annotate qiime2/qiime_longitudinal_maturity-index.xml @ 29:3ba9833030c1 draft

Uploaded
author florianbegusch
date Fri, 04 Sep 2020 13:12:49 +0000
parents
children
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
29
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
1 <?xml version="1.0" ?>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
2 <tool id="qiime_longitudinal_maturity-index" name="qiime longitudinal maturity-index"
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
3 version="2020.8">
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
4 <description>Microbial maturity index prediction.</description>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
5 <requirements>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
6 <requirement type="package" version="2020.8">qiime2</requirement>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
7 </requirements>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
8 <command><![CDATA[
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
9 qiime longitudinal maturity-index
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
10
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
11 --i-table=$itable
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
12 # if $input_files_mmetadatafile:
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
13 # def list_dict_to_string(list_dict):
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
14 # set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
15 # for d in list_dict[1:]:
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
16 # set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
17 # end for
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
18 # return $file_list
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
19 # end def
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
20 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile)
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
21 # end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
22
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
23 #if '__ob__' in str($pstatecolumn):
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
24 #set $pstatecolumn_temp = $pstatecolumn.replace('__ob__', '[')
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
25 #set $pstatecolumn = $pstatecolumn_temp
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
26 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
27 #if '__cb__' in str($pstatecolumn):
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
28 #set $pstatecolumn_temp = $pstatecolumn.replace('__cb__', ']')
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
29 #set $pstatecolumn = $pstatecolumn_temp
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
30 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
31 #if 'X' in str($pstatecolumn):
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
32 #set $pstatecolumn_temp = $pstatecolumn.replace('X', '\\')
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
33 #set $pstatecolumn = $pstatecolumn_temp
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
34 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
35 #if '__sq__' in str($pstatecolumn):
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
36 #set $pstatecolumn_temp = $pstatecolumn.replace('__sq__', "'")
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
37 #set $pstatecolumn = $pstatecolumn_temp
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
38 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
39 #if '__db__' in str($pstatecolumn):
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
40 #set $pstatecolumn_temp = $pstatecolumn.replace('__db__', '"')
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
41 #set $pstatecolumn = $pstatecolumn_temp
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
42 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
43
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
44 --p-state-column=$pstatecolumn
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
45
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
46
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
47 --p-group-by=$pgroupby
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
48
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
49 --p-control=$pcontrol
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
50
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
51 #if '__ob__' in str($pindividualidcolumn):
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
52 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__ob__', '[')
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
53 #set $pindividualidcolumn = $pindividualidcolumn_temp
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
54 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
55 #if '__cb__' in str($pindividualidcolumn):
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
56 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__cb__', ']')
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
57 #set $pindividualidcolumn = $pindividualidcolumn_temp
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
58 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
59 #if 'X' in str($pindividualidcolumn):
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
60 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('X', '\\')
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
61 #set $pindividualidcolumn = $pindividualidcolumn_temp
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
62 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
63 #if '__sq__' in str($pindividualidcolumn):
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
64 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__sq__', "'")
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
65 #set $pindividualidcolumn = $pindividualidcolumn_temp
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
66 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
67 #if '__db__' in str($pindividualidcolumn):
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
68 #set $pindividualidcolumn_temp = $pindividualidcolumn.replace('__db__', '"')
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
69 #set $pindividualidcolumn = $pindividualidcolumn_temp
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
70 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
71
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
72 #if str($pindividualidcolumn):
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
73 --p-individual-id-column=$pindividualidcolumn
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
74 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
75
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
76 #if str($pestimator) != 'None':
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
77 --p-estimator=$pestimator
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
78 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
79
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
80 --p-n-estimators=$pnestimators
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
81
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
82 --p-test-size=$ptestsize
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
83
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
84 --p-step=$pstep
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
85
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
86 --p-cv=$pcv
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
87
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
88 #if str($prandomstate):
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
89 --p-random-state=$prandomstate
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
90 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
91 --p-n-jobs=$pnjobs
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
92
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
93 #if $pparametertuning:
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
94 --p-parameter-tuning
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
95 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
96
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
97 #if $poptimizefeatureselection:
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
98 --p-optimize-feature-selection
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
99 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
100
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
101 #if $pstratify:
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
102 --p-stratify
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
103 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
104
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
105 #if str($pmissingsamples) != 'None':
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
106 --p-missing-samples=$pmissingsamples
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
107 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
108
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
109 --p-feature-count=$pfeaturecount
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
110
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
111 --o-sample-estimator=osampleestimator
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
112
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
113 --o-feature-importance=ofeatureimportance
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
114
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
115 --o-predictions=opredictions
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
116
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
117 --o-model-summary=omodelsummary
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
118
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
119 --o-accuracy-results=oaccuracyresults
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
120
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
121 --o-maz-scores=omazscores
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
122
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
123 --o-clustermap=oclustermap
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
124
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
125 --o-volatility-plots=ovolatilityplots
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
126
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
127 #if str($examples) != 'None':
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
128 --examples=$examples
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
129 #end if
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
130
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
131 ;
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
132 cp omazscores.qza $omazscores
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
133
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
134 ;
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
135 qiime tools export oclustermap.qzv --output-path out
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
136 && mkdir -p '$oclustermap.files_path'
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
137 && cp -r out/* '$oclustermap.files_path'
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
138 && mv '$oclustermap.files_path/index.html' '$oclustermap'
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
139
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
140 ;
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
141 qiime tools export ovolatilityplots.qzv --output-path out
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
142 && mkdir -p '$ovolatilityplots.files_path'
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
143 && cp -r out/* '$ovolatilityplots.files_path'
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
144 && mv '$ovolatilityplots.files_path/index.html' '$ovolatilityplots'
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
145
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
146 ]]></command>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
147 <inputs>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
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" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
149 <repeat name="input_files_mmetadatafile" optional="False" title="--m-metadata-file">
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
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" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
151 </repeat>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
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" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
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" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
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" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
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" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
156 <param label="--p-estimator: " name="pestimator" optional="True" type="select">
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
157 <option selected="True" value="None">Selection is Optional</option>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
158 <option value="RandomForestRegressor">RandomForestRegressor</option>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
159 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
160 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
161 <option value="AdaBoostRegressor">AdaBoostRegressor</option>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
162 <option value="ElasticNet">ElasticNet</option>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
163 <option value="Ridge">Ridge</option>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
164 <option value="Lasso">Lasso</option>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
165 <option value="KNeighborsRegressor">KNeighborsRegressor</option>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
166 <option value="LinearSVR">LinearSVR</option>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
167 <option value="SVR">SVR</option>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
168 </param>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
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" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
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" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
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" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
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" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
173 <param label="--p-random-state: INTEGER Seed used by random number generator. [optional]" name="prandomstate" optional="False" type="text" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
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" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
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" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
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" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
177 <param label="--p-missing-samples: " name="pmissingsamples" optional="True" type="select">
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
178 <option selected="True" value="None">Selection is Optional</option>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
179 <option value="error">error</option>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
180 <option value="ignore">ignore</option>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
181 </param>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
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" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
183 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
184
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
185 </inputs>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
186
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
187 <outputs>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
188 <data format="qza" label="${tool.name} on ${on_string}: sampleestimator.qza" name="osampleestimator" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
189 <data format="qza" label="${tool.name} on ${on_string}: featureimportance.qza" name="ofeatureimportance" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
190 <data format="qza" label="${tool.name} on ${on_string}: predictions.qza" name="opredictions" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
191 <data format="html" label="${tool.name} on ${on_string}: modelsummary.html" name="omodelsummary" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
192 <data format="html" label="${tool.name} on ${on_string}: accuracyresults.html" name="oaccuracyresults" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
193 <data format="qza" label="${tool.name} on ${on_string}: mazscores.qza" name="omazscores" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
194 <data format="html" label="${tool.name} on ${on_string}: clustermap.html" name="oclustermap" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
195 <data format="html" label="${tool.name} on ${on_string}: volatilityplots.html" name="ovolatilityplots" />
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
196
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
197 </outputs>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
198
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
199 <help><![CDATA[
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
200 Microbial maturity index prediction.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
201 ###############################################################
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
202
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
203 Calculates a "microbial maturity" index from a regression model trained on
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
204 feature data to predict a given continuous metadata column, e.g., to
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
205 predict age as a function of microbiota composition. The model is trained
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
206 on a subset of control group samples, then predicts the column value for
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
207 all samples. This visualization computes maturity index z-scores to compare
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
208 relative "maturity" between each group, as described in
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
209 doi:10.1038/nature13421. This method can be used to predict between-group
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
210 differences in relative trajectory across any type of continuous metadata
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
211 gradient, e.g., intestinal microbiome development by age, microbial
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
212 succession during wine fermentation, or microbial community differences
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
213 along environmental gradients, as a function of two or more different
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
214 "treatment" groups.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
215
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
216 Parameters
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
217 ----------
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
218 table : FeatureTable[Frequency]
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
219 Feature table containing all features that should be used for target
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
220 prediction.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
221 metadata : Metadata
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
222 state_column : Str
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
223 Numeric metadata column containing sampling time (state) data to use as
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
224 prediction target.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
225 group_by : Str
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
226 Categorical metadata column to use for plotting and significance
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
227 testing between main treatment groups.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
228 control : Str
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
229 Value of group_by to use as control group. The regression model will be
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
230 trained using only control group data, and the maturity scores of other
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
231 groups consequently will be assessed relative to this group.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
232 individual_id_column : Str, optional
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
233 Optional metadata column containing IDs for individual subjects. Adds
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
234 individual subject (spaghetti) vectors to volatility charts if a column
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
235 name is provided.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
236 estimator : Str % Choices('RandomForestRegressor', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'AdaBoostRegressor', 'ElasticNet', 'Ridge', 'Lasso', 'KNeighborsRegressor', 'LinearSVR', 'SVR'), optional
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
237 Regression model to use for prediction.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
238 n_estimators : Int % Range(1, None), optional
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
239 Number of trees to grow for estimation. More trees will improve
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
240 predictive accuracy up to a threshold level, but will also increase
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
241 time and memory requirements. This parameter only affects ensemble
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
242 estimators, such as Random Forest, AdaBoost, ExtraTrees, and
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
243 GradientBoosting.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
244 test_size : Float % Range(0.0, 1.0, inclusive_start=False), optional
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
245 Fraction of input samples to exclude from training set and use for
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
246 classifier testing.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
247 step : Float % Range(0.0, 1.0, inclusive_start=False), optional
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
248 If optimize_feature_selection is True, step is the percentage of
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
249 features to remove at each iteration.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
250 cv : Int % Range(1, None), optional
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
251 Number of k-fold cross-validations to perform.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
252 random_state : Int, optional
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
253 Seed used by random number generator.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
254 n_jobs : Int, optional
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
255 Number of jobs to run in parallel.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
256 parameter_tuning : Bool, optional
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
257 Automatically tune hyperparameters using random grid search.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
258 optimize_feature_selection : Bool, optional
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
259 Automatically optimize input feature selection using recursive feature
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
260 elimination.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
261 stratify : Bool, optional
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
262 Evenly stratify training and test data among metadata categories. If
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
263 True, all values in column must match at least two samples.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
264 missing_samples : Str % Choices('error', 'ignore'), optional
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
265 How to handle missing samples in metadata. "error" will fail if missing
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
266 samples are detected. "ignore" will cause the feature table and
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
267 metadata to be filtered, so that only samples found in both files are
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
268 retained.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
269 feature_count : Int % Range(0, None), optional
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
270 Filter feature table to include top N most important features. Set to
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
271 zero to include all features.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
272
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
273 Returns
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
274 -------
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
275 sample_estimator : SampleEstimator[Regressor]
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
276 Trained sample estimator.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
277 feature_importance : FeatureData[Importance]
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
278 Importance of each input feature to model accuracy.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
279 predictions : SampleData[RegressorPredictions]
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
280 Predicted target values for each input sample.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
281 model_summary : Visualization
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
282 Summarized parameter and (if enabled) feature selection information for
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
283 the trained estimator.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
284 accuracy_results : Visualization
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
285 Accuracy results visualization.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
286 maz_scores : SampleData[RegressorPredictions]
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
287 Microbiota-for-age z-score predictions.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
288 clustermap : Visualization
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
289 Heatmap of important feature abundance at each time point in each
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
290 group.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
291 volatility_plots : Visualization
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
292 Interactive volatility plots of MAZ and maturity scores, target
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
293 (column) predictions, and the sample metadata.
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
294 ]]></help>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
295 <macros>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
296 <import>qiime_citation.xml</import>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
297 </macros>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
298 <expand macro="qiime_citation"/>
3ba9833030c1 Uploaded
florianbegusch
parents:
diff changeset
299 </tool>