Mercurial > repos > galaxyp > thermo_raw_file_converter
diff thermo_converter.xml @ 9:92ac8e086317 draft
"planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/ThermoRawFileParser commit 9bb883e027809047684fd6c45e9a6f1f3bf69351"
| author | galaxyp |
|---|---|
| date | Wed, 17 Feb 2021 09:50:26 +0000 |
| parents | 26c6706bfb07 |
| children | b9b385097f13 |
line wrap: on
line diff
--- a/thermo_converter.xml Sat Jul 25 16:26:42 2020 -0400 +++ b/thermo_converter.xml Wed Feb 17 09:50:26 2021 +0000 @@ -1,145 +1,202 @@ -<tool id="thermo_raw_file_converter" name="Thermo" version="1.2.3+galaxy0"> +<tool id="thermo_raw_file_converter" name="Thermo" version="@TOOL_VERSION@+galaxy0" profile="20.05"> <description>RAW file converter</description> + <macros> + <token name="@TOOL_VERSION@">1.3.2</token> + </macros> <requirements> - <requirement type="package" version="1.2.3">thermorawfileparser</requirement> + <requirement type="package" version="@TOOL_VERSION@">thermorawfileparser</requirement> </requirements> + <stdio> + <regex match="ERROR" source="both" level="fatal" description="Fatal error"/> + </stdio> + <version_command><![CDATA[ThermoRawFileParser.sh --version]]></version_command> <command> <![CDATA[ #import re -mkdir ./raws_folder && -mkdir ./output_folder && -#for $input_raw in $input_files: - #set $input_name = re.sub('[^\w\-\.]', '_',$input_raw.element_identifier.split('/')[-1].replace(".raw", "") + ".raw") - ln -s -f '${input_raw}' './raws_folder/${input_name}' && -#end for +#set $input_name = re.sub('[^\w\-\.]', '_', $input_file.element_identifier.replace(".raw", "") + ".raw") +ln -s -f '$input_file' '$input_name' && ThermoRawFileParser.sh - -d=./raws_folder - -o=./output_folder - -f=$output_format + --input='$input_name' + --output_file='$output' + -f=$format_cond.output_format #if $output_metadata_selector != "off": - --metadata="${output_metadata_selector}" + --metadata="$output_metadata_selector" + --metadata_output_file='$output_metadata' + #end if + #if $format_cond.output_format == "0" + $format_cond.mgfPrecursor #end if - $zlib_boolean - $peakpicking_boolean + #if $format_cond.output_format in ['1', '2'] + $format_cond.zlib_boolean + $format_cond.peakpicking_boolean + #end if $ignore_instrument_errors_boolean - + $allDetectors + $includeExceptionData + #if $msLevel != '' + --msLevel="$msLevel" + #end if ]]> </command> <inputs> - <param name="input_files" type="data" format="thermo.raw" label="Thermo RAW file" help="" multiple="true" - optional="False" /> - - <param name="output_format" type="select" label="Output format"> - <option value="0">mgf</option> - <option value="1" selected="True">mzml</option> - <option value="2">Indexed mzml</option> - </param> - - <param name="zlib_boolean" type="boolean" truevalue="" falsevalue="-z" checked="true" - label="Use zlib compression for the m/z ratios and intensities" help="" /> - - <param name="peakpicking_boolean" type="boolean" truevalue="" falsevalue="-p" checked="true" - label="Use the peak picking provided by the native thermo library" help="" /> - - <param name="ignore_instrument_errors_boolean" type="boolean" truevalue="-e" falsevalue="" checked="true" - label="Ignore missing instrument properties" help="If false, it stops the conversion if instrument properties are missing" /> - - <param name="output_metadata_selector" type="select" label="Output metadata" > + <param argument="--input" name="input_file" type="data" format="thermo.raw" label="Thermo RAW file" help="" optional="False"/> + <conditional name="format_cond"> + <param argument="--format" name="output_format" type="select" label="Output format"> + <option value="0">mgf</option> + <option value="1" selected="True">mzml</option> + <option value="2">Indexed mzml</option> + <!-- <option value="3">Parquet</option> --> + </param> + <when value="0"> + <param argument="--mgfPrecursor" type="boolean" truevalue="--mgfPrecursor" falsevalue="" label="Include precursor scan number in MGF file" help=""/> + </when> + <when value="1"> + <param argument="--noZlibCompression" name="zlib_boolean" type="boolean" truevalue="" falsevalue="-z" checked="true" + label="Use zlib compression for the m/z ratios and intensities" help=""/> + <param argument="--noPeakPicking" name="peakpicking_boolean" type="boolean" truevalue="" falsevalue="-p" checked="true" + label="Use the peak picking provided by the native thermo library" help=""/> + </when> + <when value="2"> + <param argument="--noZlibCompression" name="zlib_boolean" type="boolean" truevalue="" falsevalue="-z" checked="true" + label="Use zlib compression for the m/z ratios and intensities" help=""/> + <param argument="--noPeakPicking" name="peakpicking_boolean" type="boolean" truevalue="" falsevalue="-p" checked="true" + label="Use the peak picking provided by the native thermo library" help=""/> + </when> + <when value="3"/> + </conditional> + <param argument="--metadata" name="output_metadata_selector" type="select" label="Output metadata"> <option value="off" selected="True">No</option> <option value="0">json</option> <option value="1">txt</option> </param> - + <param argument="--ignoreInstrumentErrors" name="ignore_instrument_errors_boolean" type="boolean" truevalue="-e" falsevalue="" checked="true" + label="Ignore missing instrument properties" help="If false, it stops the conversion if instrument properties are missing"/> + <param argument="--allDetectors" type="boolean" truevalue="--allDetectors" falsevalue="" checked="false" label="Extract additional detector data" help="UV/PDA etc"/> + <param argument="--includeExceptionData" type="boolean" truevalue="--includeExceptionData" falsevalue="" label="Include reference and exception data"/> + <param argument="--msLevel" type="text" value="" label="Select MS levels " help="(MS1, MS2, etc) included in the output, should be a comma-separated list of integers ( 1,2,3 ) and/or intervals ( 1-3 ), open-end intervals ( 1- ) are allowed"> + <sanitizer invalid_char=""> + <valid initial="string.digits"> + <add value="-"/> + <add value=","/> + </valid> + </sanitizer> + </param> </inputs> <outputs> - - <collection name="output_mgf_collection" type="list" label="${tool.name} on ${on_string}: MGF collection"> - <filter>output_format == "0"</filter> - <discover_datasets pattern="(?P<designation>.+)\.mgf" directory="output_folder" ext="mgf"/> - </collection> - - <collection name="output_mzml_collection" type="list" label="${tool.name} on ${on_string}: mzML collection"> - <filter>output_format == "1"</filter> - <discover_datasets pattern="(?P<designation>.+)\.mzML" ext="mzml" directory="output_folder"/> - </collection> - - <collection name="output_indexedmzml_collection" type="list" label="${tool.name} on ${on_string}: Indexed mzML collection"> - <filter>output_format == "2"</filter> - <discover_datasets pattern="(?P<designation>.+)\.mzML" ext="mzml" directory="output_folder"/> - </collection> - - <collection name="output_metadata_collection" type="list" label="${tool.name} on ${on_string}: metadata collection"> + <data name="output" format="mzml" label="${tool.name} on ${on_string}"> + <change_format> + <when input="format_cond.output_format" value="0" format="mgf"/> + <!-- <when input="format_cond.output_format" value="3" format="parquet"/> --> + </change_format> + </data> + <data name="output_metadata" format="txt" label="${tool.name} on ${on_string}: metadata"> <filter>output_metadata_selector != "off"</filter> - <discover_datasets pattern="(?P<designation>.+)-metadata.txt" ext="txt" directory="output_folder"/> - <discover_datasets pattern="(?P<designation>.+)-metadata.json" ext="json" directory="output_folder"/> - </collection> - + <change_format> + <when input="output_metadata_selector" value="0" format="json"/> + </change_format> + </data> </outputs> <tests> - <!-- Basic mgf test - 1 file --> + <!-- mgf test, no metadata --> <test expect_num_outputs="1"> - <param name="input_files" value="really_small.raw" ftype="thermo.raw"/> - <param name="output_format" value="0"/> - <output_collection name="output_mgf_collection" type="list" count="1"/> - - <!--<output name="output" file="really_small.mzml" ftype="mzml" compare="sim_size" delta="3000" />--> + <param name="input_file" value="really_small.raw" ftype="thermo.raw"/> + <conditional name="format_cond"> + <param name="output_format" value="0"/> + <param name="mgfPrecursor" value="true"/> + </conditional> + <output name="output" ftype="mgf" value="really_small.mgf"> + <assert_contents> + <has_text text="SCANS=36"/> + <has_text text="RTINSECONDS=73.863181104"/> + <has_text text="PEPMASS=675.248779296875"/> + <has_text text="CHARGE=2+"/> + <has_text text="121.3116455 920.2367553711"/> + <has_text text="229.2241211 1137.6958007813"/> + <has_text text="1577.8967285 1487.9519042969"/> + </assert_contents> + </output> + <assert_command> + <has_text text="--mgfPrecursor"></has_text> + </assert_command> </test> - - <!-- Basic mzml test - 2 files --> - <test expect_num_outputs="1"> - <param name="input_files" value="really_small.raw,really_small_2.raw" ftype="thermo.raw"/> - <param name="output_format" value="1"/> - <output_collection name="output_mzml_collection" type="list" count="2"/> + <!-- mzml test and json metadata --> + <test expect_num_outputs="2"> + <param name="input_file" value="really_small.raw" ftype="thermo.raw"/> + <conditional name="format_cond"> + <param name="output_format" value="1"/> + </conditional> + <param name="output_metadata_selector" value="0"/> + <output name="output" file="really_small.mzml" ftype="mzml"/> + <output name="output_metadata" value="really_small.json" ftype="json"/> + <assert_command> + <not_has_text text="--mgfPrecursor"></not_has_text> + </assert_command> </test> - <!-- Testing contents of converted mgf file with txt metadata --> + <!-- mzml test (wo zlib compression and peak picking) and json metadata --> <test expect_num_outputs="2"> - <param name="input_files" value="really_small.raw" ftype="thermo.raw"/> - <param name="output_format" value="0"/> - <param name="output_metadata_selector" value="1"/> - <output_collection name="output_mgf_collection" type="list" count="1"> - <element name="really_small" ftype="mgf"> - <assert_contents> - <has_text text="SCANS=36"/> - <has_text text="RTINSECONDS=73.863181104"/> - <has_text text="PEPMASS=675.248779296875"/> - <has_text text="CHARGE=2+"/> - <has_text text="121.3116455 920.2367553711"/> - <has_text text="229.2241211 1137.6958007813"/> - <has_text text="1577.8967285 1487.9519042969"/> - </assert_contents> - </element> - </output_collection> - <output_collection name="output_metadata_collection" type="list"> - <element name="really_small" ftype="txt"> - <assert_contents> - <has_text text="Instrument model=[MS, MS:1000494, Thermo Scientific instrument model, Orbitrap Fusion]"/> - <has_text text="Instrument name=Orbitrap Fusion"/> - <has_text text="Instrument serial number=[MS, MS:1000529, instrument serial number, FSN10188]"/> - <has_text text="Software version=[NCIT, NCIT:C111093, Software Version, 3.1.2412.17]"/> - <has_text text="Mass resolution=[MS, MS:1000011, mass resolution, 0.500]"/> - <has_text text="Number of scans=101"/> - <has_text text="Scan range=1;101"/> - <has_text text="Scan start time=[MS, MS:1000016, scan start time, 0.89]"/> - <has_text text="Time range=0.89;1.59"/> - <has_text text="Mass range=120.0000;2000.0000"/> - </assert_contents> - </element> - </output_collection> + <param name="input_file" value="really_small.raw" ftype="thermo.raw"/> + <conditional name="format_cond"> + <param name="output_format" value="1"/> + <param name="zlib_boolean" value="false"/> + <param name="peakpicking_boolean" value="false"/> + </conditional> + <param name="output_metadata_selector" value="0"/> + <output name="output" file="really_small_ext.mzml" ftype="mzml"/> + <output name="output_metadata" value="really_small.json" ftype="json"/> + <assert_command> + <not_has_text text="--mgfPrecursor"></not_has_text> + <has_text text="-z "></has_text> + <has_text text="-p "></has_text> + </assert_command> </test> - <!-- mgf collection test with metadata --> + <!-- indexed mzml, txt metadata (+ extra options) --> <test expect_num_outputs="2"> - <param name="input_files" value="really_small.raw,really_small_2.raw,really_small_3.raw"/> - <param name="output_format" value="0"/> - <param name="output_metadata_selector" value="0"/> - <output_collection name="output_mgf_collection" type="list" count="3"/> - <output_collection name="output_metadata_collection" type="list" count="3"/> + <param name="input_file" value="really_small.raw" ftype="thermo.raw"/> + <conditional name="format_cond"> + <param name="output_format" value="2"/> + </conditional> + <param name="output_metadata_selector" value="1"/> + <param name="ignore_instrument_errors_boolean" value="true"/> + <param name="allDetectors" value="true"/> + <param name="includeExceptionData" value="--includeExceptionData"/> + <param name="msLevel" value="1"/> + <output name="output" value="really_small.indexed_mzML" ftype="mzml"/> + <output name="output_metadata" ftype="txt"> + <assert_contents> + <has_text text="Instrument model=[MS, MS:1000494, Thermo Scientific instrument model, Orbitrap Fusion]"/> + <has_text text="Instrument name=Orbitrap Fusion"/> + <has_text text="Instrument serial number=[MS, MS:1000529, instrument serial number, FSN10188]"/> + <has_text text="Software version=[NCIT, NCIT:C111093, Software Version, 3.1.2412.17]"/> + <has_text text="Mass resolution=[MS, MS:1000011, mass resolution, 0.500]"/> + <has_text text="Number of scans=101"/> + <has_text text="Scan range=1;101"/> + <has_text text="Scan start time=[MS, MS:1000016, scan start time, 0.89]"/> + <has_text text="Time range=0.89;1.59"/> + <has_text text="Mass range=120.0000;2000.0000"/> + </assert_contents> + </output> + <assert_command> + <not_has_text text="--mgfPrecursor"></not_has_text> + <has_text text="-e "/> + <has_text text="--allDetectors"/> + <has_text text="--includeExceptionData"/> + <has_text text="--msLevel="1""/> + </assert_command> </test> +<!-- parquet test, no metadata + <test expect_num_outputs="1"> + <param name="input_file" value="really_small.raw" ftype="thermo.raw"/> + <conditional name="format_cond"> + <param name="output_format" value="3"/> + </conditional> + <output name="output" ftype="parquet" value="really_small.parquet"/> + </test> --> </tests> <help> <![CDATA[ @@ -149,12 +206,6 @@ ]]> </help> <citations> - <citation type="bibtex">@misc{Galaxy Proteomics Tools, - author = {Niels Hulstaert, et al.}, - title = {Galaxy Proteomics Tools}, - publisher = {GitHub}, - journal = {GitHub repository}, - year = {2017}, url = {https://github.com/compomics/ThermoRawFileParser}} - </citation> + <citation type="doi">10.1021/acs.jproteome.9b00328</citation> </citations> </tool>