diff qiime2/qiime_longitudinal_maturity-index.xml @ 0:370e0b6e9826 draft

Uploaded

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/qiime2/qiime_longitudinal_maturity-index.xml	Wed Jul 17 03:05:17 2019 -0400
@@ -0,0 +1,255 @@
+<?xml version="1.0" ?>
+<tool id="qiime_longitudinal_maturity-index" name="qiime longitudinal maturity-index" version="2019.4">
+	<description> - Microbial maturity index prediction.</description>
+	<requirements>
+		<requirement type="package" version="2019.4">qiime2</requirement>
+	</requirements>
+	<command><![CDATA[
+qiime longitudinal maturity-index
+
+--i-table=$itable
+--p-state-column="$pstatecolumn"
+--p-group-by="$pgroupby"
+--p-control="$pcontrol"
+
+#if str($pindividualidcolumn):
+ --p-individual-id-column="$pindividualidcolumn"
+#end if
+
+#if str($pestimator) != 'None':
+ --p-estimator=$pestimator
+#end if
+
+#if $pnestimators:
+ --p-n-estimators=$pnestimators
+#end if
+
+#if $ptestsize:
+ --p-test-size=$ptestsize
+#end if
+
+#if $pstep:
+ --p-step=$pstep
+#end if
+
+#if $pcv:
+ --p-cv=$pcv
+#end if
+
+#if str($prandomstate):
+ --p-random-state="$prandomstate"
+#end if
+
+#set $pnjobs = '${GALAXY_SLOTS:-4}'
+#if str($pnjobs):
+ --p-n-jobs="$pnjobs"
+#end if
+
+
+#if $pparametertuning:
+ --p-parameter-tuning
+#end if
+
+#if $poptimizefeatureselection:
+ --p-optimize-feature-selection
+#end if
+
+#if $pstratify:
+ --p-stratify
+#end if
+
+#if str($pmissingsamples) != 'None':
+ --p-missing-samples=$pmissingsamples
+#end if
+
+#if $pfeaturecount:
+ --p-feature-count=$pfeaturecount
+#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)
+#end if
+
+
+--o-sample-estimator=osampleestimator
+--o-feature-importance=ofeatureimportance
+--o-predictions=opredictions
+--o-model-summary=omodelsummary
+--o-accuracy-results=oaccuracyresults
+--o-maz-scores=omazscores
+--o-clustermap=oclustermap
+--o-volatility-plots=ovolatilityplots
+;
+cp osampleestimator.qza $osampleestimator;
+cp ofeatureimportance.qza $ofeatureimportance;
+cp opredictions.qza $opredictions;
+qiime tools export --input-path omodelsummary.qzv --output-path out   && mkdir -p '$omodelsummary.files_path'
+&& cp -r out/* '$omodelsummary.files_path'
+&& mv '$omodelsummary.files_path/index.html' '$omodelsummary';
+qiime tools export --input-path oaccuracyresults.qzv --output-path out   && mkdir -p '$oaccuracyresults.files_path'
+&& cp -r out/* '$oaccuracyresults.files_path'
+&& mv '$oaccuracyresults.files_path/index.html' '$oaccuracyresults';
+cp omazscores.qza $omazscores;
+qiime tools export --input-path oclustermap.qzv --output-path out   && mkdir -p '$oclustermap.files_path'
+&& cp -r out/* '$oclustermap.files_path'
+&& mv '$oclustermap.files_path/index.html' '$oclustermap';
+qiime tools export --input-path ovolatilityplots.qzv --output-path out   && mkdir -p '$ovolatilityplots.files_path'
+&& cp -r out/* '$ovolatilityplots.files_path'
+&& mv '$ovolatilityplots.files_path/index.html' '$ovolatilityplots'
+	]]></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  Numeric metadata column containing sampling time (state) data to use as prediction target.  [required]" name="pstatecolumn" optional="False" type="text"/>
+		<param label="--p-group-by: TEXT      Categorical metadata column to use for plotting and significance testing between main treatment groups. [required]" name="pgroupby" optional="False" type="text"/>
+		<param label="--p-control: TEXT       Value of group-by to use as control group. The regression model will be trained using only control group data, and the maturity scores of other groups consequently will be assessed relative to this group. [required]" name="pcontrol" optional="False" type="text"/>
+		<param label="--p-individual-id-column: TEXT Optional metadata column containing IDs for individual subjects. Adds individual subject (spaghetti) vectors to volatility charts if a column name is provided.                          [optional]" name="pindividualidcolumn" optional="True" type="text"/>
+		<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-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-test-size: PROPORTION Range(0.0, 1.0, inclusive_start=False) Fraction of input samples to exclude from training set and use for classifier testing.    [default: 0.5]" name="ptestsize" optional="True" type="float" exclusive_start="True" min="0" max="1" value="0.5"/>
+		<param label="--p-step: PROPORTION Range(0.0, 1.0, inclusive_start=False) If optimize-feature-selection is True, step is the percentage of features to remove at each iteration. [default: 0.05]" name="pstep" optional="True" type="float" exclusive_start="True" min="0" max="1" value="0.05"/>
+		<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-parameter-tuning: --p-no-parameter-tuning Automatically tune hyperparameters using random grid search.                              [default: False]" name="pparametertuning" selected="False" type="boolean"/>
+		<param label="--p-optimize-feature-selection: --p-no-optimize-feature-selection Automatically optimize input feature selection using recursive feature elimination.       [default: False]" name="poptimizefeatureselection" selected="False" type="boolean"/>
+		<param label="--p-stratify: --p-no-stratify Evenly stratify training and test data among metadata categories. If True, all values in column must match at least two samples.     [default: False]" name="pstratify" 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-feature-count: INTEGER Range(0, None)       Filter feature table to include top N most important features. Set to zero to include all features. [default: 50]" name="pfeaturecount" optional="True" type="integer" min="0" value="50"/>
+
+		<repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file">
+			<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>	</inputs>
+
+	<outputs>
+		<data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator"/>
+		<data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance"/>
+		<data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions"/>
+		<data format="html" label="${tool.name} on ${on_string}: modelsummary.qzv" name="omodelsummary"/>
+		<data format="html" label="${tool.name} on ${on_string}: accuracyresults.qzv" name="oaccuracyresults"/>
+		<data format="qza" label="${tool.name} on ${on_string}: mazscores.qza" name="omazscores"/>
+		<data format="html" label="${tool.name} on ${on_string}: clustermap.qzv" name="oclustermap"/>
+		<data format="html" label="${tool.name} on ${on_string}: volatilityplots.qzv" name="ovolatilityplots"/>
+	</outputs>
+	<help><![CDATA[
+Microbial maturity index prediction.
+####################################
+
+Calculates a "microbial maturity" index from a regression model trained on
+feature data to predict a given continuous metadata column, e.g., to
+predict age as a function of microbiota composition. The model is trained
+on a subset of control group samples, then predicts the column value for
+all samples. This visualization computes maturity index z-scores to compare
+relative "maturity" between each group, as described in
+doi:10.1038/nature13421. This method can be used to predict between-group
+differences in relative trajectory across any type of continuous metadata
+gradient, e.g., intestinal microbiome development by age, microbial
+succession during wine fermentation, or microbial community differences
+along environmental gradients, as a function of two or more different
+"treatment" groups.
+
+Parameters
+----------
+table : FeatureTable[Frequency]
+    Feature table containing all features that should be used for target
+    prediction.
+metadata : Metadata
+	\
+state_column : Str
+    Numeric metadata column containing sampling time (state) data to use as
+    prediction target.
+group_by : Str
+    Categorical metadata column to use for plotting and significance
+    testing between main treatment groups.
+control : Str
+    Value of group_by to use as control group. The regression model will be
+    trained using only control group data, and the maturity scores of other
+    groups consequently will be assessed relative to this group.
+individual_id_column : Str, optional
+    Optional metadata column containing IDs for individual subjects. Adds
+    individual subject (spaghetti) vectors to volatility charts if a column
+    name is provided.
+estimator : Str % Choices('RandomForestRegressor', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'AdaBoostRegressor', 'ElasticNet', 'Ridge', 'Lasso', 'KNeighborsRegressor', 'LinearSVR', 'SVR'), optional
+    Regression model to use for prediction.
+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
+    time and memory requirements. This parameter only affects ensemble
+    estimators, such as Random Forest, AdaBoost, ExtraTrees, and
+    GradientBoosting.
+test_size : Float % Range(0.0, 1.0, inclusive_start=False), optional
+    Fraction of input samples to exclude from training set and use for
+    classifier testing.
+step : Float % Range(0.0, 1.0, inclusive_start=False), optional
+    If optimize_feature_selection is True, step is the percentage of
+    features to remove at each iteration.
+cv : Int % Range(1, None), optional
+    Number of k-fold cross-validations to perform.
+random_state : Int, optional
+    Seed used by random number generator.
+parameter_tuning : Bool, optional
+    Automatically tune hyperparameters using random grid search.
+optimize_feature_selection : Bool, optional
+    Automatically optimize input feature selection using recursive feature
+    elimination.
+stratify : Bool, optional
+    Evenly stratify training and test data among metadata categories. If
+    True, all values in column must match at least two samples.
+missing_samples : Str % Choices('error', 'ignore'), optional
+    How to handle missing samples in metadata. "error" will fail if missing
+    samples are detected. "ignore" will cause the feature table and
+    metadata to be filtered, so that only samples found in both files are
+    retained.
+feature_count : Int % Range(0, None), optional
+    Filter feature table to include top N most important features. Set to
+    zero to include all features.
+
+Returns
+-------
+sample_estimator : SampleEstimator[Regressor]
+    Trained sample estimator.
+feature_importance : FeatureData[Importance]
+    Importance of each input feature to model accuracy.
+predictions : SampleData[RegressorPredictions]
+    Predicted target values for each input sample.
+model_summary : Visualization
+    Summarized parameter and (if enabled) feature selection information for
+    the trained estimator.
+accuracy_results : Visualization
+    Accuracy results visualization.
+maz_scores : SampleData[RegressorPredictions]
+    Microbiota-for-age z-score predictions.
+clustermap : Visualization
+    Heatmap of important feature abundance at each time point in each
+    group.
+volatility_plots : Visualization
+    Interactive volatility plots of MAZ and maturity scores, target
+    (column) predictions, and the sample metadata.
+	]]></help>
+<macros>
+    <import>qiime_citation.xml</import>
+</macros>
+<expand macro="qiime_citation"/>
+</tool>