annotate qiime2/qiime_sample-classifier_regress-samples-ncv.xml @ 3:558645416841 draft

Uploaded
author florianbegusch
date Sun, 21 Jul 2019 02:21:34 -0400
parents 370e0b6e9826
children a025a4a89e07
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
1 <?xml version="1.0" ?>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
2 <tool id="qiime_sample-classifier_regress-samples-ncv" name="qiime sample-classifier regress-samples-ncv" version="2019.4">
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
3 <description> - Nested cross-validated supervised learning regressor.</description>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
4 <requirements>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
5 <requirement type="package" version="2019.4">qiime2</requirement>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
6 </requirements>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
7 <command><![CDATA[
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
8 qiime sample-classifier regress-samples-ncv
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
9
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
10 --i-table=$itable
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
11 --m-metadata-column="$mmetadatacolumn"
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
12
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
13 #if $pcv:
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
14 --p-cv=$pcv
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
15 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
16
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
17 #if str($prandomstate):
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
18 --p-random-state="$prandomstate"
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
19 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
20
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
21 #set $pnjobs = '${GALAXY_SLOTS:-4}'
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
22
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
23 #if str($pnjobs):
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
24 --p-n-jobs="$pnjobs"
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
25 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
26
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
27
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
28 #if $pnestimators:
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
29 --p-n-estimators=$pnestimators
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
30 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
31
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
32 #if str($pestimator) != 'None':
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
33 --p-estimator=$pestimator
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
34 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
35
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
36 #if $pstratify:
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
37 --p-stratify
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
38 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
39
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
40 #if $pparametertuning:
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
41 --p-parameter-tuning
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
42 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
43
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
44 #if str($pmissingsamples) != 'None':
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
45 --p-missing-samples=$pmissingsamples
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
46 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
47
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
48
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
49 #if $input_files_mmetadatafile:
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
50 #def list_dict_to_string(list_dict):
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
51 #set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
52 #for d in list_dict[1:]:
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
53 #set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
54 #end for
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
55 #return $file_list
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
56 #end def
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
57 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile)
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
58 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
59
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
60
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
61 --o-predictions=opredictions
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
62 --o-feature-importance=ofeatureimportance
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
63 ;
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
64 cp opredictions.qza $opredictions;
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
65 cp ofeatureimportance.qza $ofeatureimportance
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
66 ]]></command>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
67 <inputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
68 <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"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
69 <param label="--m-metadata-column: COLUMN MetadataColumn[Numeric] Numeric metadata column to use as prediction target. [required]" name="mmetadatacolumn" optional="False" type="text"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
70 <param label="--p-cv: INTEGER Number of k-fold cross-validations to perform. Range(1, None) [default: 5]" name="pcv" optional="True" type="integer" value="5" min="1"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
71 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="True" type="integer"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
72 <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" value="100" min="1"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
73 <param label="--p-estimator: " name="pestimator" optional="True" type="select">
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
74 <option selected="True" value="None">Selection is Optional</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
75 <option value="RandomForestRegressor">RandomForestRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
76 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
77 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
78 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
79 <option value="ElasticNet">ElasticNet</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
80 <option value="Ridge">Ridge</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
81 <option value="Lasso">Lasso</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
82 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
83 <option value="LinearSVR">LinearSVR</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
84 <option value="SVR">SVR</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
85 </param>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
86 <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"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
87 <param label="--p-parameter-tuning: --p-no-parameter-tuning Automatically tune hyperparameters using random grid search. [default: False]" name="pparametertuning" selected="False" type="boolean"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
88 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
89 <option selected="True" value="None">Selection is Optional</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
90 <option value="error">error</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
91 <option value="ignore">ignore</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
92 </param>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
93
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
94 <repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file">
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
95 <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" />
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
96 </repeat>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
97 </inputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
98 <outputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
99 <data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
100 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
101 </outputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
102 <help><![CDATA[
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
103 Nested cross-validated supervised learning classifier.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
104 ######################################################
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
105
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
106 Predicts a categorical sample metadata column using a supervised learning
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
107 classifier. Uses nested stratified k-fold cross validation for automated
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
108 hyperparameter optimization and sample prediction. Outputs predicted values
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
109 for each input sample, and relative importance of each feature for model
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
110 accuracy.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
111
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
112 Parameters
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
113 ----------
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
114 table : FeatureTable[Frequency]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
115 Feature table containing all features that should be used for target
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
116 prediction.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
117 metadata : MetadataColumn[Categorical]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
118 Categorical metadata column to use as prediction target.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
119 cv : Int % Range(1, None), optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
120 Number of k-fold cross-validations to perform.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
121 random_state : Int, optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
122 Seed used by random number generator.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
123 n_estimators : Int % Range(1, None), optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
124 Number of trees to grow for estimation. More trees will improve
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
125 predictive accuracy up to a threshold level, but will also increase
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
126 time and memory requirements. This parameter only affects ensemble
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
127 estimators, such as Random Forest, AdaBoost, ExtraTrees, and
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
128 GradientBoosting.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
129 estimator : Str % Choices('RandomForestClassifier', 'ExtraTreesClassifier', 'GradientBoostingClassifier', 'AdaBoostClassifier', 'KNeighborsClassifier', 'LinearSVC', 'SVC'), optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
130 Estimator method to use for sample prediction.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
131 parameter_tuning : Bool, optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
132 Automatically tune hyperparameters using random grid search.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
133 missing_samples : Str % Choices('error', 'ignore'), optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
134 How to handle missing samples in metadata. "error" will fail if missing
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
135 samples are detected. "ignore" will cause the feature table and
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
136 metadata to be filtered, so that only samples found in both files are
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
137 retained.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
138
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
139 Returns
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
140 -------
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
141 predictions : SampleData[ClassifierPredictions]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
142 Predicted target values for each input sample.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
143 feature_importance : FeatureData[Importance]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
144 Importance of each input feature to model accuracy.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
145 ]]></help>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
146 <macros>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
147 <import>qiime_citation.xml</import>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
148 </macros>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
149 <expand macro="qiime_citation"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
150 </tool>