|
2
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_longitudinal_maturity-index" name="qiime longitudinal maturity-index" version="2019.4">
|
|
|
3 <description> - Microbial maturity index prediction.</description>
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="2019.4">qiime2</requirement>
|
|
|
6 </requirements>
|
|
|
7 <command><![CDATA[
|
|
|
8 qiime longitudinal maturity-index
|
|
|
9
|
|
|
10 --i-table=$itable
|
|
|
11 --p-state-column="$pstatecolumn"
|
|
|
12 --p-group-by="$pgroupby"
|
|
|
13 --p-control="$pcontrol"
|
|
|
14
|
|
|
15 #if str($pindividualidcolumn):
|
|
|
16 --p-individual-id-column="$pindividualidcolumn"
|
|
|
17 #end if
|
|
|
18
|
|
|
19 #if str($pestimator) != 'None':
|
|
|
20 --p-estimator=$pestimator
|
|
|
21 #end if
|
|
|
22
|
|
|
23 #if $pnestimators:
|
|
|
24 --p-n-estimators=$pnestimators
|
|
|
25 #end if
|
|
|
26
|
|
|
27 #if $ptestsize:
|
|
|
28 --p-test-size=$ptestsize
|
|
|
29 #end if
|
|
|
30
|
|
|
31 #if $pstep:
|
|
|
32 --p-step=$pstep
|
|
|
33 #end if
|
|
|
34
|
|
|
35 #if $pcv:
|
|
|
36 --p-cv=$pcv
|
|
|
37 #end if
|
|
|
38
|
|
|
39 #if str($prandomstate):
|
|
|
40 --p-random-state="$prandomstate"
|
|
|
41 #end if
|
|
|
42
|
|
|
43 #set $pnjobs = '${GALAXY_SLOTS:-4}'
|
|
|
44 #if str($pnjobs):
|
|
|
45 --p-n-jobs="$pnjobs"
|
|
|
46 #end if
|
|
|
47
|
|
|
48
|
|
|
49 #if $pparametertuning:
|
|
|
50 --p-parameter-tuning
|
|
|
51 #end if
|
|
|
52
|
|
|
53 #if $poptimizefeatureselection:
|
|
|
54 --p-optimize-feature-selection
|
|
|
55 #end if
|
|
|
56
|
|
|
57 #if $pstratify:
|
|
|
58 --p-stratify
|
|
|
59 #end if
|
|
|
60
|
|
|
61 #if str($pmissingsamples) != 'None':
|
|
|
62 --p-missing-samples=$pmissingsamples
|
|
|
63 #end if
|
|
|
64
|
|
|
65 #if $pfeaturecount:
|
|
|
66 --p-feature-count=$pfeaturecount
|
|
|
67 #end if
|
|
|
68
|
|
|
69
|
|
|
70 #if $input_files_mmetadatafile:
|
|
|
71 #def list_dict_to_string(list_dict):
|
|
|
72 #set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
|
|
|
73 #for d in list_dict[1:]:
|
|
|
74 #set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
|
|
|
75 #end for
|
|
|
76 #return $file_list
|
|
|
77 #end def
|
|
|
78 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile)
|
|
|
79 #end if
|
|
|
80
|
|
|
81
|
|
|
82 --o-sample-estimator=osampleestimator
|
|
|
83 --o-feature-importance=ofeatureimportance
|
|
|
84 --o-predictions=opredictions
|
|
|
85 --o-model-summary=omodelsummary
|
|
|
86 --o-accuracy-results=oaccuracyresults
|
|
|
87 --o-maz-scores=omazscores
|
|
|
88 --o-clustermap=oclustermap
|
|
|
89 --o-volatility-plots=ovolatilityplots
|
|
|
90 ;
|
|
|
91 cp osampleestimator.qza $osampleestimator;
|
|
|
92 cp ofeatureimportance.qza $ofeatureimportance;
|
|
|
93 cp opredictions.qza $opredictions;
|
|
|
94 qiime tools export --input-path omodelsummary.qzv --output-path out && mkdir -p '$omodelsummary.files_path'
|
|
|
95 && cp -r out/* '$omodelsummary.files_path'
|
|
|
96 && mv '$omodelsummary.files_path/index.html' '$omodelsummary';
|
|
|
97 qiime tools export --input-path oaccuracyresults.qzv --output-path out && mkdir -p '$oaccuracyresults.files_path'
|
|
|
98 && cp -r out/* '$oaccuracyresults.files_path'
|
|
|
99 && mv '$oaccuracyresults.files_path/index.html' '$oaccuracyresults';
|
|
|
100 cp omazscores.qza $omazscores;
|
|
|
101 qiime tools export --input-path oclustermap.qzv --output-path out && mkdir -p '$oclustermap.files_path'
|
|
|
102 && cp -r out/* '$oclustermap.files_path'
|
|
|
103 && mv '$oclustermap.files_path/index.html' '$oclustermap';
|
|
|
104 qiime tools export --input-path ovolatilityplots.qzv --output-path out && mkdir -p '$ovolatilityplots.files_path'
|
|
|
105 && cp -r out/* '$ovolatilityplots.files_path'
|
|
|
106 && mv '$ovolatilityplots.files_path/index.html' '$ovolatilityplots'
|
|
|
107 ]]></command>
|
|
|
108 <inputs>
|
|
|
109 <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"/>
|
|
|
110 <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"/>
|
|
|
111 <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"/>
|
|
|
112 <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"/>
|
|
|
113 <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"/>
|
|
|
114 <param label="--p-estimator: " name="pestimator" optional="True" type="select">
|
|
|
115 <option selected="True" value="None">Selection is Optional</option>
|
|
|
116 <option value="RandomForestRegressor">RandomForestRegressor</option>
|
|
|
117 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
|
|
|
118 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
|
|
|
119 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
|
|
|
120 <option value="ElasticNet">ElasticNet</option>
|
|
|
121 <option value="Ridge">Ridge</option>
|
|
|
122 <option value="Lasso">Lasso</option>
|
|
|
123 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
|
|
|
124 <option value="LinearSVR">LinearSVR</option>
|
|
|
125 <option value="SVR">SVR</option>
|
|
|
126 </param>
|
|
|
127 <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"/>
|
|
|
128 <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"/>
|
|
|
129 <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"/>
|
|
|
130 <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"/>
|
|
|
131 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="True" type="integer"/>
|
|
|
132 <param label="--p-parameter-tuning: --p-no-parameter-tuning Automatically tune hyperparameters using random grid search. [default: False]" name="pparametertuning" selected="False" type="boolean"/>
|
|
|
133 <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"/>
|
|
|
134 <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"/>
|
|
|
135 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
|
|
|
136 <option selected="True" value="None">Selection is Optional</option>
|
|
|
137 <option value="error">error</option>
|
|
|
138 <option value="ignore">ignore</option>
|
|
|
139 </param>
|
|
|
140 <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"/>
|
|
|
141
|
|
|
142 <repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file">
|
|
|
143 <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" />
|
|
|
144 </repeat> </inputs>
|
|
|
145
|
|
|
146 <outputs>
|
|
|
147 <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator"/>
|
|
|
148 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance"/>
|
|
|
149 <data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions"/>
|
|
|
150 <data format="html" label="${tool.name} on ${on_string}: modelsummary.qzv" name="omodelsummary"/>
|
|
|
151 <data format="html" label="${tool.name} on ${on_string}: accuracyresults.qzv" name="oaccuracyresults"/>
|
|
|
152 <data format="qza" label="${tool.name} on ${on_string}: mazscores.qza" name="omazscores"/>
|
|
|
153 <data format="html" label="${tool.name} on ${on_string}: clustermap.qzv" name="oclustermap"/>
|
|
|
154 <data format="html" label="${tool.name} on ${on_string}: volatilityplots.qzv" name="ovolatilityplots"/>
|
|
|
155 </outputs>
|
|
|
156 <help><![CDATA[
|
|
|
157 Microbial maturity index prediction.
|
|
|
158 ####################################
|
|
|
159
|
|
|
160 Calculates a "microbial maturity" index from a regression model trained on
|
|
|
161 feature data to predict a given continuous metadata column, e.g., to
|
|
|
162 predict age as a function of microbiota composition. The model is trained
|
|
|
163 on a subset of control group samples, then predicts the column value for
|
|
|
164 all samples. This visualization computes maturity index z-scores to compare
|
|
|
165 relative "maturity" between each group, as described in
|
|
|
166 doi:10.1038/nature13421. This method can be used to predict between-group
|
|
|
167 differences in relative trajectory across any type of continuous metadata
|
|
|
168 gradient, e.g., intestinal microbiome development by age, microbial
|
|
|
169 succession during wine fermentation, or microbial community differences
|
|
|
170 along environmental gradients, as a function of two or more different
|
|
|
171 "treatment" groups.
|
|
|
172
|
|
|
173 Parameters
|
|
|
174 ----------
|
|
|
175 table : FeatureTable[Frequency]
|
|
|
176 Feature table containing all features that should be used for target
|
|
|
177 prediction.
|
|
|
178 metadata : Metadata
|
|
|
179 \
|
|
|
180 state_column : Str
|
|
|
181 Numeric metadata column containing sampling time (state) data to use as
|
|
|
182 prediction target.
|
|
|
183 group_by : Str
|
|
|
184 Categorical metadata column to use for plotting and significance
|
|
|
185 testing between main treatment groups.
|
|
|
186 control : Str
|
|
|
187 Value of group_by to use as control group. The regression model will be
|
|
|
188 trained using only control group data, and the maturity scores of other
|
|
|
189 groups consequently will be assessed relative to this group.
|
|
|
190 individual_id_column : Str, optional
|
|
|
191 Optional metadata column containing IDs for individual subjects. Adds
|
|
|
192 individual subject (spaghetti) vectors to volatility charts if a column
|
|
|
193 name is provided.
|
|
|
194 estimator : Str % Choices('RandomForestRegressor', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'AdaBoostRegressor', 'ElasticNet', 'Ridge', 'Lasso', 'KNeighborsRegressor', 'LinearSVR', 'SVR'), optional
|
|
|
195 Regression model to use for prediction.
|
|
|
196 n_estimators : Int % Range(1, None), optional
|
|
|
197 Number of trees to grow for estimation. More trees will improve
|
|
|
198 predictive accuracy up to a threshold level, but will also increase
|
|
|
199 time and memory requirements. This parameter only affects ensemble
|
|
|
200 estimators, such as Random Forest, AdaBoost, ExtraTrees, and
|
|
|
201 GradientBoosting.
|
|
|
202 test_size : Float % Range(0.0, 1.0, inclusive_start=False), optional
|
|
|
203 Fraction of input samples to exclude from training set and use for
|
|
|
204 classifier testing.
|
|
|
205 step : Float % Range(0.0, 1.0, inclusive_start=False), optional
|
|
|
206 If optimize_feature_selection is True, step is the percentage of
|
|
|
207 features to remove at each iteration.
|
|
|
208 cv : Int % Range(1, None), optional
|
|
|
209 Number of k-fold cross-validations to perform.
|
|
|
210 random_state : Int, optional
|
|
|
211 Seed used by random number generator.
|
|
|
212 parameter_tuning : Bool, optional
|
|
|
213 Automatically tune hyperparameters using random grid search.
|
|
|
214 optimize_feature_selection : Bool, optional
|
|
|
215 Automatically optimize input feature selection using recursive feature
|
|
|
216 elimination.
|
|
|
217 stratify : Bool, optional
|
|
|
218 Evenly stratify training and test data among metadata categories. If
|
|
|
219 True, all values in column must match at least two samples.
|
|
|
220 missing_samples : Str % Choices('error', 'ignore'), optional
|
|
|
221 How to handle missing samples in metadata. "error" will fail if missing
|
|
|
222 samples are detected. "ignore" will cause the feature table and
|
|
|
223 metadata to be filtered, so that only samples found in both files are
|
|
|
224 retained.
|
|
|
225 feature_count : Int % Range(0, None), optional
|
|
|
226 Filter feature table to include top N most important features. Set to
|
|
|
227 zero to include all features.
|
|
|
228
|
|
|
229 Returns
|
|
|
230 -------
|
|
|
231 sample_estimator : SampleEstimator[Regressor]
|
|
|
232 Trained sample estimator.
|
|
|
233 feature_importance : FeatureData[Importance]
|
|
|
234 Importance of each input feature to model accuracy.
|
|
|
235 predictions : SampleData[RegressorPredictions]
|
|
|
236 Predicted target values for each input sample.
|
|
|
237 model_summary : Visualization
|
|
|
238 Summarized parameter and (if enabled) feature selection information for
|
|
|
239 the trained estimator.
|
|
|
240 accuracy_results : Visualization
|
|
|
241 Accuracy results visualization.
|
|
|
242 maz_scores : SampleData[RegressorPredictions]
|
|
|
243 Microbiota-for-age z-score predictions.
|
|
|
244 clustermap : Visualization
|
|
|
245 Heatmap of important feature abundance at each time point in each
|
|
|
246 group.
|
|
|
247 volatility_plots : Visualization
|
|
|
248 Interactive volatility plots of MAZ and maturity scores, target
|
|
|
249 (column) predictions, and the sample metadata.
|
|
|
250 ]]></help>
|
|
|
251 <macros>
|
|
|
252 <import>qiime_citation.xml</import>
|
|
|
253 </macros>
|
|
|
254 <expand macro="qiime_citation"/>
|
|
|
255 </tool>
|
