diff IDPosteriorErrorProbability.xml @ 14:986e03d3201e draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/openms commit 3d1e5f37fd16524a415f707772eeb7ead848c5e3
author galaxyp
date Thu, 01 Dec 2022 18:59:09 +0000
parents 711a081d80ba
children 93e6ec445d5d
line wrap: on
line diff
--- a/IDPosteriorErrorProbability.xml	Fri Nov 06 20:28:25 2020 +0000
+++ b/IDPosteriorErrorProbability.xml	Thu Dec 01 18:59:09 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: [ID Processing]-->
-<tool id="IDPosteriorErrorProbability" name="IDPosteriorErrorProbability" version="@TOOL_VERSION@+galaxy@GALAXY_VERSION@" profile="20.05">
+<tool id="IDPosteriorErrorProbability" name="IDPosteriorErrorProbability" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="21.05">
   <description>Estimates probabilities for incorrectly assigned peptide sequences and a set of search engine scores using a mixture model.</description>
   <macros>
     <token name="@EXECUTABLE@">IDPosteriorErrorProbability</token>
     <import>macros.xml</import>
-    <import>macros_autotest.xml</import>
-    <import>macros_test.xml</import>
   </macros>
   <expand macro="requirements"/>
   <expand macro="stdio"/>
@@ -54,33 +52,33 @@
     <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="idxml" optional="false" label="input file" help=" select idxml data sets(s)"/>
-    <param name="split_charge" argument="-split_charge" type="boolean" truevalue="true" falsevalue="false" checked="false" label="The search engine scores are split by charge if this flag is set" help="Thus, for each charge state a new model will be computed"/>
-    <param name="top_hits_only" argument="-top_hits_only" type="boolean" truevalue="true" falsevalue="false" checked="false" label="If set only the top hits of every PeptideIdentification will be used" help=""/>
-    <param name="ignore_bad_data" argument="-ignore_bad_data" type="boolean" truevalue="true" falsevalue="false" checked="false" label="If set errors will be written but ignored" help="Useful for pipelines with many datasets where only a few are bad, but the pipeline should run through"/>
-    <param name="prob_correct" argument="-prob_correct" type="boolean" truevalue="true" falsevalue="false" checked="false" label="If set scores will be calculated as '1 - ErrorProbabilities' and can be interpreted as probabilities for correct identifications" help=""/>
+    <param argument="-in" type="data" format="idxml" optional="false" label="input file" help=" select idxml data sets(s)"/>
+    <param argument="-split_charge" type="boolean" truevalue="true" falsevalue="false" checked="false" label="The search engine scores are split by charge if this flag is set" help="Thus, for each charge state a new model will be computed"/>
+    <param argument="-top_hits_only" type="boolean" truevalue="true" falsevalue="false" checked="false" label="If set only the top hits of every PeptideIdentification will be used" help=""/>
+    <param argument="-ignore_bad_data" type="boolean" truevalue="true" falsevalue="false" checked="false" label="If set errors will be written but ignored" help="Useful for pipelines with many datasets where only a few are bad, but the pipeline should run through"/>
+    <param argument="-prob_correct" type="boolean" truevalue="true" falsevalue="false" checked="false" label="If set scores will be calculated as '1 - ErrorProbabilities' and can be interpreted as probabilities for correct identifications" help=""/>
     <section name="fit_algorithm" title="Algorithm parameter subsection" help="" expanded="false">
       <param name="number_of_bins" argument="-fit_algorithm:number_of_bins" type="integer" optional="true" value="100" label="Number of bins used for visualization" help="Only needed if each iteration step of the EM-Algorithm will be visualized"/>
-      <param name="incorrectly_assigned" argument="-fit_algorithm:incorrectly_assigned" display="radio" type="select" optional="false" label="for 'Gumbel', the Gumbel distribution is used to plot incorrectly assigned sequences" help="For 'Gauss', the Gauss distribution is used">
+      <param name="incorrectly_assigned" argument="-fit_algorithm:incorrectly_assigned" type="select" optional="true" label="for 'Gumbel', the Gumbel distribution is used to plot incorrectly assigned sequences" help="For 'Gauss', the Gauss distribution is used">
         <option value="Gumbel" selected="true">Gumbel</option>
         <option value="Gauss">Gauss</option>
-        <expand macro="list_string_san"/>
+        <expand macro="list_string_san" name="incorrectly_assigned"/>
       </param>
       <param name="max_nr_iterations" argument="-fit_algorithm:max_nr_iterations" type="integer" optional="true" value="1000" label="Bounds the number of iterations for the EM algorithm when convergence is slow" help=""/>
       <param name="neg_log_delta" argument="-fit_algorithm:neg_log_delta" type="integer" optional="true" value="6" label="The negative logarithm of the convergence threshold for the likelihood increase" help=""/>
-      <param name="outlier_handling" argument="-fit_algorithm:outlier_handling" display="radio" type="select" optional="false" label="What to do with outliers:" help="- ignore_iqr_outliers: ignore outliers outside of 3*IQR from Q1/Q3 for fitting. - set_iqr_to_closest_valid: set IQR-based outliers to the last valid value for fitting. - ignore_extreme_percentiles: ignore everything outside 99th and 1st percentile (also removes equal values like potential censored max values in XTandem). - none: do nothing">
+      <param name="outlier_handling" argument="-fit_algorithm:outlier_handling" type="select" optional="true" label="What to do with outliers:" help="- ignore_iqr_outliers: ignore outliers outside of 3*IQR from Q1/Q3 for fitting. - set_iqr_to_closest_valid: set IQR-based outliers to the last valid value for fitting. - ignore_extreme_percentiles: ignore everything outside 99th and 1st percentile (also removes equal values like potential censored max values in XTandem). - none: do nothing">
         <option value="ignore_iqr_outliers" selected="true">ignore_iqr_outliers</option>
         <option value="set_iqr_to_closest_valid">set_iqr_to_closest_valid</option>
         <option value="ignore_extreme_percentiles">ignore_extreme_percentiles</option>
         <option value="none">none</option>
-        <expand macro="list_string_san"/>
+        <expand macro="list_string_san" name="outlier_handling"/>
       </param>
     </section>
     <expand macro="adv_opts_macro">
-      <param name="fdr_for_targets_smaller" argument="-fdr_for_targets_smaller" type="float" optional="true" value="0.05" label="Only used, when top_hits_only set" help="Additionally, target/decoy information should be available. The score_type must be q-value from an previous False Discovery Rate run"/>
-      <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="-fdr_for_targets_smaller" type="float" optional="true" value="0.05" label="Only used, when top_hits_only set" help="Additionally, target/decoy information should be available. The score_type must be q-value from an previous False Discovery Rate run"/>
+      <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">
@@ -97,13 +95,226 @@
       <filter>OPTIONAL_OUTPUTS is not None and "ctd_out_FLAG" in OPTIONAL_OUTPUTS</filter>
     </data>
   </outputs>
-  <tests>
-    <expand macro="autotest_IDPosteriorErrorProbability"/>
-    <expand macro="manutest_IDPosteriorErrorProbability"/>
+  <tests><!-- TOPP_IDPosteriorErrorProbability_1 -->
+    <test expect_num_outputs="2">
+      <section name="adv_opts">
+        <param name="fdr_for_targets_smaller" value="0.05"/>
+        <param name="force" value="false"/>
+        <param name="test" value="true"/>
+      </section>
+      <param name="in" value="IDPosteriorErrorProbability_Mascot_input.idXML"/>
+      <output name="out" file="IDPosteriorErrorProbability_Mascot_output.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/>
+      <param name="split_charge" value="false"/>
+      <param name="top_hits_only" value="false"/>
+      <param name="ignore_bad_data" value="false"/>
+      <param name="prob_correct" value="false"/>
+      <section name="fit_algorithm">
+        <param name="number_of_bins" value="100"/>
+        <param name="incorrectly_assigned" value="Gumbel"/>
+        <param name="max_nr_iterations" value="1000"/>
+        <param name="neg_log_delta" value="6"/>
+        <param name="outlier_handling" value="ignore_iqr_outliers"/>
+      </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_IDPosteriorErrorProbability_2 -->
+    <test expect_num_outputs="2">
+      <section name="adv_opts">
+        <param name="fdr_for_targets_smaller" value="0.05"/>
+        <param name="force" value="false"/>
+        <param name="test" value="true"/>
+      </section>
+      <param name="in" value="IDPosteriorErrorProbability_XTandem_input.idXML"/>
+      <output name="out" file="IDPosteriorErrorProbability_XTandem_output.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/>
+      <param name="split_charge" value="false"/>
+      <param name="top_hits_only" value="false"/>
+      <param name="ignore_bad_data" value="false"/>
+      <param name="prob_correct" value="false"/>
+      <section name="fit_algorithm">
+        <param name="number_of_bins" value="100"/>
+        <param name="incorrectly_assigned" value="Gumbel"/>
+        <param name="max_nr_iterations" value="1000"/>
+        <param name="neg_log_delta" value="6"/>
+        <param name="outlier_handling" value="ignore_iqr_outliers"/>
+      </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_IDPosteriorErrorProbability_3 -->
+    <test expect_num_outputs="2">
+      <section name="adv_opts">
+        <param name="fdr_for_targets_smaller" value="0.05"/>
+        <param name="force" value="false"/>
+        <param name="test" value="true"/>
+      </section>
+      <param name="in" value="IDPosteriorErrorProbability_OMSSA_input.idXML"/>
+      <output name="out" file="IDPosteriorErrorProbability_OMSSA_output.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/>
+      <param name="split_charge" value="false"/>
+      <param name="top_hits_only" value="false"/>
+      <param name="ignore_bad_data" value="false"/>
+      <param name="prob_correct" value="false"/>
+      <section name="fit_algorithm">
+        <param name="number_of_bins" value="100"/>
+        <param name="incorrectly_assigned" value="Gumbel"/>
+        <param name="max_nr_iterations" value="1000"/>
+        <param name="neg_log_delta" value="6"/>
+        <param name="outlier_handling" value="ignore_iqr_outliers"/>
+      </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_IDPosteriorErrorProbability_4 -->
+    <test expect_num_outputs="2">
+      <section name="adv_opts">
+        <param name="fdr_for_targets_smaller" value="0.05"/>
+        <param name="force" value="false"/>
+        <param name="test" value="true"/>
+      </section>
+      <param name="in" value="IDPosteriorErrorProbability_OMSSA_input2.idXML"/>
+      <output name="out" file="IDPosteriorErrorProbability_OMSSA_output2.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/>
+      <param name="split_charge" value="true"/>
+      <param name="top_hits_only" value="false"/>
+      <param name="ignore_bad_data" value="false"/>
+      <param name="prob_correct" value="false"/>
+      <section name="fit_algorithm">
+        <param name="number_of_bins" value="100"/>
+        <param name="incorrectly_assigned" value="Gumbel"/>
+        <param name="max_nr_iterations" value="1000"/>
+        <param name="neg_log_delta" value="6"/>
+        <param name="outlier_handling" value="ignore_iqr_outliers"/>
+      </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_IDPosteriorErrorProbability_5 -->
+    <test expect_num_outputs="2">
+      <section name="adv_opts">
+        <param name="fdr_for_targets_smaller" value="0.05"/>
+        <param name="force" value="false"/>
+        <param name="test" value="true"/>
+      </section>
+      <param name="in" value="IDPosteriorErrorProbability_XTandem_input2.idXML"/>
+      <output name="out" file="IDPosteriorErrorProbability_XTandem_output2.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/>
+      <param name="split_charge" value="true"/>
+      <param name="top_hits_only" value="false"/>
+      <param name="ignore_bad_data" value="false"/>
+      <param name="prob_correct" value="false"/>
+      <section name="fit_algorithm">
+        <param name="number_of_bins" value="100"/>
+        <param name="incorrectly_assigned" value="Gumbel"/>
+        <param name="max_nr_iterations" value="1000"/>
+        <param name="neg_log_delta" value="6"/>
+        <param name="outlier_handling" value="ignore_iqr_outliers"/>
+      </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_IDPosteriorErrorProbability_6 -->
+    <test expect_num_outputs="2">
+      <section name="adv_opts">
+        <param name="fdr_for_targets_smaller" value="0.05"/>
+        <param name="force" value="false"/>
+        <param name="test" value="true"/>
+      </section>
+      <param name="in" value="IDPosteriorErrorProbability_Mascot_input2.idXML"/>
+      <output name="out" file="IDPosteriorErrorProbability_Mascot_output2.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/>
+      <param name="split_charge" value="true"/>
+      <param name="top_hits_only" value="false"/>
+      <param name="ignore_bad_data" value="false"/>
+      <param name="prob_correct" value="false"/>
+      <section name="fit_algorithm">
+        <param name="number_of_bins" value="100"/>
+        <param name="incorrectly_assigned" value="Gumbel"/>
+        <param name="max_nr_iterations" value="1000"/>
+        <param name="neg_log_delta" value="6"/>
+        <param name="outlier_handling" value="ignore_iqr_outliers"/>
+      </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_IDPosteriorErrorProbability_7 -->
+    <test expect_num_outputs="2">
+      <section name="adv_opts">
+        <param name="fdr_for_targets_smaller" value="0.05"/>
+        <param name="force" value="false"/>
+        <param name="test" value="true"/>
+      </section>
+      <param name="in" value="IDPosteriorErrorProbability_bad_data.idXML"/>
+      <output name="out" file="IDPosteriorErrorProbability_bad_data_out.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/>
+      <param name="split_charge" value="false"/>
+      <param name="top_hits_only" value="false"/>
+      <param name="ignore_bad_data" value="true"/>
+      <param name="prob_correct" value="false"/>
+      <section name="fit_algorithm">
+        <param name="number_of_bins" value="100"/>
+        <param name="incorrectly_assigned" value="Gumbel"/>
+        <param name="max_nr_iterations" value="1000"/>
+        <param name="neg_log_delta" value="6"/>
+        <param name="outlier_handling" value="ignore_iqr_outliers"/>
+      </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_IDPosteriorErrorProbability_8 -->
+    <test expect_num_outputs="2">
+      <section name="adv_opts">
+        <param name="fdr_for_targets_smaller" value="0.05"/>
+        <param name="force" value="false"/>
+        <param name="test" value="true"/>
+      </section>
+      <param name="in" value="IDPosteriorErrorProbability_OMSSA_input.idXML"/>
+      <output name="out" file="IDPosteriorErrorProbability_prob_correct_output.idXML" compare="sim_size" delta_frac="0.7" ftype="idxml"/>
+      <param name="split_charge" value="false"/>
+      <param name="top_hits_only" value="false"/>
+      <param name="ignore_bad_data" value="false"/>
+      <param name="prob_correct" value="true"/>
+      <section name="fit_algorithm">
+        <param name="number_of_bins" value="100"/>
+        <param name="incorrectly_assigned" value="Gumbel"/>
+        <param name="max_nr_iterations" value="1000"/>
+        <param name="neg_log_delta" value="6"/>
+        <param name="outlier_handling" value="ignore_iqr_outliers"/>
+      </section>
+      <param name="OPTIONAL_OUTPUTS" value="ctd_out_FLAG"/>
+      <output name="ctd_out" ftype="xml">
+        <assert_contents>
+          <is_valid_xml/>
+        </assert_contents>
+      </output>
+    </test>
   </tests>
   <help><![CDATA[Estimates probabilities for incorrectly assigned peptide sequences and a set of search engine scores using a mixture model.
 
 
-For more information, visit http://www.openms.de/doxygen/release/2.6.0/html/TOPP_IDPosteriorErrorProbability.html]]></help>
+For more information, visit http://www.openms.de/doxygen/release/2.8.0/html/TOPP_IDPosteriorErrorProbability.html]]></help>
   <expand macro="references"/>
 </tool>