annotate qiime2/qiime_longitudinal_feature-volatility.xml @ 7:85b520815e85 draft

Uploaded
author florianbegusch
date Tue, 13 Aug 2019 07:53:59 -0400
parents de4c22a52df4
children f190567fe3f6
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_longitudinal_feature-volatility" name="qiime longitudinal feature-volatility" version="2019.4">
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
3 <description> - Feature volatility analysis</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 longitudinal feature-volatility
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
9
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
10 --i-table=$itable
4
florianbegusch
parents: 0
diff changeset
11
florianbegusch
parents: 0
diff changeset
12
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
13 --p-state-column="$pstatecolumn"
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
14
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
15 #if str($pindividualidcolumn):
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
16 --p-individual-id-column="$pindividualidcolumn"
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
17 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
18
6
florianbegusch
parents: 4
diff changeset
19 #if str($pcv):
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
20 --p-cv=$pcv
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
21 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
22
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
23 #if str($prandomstate):
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
24 --p-random-state="$prandomstate"
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
25 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
26
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
27 #set $pnjobs = '${GALAXY_SLOTS:-4}'
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
28
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
29 #if str($pnjobs):
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
30 --p-n-jobs="$pnjobs"
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
31 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
32
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
33
6
florianbegusch
parents: 4
diff changeset
34 #if str($pnestimators):
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
35 --p-n-estimators=$pnestimators
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
36 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
37
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
38 #if str($pestimator) != 'None':
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
39 --p-estimator=$pestimator
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
40 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
41
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
42 #if $pparametertuning:
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
43 --p-parameter-tuning
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
44 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
45
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
46 #if str($pmissingsamples) != 'None':
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
47 --p-missing-samples=$pmissingsamples
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
48 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
49
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
50
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
51 #if $input_files_mmetadatafile:
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
52 #def list_dict_to_string(list_dict):
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
53 #set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
54 #for d in list_dict[1:]:
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
55 #set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
56 #end for
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
57 #return $file_list
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
58 #end def
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
59 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile)
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
60 #end if
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
61
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
62
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
63 --o-filtered-table=ofilteredtable
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
64 --o-feature-importance=ofeatureimportance
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
65 --o-volatility-plot=ovolatilityplot
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
66 --o-accuracy-results=oaccuracyresults
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
67 --o-sample-estimator=osampleestimator
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
68 ;
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
69 cp ofilteredtable.qza $ofilteredtable;
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
70 cp ofeatureimportance.qza $ofeatureimportance;
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
71 qiime tools export --input-path ovolatilityplot.qzv --output-path out && mkdir -p '$ovolatilityplot.files_path'
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
72 && cp -r out/* '$ovolatilityplot.files_path'
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
73 && mv '$ovolatilityplot.files_path/index.html' '$ovolatilityplot';
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
74 qiime tools export --input-path oaccuracyresults.qzv --output-path out && mkdir -p '$oaccuracyresults.files_path'
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
75 && cp -r out/* '$oaccuracyresults.files_path'
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
76 && mv '$oaccuracyresults.files_path/index.html' '$oaccuracyresults';
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
77 cp osampleestimator.qza $osampleestimator
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
78 ]]></command>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
79 <inputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
80 <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
81 <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"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
82 <param label="--p-individual-id-column: TEXT Metadata column containing IDs for individual subjects. [optional]" name="pindividualidcolumn" optional="True" type="text"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
83 <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"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
84 <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
85 <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"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
86 <param label="--p-estimator: " name="pestimator" optional="True" type="select">
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
87 <option selected="True" value="None">Selection is Optional</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
88 <option value="RandomForestRegressor">RandomForestRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
89 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
90 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
91 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
92 <option value="ElasticNet">ElasticNet</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
93 <option value="Ridge">Ridge</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
94 <option value="Lasso">Lasso</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
95 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
96 <option value="LinearSVR">LinearSVR</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
97 <option value="SVR">SVR</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
98 </param>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
99 <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
100 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
101 <option selected="True" value="None">Selection is Optional</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
102 <option value="error">error</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
103 <option value="ignore">ignore</option>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
104 </param>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
105
4
florianbegusch
parents: 0
diff changeset
106 <repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file [required]">
0
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
107 <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
108 </repeat>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
109
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
110 </inputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
111 <outputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
112 <data format="qza" label="${tool.name} on ${on_string}: filteredtable.qza" name="ofilteredtable"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
113 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
114 <data format="html" label="${tool.name} on ${on_string}: volatilityplot.qzv" name="ovolatilityplot"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
115 <data format="html" label="${tool.name} on ${on_string}: accuracyresults.qzv" name="oaccuracyresults"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
116 <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
117 </outputs>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
118 <help><![CDATA[
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
119 Feature volatility analysis
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
120 ###########################
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
121
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
122 Identify features that are predictive of a numeric metadata column,
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
123 state_column (e.g., time), and plot their relative frequencies across
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
124 states using interactive feature volatility plots. A supervised learning
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
125 regressor is used to identify important features and assess their ability
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
126 to predict sample states. state_column will typically be a measure of time,
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
127 but any numeric metadata column can be used.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
128
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
129 Parameters
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
130 ----------
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
131 table : FeatureTable[Frequency]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
132 Feature table containing all features that should be used for target
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
133 prediction.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
134 metadata : Metadata
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
135 Sample metadata file containing individual_id_column.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
136 state_column : Str
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
137 Metadata containing collection time (state) values for each sample.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
138 Must contain exclusively numeric values.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
139 individual_id_column : Str, optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
140 Metadata column containing IDs for individual subjects.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
141 cv : Int % Range(1, None), optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
142 Number of k-fold cross-validations to perform.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
143 random_state : Int, optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
144 Seed used by random number generator.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
145 n_estimators : Int % Range(1, None), optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
146 Number of trees to grow for estimation. More trees will improve
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
147 predictive accuracy up to a threshold level, but will also increase
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
148 time and memory requirements. This parameter only affects ensemble
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
149 estimators, such as Random Forest, AdaBoost, ExtraTrees, and
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
150 GradientBoosting.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
151 estimator : Str % Choices('RandomForestRegressor', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'AdaBoostRegressor', 'ElasticNet', 'Ridge', 'Lasso', 'KNeighborsRegressor', 'LinearSVR', 'SVR'), optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
152 Estimator method to use for sample prediction.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
153 parameter_tuning : Bool, optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
154 Automatically tune hyperparameters using random grid search.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
155 missing_samples : Str % Choices('error', 'ignore'), optional
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
156 How to handle missing samples in metadata. "error" will fail if missing
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
157 samples are detected. "ignore" will cause the feature table and
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
158 metadata to be filtered, so that only samples found in both files are
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
159 retained.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
160
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
161 Returns
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
162 -------
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
163 filtered_table : FeatureTable[RelativeFrequency]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
164 Feature table containing only important features.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
165 feature_importance : FeatureData[Importance]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
166 Importance of each input feature to model accuracy.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
167 volatility_plot : Visualization
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
168 Interactive volatility plot visualization.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
169 accuracy_results : Visualization
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
170 Accuracy results visualization.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
171 sample_estimator : SampleEstimator[Regressor]
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
172 Trained sample regressor.
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
173 ]]></help>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
174 <macros>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
175 <import>qiime_citation.xml</import>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
176 </macros>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
177 <expand macro="qiime_citation"/>
370e0b6e9826 Uploaded
florianbegusch
parents:
diff changeset
178 </tool>