Mercurial > repos > iuc > ont_fast5_api_compress_fast5
changeset 0:7147b894702a draft
"planemo upload for repository https://github.com/nanoporetech/ont_fast5_api/ commit a5d038871ff0e1b133039b59183dee795449b383"
| author | iuc |
|---|---|
| date | Fri, 12 Jun 2020 15:08:47 -0400 |
| parents | |
| children | 52da1e2c82d3 |
| files | compress_fast5.xml macros.xml test-data/list.txt test-data/multi.fast5.tar test-data/single.fast5.tar |
| diffstat | 5 files changed, 175 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/compress_fast5.xml Fri Jun 12 15:08:47 2020 -0400 @@ -0,0 +1,89 @@ +<?xml version="1.0"?> +<tool id="ont_fast5_api_compress_fast5" name="@TOOL_NAME@ Compress" version="@TOOL_VERSION@+galaxy0" profile="18.01"> + <description>multi read file(s)</description> + <macros> + <import>macros.xml</import> + </macros> + <expand macro="requirements"/> + <version_command><![CDATA[compress_fast5 -v]]></version_command> + <command detect_errors="exit_code"><![CDATA[ +## initialize +@INITIALIZE@ + +## run +compress_fast5 +## required +@INPUTPATH@ +@SAVEPATH@ +@COMPRESSION@ +## optional +@THREADS@ + +## create tarball +@TARBALL@ + ]]></command> + <inputs> + <expand macro="input"/> + <expand macro="compression"> + <option value="vbz" selected="true">VBZ</option> + </expand> + </inputs> + <outputs> + <expand macro="output"/> + </outputs> + <tests> + <!-- #1 default --> + <test expect_num_outputs="1"> + <param name="input_path" value="multi.fast5.tar"/> + <output name="out_results"> + <assert_contents> + <has_size value="40960"/> + </assert_contents> + </output> + </test> + <!-- #2 --> + <test expect_num_outputs="1"> + <param name="input_path" value="multi.fast5.tar"/> + <param name="compression" value="vbz_legacy_v0"/> + <output name="out_results"> + <assert_contents> + <has_size value="40960"/> + </assert_contents> + </output> + </test> + <!-- #3 --> + <test expect_num_outputs="1"> + <param name="input_path" value="multi.fast5.tar"/> + <param name="compression" value="gzip"/> + <output name="out_results"> + <assert_contents> + <has_size value="40960"/> + </assert_contents> + </output> + </test> + </tests> + <help><![CDATA[ +.. class:: infomark + +**What it does** + +@WID@ + +*compress_fast5* copies and converts raw data between vbz and gzip compression formats. + +**Input** + +Multi read file(s) in FAST5 format that are stored in a flat TAR. + +**Output** + +Multi read FAST5 file(s) containing compressed reads that are stored in a flat TAR. Further detail of HDF5 data management strategies can be found `here <https://support.hdfgroup.org/HDF5/doc/Advanced/FileSpaceManagement/FileSpaceManagement.pdf>`_. + +.. class:: infomark + +**References** + +@REFERENCES@ + ]]></help> + <expand macro="citations"/> +</tool> \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Fri Jun 12 15:08:47 2020 -0400 @@ -0,0 +1,83 @@ +<?xml version="1.0"?> +<macros> + <token name="@TOOL_VERSION@">3.1.3</token> + <token name="@TOOL_NAME@">ont_fast5_api:</token> + <xml name="requirements"> + <requirements> + <requirement type="package" version="@TOOL_VERSION@">ont-fast5-api</requirement> + <requirement type="package" version="1.10.5">hdf5</requirement> + </requirements> + </xml> + + <!-- command --> + <token name="@BATCHSIZE@"><![CDATA[ +--batch_size $batch_size + ]]></token> + <token name="@COMPRESSION@"><![CDATA[ +#if $compression != 'none' + --compression '$compression' +#end if + ]]></token> + <token name="@INITIALIZE@"><![CDATA[ +mkdir -p './data' && +tar -xf '$input_path' -C './data' && + ]]></token> + <token name="@INPUTPATH@"><![CDATA[ +--input_path './data' + ]]></token> + <token name="@SAVEPATH@"><![CDATA[ +--save_path './results' + ]]></token> + <token name="@TARBALL@"><![CDATA[ +&& find './results' -type f -name '*.fast5' | tar --transform 's/.*\///g' -cvf './results.fast5.tar' --files-from=/dev/stdin + ]]></token> + <token name="@THREADS@"><![CDATA[ +--threads \${GALAXY_SLOTS:-4} + ]]></token> + + <!-- input --> + <xml name="input" token_argument="--input_path" token_label="multi"> + <param argument="@ARGUMENT@" type="data" format="fast5.tar" label="Select @LABEL@ read input file"/> + </xml> + <xml name="batch_size"> + <param argument="--batch_size" type="integer" value="4000" min="1" label="Set batch size" help="Number of single reads to include in each multi read file"/> + </xml> + <xml name="compression"> + <param argument="compression" type="select" label="Select output compression type"> + <yield/> + <option value="vbz_legacy_v0">VBZ legacy v0</option> + <option value="gzip">GZIP</option> + </param> + </xml> + + <!-- output --> + <xml name="output"> + <data name="out_results" format="fast5.tar" from_work_dir="results.fast5.tar" label="${tool.name} on ${on_string}: Results"/> + </xml> + + <!-- help --> + <token name="@WID@"><![CDATA[ +*ont_fast5_api* is a simple interface to HDF5 files of the Oxford Nanopore FAST5 file format. + +- concrete implementation of the FAST5 file schema using the generic h5py library +- plain-english-named methods to interact with and reflect the FAST5 file schema +- tools to convert between multi_read and single_read formats +- tools to compress/decompress raw data in files + ]]></token> + <token name="@REFERENCES@"><![CDATA[ +More information are available on `github <https://github.com/nanoporetech/ont_fast5_api>`_. + ]]></token> + + <xml name="citations"> + <citations> + <citation type="bibtex"> + @online{ont_fast5_api, + author = {Oxford Nanopore Technologies }, + title = {ont_fast5_api}, + year = 2020, + url = {https://github.com/nanoporetech/ont_fast5_api}, + urldate = {2020-06-01} + }</citation> + </citations> + </xml> +</macros>