Mercurial > repos > florianbegusch > qiime2_suite

diff qiime2/qiime_longitudinal_feature-volatility.xml @ 14:a0a8d77a991c draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author florianbegusch
date Thu, 03 Sep 2020 09:51:29 +0000
parents f190567fe3f6
children
line wrap: on
line diff
--- a/qiime2/qiime_longitudinal_feature-volatility.xml	Thu Sep 03 09:46:00 2020 +0000
+++ b/qiime2/qiime_longitudinal_feature-volatility.xml	Thu Sep 03 09:51:29 2020 +0000
@@ -1,42 +1,85 @@
 <?xml version="1.0" ?>
-<tool id="qiime_longitudinal_feature-volatility" name="qiime longitudinal feature-volatility" version="2019.7">
-	<description> - Feature volatility analysis</description>
-	<requirements>
-		<requirement type="package" version="2019.7">qiime2</requirement>
-	</requirements>
-	<command><![CDATA[
+<tool id="qiime_longitudinal_feature-volatility" name="qiime longitudinal feature-volatility"
+      version="2020.8">
+  <description>Feature volatility analysis</description>
+  <requirements>
+    <requirement type="package" version="2020.8">qiime2</requirement>
+  </requirements>
+  <command><![CDATA[
 qiime longitudinal feature-volatility
 
 --i-table=$itable
+# if $input_files_mmetadatafile:
+  # def list_dict_to_string(list_dict):
+    # set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
+    # for d in list_dict[1:]:
+      # set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
+    # end for
+    # return $file_list
+  # end def
+--m-metadata-file=$list_dict_to_string($input_files_mmetadatafile)
+# end if
+
+#if '__ob__' in str($pstatecolumn):
+  #set $pstatecolumn_temp = $pstatecolumn.replace('__ob__', '[')
+  #set $pstatecolumn = $pstatecolumn_temp
+#end if
+#if '__cb__' in str($pstatecolumn):
+  #set $pstatecolumn_temp = $pstatecolumn.replace('__cb__', ']')
+  #set $pstatecolumn = $pstatecolumn_temp
+#end if
+#if 'X' in str($pstatecolumn):
+  #set $pstatecolumn_temp = $pstatecolumn.replace('X', '\\')
+  #set $pstatecolumn = $pstatecolumn_temp
+#end if
+#if '__sq__' in str($pstatecolumn):
+  #set $pstatecolumn_temp = $pstatecolumn.replace('__sq__', "'")
+  #set $pstatecolumn = $pstatecolumn_temp
+#end if
+#if '__db__' in str($pstatecolumn):
+  #set $pstatecolumn_temp = $pstatecolumn.replace('__db__', '"')
+  #set $pstatecolumn = $pstatecolumn_temp
+#end if
+
+--p-state-column=$pstatecolumn
 
 
---p-state-column="$pstatecolumn"
+#if '__ob__' in str($pindividualidcolumn):
+  #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__ob__', '[')
+  #set $pindividualidcolumn = $pindividualidcolumn_temp
+#end if
+#if '__cb__' in str($pindividualidcolumn):
+  #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__cb__', ']')
+  #set $pindividualidcolumn = $pindividualidcolumn_temp
+#end if
+#if 'X' in str($pindividualidcolumn):
+  #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('X', '\\')
+  #set $pindividualidcolumn = $pindividualidcolumn_temp
+#end if
+#if '__sq__' in str($pindividualidcolumn):
+  #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__sq__', "'")
+  #set $pindividualidcolumn = $pindividualidcolumn_temp
+#end if
+#if '__db__' in str($pindividualidcolumn):
+  #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__db__', '"')
+  #set $pindividualidcolumn = $pindividualidcolumn_temp
+#end if
 
 #if str($pindividualidcolumn):
- --p-individual-id-column="$pindividualidcolumn"
+  --p-individual-id-column=$pindividualidcolumn
 #end if
 
-#if str($pcv):
- --p-cv=$pcv
-#end if
+--p-cv=$pcv
 
 #if str($prandomstate):
- --p-random-state="$prandomstate"
+  --p-random-state=$prandomstate
 #end if
-
-#set $pnjobs = '${GALAXY_SLOTS:-4}'
+--p-n-jobs=$pnjobs
 
-#if str($pnjobs):
- --p-n-jobs="$pnjobs"
-#end if
-
-
-#if str($pnestimators):
- --p-n-estimators=$pnestimators
-#end if
+--p-n-estimators=$pnestimators
 
 #if str($pestimator) != 'None':
- --p-estimator=$pestimator
+--p-estimator=$pestimator
 #end if
 
 #if $pparametertuning:
@@ -44,80 +87,91 @@
 #end if
 
 #if str($pmissingsamples) != 'None':
- --p-missing-samples=$pmissingsamples
+--p-missing-samples=$pmissingsamples
 #end if
 
-
-#if $input_files_mmetadatafile:
-#def list_dict_to_string(list_dict):
-	#set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
-	#for d in list_dict[1:]:
-		#set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
-	#end for
-	#return $file_list
-#end def
- --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile)
+#if str($pimportancethreshold) != 'None':
+--p-importance-threshold=$pimportancethreshold
 #end if
 
+#if str($pfeaturecount) != 'None':
+--p-feature-count=$pfeaturecount
+#end if
 
 --o-filtered-table=ofilteredtable
+
 --o-feature-importance=ofeatureimportance
+
 --o-volatility-plot=ovolatilityplot
+
 --o-accuracy-results=oaccuracyresults
+
 --o-sample-estimator=osampleestimator
+
+#if str($examples) != 'None':
+--examples=$examples
+#end if
+
 ;
-cp ofilteredtable.qza $ofilteredtable;
-cp ofeatureimportance.qza $ofeatureimportance;
-qiime tools export --input-path ovolatilityplot.qzv --output-path out   && mkdir -p '$ovolatilityplot.files_path'
-&& cp -r out/* '$ovolatilityplot.files_path'
-&& mv '$ovolatilityplot.files_path/index.html' '$ovolatilityplot';
-qiime tools export --input-path oaccuracyresults.qzv --output-path out   && mkdir -p '$oaccuracyresults.files_path'
-&& cp -r out/* '$oaccuracyresults.files_path'
-&& mv '$oaccuracyresults.files_path/index.html' '$oaccuracyresults';
 cp osampleestimator.qza $osampleestimator
-	]]></command>
-	<inputs>
-		<param format="qza,no_unzip.zip" label="--i-table: ARTIFACT FeatureTable[Frequency] Feature table containing all features that should be used for target prediction.                [required]" name="itable" optional="False" type="data"/>
-		<param label="--p-state-column: TEXT  Metadata containing collection time (state) values for each sample. Must contain exclusively numeric values.                                    [required]" name="pstatecolumn" optional="False" type="text"/>
-		<param label="--p-individual-id-column: TEXT Metadata column containing IDs for individual subjects.                                  [optional]" name="pindividualidcolumn" optional="True" type="text"/>
-		<param label="--p-cv: INTEGER         Number of k-fold cross-validations to perform. Range(1, None)                                                [default: 5]" name="pcv" optional="True" type="integer" min="1" value="5"/>
-		<param label="--p-random-state: INTEGER Seed used by random number generator.      [optional]" name="prandomstate" optional="True" type="integer"/>
-		<param label="--p-n-estimators: INTEGER Range(1, None)       Number of trees to grow for estimation. More trees will improve predictive accuracy up to a threshold level, but will also increase time and memory requirements. This parameter only affects ensemble estimators, such as Random Forest, AdaBoost, ExtraTrees, and GradientBoosting.      [default: 100]" name="pnestimators" optional="True" type="integer" min="1" value="100"/>
-		<param label="--p-estimator: " name="pestimator" optional="True" type="select">
-			<option selected="True" value="None">Selection is Optional</option>
-			<option value="RandomForestRegressor">RandomForestRegressor</option>
-			<option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
-			<option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
-			<option value="AdaBoostRegressor">AdaBoostRegressor</option>
-			<option value="ElasticNet">ElasticNet</option>
-			<option value="Ridge">Ridge</option>
-			<option value="Lasso">Lasso</option>
-			<option value="KNeighborsRegressor">KNeighborsRegressor</option>
-			<option value="LinearSVR">LinearSVR</option>
-			<option value="SVR">SVR</option>
-		</param>
-		<param label="--p-parameter-tuning: --p-no-parameter-tuning Automatically tune hyperparameters using random grid search.                              [default: False]" name="pparametertuning" selected="False" type="boolean"/>
-		<param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
-			<option selected="True" value="None">Selection is Optional</option>
-			<option value="error">error</option>
-			<option value="ignore">ignore</option>
-		</param>
 
-		<repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file  [required]">
-			<param label="--m-metadata-file: Metadata file or artifact viewable as metadata. This option may be supplied multiple times to merge metadata. [optional]" name="additional_input" type="data" format="tabular,qza,no_unzip.zip" />
-		</repeat>
+  ]]></command>
+  <inputs>
+    <param format="qza,no_unzip.zip" label="--i-table: ARTIFACT FeatureTable[Frequency] Feature table containing all features that should be used for target prediction.                [required]" name="itable" optional="False" type="data" />
+    <repeat name="input_files_mmetadatafile" optional="False" title="--m-metadata-file">
+      <param format="tabular,qza,no_unzip.zip" label="--m-metadata-file: METADATA... (multiple            Sample metadata file containing arguments will be   individual-id-column. merged)                                                        [required]" name="additional_input" optional="False" type="data" />
+    </repeat>
+    <param label="--p-state-column: TEXT  Metadata containing collection time (state) values for each sample. Must contain exclusively numeric values.                                    [required]" name="pstatecolumn" optional="False" type="text" />
+    <param label="--p-individual-id-column: TEXT Metadata column containing IDs for individual subjects.                                  [optional]" name="pindividualidcolumn" optional="False" type="text" />
+    <param label="--p-cv: INTEGER         Number of k-fold cross-validations to perform. Range(1, None)                                                [default: 5]" min="1" name="pcv" optional="True" type="integer" value="5" />
+    <param label="--p-random-state: INTEGER Seed used by random number generator.      [optional]" name="prandomstate" optional="False" type="text" />
+    <param label="--p-n-estimators: INTEGER Range(1, None)       Number of trees to grow for estimation. More trees will improve predictive accuracy up to a threshold level, but will also increase time and memory requirements. This parameter only affects ensemble estimators, such as Random Forest, AdaBoost, ExtraTrees, and GradientBoosting.      [default: 100]" min="1" name="pnestimators" optional="True" type="integer" value="100" />
+    <param label="--p-estimator: " name="pestimator" optional="True" type="select">
+      <option selected="True" value="None">Selection is Optional</option>
+      <option value="RandomForestRegressor">RandomForestRegressor</option>
+      <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
+      <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
+      <option value="AdaBoostRegressor">AdaBoostRegressor</option>
+      <option value="ElasticNet">ElasticNet</option>
+      <option value="Ridge">Ridge</option>
+      <option value="Lasso">Lasso</option>
+      <option value="KNeighborsRegressor">KNeighborsRegressor</option>
+      <option value="LinearSVR">LinearSVR</option>
+      <option value="SVR">SVR</option>
+    </param>
+    <param label="--p-parameter-tuning: --p-parameter-tuning: / --p-no-parameter-tuning Automatically tune hyperparameters using random grid search.                              [default: False]" name="pparametertuning" selected="False" type="boolean" />
+    <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
+      <option selected="True" value="None">Selection is Optional</option>
+      <option value="error">error</option>
+      <option value="ignore">ignore</option>
+    </param>
+    <param label="--p-importance-threshold: " name="pimportancethreshold" optional="True" type="select">
+      <option selected="True" value="None">Selection is Optional</option>
+      <option value="Float % Range(0">Float % Range(0</option>
+      <option value="None">None</option>
+      <option value="inclusive_start=False">inclusive_start=False</option>
+    </param>
+    <param label="--p-feature-count: " name="pfeaturecount" optional="True" type="select">
+      <option selected="True" value="None">Selection is Optional</option>
+      <option value="Int % Range(1">Int % Range(1</option>
+      <option value="None">None</option>
+    </param>
+    <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
+    
+  </inputs>
 
-	</inputs>
-	<outputs>
-		<data format="qza" label="${tool.name} on ${on_string}: filteredtable.qza" name="ofilteredtable"/>
-		<data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance"/>
-		<data format="html" label="${tool.name} on ${on_string}: volatilityplot.qzv" name="ovolatilityplot"/>
-		<data format="html" label="${tool.name} on ${on_string}: accuracyresults.qzv" name="oaccuracyresults"/>
-		<data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator"/>
-	</outputs>
-	<help><![CDATA[
+  <outputs>
+    <data format="qza" label="${tool.name} on ${on_string}: filteredtable.qza" name="ofilteredtable" />
+    <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance" />
+    <data format="html" label="${tool.name} on ${on_string}: volatilityplot.html" name="ovolatilityplot" />
+    <data format="html" label="${tool.name} on ${on_string}: accuracyresults.html" name="oaccuracyresults" />
+    <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator" />
+    
+  </outputs>
+
+  <help><![CDATA[
 Feature volatility analysis
-###########################
+###############################################################
 
 Identify features that are predictive of a numeric metadata column,
 state_column (e.g., time), and plot their relative frequencies across
@@ -142,6 +196,8 @@
     Number of k-fold cross-validations to perform.
 random_state : Int, optional
     Seed used by random number generator.
+n_jobs : Int, optional
+    Number of jobs to run in parallel.
 n_estimators : Int % Range(1, None), optional
     Number of trees to grow for estimation. More trees will improve
     predictive accuracy up to a threshold level, but will also increase
@@ -157,6 +213,14 @@
     samples are detected. "ignore" will cause the feature table and
     metadata to be filtered, so that only samples found in both files are
     retained.
+importance_threshold : Float % Range(0, None, inclusive_start=False) | Str % Choices('q1', 'q2', 'q3'), optional
+    Filter feature table to exclude any features with an importance score
+    less than this threshold. Set to "q1", "q2", or "q3" to select the
+    first, second, or third quartile of values. Set to "None" to disable
+    this filter.
+feature_count : Int % Range(1, None) | Str % Choices('all'), optional
+    Filter feature table to include top N most important features. Set to
+    "all" to include all features.
 
 Returns
 -------
@@ -170,9 +234,9 @@
     Accuracy results visualization.
 sample_estimator : SampleEstimator[Regressor]
     Trained sample regressor.
-	]]></help>
-<macros>
+  ]]></help>
+  <macros>
     <import>qiime_citation.xml</import>
-</macros>
-<expand macro="qiime_citation"/>
-</tool>
+  </macros>
+  <expand macro="qiime_citation"/>
+</tool>
\ No newline at end of file