Mercurial > repos > galaxyp > openms_nucleicacidsearchengine
diff NucleicAcidSearchEngine.xml @ 4:92864c71ac6a draft
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/openms commit 3d1e5f37fd16524a415f707772eeb7ead848c5e3
| author | galaxyp |
|---|---|
| date | Thu, 01 Dec 2022 19:13:13 +0000 |
| parents | 00b91aaec050 |
| children | a19e844b82ad |
line wrap: on
line diff
--- a/NucleicAcidSearchEngine.xml Fri Nov 06 19:56:00 2020 +0000 +++ b/NucleicAcidSearchEngine.xml Thu Dec 01 19:13:13 2022 +0000 @@ -1,13 +1,11 @@ <?xml version='1.0' encoding='UTF-8'?> <!--This is a configuration file for the integration of a tools into Galaxy (https://galaxyproject.org/). This file was automatically generated using CTDConverter.--> <!--Proposed Tool Section: [Utilities]--> -<tool id="NucleicAcidSearchEngine" name="NucleicAcidSearchEngine" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@" profile="20.05"> +<tool id="NucleicAcidSearchEngine" name="NucleicAcidSearchEngine" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05"> <description>Annotate nucleic acid identifications to MS/MS spectra.</description> <macros> <token name="@EXECUTABLE@">NucleicAcidSearchEngine</token> <import>macros.xml</import> - <import>macros_autotest.xml</import> - <import>macros_test.xml</import> </macros> <expand macro="requirements"/> <expand macro="stdio"/> @@ -18,12 +16,24 @@ ## Preprocessing mkdir in && ln -s '$in' 'in/${re.sub("[^\w\-_]", "_", $in.element_identifier)}.$gxy2omsext($in.ext)' && -mkdir database && -ln -s '$database' 'database/${re.sub("[^\w\-_]", "_", $database.element_identifier)}.$gxy2omsext($database.ext)' && +#if $database: + mkdir database && + ln -s '$database' 'database/${re.sub("[^\w\-_]", "_", $database.element_identifier)}.$gxy2omsext($database.ext)' && +#end if +#if $digest: + mkdir digest && + ln -s '$digest' 'digest/${re.sub("[^\w\-_]", "_", $digest.element_identifier)}.$gxy2omsext($digest.ext)' && +#end if mkdir out && #if "id_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') mkdir id_out && #end if +#if "db_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') + mkdir db_out && +#end if +#if "digest_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') + mkdir digest_out && +#end if #if "lfq_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') mkdir lfq_out && #end if @@ -42,14 +52,28 @@ @EXECUTABLE@ -ini @EXECUTABLE@.ctd -in 'in/${re.sub("[^\w\-_]", "_", $in.element_identifier)}.$gxy2omsext($in.ext)' --database -'database/${re.sub("[^\w\-_]", "_", $database.element_identifier)}.$gxy2omsext($database.ext)' +#if $database: + -database + 'database/${re.sub("[^\w\-_]", "_", $database.element_identifier)}.$gxy2omsext($database.ext)' +#end if +#if $digest: + -digest + 'digest/${re.sub("[^\w\-_]", "_", $digest.element_identifier)}.$gxy2omsext($digest.ext)' +#end if -out 'out/output.${gxy2omsext("mztab")}' #if "id_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') -id_out 'id_out/output.${gxy2omsext("idxml")}' #end if +#if "db_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') + -db_out + 'db_out/output.${gxy2omsext("sqlite")}' +#end if +#if "digest_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') + -digest_out + 'digest_out/output.${gxy2omsext("sqlite")}' +#end if #if "lfq_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') -lfq_out 'lfq_out/output.${gxy2omsext("tabular")}' @@ -71,6 +95,12 @@ #if "id_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') && mv 'id_out/output.${gxy2omsext("idxml")}' '$id_out' #end if +#if "db_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') + && mv 'db_out/output.${gxy2omsext("sqlite")}' '$db_out' +#end if +#if "digest_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') + && mv 'digest_out/output.${gxy2omsext("sqlite")}' '$digest_out' +#end if #if "lfq_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',') && mv 'lfq_out/output.${gxy2omsext("tabular")}' '$lfq_out' #end if @@ -88,14 +118,15 @@ <configfile name="hardcoded_json"><![CDATA[{"log": "log.txt", "threads": "\${GALAXY_SLOTS:-1}", "no_progress": true}]]></configfile> </configfiles> <inputs> - <param name="in" argument="-in" type="data" format="mzml" optional="false" label="Input file: spectra" help=" select mzml data sets(s)"/> - <param name="database" argument="-database" type="data" format="fasta" optional="false" label="Input file: sequence database" help=" select fasta data sets(s)"/> - <section name="precursor" title="Precursor (Parent Ion) Options" help="" expanded="false"> + <param argument="-in" type="data" format="mzml" optional="false" label="Input file: spectra" help=" select mzml data sets(s)"/> + <param argument="-database" type="data" format="fasta" optional="true" label="Input file: sequence database" help="Required unless 'digest' is set select fasta data sets(s)"/> + <param argument="-digest" type="data" format="sqlite" optional="true" label="Input file: pre-digested sequence database" help="Can be used instead of 'database'. Sets all 'oligo:...' parameters select sqlite data sets(s)"/> + <section name="precursor" title="Precursor (parent ion) options" help="" expanded="false"> <param name="mass_tolerance" argument="-precursor:mass_tolerance" type="float" optional="true" value="10.0" label="Precursor mass tolerance (+/- around uncharged precursor mass)" help=""/> - <param name="mass_tolerance_unit" argument="-precursor:mass_tolerance_unit" display="radio" type="select" optional="false" label="Unit of precursor mass tolerance" help=""> + <param name="mass_tolerance_unit" argument="-precursor:mass_tolerance_unit" type="select" optional="true" label="Unit of precursor mass tolerance" help=""> <option value="Da">Da</option> <option value="ppm" selected="true">ppm</option> - <expand macro="list_string_san"/> + <expand macro="list_string_san" name="mass_tolerance_unit"/> </param> <param name="min_charge" argument="-precursor:min_charge" type="integer" optional="true" value="-1" label="Minimum precursor charge to be considered" help=""/> <param name="max_charge" argument="-precursor:max_charge" type="integer" optional="true" value="-20" label="Maximum precursor charge to be considered" help=""/> @@ -103,19 +134,19 @@ <param name="use_avg_mass" argument="-precursor:use_avg_mass" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Use average instead of monoisotopic precursor masses (appropriate for low-resolution instruments)" help=""/> <param name="use_adducts" argument="-precursor:use_adducts" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Consider possible salt adducts (see 'precursor:potential_adducts') when matching precursor masses" help=""/> <param name="potential_adducts" argument="-precursor:potential_adducts" type="text" optional="true" value="Na:+" label="Adducts considered to explain mass differences" help="Format: 'Element:Charge(+/-)', i.e. the number of '+' or '-' indicates the charge, e.g. 'Ca:++' indicates +2. Only used if 'precursor:use_adducts' is set (space separated list, in order to allow for spaces in list items surround them by single quotes)"> - <expand macro="list_string_val"/> - <expand macro="list_string_san"/> + <expand macro="list_string_val" name="potential_adducts"/> + <expand macro="list_string_san" name="potential_adducts"/> </param> <param name="isotopes" argument="-precursor:isotopes" type="text" optional="true" value="0 1 2 3 4" label="Correct for mono-isotopic peak misassignments" help="E.g.: 1 = precursor may be misassigned to the first isotopic peak. Ignored if 'use_avg_mass' is set (space separated list, in order to allow for spaces in list items surround them by single quotes)"> - <expand macro="list_integer_valsan"/> + <expand macro="list_integer_valsan" name="isotopes"/> </param> </section> <section name="fragment" title="Fragment (Product Ion) Options" help="" expanded="false"> <param name="mass_tolerance" argument="-fragment:mass_tolerance" type="float" optional="true" value="10.0" label="Fragment mass tolerance (+/- around fragment m/z)" help=""/> - <param name="mass_tolerance_unit" argument="-fragment:mass_tolerance_unit" display="radio" type="select" optional="false" label="Unit of fragment mass tolerance" help=""> + <param name="mass_tolerance_unit" argument="-fragment:mass_tolerance_unit" type="select" optional="true" label="Unit of fragment mass tolerance" help=""> <option value="Da">Da</option> <option value="ppm" selected="true">ppm</option> - <expand macro="list_string_san"/> + <expand macro="list_string_san" name="mass_tolerance_unit"/> </param> <param name="ions" argument="-fragment:ions" multiple="true" type="select" optional="true" label="Fragment ions to include in theoretical spectra" help=""> <option value="a-B" selected="true">a-B</option> @@ -127,12 +158,11 @@ <option value="x" selected="true">x</option> <option value="y" selected="true">y</option> <option value="z" selected="true">z</option> - <expand macro="list_string_san"/> + <expand macro="list_string_san" name="ions"/> </param> </section> - <section name="modifications" title="Modifications Options" help="" expanded="false"> + <section name="modifications" title="Modification options" help="" expanded="false"> <param name="variable" argument="-modifications:variable" multiple="true" type="select" optional="true" label="Variable modifications" help=""> - <option value="">default (nothing chosen)</option> <option value="m1Am">m1Am</option> <option value="m1Gm">m1Gm</option> <option value="m1Im">m1Im</option> @@ -301,6 +331,11 @@ <option value="mcmo5U">mcmo5U</option> <option value="yW">yW</option> <option value="imG">imG</option> + <option value="dA">dA</option> + <option value="dC">dC</option> + <option value="dG">dG</option> + <option value="dU">dU</option> + <option value="dT">dT</option> <option value="3'-p">3'-p</option> <option value="5'-p">5'-p</option> <option value="mA">mA</option> @@ -330,47 +365,51 @@ <option value="mmmG?">mmmG?</option> <option value="ac4C/f5Cm?">ac4C/f5Cm?</option> <option value="acp3U/cmnm5Um?">acp3U/cmnm5Um?</option> - <expand macro="list_string_san"/> + <expand macro="list_string_san" name="variable"/> </param> <param name="variable_max_per_oligo" argument="-modifications:variable_max_per_oligo" type="integer" optional="true" value="2" label="Maximum number of residues carrying a variable modification per candidate oligonucleotide" help=""/> <param name="resolve_ambiguities" argument="-modifications:resolve_ambiguities" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Attempt to resolve ambiguous modifications" help="(e.g. 'mA?' for 'mA'/'Am') based on a-B ions.. This incurs a performance cost because two modifications have to be considered for each case.. Requires a-B ions to be enabled in parameter 'fragment:ions'"/> </section> - <section name="oligo" title="Oligonucleotide Options" help="" expanded="false"> + <section name="oligo" title="Oligonucleotide (digestion) options (ignored if 'digest' input is used)" help="" expanded="false"> <param name="min_size" argument="-oligo:min_size" type="integer" optional="true" value="5" label="Minimum size an oligonucleotide must have after digestion to be considered in the search" help=""/> <param name="max_size" argument="-oligo:max_size" type="integer" optional="true" value="0" label="Maximum size an oligonucleotide must have after digestion to be considered in the search, leave at 0 for no limit" help=""/> <param name="missed_cleavages" argument="-oligo:missed_cleavages" type="integer" optional="true" value="1" label="Number of missed cleavages" help=""/> - <param name="enzyme" argument="-oligo:enzyme" type="select" optional="false" label="The enzyme used for RNA digestion" help=""> + <param name="enzyme" argument="-oligo:enzyme" type="select" optional="true" label="The enzyme used for RNA digestion" help=""> <option value="RNase_T1">RNase_T1</option> <option value="cusativin">cusativin</option> + <option value="RNase_H">RNase_H</option> + <option value="mazF">mazF</option> + <option value="colicin_E5">colicin_E5</option> + <option value="no cleavage" selected="true">no cleavage</option> <option value="RNase_U2">RNase_U2</option> <option value="RNase_A">RNase_A</option> <option value="RNase_MC1">RNase_MC1</option> - <option value="RNase_H">RNase_H</option> - <option value="no cleavage" selected="true">no cleavage</option> <option value="unspecific cleavage">unspecific cleavage</option> - <expand macro="list_string_san"/> + <expand macro="list_string_san" name="enzyme"/> </param> </section> <section name="report" title="Reporting Options" help="" expanded="false"> <param name="top_hits" argument="-report:top_hits" type="integer" optional="true" min="0" value="1" label="Maximum number of top-scoring hits per spectrum that are reported ('0' for all hits)" help=""/> </section> - <section name="fdr" title="False Discovery Rate Options" help="" expanded="false"> + <section name="fdr" title="False Discovery Rate options" help="" expanded="false"> <param name="decoy_pattern" argument="-fdr:decoy_pattern" type="text" optional="true" value="" label="String used as part of the accession to annotate decoy sequences" help="(e.g. 'DECOY_'). Leave empty to skip the FDR/q-value calculation"> - <expand macro="list_string_san"/> + <expand macro="list_string_san" name="decoy_pattern"/> </param> <param name="cutoff" argument="-fdr:cutoff" type="float" optional="true" min="0.0" max="1.0" value="1.0" label="Cut-off for FDR filtering; search hits with higher q-values will be removed" help=""/> <param name="remove_decoys" argument="-fdr:remove_decoys" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Do not score hits to decoy sequences and remove them when filtering" help=""/> </section> <expand macro="adv_opts_macro"> - <param name="decharge_ms2" argument="-decharge_ms2" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Decharge the MS2 spectra for scoring" help=""/> - <param name="force" argument="-force" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Overrides tool-specific checks" help=""/> - <param name="test" argument="-test" type="hidden" optional="true" value="False" label="Enables the test mode (needed for internal use only)" help=""> - <expand macro="list_string_san"/> + <param argument="-decharge_ms2" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Decharge the MS2 spectra for scoring" help=""/> + <param argument="-force" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Overrides tool-specific checks" help=""/> + <param argument="-test" type="hidden" optional="true" value="False" label="Enables the test mode (needed for internal use only)" help=""> + <expand macro="list_string_san" name="test"/> </param> </expand> <param name="OPTIONAL_OUTPUTS" type="select" optional="true" multiple="true" label="Optional outputs"> <option value="id_out_FLAG">id_out (Output file: idXML (for visualization in TOPPView))</option> - <option value="lfq_out_FLAG">lfq_out (Output file: Targets for label-free quantification using FeatureFinderMetaboIdent ('id' input))</option> + <option value="db_out_FLAG">db_out (Output file: oms (SQLite database))</option> + <option value="digest_out_FLAG">digest_out (Output file: sequence database digest)</option> + <option value="lfq_out_FLAG">lfq_out (Output file: targets for label-free quantification using FeatureFinderMetaboIdent ('id' input))</option> <option value="theo_ms2_out_FLAG">theo_ms2_out (Output file: theoretical MS2 spectra for precursor mass matches)</option> <option value="exp_ms2_out_FLAG">exp_ms2_out (Output file: experimental MS2 spectra for precursor mass matches)</option> <option value="ctd_out_FLAG">Output used ctd (ini) configuration file</option> @@ -381,6 +420,12 @@ <data name="id_out" label="${tool.name} on ${on_string}: id_out" format="idxml"> <filter>OPTIONAL_OUTPUTS is not None and "id_out_FLAG" in OPTIONAL_OUTPUTS</filter> </data> + <data name="db_out" label="${tool.name} on ${on_string}: db_out" format="sqlite"> + <filter>OPTIONAL_OUTPUTS is not None and "db_out_FLAG" in OPTIONAL_OUTPUTS</filter> + </data> + <data name="digest_out" label="${tool.name} on ${on_string}: digest_out" format="sqlite"> + <filter>OPTIONAL_OUTPUTS is not None and "digest_out_FLAG" in OPTIONAL_OUTPUTS</filter> + </data> <data name="lfq_out" label="${tool.name} on ${on_string}: lfq_out" format="tabular"> <filter>OPTIONAL_OUTPUTS is not None and "lfq_out_FLAG" in OPTIONAL_OUTPUTS</filter> </data> @@ -394,13 +439,119 @@ <filter>OPTIONAL_OUTPUTS is not None and "ctd_out_FLAG" in OPTIONAL_OUTPUTS</filter> </data> </outputs> - <tests> - <expand macro="autotest_NucleicAcidSearchEngine"/> - <expand macro="manutest_NucleicAcidSearchEngine"/> + <tests><!-- UTILS_NucleicAcidSearchEngine_1 --> + <test expect_num_outputs="5"> + <section name="adv_opts"> + <param name="decharge_ms2" value="false"/> + <param name="force" value="false"/> + <param name="test" value="true"/> + </section> + <param name="in" value="NucleicAcidSearchEngine_1.mzML"/> + <param name="database" value="NucleicAcidSearchEngine_1.fasta"/> + <output name="out" file="NucleicAcidSearchEngine_12_out.mzTab" compare="sim_size" delta_frac="0.7" ftype="mztab"/> + <output name="id_out" file="NucleicAcidSearchEngine_11_out.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/> + <output name="db_out" file="NucleicAcidSearchEngine_13_out.tmp" compare="sim_size" delta_frac="0.7" ftype="sqlite"/> + <output name="digest_out" file="NucleicAcidSearchEngine_1_digest.oms" compare="sim_size" delta_frac="0.7" ftype="sqlite"/> + <section name="precursor"> + <param name="mass_tolerance" value="5.0"/> + <param name="mass_tolerance_unit" value="ppm"/> + <param name="min_charge" value="-2"/> + <param name="max_charge" value="-14"/> + <param name="include_unknown_charge" value="true"/> + <param name="use_avg_mass" value="false"/> + <param name="use_adducts" value="false"/> + <param name="potential_adducts" value=""K:+" "Na:+" "Na2:++" "K2:++" "NaK:++" "K3:+++" "Na3:+++" "NaK2:+++" "Na2K:+++""/> + <param name="isotopes" value="0 1 2"/> + </section> + <section name="fragment"> + <param name="mass_tolerance" value="5.0"/> + <param name="mass_tolerance_unit" value="ppm"/> + <param name="ions" value="a-B,c,w,y"/> + </section> + <section name="modifications"> + <param name="variable"/> + <param name="variable_max_per_oligo" value="2"/> + <param name="resolve_ambiguities" value="false"/> + </section> + <section name="oligo"> + <param name="min_size" value="5"/> + <param name="max_size" value="0"/> + <param name="missed_cleavages" value="22"/> + <param name="enzyme" value="no cleavage"/> + </section> + <section name="report"> + <param name="top_hits" value="1"/> + </section> + <section name="fdr"> + <param name="decoy_pattern" value="DECOY_"/> + <param name="cutoff" value="0.05"/> + <param name="remove_decoys" value="true"/> + </section> + <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG,id_out_FLAG,db_out_FLAG,digest_out_FLAG"/> + <output name="ctd_out" ftype="xml"> + <assert_contents> + <is_valid_xml/> + </assert_contents> + </output> + </test> + <!-- UTILS_NucleicAcidSearchEngine_2 --> + <test expect_num_outputs="4"> + <section name="adv_opts"> + <param name="decharge_ms2" value="false"/> + <param name="force" value="false"/> + <param name="test" value="true"/> + </section> + <param name="in" value="NucleicAcidSearchEngine_1.mzML"/> + <param name="digest" value="NucleicAcidSearchEngine_1_digest.oms"/> + <output name="out" file="NucleicAcidSearchEngine_12_out.mzTab" compare="sim_size" delta_frac="0.7" ftype="mztab"/> + <output name="id_out" file="NucleicAcidSearchEngine_11_out.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/> + <output name="db_out" file="NucleicAcidSearchEngine_23_out.tmp" compare="sim_size" delta_frac="0.7" ftype="sqlite"/> + <section name="precursor"> + <param name="mass_tolerance" value="5.0"/> + <param name="mass_tolerance_unit" value="ppm"/> + <param name="min_charge" value="-2"/> + <param name="max_charge" value="-14"/> + <param name="include_unknown_charge" value="true"/> + <param name="use_avg_mass" value="false"/> + <param name="use_adducts" value="false"/> + <param name="potential_adducts" value=""K:+" "Na:+" "Na2:++" "K2:++" "NaK:++" "K3:+++" "Na3:+++" "NaK2:+++" "Na2K:+++""/> + <param name="isotopes" value="0 1 2"/> + </section> + <section name="fragment"> + <param name="mass_tolerance" value="5.0"/> + <param name="mass_tolerance_unit" value="ppm"/> + <param name="ions" value="a-B,c,w,y"/> + </section> + <section name="modifications"> + <param name="variable"/> + <param name="variable_max_per_oligo" value="2"/> + <param name="resolve_ambiguities" value="false"/> + </section> + <section name="oligo"> + <param name="min_size" value="5"/> + <param name="max_size" value="0"/> + <param name="missed_cleavages" value="22"/> + <param name="enzyme" value="no cleavage"/> + </section> + <section name="report"> + <param name="top_hits" value="1"/> + </section> + <section name="fdr"> + <param name="decoy_pattern" value="DECOY_"/> + <param name="cutoff" value="0.05"/> + <param name="remove_decoys" value="true"/> + </section> + <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG,id_out_FLAG,db_out_FLAG"/> + <output name="ctd_out" ftype="xml"> + <assert_contents> + <is_valid_xml/> + </assert_contents> + </output> + </test> </tests> <help><![CDATA[Annotate nucleic acid identifications to MS/MS spectra. -For more information, visit http://www.openms.de/doxygen/release/2.6.0/html/UTILS_NucleicAcidSearchEngine.html]]></help> +For more information, visit http://www.openms.de/doxygen/release/2.8.0/html/UTILS_NucleicAcidSearchEngine.html]]></help> <expand macro="references"/> </tool>