|
2
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_longitudinal_feature-volatility" name="qiime longitudinal feature-volatility" version="2019.4">
|
|
|
3 <description> - Feature volatility analysis</description>
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="2019.4">qiime2</requirement>
|
|
|
6 </requirements>
|
|
|
7 <command><![CDATA[
|
|
|
8 qiime longitudinal feature-volatility
|
|
|
9
|
|
|
10 --i-table=$itable
|
|
4
|
11
|
|
|
12
|
|
2
|
13 --p-state-column="$pstatecolumn"
|
|
|
14
|
|
|
15 #if str($pindividualidcolumn):
|
|
|
16 --p-individual-id-column="$pindividualidcolumn"
|
|
|
17 #end if
|
|
|
18
|
|
4
|
19 #if str($pcv):
|
|
2
|
20 --p-cv=$pcv
|
|
|
21 #end if
|
|
|
22
|
|
|
23 #if str($prandomstate):
|
|
|
24 --p-random-state="$prandomstate"
|
|
|
25 #end if
|
|
|
26
|
|
|
27 #set $pnjobs = '${GALAXY_SLOTS:-4}'
|
|
|
28
|
|
|
29 #if str($pnjobs):
|
|
|
30 --p-n-jobs="$pnjobs"
|
|
|
31 #end if
|
|
|
32
|
|
|
33
|
|
4
|
34 #if str($pnestimators):
|
|
2
|
35 --p-n-estimators=$pnestimators
|
|
|
36 #end if
|
|
|
37
|
|
|
38 #if str($pestimator) != 'None':
|
|
|
39 --p-estimator=$pestimator
|
|
|
40 #end if
|
|
|
41
|
|
|
42 #if $pparametertuning:
|
|
|
43 --p-parameter-tuning
|
|
|
44 #end if
|
|
|
45
|
|
|
46 #if str($pmissingsamples) != 'None':
|
|
|
47 --p-missing-samples=$pmissingsamples
|
|
|
48 #end if
|
|
|
49
|
|
|
50
|
|
|
51 #if $input_files_mmetadatafile:
|
|
|
52 #def list_dict_to_string(list_dict):
|
|
|
53 #set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
|
|
|
54 #for d in list_dict[1:]:
|
|
|
55 #set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
|
|
|
56 #end for
|
|
|
57 #return $file_list
|
|
|
58 #end def
|
|
|
59 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile)
|
|
|
60 #end if
|
|
|
61
|
|
|
62
|
|
|
63 --o-filtered-table=ofilteredtable
|
|
|
64 --o-feature-importance=ofeatureimportance
|
|
|
65 --o-volatility-plot=ovolatilityplot
|
|
|
66 --o-accuracy-results=oaccuracyresults
|
|
|
67 --o-sample-estimator=osampleestimator
|
|
|
68 ;
|
|
|
69 cp ofilteredtable.qza $ofilteredtable;
|
|
|
70 cp ofeatureimportance.qza $ofeatureimportance;
|
|
|
71 qiime tools export --input-path ovolatilityplot.qzv --output-path out && mkdir -p '$ovolatilityplot.files_path'
|
|
|
72 && cp -r out/* '$ovolatilityplot.files_path'
|
|
|
73 && mv '$ovolatilityplot.files_path/index.html' '$ovolatilityplot';
|
|
|
74 qiime tools export --input-path oaccuracyresults.qzv --output-path out && mkdir -p '$oaccuracyresults.files_path'
|
|
|
75 && cp -r out/* '$oaccuracyresults.files_path'
|
|
|
76 && mv '$oaccuracyresults.files_path/index.html' '$oaccuracyresults';
|
|
|
77 cp osampleestimator.qza $osampleestimator
|
|
|
78 ]]></command>
|
|
|
79 <inputs>
|
|
|
80 <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"/>
|
|
|
81 <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"/>
|
|
|
82 <param label="--p-individual-id-column: TEXT Metadata column containing IDs for individual subjects. [optional]" name="pindividualidcolumn" optional="True" type="text"/>
|
|
|
83 <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"/>
|
|
|
84 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="True" type="integer"/>
|
|
|
85 <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"/>
|
|
|
86 <param label="--p-estimator: " name="pestimator" optional="True" type="select">
|
|
|
87 <option selected="True" value="None">Selection is Optional</option>
|
|
|
88 <option value="RandomForestRegressor">RandomForestRegressor</option>
|
|
|
89 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
|
|
|
90 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
|
|
|
91 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
|
|
|
92 <option value="ElasticNet">ElasticNet</option>
|
|
|
93 <option value="Ridge">Ridge</option>
|
|
|
94 <option value="Lasso">Lasso</option>
|
|
|
95 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
|
|
|
96 <option value="LinearSVR">LinearSVR</option>
|
|
|
97 <option value="SVR">SVR</option>
|
|
|
98 </param>
|
|
|
99 <param label="--p-parameter-tuning: --p-no-parameter-tuning Automatically tune hyperparameters using random grid search. [default: False]" name="pparametertuning" selected="False" type="boolean"/>
|
|
|
100 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
|
|
|
101 <option selected="True" value="None">Selection is Optional</option>
|
|
|
102 <option value="error">error</option>
|
|
|
103 <option value="ignore">ignore</option>
|
|
|
104 </param>
|
|
|
105
|
|
4
|
106 <repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file [required]">
|
|
2
|
107 <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" />
|
|
|
108 </repeat>
|
|
|
109
|
|
|
110 </inputs>
|
|
|
111 <outputs>
|
|
|
112 <data format="qza" label="${tool.name} on ${on_string}: filteredtable.qza" name="ofilteredtable"/>
|
|
|
113 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance"/>
|
|
|
114 <data format="html" label="${tool.name} on ${on_string}: volatilityplot.qzv" name="ovolatilityplot"/>
|
|
|
115 <data format="html" label="${tool.name} on ${on_string}: accuracyresults.qzv" name="oaccuracyresults"/>
|
|
|
116 <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator"/>
|
|
|
117 </outputs>
|
|
|
118 <help><![CDATA[
|
|
|
119 Feature volatility analysis
|
|
|
120 ###########################
|
|
|
121
|
|
|
122 Identify features that are predictive of a numeric metadata column,
|
|
|
123 state_column (e.g., time), and plot their relative frequencies across
|
|
|
124 states using interactive feature volatility plots. A supervised learning
|
|
|
125 regressor is used to identify important features and assess their ability
|
|
|
126 to predict sample states. state_column will typically be a measure of time,
|
|
|
127 but any numeric metadata column can be used.
|
|
|
128
|
|
|
129 Parameters
|
|
|
130 ----------
|
|
|
131 table : FeatureTable[Frequency]
|
|
|
132 Feature table containing all features that should be used for target
|
|
|
133 prediction.
|
|
|
134 metadata : Metadata
|
|
|
135 Sample metadata file containing individual_id_column.
|
|
|
136 state_column : Str
|
|
|
137 Metadata containing collection time (state) values for each sample.
|
|
|
138 Must contain exclusively numeric values.
|
|
|
139 individual_id_column : Str, optional
|
|
|
140 Metadata column containing IDs for individual subjects.
|
|
|
141 cv : Int % Range(1, None), optional
|
|
|
142 Number of k-fold cross-validations to perform.
|
|
|
143 random_state : Int, optional
|
|
|
144 Seed used by random number generator.
|
|
|
145 n_estimators : Int % Range(1, None), optional
|
|
|
146 Number of trees to grow for estimation. More trees will improve
|
|
|
147 predictive accuracy up to a threshold level, but will also increase
|
|
|
148 time and memory requirements. This parameter only affects ensemble
|
|
|
149 estimators, such as Random Forest, AdaBoost, ExtraTrees, and
|
|
|
150 GradientBoosting.
|
|
|
151 estimator : Str % Choices('RandomForestRegressor', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'AdaBoostRegressor', 'ElasticNet', 'Ridge', 'Lasso', 'KNeighborsRegressor', 'LinearSVR', 'SVR'), optional
|
|
|
152 Estimator method to use for sample prediction.
|
|
|
153 parameter_tuning : Bool, optional
|
|
|
154 Automatically tune hyperparameters using random grid search.
|
|
|
155 missing_samples : Str % Choices('error', 'ignore'), optional
|
|
|
156 How to handle missing samples in metadata. "error" will fail if missing
|
|
|
157 samples are detected. "ignore" will cause the feature table and
|
|
|
158 metadata to be filtered, so that only samples found in both files are
|
|
|
159 retained.
|
|
|
160
|
|
|
161 Returns
|
|
|
162 -------
|
|
|
163 filtered_table : FeatureTable[RelativeFrequency]
|
|
|
164 Feature table containing only important features.
|
|
|
165 feature_importance : FeatureData[Importance]
|
|
|
166 Importance of each input feature to model accuracy.
|
|
|
167 volatility_plot : Visualization
|
|
|
168 Interactive volatility plot visualization.
|
|
|
169 accuracy_results : Visualization
|
|
|
170 Accuracy results visualization.
|
|
|
171 sample_estimator : SampleEstimator[Regressor]
|
|
|
172 Trained sample regressor.
|
|
|
173 ]]></help>
|
|
|
174 <macros>
|
|
|
175 <import>qiime_citation.xml</import>
|
|
|
176 </macros>
|
|
|
177 <expand macro="qiime_citation"/>
|
|
|
178 </tool>
|
