Mercurial > repos > iuc > khmer_partition
changeset 6:e562293ee5ec draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/khmer commit 7de685f4763d988a5a9abce4a9c2b4714daaf165"
| author | iuc |
|---|---|
| date | Wed, 18 Dec 2019 16:03:58 -0500 |
| parents | 766ec3dad7ff |
| children | b7429b53be2a |
| files | do-partition.xml macros.xml test-data/test-abund-read-2.fa.gz |
| diffstat | 3 files changed, 44 insertions(+), 31 deletions(-) [+] |
line wrap: on
line diff
--- a/do-partition.xml Fri Sep 07 11:02:11 2018 -0400 +++ b/do-partition.xml Wed Dec 18 16:03:58 2019 -0500 @@ -1,5 +1,5 @@ -<tool id="khmer_partition" name="Sequence partition all-in-one" version="@WRAPPER_VERSION@.0"> - <description>Load, partition, and annotate FAST[AQ] sequences</description> +<tool id="khmer_partition" name="khmer: Sequence partition all-in-one" version="@WRAPPER_VERSION@@TOOL_VERSION@"> + <description>Load, partition, and annotate sequences</description> <macros> <token name="@BINARY@">do-partition.py</token> <import>macros.xml</import> @@ -8,16 +8,14 @@ <expand macro="stdio" /> <expand macro="version" /> <command><![CDATA[ -set -xu && -#for $num, $input in enumerate($inputs) - ln -s ${input} sequence-${num} && -#end for +set -u && +@LINK_SEQUENCES@ mkdir -p output && cd output && @BINARY@ @TABLEPARAMS@ @THREADS@ output -../sequence-* +@USE_SEQUENCES@ ]]> </command> <inputs> @@ -25,21 +23,18 @@ <expand macro="tableinputs" /> </inputs> <outputs> - <data name="information" format="txt" from_work_dir="output.info" label="${tool.name} summary." /> - <collection name="annotated_sequence_files" type="list"> - <discover_datasets pattern="__name__" directory="output" /> - </collection> + <data name="information" format="txt" from_work_dir="output.info" label="${tool.name} on ${on_string}: summary." /> + <expand macro="output_sequences" extension="part"/> </outputs> <tests> <test> <param name="inputs" value="random-20-a.fa"/> - <output_collection name="annotated_sequence_files" type="list"> - <element name="sequence-0.part" file="random-20-a.fa.part" /> + <output_collection name="sequences" type="list"> + <element name="random-20-a.fa" file="random-20-a.fa.part" /> </output_collection> </test> </tests> <help><![CDATA[ - Load in a set of sequences, partition them, merge the partitions, and annotate the original sequences files with the partition information.
--- a/macros.xml Fri Sep 07 11:02:11 2018 -0400 +++ b/macros.xml Wed Dec 18 16:03:58 2019 -0500 @@ -1,8 +1,10 @@ <macros> - <token name="@WRAPPER_VERSION@">3.0.0a1</token> + <token name="@WRAPPER_VERSION@">3.0.0a3</token> + <token name="@TOOL_VERSION@">+galaxy1</token> <xml name="requirements"> <requirements> <requirement type="package" version="@WRAPPER_VERSION@">khmer</requirement> + <yield/> </requirements> </xml> <xml name="version"> @@ -35,7 +37,7 @@ <option value="specific">Show</option> </param> <when value="simple"> - <param name="tablesize" type="select" label="Sample Type" display="radio"> + <param argument="" name="tablesize" type="select" label="Sample Type" display="radio"> <option value="1e9" selected="true">Microbial Genome</option> <option value="2e9">Animal Transcriptome</option> <option value="4e9">Small Animal Genome or Low-Diversity Metagenome</option> @@ -43,15 +45,32 @@ </param> </when> <when value="specific"> - <param name="ksize" type="integer" value="20" label="k-mer size" help="k-mer size to use" /> - <param name="n_tables" type="integer" min="1" value="4" label="n_tables" help="number of tables to use" /> - <param name="tablesize_specific" type="text" value="1000000.0" + <param argument="--ksize" name="ksize" type="integer" value="20" label="k-mer size" help="k-mer size to use" /> + <param argument="--n_tables" name="n_tables" type="integer" min="1" value="4" label="n_tables" help="number of tables to use" /> + <param argument="--max-tablesize" name="tablesize_specific" type="text" value="1000000.0" label="tablesize" help="(--max-tablesize) upper bound on the tablesize to use" /> </when> </conditional> </xml> + <token name="@LINK_SEQUENCES@"> +<![CDATA[ +#import re +mkdir input/ && +#set gzip="" +#for $num, $input in enumerate($inputs) + ln -s '${input}' 'input/$re.sub("[^\w\-_.]", "_", $input.element_identifier).$input.ext' && + #if str($input).endswith(".gz"): + #set gzip="--gzip" + #end if +#end for]]></token> + <token name="@USE_SEQUENCES@"> +<![CDATA[ +#for $num, $input in enumerate($inputs) + '../input/$re.sub("[^\w\-_.]", "_", $input.element_identifier).$input.ext' +#end for]]></token> + <xml name="input_sequences_filenames"> - <param name="inputs" multiple="true" type="data" format="fasta,fastq" + <param name="inputs" multiple="true" type="data" format="fasta,fastq,fasta.gz,fastq.gz" label="Sequences in FASTA or FASTQ format" help="Put in order of precedence such as longest reads first." /> </xml> @@ -66,27 +85,26 @@ </xml> <xml name="abundance-histogram-output"> <data name="output_histogram_filename" format="txt" - label="${tool.name} k-mer abundance histogram. The + label="${tool.name} on ${on_string}: k-mer abundance histogram. The columns are: (1) k-mer abundance, (2) k-mer count, (3) cumulative count, (4) fraction of total distinct k-mers." /> </xml> - <xml name="output_sequences"> - <data name="output" format_source="inputs" - label="${tool.name} processed nucleotide sequence file"> - <discover_datasets pattern="__designation_and_ext__" directory="output" visible="true"/> - </data> + <xml name="output_sequences" token_extension=""> + <collection name="sequences" type="list"> + <discover_datasets pattern="(?P<name>.*)\.(?P<ext>fast[aq](\.gz)?)\.@EXTENSION@" directory="output" /> + </collection> </xml> <xml name="output_sequences_single"> <data name="output" format_source="input_sequence_filename" - label="${tool.name} processed nucleotide sequence file" /> + label="${tool.name} on ${on_string}: processed nucleotide sequence file" /> </xml> <xml name="input_zero"> - <param name="zero" type="boolean" truevalue="" falsevalue="--no-zero" checked="true" - help="Output zero count bins (--no-zero)" /> + <param argument="--no-zero" name="zero" type="boolean" truevalue="" falsevalue="--no-zero" checked="true" + help="Output zero count bins" /> </xml> <xml name="input_bigcount"> - <param name="bigcount" type="boolean" truevalue="" falsevalue="--no-bigcount" - checked="true" help="Count k-mers past 255 occurences (--no-bigcount)" /> + <param argument="--no-bigcount" name="bigcount" type="boolean" truevalue="" falsevalue="--no-bigcount" + checked="true" help="Count k-mers past 255 occurences" /> </xml> <token name="@HELP_FOOTER@"><![CDATA[ (from the khmer project: http://khmer.readthedocs.org/en/v2.0/ )]]></token>