Mercurial > repos > galaxyp > openms_openswathworkflow

changeset 5:56988709dec6 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tree/master/tools/openms commit 58476cadaaf10b494317a604ad81d41c2d15f29b
author galaxyp
date Mon, 12 Feb 2018 13:02:55 -0500
parents 1734e2933b2b
children 94d245e69164
files OpenSwathWorkflow.xml SKIP_TOOLS_FILE.txt macros.xml readme.md tools_blacklist.txt
diffstat 5 files changed, 102 insertions(+), 76 deletions(-) [+]
line wrap: on
line diff
--- a/OpenSwathWorkflow.xml	Thu Jan 11 18:12:54 2018 -0500
+++ b/OpenSwathWorkflow.xml	Mon Feb 12 13:02:55 2018 -0500
@@ -1,7 +1,7 @@
 <?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 CTD2Galaxy.-->
+<!--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="OpenSwathWorkflow" name="OpenSwathWorkflow" version="2.2.0.1">
+<tool id="OpenSwathWorkflow" name="OpenSwathWorkflow" version="2.3.0">
   <description>Complete workflow to run OpenSWATH</description>
   <macros>
     <token name="@EXECUTABLE@">OpenSwathWorkflow</token>
@@ -54,6 +54,58 @@
 #if $param_sonar:
   -sonar
 #end if
+#if $param_RTNormalization_alignmentMethod:
+  -RTNormalization:alignmentMethod
+  #if " " in str($param_RTNormalization_alignmentMethod):
+    "$param_RTNormalization_alignmentMethod"
+  #else
+    $param_RTNormalization_alignmentMethod
+  #end if
+#end if
+#if $param_RTNormalization_outlierMethod:
+  -RTNormalization:outlierMethod
+  #if " " in str($param_RTNormalization_outlierMethod):
+    "$param_RTNormalization_outlierMethod"
+  #else
+    $param_RTNormalization_outlierMethod
+  #end if
+#end if
+#if $param_RTNormalization_useIterativeChauvenet:
+  -RTNormalization:useIterativeChauvenet
+#end if
+#if $param_RTNormalization_RANSACMaxIterations:
+  -RTNormalization:RANSACMaxIterations $param_RTNormalization_RANSACMaxIterations
+#end if
+#if $param_RTNormalization_RANSACMaxPercentRTThreshold:
+  -RTNormalization:RANSACMaxPercentRTThreshold $param_RTNormalization_RANSACMaxPercentRTThreshold
+#end if
+#if $param_RTNormalization_RANSACSamplingSize:
+  -RTNormalization:RANSACSamplingSize $param_RTNormalization_RANSACSamplingSize
+#end if
+#if $param_RTNormalization_estimateBestPeptides:
+  -RTNormalization:estimateBestPeptides
+#end if
+#if $param_RTNormalization_InitialQualityCutoff:
+  -RTNormalization:InitialQualityCutoff $param_RTNormalization_InitialQualityCutoff
+#end if
+#if $param_RTNormalization_OverallQualityCutoff:
+  -RTNormalization:OverallQualityCutoff $param_RTNormalization_OverallQualityCutoff
+#end if
+#if $param_RTNormalization_NrRTBins:
+  -RTNormalization:NrRTBins $param_RTNormalization_NrRTBins
+#end if
+#if $param_RTNormalization_MinPeptidesPerBin:
+  -RTNormalization:MinPeptidesPerBin $param_RTNormalization_MinPeptidesPerBin
+#end if
+#if $param_RTNormalization_MinBinsFilled:
+  -RTNormalization:MinBinsFilled $param_RTNormalization_MinBinsFilled
+#end if
+#if $param_RTNormalization_lowess_span:
+  -RTNormalization:lowess:span $param_RTNormalization_lowess_span
+#end if
+#if $param_RTNormalization_b_spline_num_nodes:
+  -RTNormalization:b_spline:num_nodes $param_RTNormalization_b_spline_num_nodes
+#end if
 #if $param_Scoring_stop_report_after_feature:
   -Scoring:stop_report_after_feature $param_Scoring_stop_report_after_feature
 #end if
@@ -163,44 +215,6 @@
 #if $param_Scoring_EMGScoring_max_iteration:
   -Scoring:EMGScoring:max_iteration $param_Scoring_EMGScoring_max_iteration
 #end if
-#if $param_outlierDetection_outlierMethod:
-  -outlierDetection:outlierMethod
-  #if " " in str($param_outlierDetection_outlierMethod):
-    "$param_outlierDetection_outlierMethod"
-  #else
-    $param_outlierDetection_outlierMethod
-  #end if
-#end if
-#if $param_outlierDetection_useIterativeChauvenet:
-  -outlierDetection:useIterativeChauvenet
-#end if
-#if $param_outlierDetection_RANSACMaxIterations:
-  -outlierDetection:RANSACMaxIterations $param_outlierDetection_RANSACMaxIterations
-#end if
-#if $param_outlierDetection_RANSACMaxPercentRTThreshold:
-  -outlierDetection:RANSACMaxPercentRTThreshold $param_outlierDetection_RANSACMaxPercentRTThreshold
-#end if
-#if $param_outlierDetection_RANSACSamplingSize:
-  -outlierDetection:RANSACSamplingSize $param_outlierDetection_RANSACSamplingSize
-#end if
-#if $param_outlierDetection_estimateBestPeptides:
-  -outlierDetection:estimateBestPeptides
-#end if
-#if $param_outlierDetection_InitialQualityCutoff:
-  -outlierDetection:InitialQualityCutoff $param_outlierDetection_InitialQualityCutoff
-#end if
-#if $param_outlierDetection_OverallQualityCutoff:
-  -outlierDetection:OverallQualityCutoff $param_outlierDetection_OverallQualityCutoff
-#end if
-#if $param_outlierDetection_NrRTBins:
-  -outlierDetection:NrRTBins $param_outlierDetection_NrRTBins
-#end if
-#if $param_outlierDetection_MinPeptidesPerBin:
-  -outlierDetection:MinPeptidesPerBin $param_outlierDetection_MinPeptidesPerBin
-#end if
-#if $param_outlierDetection_MinBinsFilled:
-  -outlierDetection:MinBinsFilled $param_outlierDetection_MinBinsFilled
-#end if
 #if $adv_opts.adv_opts_selector=='advanced':
     #if $adv_opts.param_rt_norm:
   -rt_norm $adv_opts.param_rt_norm
@@ -297,6 +311,9 @@
     #if $adv_opts.param_Scoring_TransitionGroupPicker_use_precursors:
   -Scoring:TransitionGroupPicker:use_precursors
 #end if
+    #if $adv_opts.param_Scoring_TransitionGroupPicker_resample_boundary:
+  -Scoring:TransitionGroupPicker:resample_boundary $adv_opts.param_Scoring_TransitionGroupPicker_resample_boundary
+#end if
     #if $adv_opts.param_Scoring_Scores_use_shape_score:
   -Scoring:Scores:use_shape_score
   #if " " in str($adv_opts.param_Scoring_Scores_use_shape_score):
@@ -403,6 +420,30 @@
     <param name="param_mz_extraction_window" type="float" min="0.0" optional="True" value="0.05" label="Extraction window used (in Thomson, to use ppm see -ppm flag)" help="(-mz_extraction_window) "/>
     <param name="param_ppm" display="radio" type="boolean" truevalue="-ppm" falsevalue="" checked="false" optional="True" label="m/z extraction_window is in ppm" help="(-ppm) "/>
     <param name="param_sonar" display="radio" type="boolean" truevalue="-sonar" falsevalue="" checked="false" optional="True" label="data is scanning SWATH data" help="(-sonar) "/>
+    <param name="param_RTNormalization_alignmentMethod" display="radio" type="select" optional="False" value="linear" label="How to perform the alignment to the normalized RT space using anchor points" help="(-alignmentMethod) 'linear': perform linear regression (for few anchor points). 'interpolated': Interpolate between anchor points (for few, noise-free anchor points). 'lowess' Use local regression (for many, noisy anchor points). 'b_spline' use b splines for smoothing">
+      <option value="linear" selected="true">linear</option>
+      <option value="interpolated">interpolated</option>
+      <option value="lowess">lowess</option>
+      <option value="b_spline">b_spline</option>
+    </param>
+    <param name="param_RTNormalization_outlierMethod" display="radio" type="select" optional="False" value="iter_residual" label="Which outlier detection method to use (valid: 'iter_residual', 'iter_jackknife', 'ransac', 'none')" help="(-outlierMethod) Iterative methods remove one outlier at a time. Jackknife approach optimizes for maximum r-squared improvement while 'iter_residual' removes the datapoint with the largest residual error (removal by residual is computationally cheaper, use this with lots of peptides)">
+      <option value="iter_residual" selected="true">iter_residual</option>
+      <option value="iter_jackknife">iter_jackknife</option>
+      <option value="ransac">ransac</option>
+      <option value="none">none</option>
+    </param>
+    <param name="param_RTNormalization_useIterativeChauvenet" display="radio" type="boolean" truevalue="-RTNormalization:useIterativeChauvenet" falsevalue="" checked="false" optional="True" label="Whether to use Chauvenet's criterion when using iterative methods" help="(-useIterativeChauvenet) This should be used if the algorithm removes too many datapoints but it may lead to true outliers being retained"/>
+    <param name="param_RTNormalization_RANSACMaxIterations" type="integer" value="1000" label="Maximum iterations for the RANSAC outlier detection algorithm" help="(-RANSACMaxIterations) "/>
+    <param name="param_RTNormalization_RANSACMaxPercentRTThreshold" type="integer" value="3" label="Maximum threshold in RT dimension for the RANSAC outlier detection algorithm (in percent of the total gradient)" help="(-RANSACMaxPercentRTThreshold) Default is set to 3% which is around +/- 4 minutes on a 120 gradient"/>
+    <param name="param_RTNormalization_RANSACSamplingSize" type="integer" value="10" label="Sampling size of data points per iteration for the RANSAC outlier detection algorithm" help="(-RANSACSamplingSize) "/>
+    <param name="param_RTNormalization_estimateBestPeptides" display="radio" type="boolean" truevalue="-RTNormalization:estimateBestPeptides" falsevalue="" checked="false" optional="True" label="Whether the algorithms should try to choose the best peptides based on their peak shape for normalization. Use this option you do not expect all your peptides to be detected in a sample and too many 'bad' peptides enter the outlier removal step (" help="(-estimateBestPeptides) e.g. due to them being endogenous peptides or using a less curated list of peptides)"/>
+    <param name="param_RTNormalization_InitialQualityCutoff" type="float" value="0.5" label="The initial overall quality cutoff for a peak to be scored (range ca" help="(-InitialQualityCutoff) -2 to 2)"/>
+    <param name="param_RTNormalization_OverallQualityCutoff" type="float" value="5.5" label="The overall quality cutoff for a peak to go into the retention time estimation (range ca" help="(-OverallQualityCutoff) 0 to 10)"/>
+    <param name="param_RTNormalization_NrRTBins" type="integer" value="10" label="Number of RT bins to use to compute coverage" help="(-NrRTBins) This option should be used to ensure that there is a complete coverage of the RT space (this should detect cases where only a part of the RT gradient is actually covered by normalization peptides)"/>
+    <param name="param_RTNormalization_MinPeptidesPerBin" type="integer" value="1" label="Minimal number of peptides that are required for a bin to counted as 'covered'" help="(-MinPeptidesPerBin) "/>
+    <param name="param_RTNormalization_MinBinsFilled" type="integer" value="8" label="Minimal number of bins required to be covered" help="(-MinBinsFilled) "/>
+    <param name="param_RTNormalization_lowess_span" type="float" min="0.0" max="1.0" optional="True" value="0.666666666667" label="Span parameter for lowess" help="(-span) "/>
+    <param name="param_RTNormalization_b_spline_num_nodes" type="integer" min="0" optional="True" value="5" label="Number of nodes for b spline" help="(-num_nodes) "/>
     <param name="param_Scoring_stop_report_after_feature" type="integer" value="-1" label="Stop reporting after feature (ordered by quality; -1 means do not stop)" help="(-stop_report_after_feature) "/>
     <param name="param_Scoring_rt_normalization_factor" type="float" value="100.0" label="The normalized RT is expected to be between 0 and 1. If your normalized RT has a different range, pass this here (" help="(-rt_normalization_factor) e.g. it goes from 0 to 100, set this value to 100)"/>
     <param name="param_Scoring_uis_threshold_sn" type="integer" value="-1" label="S/N threshold to consider identification transition (set to -1 to consider all)" help="(-uis_threshold_sn) "/>
@@ -435,7 +476,7 @@
       <option value="false">false</option>
       <option value="true" selected="true">true</option>
     </param>
-    <param name="param_Scoring_TransitionGroupPicker_PeakPickerMRM_method" display="radio" type="select" optional="False" value="corrected" label="Which method to choose for chromatographic peak-picking (OpenSWATH legacy, corrected picking or Crawdad)" help="(-method) ">
+    <param name="param_Scoring_TransitionGroupPicker_PeakPickerMRM_method" display="radio" type="select" optional="False" value="corrected" label="Which method to choose for chromatographic peak-picking (OpenSWATH legacy on raw data, corrected picking on smoothed chromatogram or Crawdad on smoothed chromatogram)" help="(-method) ">
       <option value="legacy">legacy</option>
       <option value="corrected" selected="true">corrected</option>
       <option value="crawdad">crawdad</option>
@@ -448,22 +489,6 @@
     <param name="param_Scoring_DIAScoring_dia_nr_charges" type="integer" min="0" optional="True" value="4" label="DIA nr of charges to conside" help="(-dia_nr_charges) "/>
     <param name="param_Scoring_DIAScoring_peak_before_mono_max_ppm_diff" type="float" min="0.0" optional="True" value="20.0" label="DIA maximal difference in ppm to count a peak at lower m/z when searching for evidence that a peak might not be monoisotopic" help="(-peak_before_mono_max_ppm_diff) "/>
     <param name="param_Scoring_EMGScoring_max_iteration" type="integer" value="10" label="Maximum number of iterations using by Levenberg-Marquardt algorithm" help="(-max_iteration) "/>
-    <param name="param_outlierDetection_outlierMethod" display="radio" type="select" optional="False" value="iter_residual" label="Which outlier detection method to use (valid: 'iter_residual', 'iter_jackknife', 'ransac', 'none')" help="(-outlierMethod) Iterative methods remove one outlier at a time. Jackknife approach optimizes for maximum r-squared improvement while 'iter_residual' removes the datapoint with the largest residual error (removal by residual is computationally cheaper, use this with lots of peptides)">
-      <option value="iter_residual" selected="true">iter_residual</option>
-      <option value="iter_jackknife">iter_jackknife</option>
-      <option value="ransac">ransac</option>
-      <option value="none">none</option>
-    </param>
-    <param name="param_outlierDetection_useIterativeChauvenet" display="radio" type="boolean" truevalue="-outlierDetection:useIterativeChauvenet" falsevalue="" checked="false" optional="True" label="Whether to use Chauvenet's criterion when using iterative methods" help="(-useIterativeChauvenet) This should be used if the algorithm removes too many datapoints but it may lead to true outliers being retained"/>
-    <param name="param_outlierDetection_RANSACMaxIterations" type="integer" value="1000" label="Maximum iterations for the RANSAC outlier detection algorithm" help="(-RANSACMaxIterations) "/>
-    <param name="param_outlierDetection_RANSACMaxPercentRTThreshold" type="integer" value="3" label="Maximum threshold in RT dimension for the RANSAC outlier detection algorithm (in percent of the total gradient)" help="(-RANSACMaxPercentRTThreshold) Default is set to 3% which is around +/- 4 minutes on a 120 gradient"/>
-    <param name="param_outlierDetection_RANSACSamplingSize" type="integer" value="10" label="Sampling size of data points per iteration for the RANSAC outlier detection algorithm" help="(-RANSACSamplingSize) "/>
-    <param name="param_outlierDetection_estimateBestPeptides" display="radio" type="boolean" truevalue="-outlierDetection:estimateBestPeptides" falsevalue="" checked="false" optional="True" label="Whether the algorithms should try to choose the best peptides based on their peak shape for normalization. Use this option you do not expect all your peptides to be detected in a sample and too many 'bad' peptides enter the outlier removal step (" help="(-estimateBestPeptides) e.g. due to them being endogenous peptides or using a less curated list of peptides)"/>
-    <param name="param_outlierDetection_InitialQualityCutoff" type="float" value="0.5" label="The initial overall quality cutoff for a peak to be scored (range ca" help="(-InitialQualityCutoff) -2 to 2)"/>
-    <param name="param_outlierDetection_OverallQualityCutoff" type="float" value="5.5" label="The overall quality cutoff for a peak to go into the retention time estimation (range ca" help="(-OverallQualityCutoff) 0 to 10)"/>
-    <param name="param_outlierDetection_NrRTBins" type="integer" value="10" label="Number of RT bins to use to compute coverage" help="(-NrRTBins) This option should be used to ensure that there is a complete coverage of the RT space (this should detect cases where only a part of the RT gradient is actually covered by normalization peptides)"/>
-    <param name="param_outlierDetection_MinPeptidesPerBin" type="integer" value="1" label="Minimal number of peptides that are required for a bin to counted as 'covered'" help="(-MinPeptidesPerBin) "/>
-    <param name="param_outlierDetection_MinBinsFilled" type="integer" value="8" label="Minimal number of bins required to be covered" help="(-MinBinsFilled) "/>
     <expand macro="advanced_options">
       <param name="param_rt_norm" type="data" format="trafoxml" optional="True" label="RT normalization file (how to map the RTs of this run to the ones stored in the library)" help="(-rt_norm) If set, tr_irt may be omitted"/>
       <param name="param_swath_windows_file" type="data" format="txt" label="Optional, tab separated file containing the SWATH windows for extraction: lower_offset upper_offset \newline 400 425 \newline .." help="(-swath_windows_file) Note that the first line is a header and will be skipped"/>
@@ -517,6 +542,7 @@
       <param name="param_Scoring_quantification_cutoff" type="float" min="0.0" optional="True" value="0.0" label="Cutoff in m/z below which peaks should not be used for quantification any more" help="(-quantification_cutoff) "/>
       <param name="param_Scoring_write_convex_hull" display="radio" type="boolean" truevalue="-Scoring:write_convex_hull" falsevalue="" checked="false" optional="True" label="Whether to write out all points of all features into the featureXML" help="(-write_convex_hull) "/>
       <param name="param_Scoring_TransitionGroupPicker_use_precursors" display="radio" type="boolean" truevalue="-Scoring:TransitionGroupPicker:use_precursors" falsevalue="" checked="false" optional="True" label="Use precursor chromatogram for peak picking" help="(-use_precursors) "/>
+      <param name="param_Scoring_TransitionGroupPicker_resample_boundary" type="float" value="15.0" label="For computing peak quality, how many extra seconds should be sample left and right of the actual peak" help="(-resample_boundary) "/>
       <param name="param_Scoring_Scores_use_shape_score" display="radio" type="select" optional="False" value="true" label="Use the shape score (this score measures the similarity in shape of the transitions using a cross-correlation)" help="(-use_shape_score) ">
         <option value="true" selected="true">true</option>
         <option value="false">false</option>
--- a/SKIP_TOOLS_FILE.txt	Thu Jan 11 18:12:54 2018 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,9 +0,0 @@
-OMSSAAdapter
-MyriMatchAdapter
-PepNovoAdapter
-SeedListGenerator
-SpecLibSearcher
-MapAlignerIdentification
-MapAlignerPoseClustering
-MapAlignerSpectrum
-MapAlignerRTTransformer
--- a/macros.xml	Thu Jan 11 18:12:54 2018 -0500
+++ b/macros.xml	Mon Feb 12 13:02:55 2018 -0500
@@ -2,10 +2,10 @@
 <macros>
   <xml name="requirements">
     <requirements>
-      <requirement type="package" version="2.2">openms</requirement>
+      <requirement type="package" version="2.3">openms</requirement>
       <requirement type="package" version="15.12.15.2">xtandem</requirement>
       <requirement type="package" version="1.0">fido</requirement>
-      <requirement type="package" version="2016.10.26">msgf_plus</requirement>
+      <requirement type="package" version="2017.07.21">msgf_plus</requirement>
       <yield/>
     </requirements>
   </xml>
--- a/readme.md	Thu Jan 11 18:12:54 2018 -0500
+++ b/readme.md	Mon Feb 12 13:02:55 2018 -0500
@@ -53,29 +53,29 @@
  * clone or install CTD2Galaxy
 
     ```bash
-    git clone https://github.com/WorkflowConversion/CTD2Galaxy.git
+    git clone https://github.com/WorkflowConversion/CTDConverter.git
     ```
     
- * If you have CTDopts and CTD2Galaxy installed you are ready to generate Galaxy Tools from CTD definitions. Change the following command according to your needs, especially the `/PATH/TO` parts. The default files are provided in this repository. You might have to install `libxslt` and `lxml` to run it.
+ * If you have CTDopts and CTDConverter installed you are ready to generate Galaxy Tools from CTD definitions. Change the following command according to your needs, especially the `/PATH/TO` parts. The default files are provided in this repository. You might have to install `libxslt` and `lxml` to run it. Further information can be found on the CTDConverter page.
 
     ```bash
-    python generator.py \ 
+    python convert.py galaxy \ 
     -i /PATH/TO/YOUR/CTD/*.ctd \
     -o ./PATH/TO/YOUR/WRAPPERS/ -t tool.conf \
     -d datatypes_conf.xml -g openms \
     -b version log debug test no_progress threads \
      in_type executable myrimatch_executable \
      fido_executable fidocp_executable \
-     omssa_executable pepnovo_executable \
+     omssa_executable pepnovo_e xecutable \
      xtandem_executable param_model_directory \
      java_executable java_memory java_permgen \
      r_executable rt_concat_trafo_out param_id_pool \
     -f /PATH/TO/filetypes.txt -m /PATH/TO/macros.xml \
-    -s PATH/TO/SKIP_TOOLS_FILES.txt
+    -s PATH/TO/tools_blacklist.txt
     ```
 
 
- * As last step you need to change manually the binary names of all external binaries you want to use in OpenMS. For example:
+ * As last step you need to change manually the binary names of all external binaries you want to use in OpenMS. Some of these tools might already be deprecated and the files might not exist:
 
     ```
     sed -i '13 a\-fido_executable Fido' wrappers/FidoAdapter.xml
@@ -171,8 +171,8 @@
     ```
     
 
- * These tools have multiple outputs (number of inputs = number of outputs) which is not yet supported in
-   by the automatic conversion step and are therefore in `SKIP_TOOLS_FILES.txt`:
+ * `This section might not be up to date. It might be worth trying if these tools will run now.` These tools have multiple outputs (number of inputs = number of outputs) which is not yet supported in
+   by the automatic conversion step and are therefore in `tools_blacklist.txt`:
     * SeedListGenerator
     * SpecLibSearcher
     * MapAlignerIdentification
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tools_blacklist.txt	Mon Feb 12 13:02:55 2018 -0500
@@ -0,0 +1,9 @@
+OMSSAAdapter
+MyriMatchAdapter
+PepNovoAdapter
+SeedListGenerator
+SpecLibSearcher
+MapAlignerIdentification
+MapAlignerPoseClustering
+MapAlignerSpectrum
+MapAlignerRTTransformer