|
20
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_longitudinal_feature-volatility" name="qiime longitudinal feature-volatility"
|
|
|
3 version="2020.8">
|
|
|
4 <description>Feature volatility analysis</description>
|
|
|
5 <requirements>
|
|
|
6 <requirement type="package" version="2020.8">qiime2</requirement>
|
|
|
7 </requirements>
|
|
|
8 <command><![CDATA[
|
|
|
9 qiime longitudinal feature-volatility
|
|
|
10
|
|
|
11 --i-table=$itable
|
|
|
12 # if $input_files_mmetadatafile:
|
|
|
13 # def list_dict_to_string(list_dict):
|
|
|
14 # set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
|
|
|
15 # for d in list_dict[1:]:
|
|
|
16 # set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
|
|
|
17 # end for
|
|
|
18 # return $file_list
|
|
|
19 # end def
|
|
|
20 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile)
|
|
|
21 # end if
|
|
|
22
|
|
|
23 #if '__ob__' in str($pstatecolumn):
|
|
|
24 #set $pstatecolumn_temp = $pstatecolumn.replace('__ob__', '[')
|
|
|
25 #set $pstatecolumn = $pstatecolumn_temp
|
|
|
26 #end if
|
|
|
27 #if '__cb__' in str($pstatecolumn):
|
|
|
28 #set $pstatecolumn_temp = $pstatecolumn.replace('__cb__', ']')
|
|
|
29 #set $pstatecolumn = $pstatecolumn_temp
|
|
|
30 #end if
|
|
|
31 #if 'X' in str($pstatecolumn):
|
|
|
32 #set $pstatecolumn_temp = $pstatecolumn.replace('X', '\\')
|
|
|
33 #set $pstatecolumn = $pstatecolumn_temp
|
|
|
34 #end if
|
|
|
35 #if '__sq__' in str($pstatecolumn):
|
|
|
36 #set $pstatecolumn_temp = $pstatecolumn.replace('__sq__', "'")
|
|
|
37 #set $pstatecolumn = $pstatecolumn_temp
|
|
|
38 #end if
|
|
|
39 #if '__db__' in str($pstatecolumn):
|
|
|
40 #set $pstatecolumn_temp = $pstatecolumn.replace('__db__', '"')
|
|
|
41 #set $pstatecolumn = $pstatecolumn_temp
|
|
|
42 #end if
|
|
|
43
|
|
|
44 --p-state-column=$pstatecolumn
|
|
|
45
|
|
|
46
|
|
|
47 #if '__ob__' in str($pindividualidcolumn):
|
|
|
48 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__ob__', '[')
|
|
|
49 #set $pindividualidcolumn = $pindividualidcolumn_temp
|
|
|
50 #end if
|
|
|
51 #if '__cb__' in str($pindividualidcolumn):
|
|
|
52 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__cb__', ']')
|
|
|
53 #set $pindividualidcolumn = $pindividualidcolumn_temp
|
|
|
54 #end if
|
|
|
55 #if 'X' in str($pindividualidcolumn):
|
|
|
56 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('X', '\\')
|
|
|
57 #set $pindividualidcolumn = $pindividualidcolumn_temp
|
|
|
58 #end if
|
|
|
59 #if '__sq__' in str($pindividualidcolumn):
|
|
|
60 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__sq__', "'")
|
|
|
61 #set $pindividualidcolumn = $pindividualidcolumn_temp
|
|
|
62 #end if
|
|
|
63 #if '__db__' in str($pindividualidcolumn):
|
|
|
64 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__db__', '"')
|
|
|
65 #set $pindividualidcolumn = $pindividualidcolumn_temp
|
|
|
66 #end if
|
|
|
67
|
|
|
68 #if str($pindividualidcolumn):
|
|
|
69 --p-individual-id-column=$pindividualidcolumn
|
|
|
70 #end if
|
|
|
71
|
|
|
72 --p-cv=$pcv
|
|
|
73
|
|
|
74 #if str($prandomstate):
|
|
|
75 --p-random-state=$prandomstate
|
|
|
76 #end if
|
|
|
77 --p-n-jobs=$pnjobs
|
|
|
78
|
|
|
79 --p-n-estimators=$pnestimators
|
|
|
80
|
|
|
81 #if str($pestimator) != 'None':
|
|
|
82 --p-estimator=$pestimator
|
|
|
83 #end if
|
|
|
84
|
|
|
85 #if $pparametertuning:
|
|
|
86 --p-parameter-tuning
|
|
|
87 #end if
|
|
|
88
|
|
|
89 #if str($pmissingsamples) != 'None':
|
|
|
90 --p-missing-samples=$pmissingsamples
|
|
|
91 #end if
|
|
|
92
|
|
|
93 #if str($pimportancethreshold) != 'None':
|
|
|
94 --p-importance-threshold=$pimportancethreshold
|
|
|
95 #end if
|
|
|
96
|
|
|
97 #if str($pfeaturecount) != 'None':
|
|
|
98 --p-feature-count=$pfeaturecount
|
|
|
99 #end if
|
|
|
100
|
|
|
101 --o-filtered-table=ofilteredtable
|
|
|
102
|
|
|
103 --o-feature-importance=ofeatureimportance
|
|
|
104
|
|
|
105 --o-volatility-plot=ovolatilityplot
|
|
|
106
|
|
|
107 --o-accuracy-results=oaccuracyresults
|
|
|
108
|
|
|
109 --o-sample-estimator=osampleestimator
|
|
|
110
|
|
|
111 #if str($examples) != 'None':
|
|
|
112 --examples=$examples
|
|
|
113 #end if
|
|
|
114
|
|
|
115 ;
|
|
|
116 cp osampleestimator.qza $osampleestimator
|
|
|
117
|
|
|
118 ]]></command>
|
|
|
119 <inputs>
|
|
|
120 <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" />
|
|
|
121 <repeat name="input_files_mmetadatafile" optional="False" title="--m-metadata-file">
|
|
|
122 <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" />
|
|
|
123 </repeat>
|
|
|
124 <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" />
|
|
|
125 <param label="--p-individual-id-column: TEXT Metadata column containing IDs for individual subjects. [optional]" name="pindividualidcolumn" optional="False" type="text" />
|
|
|
126 <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" />
|
|
|
127 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="False" type="text" />
|
|
|
128 <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" />
|
|
|
129 <param label="--p-estimator: " name="pestimator" optional="True" type="select">
|
|
|
130 <option selected="True" value="None">Selection is Optional</option>
|
|
|
131 <option value="RandomForestRegressor">RandomForestRegressor</option>
|
|
|
132 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
|
|
|
133 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
|
|
|
134 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
|
|
|
135 <option value="ElasticNet">ElasticNet</option>
|
|
|
136 <option value="Ridge">Ridge</option>
|
|
|
137 <option value="Lasso">Lasso</option>
|
|
|
138 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
|
|
|
139 <option value="LinearSVR">LinearSVR</option>
|
|
|
140 <option value="SVR">SVR</option>
|
|
|
141 </param>
|
|
|
142 <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" />
|
|
|
143 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
|
|
|
144 <option selected="True" value="None">Selection is Optional</option>
|
|
|
145 <option value="error">error</option>
|
|
|
146 <option value="ignore">ignore</option>
|
|
|
147 </param>
|
|
|
148 <param label="--p-importance-threshold: " name="pimportancethreshold" optional="True" type="select">
|
|
|
149 <option selected="True" value="None">Selection is Optional</option>
|
|
|
150 <option value="Float % Range(0">Float % Range(0</option>
|
|
|
151 <option value="None">None</option>
|
|
|
152 <option value="inclusive_start=False">inclusive_start=False</option>
|
|
|
153 </param>
|
|
|
154 <param label="--p-feature-count: " name="pfeaturecount" optional="True" type="select">
|
|
|
155 <option selected="True" value="None">Selection is Optional</option>
|
|
|
156 <option value="Int % Range(1">Int % Range(1</option>
|
|
|
157 <option value="None">None</option>
|
|
|
158 </param>
|
|
|
159 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
|
|
|
160
|
|
|
161 </inputs>
|
|
|
162
|
|
|
163 <outputs>
|
|
|
164 <data format="qza" label="${tool.name} on ${on_string}: filteredtable.qza" name="ofilteredtable" />
|
|
|
165 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance" />
|
|
|
166 <data format="html" label="${tool.name} on ${on_string}: volatilityplot.html" name="ovolatilityplot" />
|
|
|
167 <data format="html" label="${tool.name} on ${on_string}: accuracyresults.html" name="oaccuracyresults" />
|
|
|
168 <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator" />
|
|
|
169
|
|
|
170 </outputs>
|
|
|
171
|
|
|
172 <help><![CDATA[
|
|
|
173 Feature volatility analysis
|
|
|
174 ###############################################################
|
|
|
175
|
|
|
176 Identify features that are predictive of a numeric metadata column,
|
|
|
177 state_column (e.g., time), and plot their relative frequencies across
|
|
|
178 states using interactive feature volatility plots. A supervised learning
|
|
|
179 regressor is used to identify important features and assess their ability
|
|
|
180 to predict sample states. state_column will typically be a measure of time,
|
|
|
181 but any numeric metadata column can be used.
|
|
|
182
|
|
|
183 Parameters
|
|
|
184 ----------
|
|
|
185 table : FeatureTable[Frequency]
|
|
|
186 Feature table containing all features that should be used for target
|
|
|
187 prediction.
|
|
|
188 metadata : Metadata
|
|
|
189 Sample metadata file containing individual_id_column.
|
|
|
190 state_column : Str
|
|
|
191 Metadata containing collection time (state) values for each sample.
|
|
|
192 Must contain exclusively numeric values.
|
|
|
193 individual_id_column : Str, optional
|
|
|
194 Metadata column containing IDs for individual subjects.
|
|
|
195 cv : Int % Range(1, None), optional
|
|
|
196 Number of k-fold cross-validations to perform.
|
|
|
197 random_state : Int, optional
|
|
|
198 Seed used by random number generator.
|
|
|
199 n_jobs : Int, optional
|
|
|
200 Number of jobs to run in parallel.
|
|
|
201 n_estimators : Int % Range(1, None), optional
|
|
|
202 Number of trees to grow for estimation. More trees will improve
|
|
|
203 predictive accuracy up to a threshold level, but will also increase
|
|
|
204 time and memory requirements. This parameter only affects ensemble
|
|
|
205 estimators, such as Random Forest, AdaBoost, ExtraTrees, and
|
|
|
206 GradientBoosting.
|
|
|
207 estimator : Str % Choices('RandomForestRegressor', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'AdaBoostRegressor', 'ElasticNet', 'Ridge', 'Lasso', 'KNeighborsRegressor', 'LinearSVR', 'SVR'), optional
|
|
|
208 Estimator method to use for sample prediction.
|
|
|
209 parameter_tuning : Bool, optional
|
|
|
210 Automatically tune hyperparameters using random grid search.
|
|
|
211 missing_samples : Str % Choices('error', 'ignore'), optional
|
|
|
212 How to handle missing samples in metadata. "error" will fail if missing
|
|
|
213 samples are detected. "ignore" will cause the feature table and
|
|
|
214 metadata to be filtered, so that only samples found in both files are
|
|
|
215 retained.
|
|
|
216 importance_threshold : Float % Range(0, None, inclusive_start=False) | Str % Choices('q1', 'q2', 'q3'), optional
|
|
|
217 Filter feature table to exclude any features with an importance score
|
|
|
218 less than this threshold. Set to "q1", "q2", or "q3" to select the
|
|
|
219 first, second, or third quartile of values. Set to "None" to disable
|
|
|
220 this filter.
|
|
|
221 feature_count : Int % Range(1, None) | Str % Choices('all'), optional
|
|
|
222 Filter feature table to include top N most important features. Set to
|
|
|
223 "all" to include all features.
|
|
|
224
|
|
|
225 Returns
|
|
|
226 -------
|
|
|
227 filtered_table : FeatureTable[RelativeFrequency]
|
|
|
228 Feature table containing only important features.
|
|
|
229 feature_importance : FeatureData[Importance]
|
|
|
230 Importance of each input feature to model accuracy.
|
|
|
231 volatility_plot : Visualization
|
|
|
232 Interactive volatility plot visualization.
|
|
|
233 accuracy_results : Visualization
|
|
|
234 Accuracy results visualization.
|
|
|
235 sample_estimator : SampleEstimator[Regressor]
|
|
|
236 Trained sample regressor.
|
|
|
237 ]]></help>
|
|
|
238 <macros>
|
|
|
239 <import>qiime_citation.xml</import>
|
|
|
240 </macros>
|
|
|
241 <expand macro="qiime_citation"/>
|
|
|
242 </tool> |
