diff FeatureFinderIdentification.xml @ 15:5dc928c83939 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/openms commit 3d1e5f37fd16524a415f707772eeb7ead848c5e3
author galaxyp
date Thu, 01 Dec 2022 19:24:30 +0000
parents 5471eba33b70
children 65bdfab68571
line wrap: on
line diff
--- a/FeatureFinderIdentification.xml	Fri Nov 06 20:22:43 2020 +0000
+++ b/FeatureFinderIdentification.xml	Thu Dec 01 19:24:30 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: [Quantitation]-->
-<tool id="FeatureFinderIdentification" name="FeatureFinderIdentification" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@" profile="20.05">
+<tool id="FeatureFinderIdentification" name="FeatureFinderIdentification" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
   <description>Detects features in MS1 data based on peptide identifications.</description>
   <macros>
     <token name="@EXECUTABLE@">FeatureFinderIdentification</token>
     <import>macros.xml</import>
-    <import>macros_autotest.xml</import>
-    <import>macros_test.xml</import>
   </macros>
   <expand macro="requirements"/>
   <expand macro="stdio"/>
@@ -37,12 +35,10 @@
 #if "xval_out_FLAG" in str($OPTIONAL_OUTPUTS).split(',')
   mkdir svm_xval_out &&
 #end if
-#if $adv_opts_cond.adv_opts_selector=='advanced':
-  #if $adv_opts_cond.candidates_in:
-    mkdir adv_opts_cond.candidates_in &&
-    ln -s '$adv_opts_cond.candidates_in' 'adv_opts_cond.candidates_in/${re.sub("[^\w\-_]", "_", $adv_opts_cond.candidates_in.element_identifier)}.$gxy2omsext($adv_opts_cond.candidates_in.ext)' &&
+  #if $adv_opts.candidates_in:
+    mkdir adv_opts.candidates_in &&
+    ln -s '$adv_opts.candidates_in' 'adv_opts.candidates_in/${re.sub("[^\w\-_]", "_", $adv_opts.candidates_in.element_identifier)}.$gxy2omsext($adv_opts.candidates_in.ext)' &&
   #end if
-#end if
 
 ## Main program call
 
@@ -76,12 +72,10 @@
   -svm:xval_out
   'svm_xval_out/output.${gxy2omsext("csv")}'
 #end if
-#if $adv_opts_cond.adv_opts_selector=='advanced':
-  #if $adv_opts_cond.candidates_in:
+  #if $adv_opts.candidates_in:
     -candidates_in
-    'adv_opts_cond.candidates_in/${re.sub("[^\w\-_]", "_", $adv_opts_cond.candidates_in.element_identifier)}.$gxy2omsext($adv_opts_cond.candidates_in.ext)'
+    'adv_opts.candidates_in/${re.sub("[^\w\-_]", "_", $adv_opts.candidates_in.element_identifier)}.$gxy2omsext($adv_opts.candidates_in.ext)'
   #end if
-#end if
 #if len(str($OPTIONAL_OUTPUTS).split(',')) == 0
   | tee '$stdout'
 #end if
@@ -108,11 +102,12 @@
     <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: LC-MS raw data" help=" select mzml data sets(s)"/>
-    <param name="id" argument="-id" type="data" format="idxml" optional="false" label="Input file: Peptide identifications derived directly from 'in'" help=" select idxml data sets(s)"/>
-    <param name="id_ext" argument="-id_ext" type="data" format="idxml" optional="true" label="Input file: 'External' peptide identifications" help="(e.g. from aligned runs) select idxml data sets(s)"/>
+    <param argument="-in" type="data" format="mzml" optional="false" label="Input file: LC-MS raw data" help=" select mzml data sets(s)"/>
+    <param argument="-id" type="data" format="idxml" optional="false" label="Input file: Peptide identifications derived directly from 'in'" help=" select idxml data sets(s)"/>
+    <param argument="-id_ext" type="data" format="idxml" optional="true" label="Input file: 'External' peptide identifications" help="(e.g. from aligned runs) select idxml data sets(s)"/>
+    <param argument="-quantify_decoys" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Whether decoy peptides should be quantified (true) or skipped (false)" help=""/>
     <section name="extract" title="Parameters for ion chromatogram extraction" help="" expanded="false">
-      <param name="batch_size" argument="-extract:batch_size" type="integer" optional="true" min="1" value="1000" label="Nr of peptides used in each batch of chromatogram extraction" help="Smaller values decrease memory usage but increase runtime"/>
+      <param name="batch_size" argument="-extract:batch_size" type="integer" optional="true" min="1" value="5000" label="Nr of peptides used in each batch of chromatogram extraction" help="Smaller values decrease memory usage but increase runtime"/>
       <param name="mz_window" argument="-extract:mz_window" type="float" optional="true" min="0.0" value="10.0" label="m/z window size for chromatogram extraction (unit: ppm if 1 or greater, else Da/Th)" help=""/>
       <param name="n_isotopes" argument="-extract:n_isotopes" type="integer" optional="true" min="2" value="2" label="Number of isotopes to include in each peptide assay" help=""/>
       <param name="isotope_pmin" argument="-extract:isotope_pmin" type="float" optional="true" min="0.0" max="1.0" value="0.0" label="Minimum probability for an isotope to be included in the assay for a peptide" help="If set, this parameter takes precedence over 'extract:n_isotopes'"/>
@@ -128,32 +123,32 @@
     <section name="svm" title="Parameters for scoring features using a support vector machine (SVM)" help="" expanded="false">
       <param name="samples" argument="-svm:samples" type="integer" optional="true" min="0" value="0" label="Number of observations to use for training ('0' for all)" help=""/>
       <param name="no_selection" argument="-svm:no_selection" type="boolean" truevalue="true" falsevalue="false" checked="false" label="By default, roughly the same number of positive and negative observations, with the same intensity distribution, are selected for training" help="This aims to reduce biases, but also reduces the amount of training data. Set this flag to skip this procedure and consider all available observations (subject to 'svm:samples')"/>
-      <param name="kernel" argument="-svm:kernel" display="radio" type="select" optional="false" label="SVM kernel" help="">
+      <param name="kernel" argument="-svm:kernel" type="select" optional="true" label="SVM kernel" help="">
         <option value="RBF" selected="true">RBF</option>
         <option value="linear">linear</option>
-        <expand macro="list_string_san"/>
+        <expand macro="list_string_san" name="kernel"/>
       </param>
       <param name="xval" argument="-svm:xval" type="integer" optional="true" min="1" value="5" label="Number of partitions for cross-validation (parameter optimization)" help=""/>
       <param name="log2_C" argument="-svm:log2_C" type="text" optional="true" value="-5.0 -3.0 -1.0 1.0 3.0 5.0 7.0 9.0 11.0 13.0 15.0" label="Values to try for the SVM parameter 'C' during parameter optimization" help="A value 'x' is used as 'C = 2^x' (space separated list, in order to allow for spaces in list items surround them by single quotes)">
-        <expand macro="list_float_valsan"/>
+        <expand macro="list_float_valsan" name="log2_C"/>
       </param>
       <param name="log2_gamma" argument="-svm:log2_gamma" type="text" optional="true" value="-15.0 -13.0 -11.0 -9.0 -7.0 -5.0 -3.0 -1.0 1.0 3.0" label="Values to try for the SVM parameter 'gamma' during parameter optimization (RBF kernel only)" help="A value 'x' is used as 'gamma = 2^x' (space separated list, in order to allow for spaces in list items surround them by single quotes)">
-        <expand macro="list_float_valsan"/>
+        <expand macro="list_float_valsan" name="log2_gamma"/>
       </param>
       <param name="epsilon" argument="-svm:epsilon" type="float" optional="true" min="0.0" value="0.001" label="Stopping criterion" help=""/>
       <param name="cache_size" argument="-svm:cache_size" type="float" optional="true" min="1.0" value="100.0" label="Size of the kernel cache (in MB)" help=""/>
       <param name="no_shrinking" argument="-svm:no_shrinking" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Disable the shrinking heuristics" help=""/>
-      <param name="predictors" argument="-svm:predictors" type="text" optional="true" value="peak_apices_sum,var_xcorr_coelution,var_xcorr_shape,var_library_sangle,var_intensity_score,sn_ratio,var_log_sn_score,var_elution_model_fit_score,xx_lda_prelim_score,var_isotope_correlation_score,var_isotope_overlap_score,var_massdev_score,main_var_xx_swath_prelim_score" label="Names of OpenSWATH scores to use as predictors for the SVM (comma-separated list)" help="">
-        <expand macro="list_string_san"/>
+      <param name="predictors" argument="-svm:predictors" type="text" optional="true" value="peak_apices_sum,var_xcorr_coelution,var_xcorr_shape,var_library_sangle,var_intensity_score,sn_ratio,var_log_sn_score,var_elution_model_fit_score,xx_lda_prelim_score,var_ms1_isotope_correlation_score,var_ms1_isotope_overlap_score,var_massdev_score,main_var_xx_swath_prelim_score" label="Names of OpenSWATH scores to use as predictors for the SVM (comma-separated list)" help="">
+        <expand macro="list_string_san" name="predictors"/>
       </param>
       <param name="min_prob" argument="-svm:min_prob" type="float" optional="true" min="0.0" max="1.0" value="0.0" label="Minimum probability of correctness, as predicted by the SVM, required to retain a feature candidate" help=""/>
     </section>
     <section name="model" title="Parameters for fitting elution models to features" help="" expanded="false">
-      <param name="type" argument="-model:type" display="radio" type="select" optional="false" label="Type of elution model to fit to features" help="">
+      <param name="type" argument="-model:type" type="select" optional="true" label="Type of elution model to fit to features" help="">
         <option value="symmetric" selected="true">symmetric</option>
         <option value="asymmetric">asymmetric</option>
         <option value="none">none</option>
-        <expand macro="list_string_san"/>
+        <expand macro="list_string_san" name="type"/>
       </param>
       <param name="add_zeros" argument="-model:add_zeros" type="float" optional="true" min="0.0" value="0.2" label="Add zero-intensity points outside the feature range to constrain the model fit" help="This parameter sets the weight given to these points during model fitting; '0' to disable"/>
       <param name="unweighted_fit" argument="-model:unweighted_fit" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Suppress weighting of mass traces according to theoretical intensities when fitting elution models" help=""/>
@@ -166,11 +161,15 @@
         <param name="asymmetry" argument="-model:check:asymmetry" type="float" optional="true" min="0.0" value="10.0" label="Upper limit for acceptable asymmetry of elution models (EGH only), expressed in terms of modified (median-based) z-scores" help="'0' to disable. Not applied to individual mass traces (parameter 'each_trace')"/>
       </section>
     </section>
+    <section name="EMGScoring" title="Parameters for fitting exp" help="mod. Gaussians to mass traces" expanded="false">
+      <param name="max_iteration" argument="-EMGScoring:max_iteration" type="integer" optional="true" min="1" value="100" label="Maximum number of iterations for EMG fitting" help=""/>
+      <param name="init_mom" argument="-EMGScoring:init_mom" type="boolean" truevalue="true" falsevalue="false" checked="false" label="Alternative initial parameters for fitting through method of moments" help=""/>
+    </section>
     <expand macro="adv_opts_macro">
-      <param name="candidates_in" argument="-candidates_in" type="data" format="featurexml" optional="true" label="Input file: Feature candidates from a previous run" help="If set, only feature classification and elution model fitting are carried out, if enabled. Many parameters are ignored select featurexml data sets(s)"/>
-      <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="-candidates_in" type="data" format="featurexml" optional="true" label="Input file: Feature candidates from a previous run" help="If set, only feature classification and elution model fitting are carried out, if enabled. Many parameters are ignored select featurexml data sets(s)"/>
+      <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">
@@ -199,13 +198,194 @@
       <filter>OPTIONAL_OUTPUTS is not None and "ctd_out_FLAG" in OPTIONAL_OUTPUTS</filter>
     </data>
   </outputs>
-  <tests>
-    <expand macro="autotest_FeatureFinderIdentification"/>
-    <expand macro="manutest_FeatureFinderIdentification"/>
+  <tests><!-- TOPP_FeatureFinderIdentification_1 -->
+    <test expect_num_outputs="2">
+      <section name="adv_opts">
+        <param name="force" value="false"/>
+        <param name="test" value="true"/>
+      </section>
+      <param name="in" value="FeatureFinderIdentification_1_input.mzML"/>
+      <param name="id" value="FeatureFinderIdentification_1_input.idXML"/>
+      <output name="out" file="FeatureFinderIdentification_1.tmp.featureXML" compare="sim_size" delta_frac="0.7" ftype="featurexml"/>
+      <param name="quantify_decoys" value="false"/>
+      <section name="extract">
+        <param name="batch_size" value="5000"/>
+        <param name="mz_window" value="0.1"/>
+        <param name="n_isotopes" value="2"/>
+        <param name="isotope_pmin" value="0.0"/>
+        <param name="rt_quantile" value="0.95"/>
+        <param name="rt_window" value="0.0"/>
+      </section>
+      <section name="detect">
+        <param name="peak_width" value="60.0"/>
+        <param name="min_peak_width" value="0.2"/>
+        <param name="signal_to_noise" value="0.8"/>
+        <param name="mapping_tolerance" value="0.0"/>
+      </section>
+      <section name="svm">
+        <param name="samples" value="0"/>
+        <param name="no_selection" value="false"/>
+        <param name="kernel" value="RBF"/>
+        <param name="xval" value="5"/>
+        <param name="log2_C" value="-5.0 -3.0 -1.0 1.0 3.0 5.0 7.0 9.0 11.0 13.0 15.0"/>
+        <param name="log2_gamma" value="-15.0 -13.0 -11.0 -9.0 -7.0 -5.0 -3.0 -1.0 1.0 3.0"/>
+        <param name="epsilon" value="0.001"/>
+        <param name="cache_size" value="100.0"/>
+        <param name="no_shrinking" value="false"/>
+        <param name="predictors" value="peak_apices_sum,var_xcorr_coelution,var_xcorr_shape,var_library_sangle,var_intensity_score,sn_ratio,var_log_sn_score,var_elution_model_fit_score,xx_lda_prelim_score,var_ms1_isotope_correlation_score,var_ms1_isotope_overlap_score,var_massdev_score,main_var_xx_swath_prelim_score"/>
+        <param name="min_prob" value="0.0"/>
+      </section>
+      <section name="model">
+        <param name="type" value="none"/>
+        <param name="add_zeros" value="0.2"/>
+        <param name="unweighted_fit" value="false"/>
+        <param name="no_imputation" value="false"/>
+        <param name="each_trace" value="false"/>
+        <section name="check">
+          <param name="min_area" value="1.0"/>
+          <param name="boundaries" value="0.5"/>
+          <param name="width" value="10.0"/>
+          <param name="asymmetry" value="10.0"/>
+        </section>
+      </section>
+      <section name="EMGScoring">
+        <param name="max_iteration" value="100"/>
+        <param name="init_mom" value="false"/>
+      </section>
+      <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG"/>
+      <output name="ctd_out" ftype="xml">
+        <assert_contents>
+          <is_valid_xml/>
+        </assert_contents>
+      </output>
+    </test>
+    <!-- TOPP_FeatureFinderIdentification_3 -->
+    <test expect_num_outputs="2">
+      <section name="adv_opts">
+        <param name="force" value="false"/>
+        <param name="test" value="true"/>
+      </section>
+      <param name="in" value="FeatureFinderIdentification_1_input.mzML"/>
+      <param name="id" value="FeatureFinderIdentification_1_input.idXML"/>
+      <output name="out" file="FeatureFinderIdentification_3.tmp.featureXML" compare="sim_size" delta_frac="0.7" ftype="featurexml"/>
+      <param name="quantify_decoys" value="false"/>
+      <section name="extract">
+        <param name="batch_size" value="5000"/>
+        <param name="mz_window" value="0.1"/>
+        <param name="n_isotopes" value="2"/>
+        <param name="isotope_pmin" value="0.0"/>
+        <param name="rt_quantile" value="0.95"/>
+        <param name="rt_window" value="0.0"/>
+      </section>
+      <section name="detect">
+        <param name="peak_width" value="60.0"/>
+        <param name="min_peak_width" value="0.2"/>
+        <param name="signal_to_noise" value="0.8"/>
+        <param name="mapping_tolerance" value="0.0"/>
+      </section>
+      <section name="svm">
+        <param name="samples" value="0"/>
+        <param name="no_selection" value="false"/>
+        <param name="kernel" value="RBF"/>
+        <param name="xval" value="5"/>
+        <param name="log2_C" value="-5.0 -3.0 -1.0 1.0 3.0 5.0 7.0 9.0 11.0 13.0 15.0"/>
+        <param name="log2_gamma" value="-15.0 -13.0 -11.0 -9.0 -7.0 -5.0 -3.0 -1.0 1.0 3.0"/>
+        <param name="epsilon" value="0.001"/>
+        <param name="cache_size" value="100.0"/>
+        <param name="no_shrinking" value="false"/>
+        <param name="predictors" value="peak_apices_sum,var_xcorr_coelution,var_xcorr_shape,var_library_sangle,var_intensity_score,sn_ratio,var_log_sn_score,var_elution_model_fit_score,xx_lda_prelim_score,var_ms1_isotope_correlation_score,var_ms1_isotope_overlap_score,var_massdev_score,main_var_xx_swath_prelim_score"/>
+        <param name="min_prob" value="0.0"/>
+      </section>
+      <section name="model">
+        <param name="type" value="symmetric"/>
+        <param name="add_zeros" value="0.2"/>
+        <param name="unweighted_fit" value="false"/>
+        <param name="no_imputation" value="false"/>
+        <param name="each_trace" value="false"/>
+        <section name="check">
+          <param name="min_area" value="1.0"/>
+          <param name="boundaries" value="0.5"/>
+          <param name="width" value="10.0"/>
+          <param name="asymmetry" value="10.0"/>
+        </section>
+      </section>
+      <section name="EMGScoring">
+        <param name="max_iteration" value="100"/>
+        <param name="init_mom" value="false"/>
+      </section>
+      <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG"/>
+      <output name="ctd_out" ftype="xml">
+        <assert_contents>
+          <is_valid_xml/>
+        </assert_contents>
+      </output>
+    </test>
+    <!-- TOPP_FeatureFinderIdentification_5 -->
+    <test expect_num_outputs="3">
+      <section name="adv_opts">
+        <param name="force" value="false"/>
+        <param name="test" value="true"/>
+      </section>
+      <param name="in" value="FeatureFinderIdentification_1_input.mzML"/>
+      <param name="id" value="FeatureFinderIdentification_1_input.idXML"/>
+      <output name="out" file="FeatureFinderIdentification_5.tmp.featureXML" compare="sim_size" delta_frac="0.7" ftype="featurexml"/>
+      <output name="candidates_out" file="FeatureFinderIdentification_5_candidates.tmp.featureXML" compare="sim_size" delta_frac="0.7" ftype="featurexml"/>
+      <param name="quantify_decoys" value="false"/>
+      <section name="extract">
+        <param name="batch_size" value="10"/>
+        <param name="mz_window" value="0.1"/>
+        <param name="n_isotopes" value="2"/>
+        <param name="isotope_pmin" value="0.0"/>
+        <param name="rt_quantile" value="0.95"/>
+        <param name="rt_window" value="0.0"/>
+      </section>
+      <section name="detect">
+        <param name="peak_width" value="60.0"/>
+        <param name="min_peak_width" value="0.2"/>
+        <param name="signal_to_noise" value="0.8"/>
+        <param name="mapping_tolerance" value="0.0"/>
+      </section>
+      <section name="svm">
+        <param name="samples" value="0"/>
+        <param name="no_selection" value="false"/>
+        <param name="kernel" value="RBF"/>
+        <param name="xval" value="5"/>
+        <param name="log2_C" value="-5.0 -3.0 -1.0 1.0 3.0 5.0 7.0 9.0 11.0 13.0 15.0"/>
+        <param name="log2_gamma" value="-15.0 -13.0 -11.0 -9.0 -7.0 -5.0 -3.0 -1.0 1.0 3.0"/>
+        <param name="epsilon" value="0.001"/>
+        <param name="cache_size" value="100.0"/>
+        <param name="no_shrinking" value="false"/>
+        <param name="predictors" value="peak_apices_sum,var_xcorr_coelution,var_xcorr_shape,var_library_sangle,var_intensity_score,sn_ratio,var_log_sn_score,var_elution_model_fit_score,xx_lda_prelim_score,var_ms1_isotope_correlation_score,var_ms1_isotope_overlap_score,var_massdev_score,main_var_xx_swath_prelim_score"/>
+        <param name="min_prob" value="0.0"/>
+      </section>
+      <section name="model">
+        <param name="type" value="none"/>
+        <param name="add_zeros" value="0.2"/>
+        <param name="unweighted_fit" value="false"/>
+        <param name="no_imputation" value="false"/>
+        <param name="each_trace" value="false"/>
+        <section name="check">
+          <param name="min_area" value="1.0"/>
+          <param name="boundaries" value="0.5"/>
+          <param name="width" value="10.0"/>
+          <param name="asymmetry" value="10.0"/>
+        </section>
+      </section>
+      <section name="EMGScoring">
+        <param name="max_iteration" value="100"/>
+        <param name="init_mom" value="false"/>
+      </section>
+      <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG,candidates_out_FLAG"/>
+      <output name="ctd_out" ftype="xml">
+        <assert_contents>
+          <is_valid_xml/>
+        </assert_contents>
+      </output>
+    </test>
   </tests>
   <help><![CDATA[Detects features in MS1 data based on peptide identifications.
 
 
-For more information, visit http://www.openms.de/doxygen/release/2.6.0/html/TOPP_FeatureFinderIdentification.html]]></help>
+For more information, visit http://www.openms.de/doxygen/release/2.8.0/html/TOPP_FeatureFinderIdentification.html]]></help>
   <expand macro="references"/>
 </tool>