<?xml version="1.0" ?>
<tool id="qiime_longitudinal_maturity-index" name="qiime longitudinal maturity-index"
      version="2020.8">
  <description>Microbial maturity index prediction.</description>
  <requirements>
    <requirement type="package" version="2020.8">qiime2</requirement>
  </requirements>
  <command><![CDATA[
qiime longitudinal maturity-index

--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-group-by=$pgroupby

--p-control=$pcontrol

#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
#end if

#if str($pestimator) != 'None':
--p-estimator=$pestimator
#end if

--p-n-estimators=$pnestimators

--p-test-size=$ptestsize

--p-step=$pstep

--p-cv=$pcv

#if str($prandomstate):
  --p-random-state=$prandomstate
#end if
--p-n-jobs=$pnjobs

#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

--p-feature-count=$pfeaturecount

--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

#if str($examples) != 'None':
--examples=$examples
#end if

;
cp omazscores.qza $omazscores

;
qiime tools export  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  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" />
    <repeat name="input_files_mmetadatafile" optional="False" title="--m-metadata-file">
      <param format="tabular,qza,no_unzip.zip" label="--m-metadata-file: METADATA... (multiple arguments will be merged)                                                        [required]" name="additional_input" optional="False" type="data" />
    </repeat>
    <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="False" 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]" min="1" name="pnestimators" optional="True" type="integer" value="100" />
    <param exclude_min="True" 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]" max="1.0" min="0.0" name="ptestsize" optional="True" type="float" value="0.5" />
    <param exclude_min="True" 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]" max="1.0" min="0.0" name="pstep" optional="True" type="float" value="0.05" />
    <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-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-optimize-feature-selection: --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-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]" min="0" name="pfeaturecount" optional="True" type="integer" value="50" />
    <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
    
  </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 ${on_string}: modelsummary.html" name="omodelsummary" />
    <data format="html" label="${tool.name} on ${on_string}: accuracyresults.html" name="oaccuracyresults" />
    <data format="qza" label="${tool.name} on ${on_string}: mazscores.qza" name="omazscores" />
    <data format="html" label="${tool.name} on ${on_string}: clustermap.html" name="oclustermap" />
    <data format="html" label="${tool.name} on ${on_string}: volatilityplots.html" 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.
n_jobs : Int, optional
    Number of jobs to run in parallel.
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>