|
20
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_longitudinal_maturity-index" name="qiime longitudinal maturity-index"
|
|
|
3 version="2020.8">
|
|
|
4 <description>Microbial maturity index prediction.</description>
|
|
|
5 <requirements>
|
|
|
6 <requirement type="package" version="2020.8">qiime2</requirement>
|
|
|
7 </requirements>
|
|
|
8 <command><![CDATA[
|
|
|
9 qiime longitudinal maturity-index
|
|
|
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 --p-group-by=$pgroupby
|
|
|
48
|
|
|
49 --p-control=$pcontrol
|
|
|
50
|
|
|
51 #if '__ob__' in str($pindividualidcolumn):
|
|
|
52 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__ob__', '[')
|
|
|
53 #set $pindividualidcolumn = $pindividualidcolumn_temp
|
|
|
54 #end if
|
|
|
55 #if '__cb__' in str($pindividualidcolumn):
|
|
|
56 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__cb__', ']')
|
|
|
57 #set $pindividualidcolumn = $pindividualidcolumn_temp
|
|
|
58 #end if
|
|
|
59 #if 'X' in str($pindividualidcolumn):
|
|
|
60 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('X', '\\')
|
|
|
61 #set $pindividualidcolumn = $pindividualidcolumn_temp
|
|
|
62 #end if
|
|
|
63 #if '__sq__' in str($pindividualidcolumn):
|
|
|
64 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__sq__', "'")
|
|
|
65 #set $pindividualidcolumn = $pindividualidcolumn_temp
|
|
|
66 #end if
|
|
|
67 #if '__db__' in str($pindividualidcolumn):
|
|
|
68 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__db__', '"')
|
|
|
69 #set $pindividualidcolumn = $pindividualidcolumn_temp
|
|
|
70 #end if
|
|
|
71
|
|
|
72 #if str($pindividualidcolumn):
|
|
|
73 --p-individual-id-column=$pindividualidcolumn
|
|
|
74 #end if
|
|
|
75
|
|
|
76 #if str($pestimator) != 'None':
|
|
|
77 --p-estimator=$pestimator
|
|
|
78 #end if
|
|
|
79
|
|
|
80 --p-n-estimators=$pnestimators
|
|
|
81
|
|
|
82 --p-test-size=$ptestsize
|
|
|
83
|
|
|
84 --p-step=$pstep
|
|
|
85
|
|
|
86 --p-cv=$pcv
|
|
|
87
|
|
|
88 #if str($prandomstate):
|
|
|
89 --p-random-state=$prandomstate
|
|
|
90 #end if
|
|
|
91 --p-n-jobs=$pnjobs
|
|
|
92
|
|
|
93 #if $pparametertuning:
|
|
|
94 --p-parameter-tuning
|
|
|
95 #end if
|
|
|
96
|
|
|
97 #if $poptimizefeatureselection:
|
|
|
98 --p-optimize-feature-selection
|
|
|
99 #end if
|
|
|
100
|
|
|
101 #if $pstratify:
|
|
|
102 --p-stratify
|
|
|
103 #end if
|
|
|
104
|
|
|
105 #if str($pmissingsamples) != 'None':
|
|
|
106 --p-missing-samples=$pmissingsamples
|
|
|
107 #end if
|
|
|
108
|
|
|
109 --p-feature-count=$pfeaturecount
|
|
|
110
|
|
|
111 --o-sample-estimator=osampleestimator
|
|
|
112
|
|
|
113 --o-feature-importance=ofeatureimportance
|
|
|
114
|
|
|
115 --o-predictions=opredictions
|
|
|
116
|
|
|
117 --o-model-summary=omodelsummary
|
|
|
118
|
|
|
119 --o-accuracy-results=oaccuracyresults
|
|
|
120
|
|
|
121 --o-maz-scores=omazscores
|
|
|
122
|
|
|
123 --o-clustermap=oclustermap
|
|
|
124
|
|
|
125 --o-volatility-plots=ovolatilityplots
|
|
|
126
|
|
|
127 #if str($examples) != 'None':
|
|
|
128 --examples=$examples
|
|
|
129 #end if
|
|
|
130
|
|
|
131 ;
|
|
|
132 cp omazscores.qza $omazscores
|
|
|
133
|
|
|
134 ;
|
|
|
135 qiime tools export oclustermap.qzv --output-path out
|
|
|
136 && mkdir -p '$oclustermap.files_path'
|
|
|
137 && cp -r out/* '$oclustermap.files_path'
|
|
|
138 && mv '$oclustermap.files_path/index.html' '$oclustermap'
|
|
|
139
|
|
|
140 ;
|
|
|
141 qiime tools export ovolatilityplots.qzv --output-path out
|
|
|
142 && mkdir -p '$ovolatilityplots.files_path'
|
|
|
143 && cp -r out/* '$ovolatilityplots.files_path'
|
|
|
144 && mv '$ovolatilityplots.files_path/index.html' '$ovolatilityplots'
|
|
|
145
|
|
|
146 ]]></command>
|
|
|
147 <inputs>
|
|
|
148 <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" />
|
|
|
149 <repeat name="input_files_mmetadatafile" optional="False" title="--m-metadata-file">
|
|
|
150 <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" />
|
|
|
151 </repeat>
|
|
|
152 <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" />
|
|
|
153 <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" />
|
|
|
154 <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" />
|
|
|
155 <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" />
|
|
|
156 <param label="--p-estimator: " name="pestimator" optional="True" type="select">
|
|
|
157 <option selected="True" value="None">Selection is Optional</option>
|
|
|
158 <option value="RandomForestRegressor">RandomForestRegressor</option>
|
|
|
159 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
|
|
|
160 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
|
|
|
161 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
|
|
|
162 <option value="ElasticNet">ElasticNet</option>
|
|
|
163 <option value="Ridge">Ridge</option>
|
|
|
164 <option value="Lasso">Lasso</option>
|
|
|
165 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
|
|
|
166 <option value="LinearSVR">LinearSVR</option>
|
|
|
167 <option value="SVR">SVR</option>
|
|
|
168 </param>
|
|
|
169 <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" />
|
|
|
170 <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" />
|
|
|
171 <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" />
|
|
|
172 <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" />
|
|
|
173 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="False" type="text" />
|
|
|
174 <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" />
|
|
|
175 <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" />
|
|
|
176 <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" />
|
|
|
177 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
|
|
|
178 <option selected="True" value="None">Selection is Optional</option>
|
|
|
179 <option value="error">error</option>
|
|
|
180 <option value="ignore">ignore</option>
|
|
|
181 </param>
|
|
|
182 <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" />
|
|
|
183 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
|
|
|
184
|
|
|
185 </inputs>
|
|
|
186
|
|
|
187 <outputs>
|
|
|
188 <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator" />
|
|
|
189 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance" />
|
|
|
190 <data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions" />
|
|
|
191 <data format="html" label="${tool.name} on ${on_string}: modelsummary.html" name="omodelsummary" />
|
|
|
192 <data format="html" label="${tool.name} on ${on_string}: accuracyresults.html" name="oaccuracyresults" />
|
|
|
193 <data format="qza" label="${tool.name} on ${on_string}: mazscores.qza" name="omazscores" />
|
|
|
194 <data format="html" label="${tool.name} on ${on_string}: clustermap.html" name="oclustermap" />
|
|
|
195 <data format="html" label="${tool.name} on ${on_string}: volatilityplots.html" name="ovolatilityplots" />
|
|
|
196
|
|
|
197 </outputs>
|
|
|
198
|
|
|
199 <help><![CDATA[
|
|
|
200 Microbial maturity index prediction.
|
|
|
201 ###############################################################
|
|
|
202
|
|
|
203 Calculates a "microbial maturity" index from a regression model trained on
|
|
|
204 feature data to predict a given continuous metadata column, e.g., to
|
|
|
205 predict age as a function of microbiota composition. The model is trained
|
|
|
206 on a subset of control group samples, then predicts the column value for
|
|
|
207 all samples. This visualization computes maturity index z-scores to compare
|
|
|
208 relative "maturity" between each group, as described in
|
|
|
209 doi:10.1038/nature13421. This method can be used to predict between-group
|
|
|
210 differences in relative trajectory across any type of continuous metadata
|
|
|
211 gradient, e.g., intestinal microbiome development by age, microbial
|
|
|
212 succession during wine fermentation, or microbial community differences
|
|
|
213 along environmental gradients, as a function of two or more different
|
|
|
214 "treatment" groups.
|
|
|
215
|
|
|
216 Parameters
|
|
|
217 ----------
|
|
|
218 table : FeatureTable[Frequency]
|
|
|
219 Feature table containing all features that should be used for target
|
|
|
220 prediction.
|
|
|
221 metadata : Metadata
|
|
|
222 state_column : Str
|
|
|
223 Numeric metadata column containing sampling time (state) data to use as
|
|
|
224 prediction target.
|
|
|
225 group_by : Str
|
|
|
226 Categorical metadata column to use for plotting and significance
|
|
|
227 testing between main treatment groups.
|
|
|
228 control : Str
|
|
|
229 Value of group_by to use as control group. The regression model will be
|
|
|
230 trained using only control group data, and the maturity scores of other
|
|
|
231 groups consequently will be assessed relative to this group.
|
|
|
232 individual_id_column : Str, optional
|
|
|
233 Optional metadata column containing IDs for individual subjects. Adds
|
|
|
234 individual subject (spaghetti) vectors to volatility charts if a column
|
|
|
235 name is provided.
|
|
|
236 estimator : Str % Choices('RandomForestRegressor', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'AdaBoostRegressor', 'ElasticNet', 'Ridge', 'Lasso', 'KNeighborsRegressor', 'LinearSVR', 'SVR'), optional
|
|
|
237 Regression model to use for prediction.
|
|
|
238 n_estimators : Int % Range(1, None), optional
|
|
|
239 Number of trees to grow for estimation. More trees will improve
|
|
|
240 predictive accuracy up to a threshold level, but will also increase
|
|
|
241 time and memory requirements. This parameter only affects ensemble
|
|
|
242 estimators, such as Random Forest, AdaBoost, ExtraTrees, and
|
|
|
243 GradientBoosting.
|
|
|
244 test_size : Float % Range(0.0, 1.0, inclusive_start=False), optional
|
|
|
245 Fraction of input samples to exclude from training set and use for
|
|
|
246 classifier testing.
|
|
|
247 step : Float % Range(0.0, 1.0, inclusive_start=False), optional
|
|
|
248 If optimize_feature_selection is True, step is the percentage of
|
|
|
249 features to remove at each iteration.
|
|
|
250 cv : Int % Range(1, None), optional
|
|
|
251 Number of k-fold cross-validations to perform.
|
|
|
252 random_state : Int, optional
|
|
|
253 Seed used by random number generator.
|
|
|
254 n_jobs : Int, optional
|
|
|
255 Number of jobs to run in parallel.
|
|
|
256 parameter_tuning : Bool, optional
|
|
|
257 Automatically tune hyperparameters using random grid search.
|
|
|
258 optimize_feature_selection : Bool, optional
|
|
|
259 Automatically optimize input feature selection using recursive feature
|
|
|
260 elimination.
|
|
|
261 stratify : Bool, optional
|
|
|
262 Evenly stratify training and test data among metadata categories. If
|
|
|
263 True, all values in column must match at least two samples.
|
|
|
264 missing_samples : Str % Choices('error', 'ignore'), optional
|
|
|
265 How to handle missing samples in metadata. "error" will fail if missing
|
|
|
266 samples are detected. "ignore" will cause the feature table and
|
|
|
267 metadata to be filtered, so that only samples found in both files are
|
|
|
268 retained.
|
|
|
269 feature_count : Int % Range(0, None), optional
|
|
|
270 Filter feature table to include top N most important features. Set to
|
|
|
271 zero to include all features.
|
|
|
272
|
|
|
273 Returns
|
|
|
274 -------
|
|
|
275 sample_estimator : SampleEstimator[Regressor]
|
|
|
276 Trained sample estimator.
|
|
|
277 feature_importance : FeatureData[Importance]
|
|
|
278 Importance of each input feature to model accuracy.
|
|
|
279 predictions : SampleData[RegressorPredictions]
|
|
|
280 Predicted target values for each input sample.
|
|
|
281 model_summary : Visualization
|
|
|
282 Summarized parameter and (if enabled) feature selection information for
|
|
|
283 the trained estimator.
|
|
|
284 accuracy_results : Visualization
|
|
|
285 Accuracy results visualization.
|
|
|
286 maz_scores : SampleData[RegressorPredictions]
|
|
|
287 Microbiota-for-age z-score predictions.
|
|
|
288 clustermap : Visualization
|
|
|
289 Heatmap of important feature abundance at each time point in each
|
|
|
290 group.
|
|
|
291 volatility_plots : Visualization
|
|
|
292 Interactive volatility plots of MAZ and maturity scores, target
|
|
|
293 (column) predictions, and the sample metadata.
|
|
|
294 ]]></help>
|
|
|
295 <macros>
|
|
|
296 <import>qiime_citation.xml</import>
|
|
|
297 </macros>
|
|
|
298 <expand macro="qiime_citation"/>
|
|
|
299 </tool> |
