|
0
|
1 <?xml version="1.0" ?>
|
|
14
|
2 <tool id="qiime_sample-classifier_classify-samples" name="qiime sample-classifier classify-samples"
|
|
|
3 version="2020.8">
|
|
|
4 <description>Train and test a cross-validated supervised learning classifier.</description>
|
|
|
5 <requirements>
|
|
|
6 <requirement type="package" version="2020.8">qiime2</requirement>
|
|
|
7 </requirements>
|
|
|
8 <command><![CDATA[
|
|
0
|
9 qiime sample-classifier classify-samples
|
|
|
10
|
|
|
11 --i-table=$itable
|
|
14
|
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($input_files_mmetadatafile)
|
|
|
21 # end if
|
|
0
|
22
|
|
14
|
23 #if '__ob__' in str($mmetadatacolumn):
|
|
|
24 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__ob__', '[')
|
|
|
25 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
|
26 #end if
|
|
|
27 #if '__cb__' in str($mmetadatacolumn):
|
|
|
28 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__cb__', ']')
|
|
|
29 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
|
30 #end if
|
|
|
31 #if 'X' in str($mmetadatacolumn):
|
|
|
32 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('X', '\\')
|
|
|
33 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
|
34 #end if
|
|
|
35 #if '__sq__' in str($mmetadatacolumn):
|
|
|
36 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__sq__', "'")
|
|
|
37 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
|
38 #end if
|
|
|
39 #if '__db__' in str($mmetadatacolumn):
|
|
|
40 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__db__', '"')
|
|
|
41 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
0
|
42 #end if
|
|
|
43
|
|
14
|
44 --m-metadata-column=$mmetadatacolumn
|
|
|
45
|
|
0
|
46
|
|
14
|
47 --p-test-size=$ptestsize
|
|
|
48
|
|
|
49 --p-step=$pstep
|
|
|
50
|
|
|
51 --p-cv=$pcv
|
|
0
|
52
|
|
|
53 #if str($prandomstate):
|
|
14
|
54 --p-random-state=$prandomstate
|
|
0
|
55 #end if
|
|
14
|
56 --p-n-jobs=$pnjobs
|
|
0
|
57
|
|
14
|
58 --p-n-estimators=$pnestimators
|
|
0
|
59
|
|
|
60 #if str($pestimator) != 'None':
|
|
14
|
61 --p-estimator=$pestimator
|
|
0
|
62 #end if
|
|
|
63
|
|
|
64 #if $poptimizefeatureselection:
|
|
|
65 --p-optimize-feature-selection
|
|
|
66 #end if
|
|
|
67
|
|
|
68 #if $pparametertuning:
|
|
|
69 --p-parameter-tuning
|
|
|
70 #end if
|
|
|
71
|
|
|
72 #if str($ppalette) != 'None':
|
|
14
|
73 --p-palette=$ppalette
|
|
0
|
74 #end if
|
|
|
75
|
|
|
76 #if str($pmissingsamples) != 'None':
|
|
14
|
77 --p-missing-samples=$pmissingsamples
|
|
0
|
78 #end if
|
|
|
79
|
|
14
|
80 --o-sample-estimator=osampleestimator
|
|
0
|
81
|
|
14
|
82 --o-feature-importance=ofeatureimportance
|
|
|
83
|
|
|
84 --o-predictions=opredictions
|
|
0
|
85
|
|
14
|
86 --o-model-summary=omodelsummary
|
|
0
|
87
|
|
14
|
88 --o-accuracy-results=oaccuracyresults
|
|
5
|
89
|
|
9
|
90 --o-probabilities=oprobabilities
|
|
14
|
91
|
|
|
92 --o-heatmap=oheatmap
|
|
|
93
|
|
|
94 #if str($examples) != 'None':
|
|
|
95 --examples=$examples
|
|
|
96 #end if
|
|
|
97
|
|
|
98 ;
|
|
|
99 cp oprobabilities.qza $oprobabilities
|
|
|
100
|
|
0
|
101 ;
|
|
14
|
102 qiime tools export oheatmap.qzv --output-path out
|
|
|
103 && mkdir -p '$oheatmap.files_path'
|
|
|
104 && cp -r out/* '$oheatmap.files_path'
|
|
|
105 && mv '$oheatmap.files_path/index.html' '$oheatmap'
|
|
0
|
106
|
|
14
|
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 <repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file">
|
|
|
111 <param format="tabular,qza,no_unzip.zip" label="--m-metadata-file: METADATA" name="additional_input" optional="True" type="data" />
|
|
|
112 </repeat>
|
|
|
113 <param label="--m-metadata-column: COLUMN MetadataColumn[Categorical] Categorical metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text" />
|
|
|
114 <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: 0.2]" max="1.0" min="0.0" name="ptestsize" optional="True" type="float" value="0.2" />
|
|
|
115 <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" />
|
|
|
116 <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" />
|
|
|
117 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="False" type="text" />
|
|
|
118 <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" />
|
|
|
119 <param label="--p-estimator: " name="pestimator" optional="True" type="select">
|
|
|
120 <option selected="True" value="None">Selection is Optional</option>
|
|
|
121 <option value="RandomForestClassifier">RandomForestClassifier</option>
|
|
|
122 <option value="ExtraTreesClassifier">ExtraTreesClassifier</option>
|
|
|
123 <option value="GradientBoostingClassifier">GradientBoostingClassifier</option>
|
|
|
124 <option value="AdaBoostClassifier">AdaBoostClassifier</option>
|
|
|
125 <option value="KNeighborsClassifier">KNeighborsClassifier</option>
|
|
|
126 <option value="LinearSVC">LinearSVC</option>
|
|
|
127 <option value="SVC">SVC</option>
|
|
|
128 </param>
|
|
|
129 <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" />
|
|
|
130 <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" />
|
|
|
131 <param label="--p-palette: " name="ppalette" optional="True" type="select">
|
|
|
132 <option selected="True" value="None">Selection is Optional</option>
|
|
|
133 <option value="YellowOrangeBrown">YellowOrangeBrown</option>
|
|
|
134 <option value="YellowOrangeRed">YellowOrangeRed</option>
|
|
|
135 <option value="OrangeRed">OrangeRed</option>
|
|
|
136 <option value="PurpleRed">PurpleRed</option>
|
|
|
137 <option value="RedPurple">RedPurple</option>
|
|
|
138 <option value="BluePurple">BluePurple</option>
|
|
|
139 <option value="GreenBlue">GreenBlue</option>
|
|
|
140 <option value="PurpleBlue">PurpleBlue</option>
|
|
|
141 <option value="YellowGreen">YellowGreen</option>
|
|
|
142 <option value="summer">summer</option>
|
|
|
143 <option value="copper">copper</option>
|
|
|
144 <option value="viridis">viridis</option>
|
|
|
145 <option value="cividis">cividis</option>
|
|
|
146 <option value="plasma">plasma</option>
|
|
|
147 <option value="inferno">inferno</option>
|
|
|
148 <option value="magma">magma</option>
|
|
|
149 <option value="sirocco">sirocco</option>
|
|
|
150 <option value="drifting">drifting</option>
|
|
|
151 <option value="melancholy">melancholy</option>
|
|
|
152 <option value="enigma">enigma</option>
|
|
|
153 <option value="eros">eros</option>
|
|
|
154 <option value="spectre">spectre</option>
|
|
|
155 <option value="ambition">ambition</option>
|
|
|
156 <option value="mysteriousstains">mysteriousstains</option>
|
|
|
157 <option value="daydream">daydream</option>
|
|
|
158 <option value="solano">solano</option>
|
|
|
159 <option value="navarro">navarro</option>
|
|
|
160 <option value="dandelions">dandelions</option>
|
|
|
161 <option value="deepblue">deepblue</option>
|
|
|
162 <option value="verve">verve</option>
|
|
|
163 <option value="greyscale">greyscale</option>
|
|
|
164 </param>
|
|
|
165 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
|
|
|
166 <option selected="True" value="None">Selection is Optional</option>
|
|
|
167 <option value="error">error</option>
|
|
|
168 <option value="ignore">ignore</option>
|
|
|
169 </param>
|
|
|
170 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
|
|
|
171
|
|
|
172 </inputs>
|
|
0
|
173
|
|
14
|
174 <outputs>
|
|
|
175 <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator" />
|
|
|
176 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance" />
|
|
|
177 <data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions" />
|
|
|
178 <data format="html" label="${tool.name} on ${on_string}: modelsummary.html" name="omodelsummary" />
|
|
|
179 <data format="html" label="${tool.name} on ${on_string}: accuracyresults.html" name="oaccuracyresults" />
|
|
|
180 <data format="qza" label="${tool.name} on ${on_string}: probabilities.qza" name="oprobabilities" />
|
|
|
181 <data format="html" label="${tool.name} on ${on_string}: heatmap.html" name="oheatmap" />
|
|
|
182
|
|
|
183 </outputs>
|
|
|
184
|
|
|
185 <help><![CDATA[
|
|
0
|
186 Train and test a cross-validated supervised learning classifier.
|
|
14
|
187 ###############################################################
|
|
0
|
188
|
|
|
189 Predicts a categorical sample metadata column using a supervised learning
|
|
|
190 classifier. Splits input data into training and test sets. The training set
|
|
|
191 is used to train and test the estimator using a stratified k-fold cross-
|
|
|
192 validation scheme. This includes optional steps for automated feature
|
|
|
193 extraction and hyperparameter optimization. The test set validates
|
|
|
194 classification accuracy of the optimized estimator. Outputs classification
|
|
|
195 results for test set. For more details on the learning algorithm, see
|
|
|
196 http://scikit-learn.org/stable/supervised_learning.html
|
|
|
197
|
|
|
198 Parameters
|
|
|
199 ----------
|
|
|
200 table : FeatureTable[Frequency]
|
|
|
201 Feature table containing all features that should be used for target
|
|
|
202 prediction.
|
|
|
203 metadata : MetadataColumn[Categorical]
|
|
|
204 Categorical metadata column to use as prediction target.
|
|
|
205 test_size : Float % Range(0.0, 1.0, inclusive_start=False), optional
|
|
|
206 Fraction of input samples to exclude from training set and use for
|
|
|
207 classifier testing.
|
|
|
208 step : Float % Range(0.0, 1.0, inclusive_start=False), optional
|
|
|
209 If optimize_feature_selection is True, step is the percentage of
|
|
|
210 features to remove at each iteration.
|
|
|
211 cv : Int % Range(1, None), optional
|
|
|
212 Number of k-fold cross-validations to perform.
|
|
|
213 random_state : Int, optional
|
|
|
214 Seed used by random number generator.
|
|
14
|
215 n_jobs : Int, optional
|
|
|
216 Number of jobs to run in parallel.
|
|
0
|
217 n_estimators : Int % Range(1, None), optional
|
|
|
218 Number of trees to grow for estimation. More trees will improve
|
|
|
219 predictive accuracy up to a threshold level, but will also increase
|
|
|
220 time and memory requirements. This parameter only affects ensemble
|
|
|
221 estimators, such as Random Forest, AdaBoost, ExtraTrees, and
|
|
|
222 GradientBoosting.
|
|
|
223 estimator : Str % Choices('RandomForestClassifier', 'ExtraTreesClassifier', 'GradientBoostingClassifier', 'AdaBoostClassifier', 'KNeighborsClassifier', 'LinearSVC', 'SVC'), optional
|
|
|
224 Estimator method to use for sample prediction.
|
|
|
225 optimize_feature_selection : Bool, optional
|
|
|
226 Automatically optimize input feature selection using recursive feature
|
|
|
227 elimination.
|
|
|
228 parameter_tuning : Bool, optional
|
|
|
229 Automatically tune hyperparameters using random grid search.
|
|
14
|
230 palette : Str % Choices('YellowOrangeBrown', 'YellowOrangeRed', 'OrangeRed', 'PurpleRed', 'RedPurple', 'BluePurple', 'GreenBlue', 'PurpleBlue', 'YellowGreen', 'summer', 'copper', 'viridis', 'cividis', 'plasma', 'inferno', 'magma', 'sirocco', 'drifting', 'melancholy', 'enigma', 'eros', 'spectre', 'ambition', 'mysteriousstains', 'daydream', 'solano', 'navarro', 'dandelions', 'deepblue', 'verve', 'greyscale'), optional
|
|
0
|
231 The color palette to use for plotting.
|
|
|
232 missing_samples : Str % Choices('error', 'ignore'), optional
|
|
|
233 How to handle missing samples in metadata. "error" will fail if missing
|
|
|
234 samples are detected. "ignore" will cause the feature table and
|
|
|
235 metadata to be filtered, so that only samples found in both files are
|
|
|
236 retained.
|
|
|
237
|
|
|
238 Returns
|
|
|
239 -------
|
|
|
240 sample_estimator : SampleEstimator[Classifier]
|
|
|
241 Trained sample estimator.
|
|
|
242 feature_importance : FeatureData[Importance]
|
|
|
243 Importance of each input feature to model accuracy.
|
|
|
244 predictions : SampleData[ClassifierPredictions]
|
|
|
245 Predicted target values for each input sample.
|
|
|
246 model_summary : Visualization
|
|
|
247 Summarized parameter and (if enabled) feature selection information for
|
|
|
248 the trained estimator.
|
|
|
249 accuracy_results : Visualization
|
|
|
250 Accuracy results visualization.
|
|
9
|
251 probabilities : SampleData[Probabilities]
|
|
|
252 Predicted class probabilities for each input sample.
|
|
14
|
253 heatmap : Visualization
|
|
|
254 A heatmap of the top 50 most important features from the table.
|
|
|
255 ]]></help>
|
|
|
256 <macros>
|
|
0
|
257 <import>qiime_citation.xml</import>
|
|
14
|
258 </macros>
|
|
|
259 <expand macro="qiime_citation"/>
|
|
|
260 </tool> |
