|
0
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_sample-classifier_maturity-index" name="qiime sample-classifier maturity-index" version="2018.4">
|
|
|
3 <description> - Microbial maturity index prediction.</description>
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="2018.4">qiime2</requirement>
|
|
|
6 </requirements>
|
|
|
7 <command>
|
|
|
8 <![CDATA[
|
|
|
9 qiime sample-classifier maturity-index --i-table=$itable
|
|
|
10
|
|
|
11 #def list_dict_to_string(list_dict):
|
|
|
12 #set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
|
|
|
13 #for d in list_dict[1:]:
|
|
|
14 #set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
|
|
|
15 #end for
|
|
|
16 #return $file_list
|
|
|
17 #end def
|
|
|
18
|
|
|
19 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile) --p-group-by="$pgroupby" --p-column="$pcolumn" --p-control="$pcontrol"
|
|
|
20
|
|
|
21 #set $pnjobs = '${GALAXY_SLOTS:-4}'
|
|
|
22
|
|
|
23 #if str($pnjobs):
|
|
|
24 --p-n-jobs="$pnjobs"
|
|
|
25 #end if
|
|
|
26
|
|
|
27
|
|
|
28 #if $pparametertuning:
|
|
|
29 --p-parameter-tuning
|
|
|
30 #else
|
|
|
31 --p-no-parameter-tuning
|
|
|
32 #end if
|
|
|
33
|
|
|
34 #if $pstep:
|
|
|
35 --p-step=$pstep
|
|
|
36 #end if
|
|
|
37
|
|
|
38 #if $pstratify:
|
|
|
39 --p-stratify
|
|
|
40 #else
|
|
|
41 --p-no-stratify
|
|
|
42 #end if
|
|
|
43
|
|
|
44 #if $poptimizefeatureselection:
|
|
|
45 --p-optimize-feature-selection
|
|
|
46 #else
|
|
|
47 --p-no-optimize-feature-selection
|
|
|
48 #end if
|
|
|
49
|
|
|
50 #if $ptestsize:
|
|
|
51 --p-test-size=$ptestsize
|
|
|
52 #end if
|
|
|
53 --o-visualization=ovisualization
|
|
|
54 #if str($pestimator) != 'None':
|
|
|
55 --p-estimator=$pestimator
|
|
|
56 #end if
|
|
|
57
|
|
|
58 #if $pmazstats:
|
|
|
59 --p-maz-stats
|
|
|
60 #else
|
|
|
61 --p-no-maz-stats
|
|
|
62 #end if
|
|
|
63
|
|
|
64 #if str($cmdconfig) != 'None':
|
|
|
65 --cmd-config=$cmdconfig
|
|
|
66 #end if
|
|
|
67
|
|
|
68 #if $pcv:
|
|
|
69 --p-cv=$pcv
|
|
|
70 #end if
|
|
|
71
|
|
|
72 #if $pnestimators:
|
|
|
73 --p-n-estimators=$pnestimators
|
|
|
74 #end if
|
|
|
75
|
|
|
76 #if str($prandomstate):
|
|
|
77 --p-random-state="$prandomstate"
|
|
|
78 #end if
|
|
|
79 ;
|
|
|
80 qiime tools export ovisualization.qzv --output-dir out && mkdir -p '$ovisualization.files_path'
|
|
|
81 && cp -r out/* '$ovisualization.files_path'
|
|
|
82 && mv '$ovisualization.files_path/index.html' '$ovisualization'
|
|
|
83 ]]>
|
|
|
84 </command>
|
|
|
85 <inputs>
|
|
|
86 <param format="qza,no_unzip.zip" label="--i-table: FeatureTable[Frequency] Feature table containing all features that should be used for target prediction. [required]" name="itable" optional="False" type="data"/>
|
|
|
87
|
|
|
88 <repeat name="input_files_mmetadatafile" optional="False" title="--m-metadata-file">
|
|
|
89 <param label="--m-metadata-file: Metadata file or artifact viewable as metadata. This option may be supplied multiple times to merge metadata. [required]" name="additional_input" type="data" format="tabular,qza,no_unzip.zip" />
|
|
|
90 </repeat>
|
|
|
91
|
|
|
92 <param label="--p-column: Numeric metadata column to use as prediction target. [required]" name="pcolumn" optional="False" type="text"/>
|
|
|
93
|
|
|
94 <param label="--p-group-by: Categorical metadata column to use for plotting and significance testing between main treatment groups. [required]" name="pgroupby" optional="False" type="text"/>
|
|
|
95 <param label="--p-control: 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"/>
|
|
|
96
|
|
|
97 <param label="--p-estimator: Regression model to use for prediction.
|
|
|
98 [default: RandomForestRegressor]" name="pestimator" optional="True" type="select">
|
|
|
99 <option selected="True" value="None">Selection is Optional</option>
|
|
|
100 <option value="Ridge">Ridge</option>
|
|
|
101 <option value="RandomForestRegressor">RandomForestRegressor</option>
|
|
|
102 <option value="GradientBoostingRegressor">GradientBoostingRegressor</option>
|
|
|
103 <option value="ExtraTreesRegressor">ExtraTreesRegressor</option>
|
|
|
104 <option value="SVR">SVR</option>
|
|
|
105 <option value="ElasticNet">ElasticNet</option>
|
|
|
106 <option value="Lasso">Lasso</option>
|
|
|
107 </param>
|
|
|
108 <param label="--p-n-estimators: 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"/>
|
|
|
109
|
|
|
110 <param label="--p-test-size: Fraction of input samples to exclude from training set and use for classifier testing. [default: 0.2]" name="ptestsize" optional="True" type="float" value="0.2"/>
|
|
|
111
|
|
|
112 <param label="--p-step: 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" value="0.05"/>
|
|
|
113
|
|
|
114 <param label="--p-cv: Number of k-fold cross-validations to perform. [default: 5]" name="pcv" optional="True" type="integer" value="5"/>
|
|
|
115
|
|
|
116 <param label="--p-random-state: Seed used by random number generator. [optional]" name="prandomstate" optional="True" type="text"/>
|
|
|
117
|
|
|
118 <param label="--p-parameter-tuning: --p-no-parameter-tuning Automatically tune hyperparameters using random grid search. [default: True]" name="pparametertuning" checked="True" type="boolean"/>
|
|
|
119 <param label="--p-optimize-feature-selection: --p-no-optimize-feature-selection Automatically optimize input feature selection using recursive feature elimination. [default: True]" name="poptimizefeatureselection" checked="True" type="boolean"/>
|
|
|
120
|
|
|
121 <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" checked="False" type="boolean"/>
|
|
|
122
|
|
|
123 <param label="--p-maz-stats: --p-no-maz-stats Calculate anova and pairwise tests on MAZ scores. [default: True]" name="pmazstats" checked="True" type="boolean"/>
|
|
|
124
|
|
|
125 <param label="--cmd-config: Use config file for command options" name="cmdconfig" optional="True" type="data"/>
|
|
|
126 </inputs>
|
|
|
127 <outputs>
|
|
|
128 <data format="html" label="${tool.name} on ${on_string}: visualization.qzv" name="ovisualization"/>
|
|
|
129 </outputs>
|
|
|
130 <help>
|
|
|
131 <![CDATA[
|
|
|
132 Microbial maturity index prediction.
|
|
|
133 -------------------------------------
|
|
|
134
|
|
|
135 Calculates a "microbial maturity" index from a regression model trained on
|
|
|
136 feature data to predict a given continuous metadata column, e.g., to
|
|
|
137 predict age as a function of microbiota composition. The model is trained
|
|
|
138 on a subset of control group samples, then predicts the column value for
|
|
|
139 all samples. This visualization computes maturity index z-scores to compare
|
|
|
140 relative "maturity" between each group, as described in
|
|
|
141 doi:10.1038/nature13421. This method can be used to predict between-group
|
|
|
142 differences in relative trajectory across any type of continuous metadata
|
|
|
143 gradient, e.g., intestinal microbiome development by age, microbial
|
|
|
144 succession during wine fermentation, or microbial community differences
|
|
|
145 along environmental gradients, as a function of two or more different
|
|
|
146 "treatment" groups.
|
|
|
147
|
|
|
148 Parameters
|
|
|
149 ----------
|
|
|
150 table : FeatureTable[Frequency]
|
|
|
151 Feature table containing all features that should be used for target
|
|
|
152 prediction.
|
|
|
153 metadata : Metadata
|
|
|
154 \
|
|
|
155 column : Str
|
|
|
156 Numeric metadata column to use as prediction target.
|
|
|
157 group_by : Str
|
|
|
158 Categorical metadata column to use for plotting and significance
|
|
|
159 testing between main treatment groups.
|
|
|
160 control : Str
|
|
|
161 Value of group_by to use as control group. The regression model will be
|
|
|
162 trained using only control group data, and the maturity scores of other
|
|
|
163 groups consequently will be assessed relative to this group.
|
|
|
164 estimator : Str % Choices({'ElasticNet', 'ExtraTreesRegressor', 'GradientBoostingRegressor', 'Lasso', 'RandomForestRegressor', 'Ridge', 'SVR'}), optional
|
|
|
165 Regression model to use for prediction.
|
|
|
166 n_estimators : Int % Range(1, None), optional
|
|
|
167 Number of trees to grow for estimation. More trees will improve
|
|
|
168 predictive accuracy up to a threshold level, but will also increase
|
|
|
169 time and memory requirements. This parameter only affects ensemble
|
|
|
170 estimators, such as Random Forest, AdaBoost, ExtraTrees, and
|
|
|
171 GradientBoosting.
|
|
|
172 test_size : Float % Range(0.0, 1.0, inclusive_start=False), optional
|
|
|
173 Fraction of input samples to exclude from training set and use for
|
|
|
174 classifier testing.
|
|
|
175 step : Float % Range(0.0, 1.0, inclusive_start=False), optional
|
|
|
176 If optimize_feature_selection is True, step is the percentage of
|
|
|
177 features to remove at each iteration.
|
|
|
178 cv : Int % Range(1, None), optional
|
|
|
179 Number of k-fold cross-validations to perform.
|
|
|
180 random_state : Int, optional
|
|
|
181 Seed used by random number generator.
|
|
|
182 parameter_tuning : Bool, optional
|
|
|
183 Automatically tune hyperparameters using random grid search.
|
|
|
184 optimize_feature_selection : Bool, optional
|
|
|
185 Automatically optimize input feature selection using recursive feature
|
|
|
186 elimination.
|
|
|
187 stratify : Bool, optional
|
|
|
188 Evenly stratify training and test data among metadata categories. If
|
|
|
189 True, all values in column must match at least two samples.
|
|
|
190 maz_stats : Bool, optional
|
|
|
191 Calculate anova and pairwise tests on MAZ scores.
|
|
|
192
|
|
|
193 Returns
|
|
|
194 -------
|
|
|
195 visualization : Visualization
|
|
|
196 \
|
|
|
197 ]]>
|
|
|
198 </help>
|
|
|
199 <macros>
|
|
|
200 <import>qiime_citation.xml</import>
|
|
|
201 </macros>
|
|
|
202 <expand macro="qiime_citation" />
|
|
|
203 </tool>
|
