Mercurial > repos > iuc > data_manager_mash_sketch_builder
view data_manager/mash_sketch_builder.xml @ 2:ce1d5c8d5bff draft
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/data_managers/data_manager_mash_sketch_builder/ commit 02d2967f77e3fa5a18aea63dc84aa9ab418dc165"
author | iuc |
---|---|
date | Sun, 22 Nov 2020 12:50:56 +0000 |
parents | 2af9137ba067 |
children |
line wrap: on
line source
<?xml version="1.0"?> <tool id="mash_sketch_builder" name="Mash Sketch" tool_type="manage_data" version="@TOOL_VERSION@+galaxy0" profile="18.09"> <description>builder</description> <requirements> <requirement type="package" version="@TOOL_VERSION@">mash</requirement> <requirement type="package" version="3.7">python</requirement> </requirements> <macros> <token name="@TOOL_VERSION@">2.1</token> </macros> <version_command>mash --version</version_command> <command detect_errors="exit_code"> <![CDATA[ python '$__tool_directory__/mash_sketch_builder.py' '${out_file}' --threads \${GALAXY_SLOTS:-1} #if str( $input_sequence_source.input_sequence_source_selector ) == "tool_data_table": --fasta '${input_sequence_source.input_sequence.fields.path}' #elif str( $input_sequence_source.input_sequence_source_selector ) == 'history': --fasta '${input_sequence_source.input_sequence}' #end if --sketch-name '${sketch_name}' --sketch-size '${sketch_size}' --kmer-size '${kmer_size}' --probability-threshold '${probability_threshold}' ${individual_sequences} ]]> </command> <inputs> <conditional name="input_sequence_source"> <param name="input_sequence_source_selector" type="select" label="Select a sequence from your history or use one from a tool data table?"> <option value="tool_data_table">Sequence from tool data table</option> <option selected="True" value="history">Sequence from history</option> </param> <when value="tool_data_table"> <param name="input_sequence" type="select" label="Source FASTA Sequence"> <options from_data_table="all_fasta"/> </param> </when> <when value="history"> <param name="input_sequence" type="data" format="fasta" label="Input sequence" help=""/> </when> </conditional> <param type="text" name="sketch_name" label="Sketch name" help="Human-readable description of the sketch"/> <param type="integer" name="sketch_size" value="1000" min="10" max="1000000" label="Sketch size" help="Each sketch will have at most this many non-redundant min-hashes."/> <param type="integer" name="kmer_size" value="21" min="1" max="32" label="K-mer size" help="Hashes will be based on strings of this many nucleotides."/> <param type="float" name="probability_threshold" value="0.01" min="0." max="1." label="Probability threshold for warning about low k-mer size." /> <param type="boolean" name="individual_sequences" truevalue="--individual-sequences" falsevalue="" label="Sketch individual sequences" help="e.g. for multi-fastas of single-chromosome genomes or pair-wise gene comparisons."/> </inputs> <outputs> <data name="out_file" format="data_manager_json" /> </outputs> <tests> <test> <param name="input_sequence_source_selector" value="history"/> <param name="input_sequence" value="test_assembly.fasta"/> <param name="sketch_name" value="Test Sketch" /> <output name="out_file" value="mash_sketch_data_manager.json" compare="sim_size" /> </test> </tests> <help><![CDATA[ **What it does** Create a sketch file, which is a reduced representation of a sequence or set of sequences (based on min-hashes) that can be used for fast distance estimations. For output, one sketch file will be generated, but it can have multiple sketches within it, divided by sequences or files. ]]></help> <citations> <citation type="doi">10.1186/s13059-016-0997-x</citation> </citations> </tool>