="select" multiple="true" optional="false" label="Columns in the report"> + <option value="accession">Accession</option> + <option value="description">Description</option> + <option value="ec-number">EC Number</option> + <option value="gene-symbol">Gene Symbol</option> + <option value="mapping-count">Number of Genome Mappings</option> + <option value="name-evidence-accession">Protein Name EvidenceAccession</option> + <option value="name-evidence-category">Protein Name EvidenceCategory</option> + <option value="name-evidence-source">Protein Name EvidenceSource</option> + <option value="protein-length">Protein Length</option> + <option value="protein-name">Protein Name</option> + <yield/> + </param> + </xml> <xml name="released_options" token_released_what="genomes" token_before_or_after="before"> <param argument="--released-@BEFORE_OR_AFTER@" type="text" optional="true" label="Only include @RELEASED_WHAT@ that have been released @BEFORE_OR_AFTER@ a specified date (MM/DD/YYYY)"> <validator type="regex" message="enter a date in the form MM/DD/YYYY">[0-9]{2}/[0-9]{2}/[0-9]{4}</validator> @@ -93,9 +303,9 @@ #end if </token> - <xml name="genome_fasta_assert" tokens="el1,el2,expression" token_expression_n="1"> + <xml name="genome_fasta_assert" tokens="el1,el2,expression" token_ftype="fasta" token_expression_n="1"> <element name="@EL1@"> - <element name="@EL2@"> + <element name="@EL2@" ftype="@FTYPE@" decompress="true"> <assert_contents> <has_text_matching expression="@EXPRESSION@" n="@EXPRESSION_N@"/> </assert_contents>