|
29
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_quality-control_evaluate-composition" name="qiime quality-control evaluate-composition"
|
|
|
3 version="2020.8">
|
|
|
4 <description>Evaluate expected vs. observed taxonomic composition of samples</description>
|
|
|
5 <requirements>
|
|
|
6 <requirement type="package" version="2020.8">qiime2</requirement>
|
|
|
7 </requirements>
|
|
|
8 <command><![CDATA[
|
|
|
9 qiime quality-control evaluate-composition
|
|
|
10
|
|
|
11 --i-expected-features=$iexpectedfeatures
|
|
|
12
|
|
|
13 --i-observed-features=$iobservedfeatures
|
|
|
14
|
|
|
15 --p-depth=$pdepth
|
|
|
16
|
|
|
17 #if str($ppalette) != 'None':
|
|
|
18 --p-palette=$ppalette
|
|
|
19 #end if
|
|
|
20
|
|
|
21 #if $pnoplottar:
|
|
|
22 --p-no-plot-tar
|
|
|
23 #end if
|
|
|
24
|
|
|
25 #if $pnoplottdr:
|
|
|
26 --p-no-plot-tdr
|
|
|
27 #end if
|
|
|
28
|
|
|
29 #if $pplotrvalue:
|
|
|
30 --p-plot-r-value
|
|
|
31 #end if
|
|
|
32
|
|
|
33 #if $pnoplotrsquared:
|
|
|
34 --p-no-plot-r-squared
|
|
|
35 #end if
|
|
|
36
|
|
|
37 #if $pplotbraycurtis:
|
|
|
38 --p-plot-bray-curtis
|
|
|
39 #end if
|
|
|
40
|
|
|
41 #if $pplotjaccard:
|
|
|
42 --p-plot-jaccard
|
|
|
43 #end if
|
|
|
44
|
|
|
45 #if $pplotobservedfeatures:
|
|
|
46 --p-plot-observed-features
|
|
|
47 #end if
|
|
|
48
|
|
|
49 #if $pnoplotobservedfeaturesratio:
|
|
|
50 --p-no-plot-observed-features-ratio
|
|
|
51 #end if
|
|
|
52 # if $input_files_mmetadatafile:
|
|
|
53 # def list_dict_to_string(list_dict):
|
|
|
54 # set $file_list = list_dict[0]['additional_input'].__getattr__('file_name')
|
|
|
55 # for d in list_dict[1:]:
|
|
|
56 # set $file_list = $file_list + ' --m-metadata-file=' + d['additional_input'].__getattr__('file_name')
|
|
|
57 # end for
|
|
|
58 # return $file_list
|
|
|
59 # end def
|
|
|
60 --m-metadata-file=$list_dict_to_string($input_files_mmetadatafile)
|
|
|
61 # end if
|
|
|
62
|
|
|
63 #if '__ob__' in str($mmetadatacolumn):
|
|
|
64 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__ob__', '[')
|
|
|
65 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
|
66 #end if
|
|
|
67 #if '__cb__' in str($mmetadatacolumn):
|
|
|
68 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__cb__', ']')
|
|
|
69 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
|
70 #end if
|
|
|
71 #if 'X' in str($mmetadatacolumn):
|
|
|
72 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('X', '\\')
|
|
|
73 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
|
74 #end if
|
|
|
75 #if '__sq__' in str($mmetadatacolumn):
|
|
|
76 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__sq__', "'")
|
|
|
77 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
|
78 #end if
|
|
|
79 #if '__db__' in str($mmetadatacolumn):
|
|
|
80 #set $mmetadatacolumn_temp = $mmetadatacolumn.replace('__db__', '"')
|
|
|
81 #set $mmetadatacolumn = $mmetadatacolumn_temp
|
|
|
82 #end if
|
|
|
83
|
|
|
84 #if str($mmetadatacolumn):
|
|
|
85 --m-metadata-column=$mmetadatacolumn
|
|
|
86 #end if
|
|
|
87
|
|
|
88 --o-visualization=ovisualization
|
|
|
89
|
|
|
90 #if str($examples) != 'None':
|
|
|
91 --examples=$examples
|
|
|
92 #end if
|
|
|
93
|
|
|
94 ;
|
|
|
95 cp odatabase.qza $odatabase
|
|
|
96
|
|
|
97 ;
|
|
|
98 qiime tools export ovisualization.qzv --output-path out
|
|
|
99 && mkdir -p '$ovisualization.files_path'
|
|
|
100 && cp -r out/* '$ovisualization.files_path'
|
|
|
101 && mv '$ovisualization.files_path/index.html' '$ovisualization'
|
|
|
102
|
|
|
103 ]]></command>
|
|
|
104 <inputs>
|
|
|
105 <param format="qza,no_unzip.zip" label="--i-expected-features: ARTIFACT FeatureTable[RelativeFrequency] Expected feature compositions [required]" name="iexpectedfeatures" optional="False" type="data" />
|
|
|
106 <param format="qza,no_unzip.zip" label="--i-observed-features: ARTIFACT FeatureTable[RelativeFrequency] Observed feature compositions [required]" name="iobservedfeatures" optional="False" type="data" />
|
|
|
107 <param label="--p-depth: INTEGER Maximum depth of semicolon-delimited taxonomic ranks to test (e.g., 1 = root, 7 = species for the greengenes reference sequence database). [default: 7]" name="pdepth" optional="True" type="integer" value="7" />
|
|
|
108 <param label="--p-palette: " name="ppalette" optional="True" type="select">
|
|
|
109 <option selected="True" value="None">Selection is Optional</option>
|
|
|
110 <option value="Set1">Set1</option>
|
|
|
111 <option value="Set2">Set2</option>
|
|
|
112 <option value="Set3">Set3</option>
|
|
|
113 <option value="Pastel1">Pastel1</option>
|
|
|
114 <option value="Pastel2">Pastel2</option>
|
|
|
115 <option value="Paired">Paired</option>
|
|
|
116 <option value="Accent">Accent</option>
|
|
|
117 <option value="Dark2">Dark2</option>
|
|
|
118 <option value="tab10">tab10</option>
|
|
|
119 <option value="tab20">tab20</option>
|
|
|
120 <option value="tab20b">tab20b</option>
|
|
|
121 <option value="tab20c">tab20c</option>
|
|
|
122 <option value="viridis">viridis</option>
|
|
|
123 <option value="plasma">plasma</option>
|
|
|
124 <option value="inferno">inferno</option>
|
|
|
125 <option value="magma">magma</option>
|
|
|
126 <option value="terrain">terrain</option>
|
|
|
127 <option value="rainbow">rainbow</option>
|
|
|
128 </param>
|
|
|
129 <param label="--p-no-plot-tar: Do not plot taxon accuracy rate (TAR) on score plot. TAR is the number of true positive features divided by the total number of observed features (TAR = true positives / (true positives + false positives)). [default: True]" name="pnoplottar" selected="False" type="boolean" />
|
|
|
130 <param label="--p-no-plot-tdr: Do not plot taxon detection rate (TDR) on score plot. TDR is the number of true positive features divided by the total number of expected features (TDR = true positives / (true positives + false negatives)). [default: True]" name="pnoplottdr" selected="False" type="boolean" />
|
|
|
131 <param label="--p-plot-r-value: --p-plot-r-value: / --p-no-plot-r-value Plot expected vs. observed linear regression r value on score plot. [default: False]" name="pplotrvalue" selected="False" type="boolean" />
|
|
|
132 <param label="--p-no-plot-r-squared: Do not plot expected vs. observed linear regression r-squared value on score plot. [default: True]" name="pnoplotrsquared" selected="False" type="boolean" />
|
|
|
133 <param label="--p-plot-bray-curtis: --p-plot-bray-curtis: / --p-no-plot-bray-curtis Plot expected vs. observed Bray-Curtis dissimilarity scores on score plot. [default: False]" name="pplotbraycurtis" selected="False" type="boolean" />
|
|
|
134 <param label="--p-plot-jaccard: --p-plot-jaccard: / --p-no-plot-jaccard Plot expected vs. observed Jaccard distances scores on score plot. [default: False]" name="pplotjaccard" selected="False" type="boolean" />
|
|
|
135 <param label="--p-plot-observed-features: --p-plot-observed-features: / --p-no-plot-observed-features Plot observed features count on score plot. [default: False]" name="pplotobservedfeatures" selected="False" type="boolean" />
|
|
|
136 <param label="--p-no-plot-observed-features-ratio: Do not plot ratio of observed:expected features on score plot. [default: True]" name="pnoplotobservedfeaturesratio" selected="False" type="boolean" />
|
|
|
137 <repeat name="input_files_mmetadatafile" optional="True" title="--m-metadata-file">
|
|
|
138 <param format="tabular,qza,no_unzip.zip" label="--m-metadata-file: METADATA" name="additional_input" optional="True" type="data" />
|
|
|
139 </repeat>
|
|
|
140 <param label="--m-metadata-column: COLUMN MetadataColumn[Categorical] Optional sample metadata that maps observed-features sample IDs to expected-features sample IDs. [optional]" name="mmetadatacolumn" optional="False" type="text" />
|
|
|
141 <param label="--examples: Show usage examples and exit." name="examples" optional="False" type="data" />
|
|
|
142
|
|
|
143 </inputs>
|
|
|
144
|
|
|
145 <outputs>
|
|
|
146 <data format="html" label="${tool.name} on ${on_string}: visualization.html" name="ovisualization" />
|
|
|
147
|
|
|
148 </outputs>
|
|
|
149
|
|
|
150 <help><![CDATA[
|
|
|
151 Evaluate expected vs. observed taxonomic composition of samples
|
|
|
152 ###############################################################
|
|
|
153
|
|
|
154 This visualizer compares the feature composition of pairs of observed and
|
|
|
155 expected samples containing the same sample ID in two separate feature
|
|
|
156 tables. Typically, feature composition will consist of taxonomy
|
|
|
157 classifications or other semicolon-delimited feature annotations. Taxon
|
|
|
158 accuracy rate, taxon detection rate, and linear regression scores between
|
|
|
159 expected and observed observations are calculated at each semicolon-
|
|
|
160 delimited rank, and plots of per-level accuracy and observation
|
|
|
161 correlations are plotted. A histogram of distance between false positive
|
|
|
162 observations and the nearest expected feature is also generated, where
|
|
|
163 distance equals the number of rank differences between the observed feature
|
|
|
164 and the nearest common lineage in the expected feature. This visualizer is
|
|
|
165 most suitable for testing per-run data quality on sequencing runs that
|
|
|
166 contain mock communities or other samples with known composition. Also
|
|
|
167 suitable for sanity checks of bioinformatics pipeline performance.
|
|
|
168
|
|
|
169 Parameters
|
|
|
170 ----------
|
|
|
171 expected_features : FeatureTable[RelativeFrequency]
|
|
|
172 Expected feature compositions
|
|
|
173 observed_features : FeatureTable[RelativeFrequency]
|
|
|
174 Observed feature compositions
|
|
|
175 depth : Int, optional
|
|
|
176 Maximum depth of semicolon-delimited taxonomic ranks to test (e.g., 1 =
|
|
|
177 root, 7 = species for the greengenes reference sequence database).
|
|
|
178 palette : Str % Choices('Set1', 'Set2', 'Set3', 'Pastel1', 'Pastel2', 'Paired', 'Accent', 'Dark2', 'tab10', 'tab20', 'tab20b', 'tab20c', 'viridis', 'plasma', 'inferno', 'magma', 'terrain', 'rainbow'), optional
|
|
|
179 Color palette to utilize for plotting.
|
|
|
180 plot_tar : Bool, optional
|
|
|
181 Plot taxon accuracy rate (TAR) on score plot. TAR is the number of true
|
|
|
182 positive features divided by the total number of observed features (TAR
|
|
|
183 = true positives / (true positives + false positives)).
|
|
|
184 plot_tdr : Bool, optional
|
|
|
185 Plot taxon detection rate (TDR) on score plot. TDR is the number of
|
|
|
186 true positive features divided by the total number of expected features
|
|
|
187 (TDR = true positives / (true positives + false negatives)).
|
|
|
188 plot_r_value : Bool, optional
|
|
|
189 Plot expected vs. observed linear regression r value on score plot.
|
|
|
190 plot_r_squared : Bool, optional
|
|
|
191 Plot expected vs. observed linear regression r-squared value on score
|
|
|
192 plot.
|
|
|
193 plot_bray_curtis : Bool, optional
|
|
|
194 Plot expected vs. observed Bray-Curtis dissimilarity scores on score
|
|
|
195 plot.
|
|
|
196 plot_jaccard : Bool, optional
|
|
|
197 Plot expected vs. observed Jaccard distances scores on score plot.
|
|
|
198 plot_observed_features : Bool, optional
|
|
|
199 Plot observed features count on score plot.
|
|
|
200 plot_observed_features_ratio : Bool, optional
|
|
|
201 Plot ratio of observed:expected features on score plot.
|
|
|
202 metadata : MetadataColumn[Categorical], optional
|
|
|
203 Optional sample metadata that maps observed_features sample IDs to
|
|
|
204 expected_features sample IDs.
|
|
|
205
|
|
|
206 Returns
|
|
|
207 -------
|
|
|
208 visualization : Visualization
|
|
|
209 ]]></help>
|
|
|
210 <macros>
|
|
|
211 <import>qiime_citation.xml</import>
|
|
|
212 </macros>
|
|
|
213 <expand macro="qiime_citation"/>
|
|
|
214 </tool> |
