|
2
|
1 <?xml version="1.0" ?>
|
|
|
2 <tool id="qiime_quality-control_evaluate-composition" name="qiime quality-control evaluate-composition" version="2019.4">
|
|
|
3 <description> - Evaluate expected vs. observed taxonomic composition of samples</description>
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="2019.4">qiime2</requirement>
|
|
|
6 </requirements>
|
|
|
7 <command><![CDATA[
|
|
|
8 qiime quality-control evaluate-composition
|
|
|
9
|
|
|
10 --i-expected-features=$iexpectedfeatures
|
|
|
11 --i-observed-features=$iobservedfeatures
|
|
|
12
|
|
4
|
13
|
|
|
14 #if $metadatafile:
|
|
|
15 --m-metadata-file=$metadatafile
|
|
2
|
16 #end if
|
|
|
17
|
|
|
18
|
|
4
|
19 #if str($pdepth):
|
|
2
|
20 --p-depth=$pdepth
|
|
|
21 #end if
|
|
|
22
|
|
|
23 #if str($ppalette) != 'None':
|
|
|
24 --p-palette=$ppalette
|
|
|
25 #end if
|
|
|
26
|
|
|
27 #if $pplottar:
|
|
|
28 --p-plot-tar
|
|
|
29 #end if
|
|
|
30
|
|
|
31 #if $pplottdr:
|
|
|
32 --p-plot-tdr
|
|
|
33 #end if
|
|
|
34
|
|
|
35 #if $pplotrvalue:
|
|
|
36 --p-plot-r-value
|
|
|
37 #end if
|
|
|
38
|
|
|
39 #if $pnoplotrsquared:
|
|
|
40 --p-no-plot-r-squared
|
|
|
41 #end if
|
|
|
42
|
|
|
43 #if $pplotbraycurtis:
|
|
|
44 --p-plot-bray-curtis
|
|
|
45 #end if
|
|
|
46
|
|
|
47 #if $pplotjaccard:
|
|
|
48 --p-plot-jaccard
|
|
|
49 #end if
|
|
|
50
|
|
|
51 #if $pplotobservedfeatures:
|
|
|
52 --p-plot-observed-features
|
|
|
53 #end if
|
|
|
54
|
|
4
|
55 #if $pnoplotobservedfeaturesratio:
|
|
|
56 --p-no-plot-observed-features-ratio
|
|
2
|
57 #end if
|
|
|
58
|
|
|
59 #if str($mmetadatacolumn):
|
|
|
60 --m-metadata-column="$mmetadatacolumn"
|
|
|
61 #end if
|
|
|
62
|
|
|
63 --o-visualization=ovisualization
|
|
|
64 ;
|
|
|
65 qiime tools export --input-path ovisualization.qzv --output-path out && mkdir -p '$ovisualization.files_path'
|
|
|
66 && cp -r out/* '$ovisualization.files_path'
|
|
|
67 && mv '$ovisualization.files_path/index.html' '$ovisualization'
|
|
|
68 ]]></command>
|
|
|
69 <inputs>
|
|
|
70 <param format="qza,no_unzip.zip" label="--i-expected-features: ARTIFACT FeatureTable[RelativeFrequency] Expected feature compositions [required]" name="iexpectedfeatures" optional="False" type="data"/>
|
|
|
71 <param format="qza,no_unzip.zip" label="--i-observed-features: ARTIFACT FeatureTable[RelativeFrequency] Observed feature compositions [required]" name="iobservedfeatures" optional="False" type="data"/>
|
|
|
72 <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"/>
|
|
|
73 <param label="--p-palette: " name="ppalette" optional="True" type="select">
|
|
|
74 <option selected="True" value="None">Selection is Optional</option>
|
|
|
75 <option value="Set1">Set1</option>
|
|
|
76 <option value="Set2">Set2</option>
|
|
|
77 <option value="Set3">Set3</option>
|
|
|
78 <option value="Pastel1">Pastel1</option>
|
|
|
79 <option value="Pastel2">Pastel2</option>
|
|
|
80 <option value="Paired">Paired</option>
|
|
|
81 <option value="Accent">Accent</option>
|
|
|
82 <option value="Dark2">Dark2</option>
|
|
|
83 <option value="tab10">tab10</option>
|
|
|
84 <option value="tab20">tab20</option>
|
|
|
85 <option value="tab20b">tab20b</option>
|
|
|
86 <option value="tab20c">tab20c</option>
|
|
|
87 <option value="viridis">viridis</option>
|
|
|
88 <option value="plasma">plasma</option>
|
|
|
89 <option value="inferno">inferno</option>
|
|
|
90 <option value="magma">magma</option>
|
|
|
91 <option value="terrain">terrain</option>
|
|
|
92 <option value="rainbow">rainbow</option>
|
|
|
93 </param>
|
|
|
94 <param label="--p-plot-tar: --p-no-plot-tar 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 " name="pplottar" selected="False" type="boolean"/>
|
|
|
95 <param label="--p-plot-tdr: --p-no-plot-tdr 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 " name="pplottdr" selected="False" type="boolean"/>
|
|
|
96 <param label="--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"/>
|
|
|
97 <param label="--p-no-plot-r-squared: Do not plot expected vs. observed linear regression r-squared value on score plot. [default: False]" name="pnoplotrsquared" selected="False" type="boolean"/>
|
|
|
98 <param label="--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"/>
|
|
|
99 <param label="--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"/>
|
|
|
100 <param label="--p-plot-observed-features: --p-no-plot-observed-features Plot observed features count on score plot. [default: False]" name="pplotobservedfeatures" selected="False" type="boolean"/>
|
|
|
101 <param label="--p-no-plot-observed-features-ratio: Do not plot ratio of observed:expected features on score plot. [default: False]" name="pnoplotobservedfeaturesratio" selected="False" type="boolean"/>
|
|
|
102 <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="True" type="text"/>
|
|
|
103
|
|
4
|
104 <param label="--m-metadata-file METADATA" name="metadatafile" type="data" format="tabular,qza,no_unzip.zip" />
|
|
|
105
|
|
2
|
106
|
|
|
107 </inputs>
|
|
|
108 <outputs>
|
|
|
109 <data format="html" label="${tool.name} on ${on_string}: visualization.qzv" name="ovisualization"/>
|
|
|
110 </outputs>
|
|
|
111 <help><![CDATA[
|
|
|
112 Evaluate expected vs. observed taxonomic composition of samples
|
|
|
113 ###############################################################
|
|
|
114
|
|
|
115 This visualizer compares the feature composition of pairs of observed and
|
|
|
116 expected samples containing the same sample ID in two separate feature
|
|
|
117 tables. Typically, feature composition will consist of taxonomy
|
|
|
118 classifications or other semicolon-delimited feature annotations. Taxon
|
|
|
119 accuracy rate, taxon detection rate, and linear regression scores between
|
|
|
120 expected and observed observations are calculated at each semicolon-
|
|
|
121 delimited rank, and plots of per-level accuracy and observation
|
|
|
122 correlations are plotted. A histogram of distance between false positive
|
|
|
123 observations and the nearest expected feature is also generated, where
|
|
|
124 distance equals the number of rank differences between the observed feature
|
|
|
125 and the nearest common lineage in the expected feature. This visualizer is
|
|
|
126 most suitable for testing per-run data quality on sequencing runs that
|
|
|
127 contain mock communities or other samples with known composition. Also
|
|
|
128 suitable for sanity checks of bioinformatics pipeline performance.
|
|
|
129
|
|
|
130 Parameters
|
|
|
131 ----------
|
|
|
132 expected_features : FeatureTable[RelativeFrequency]
|
|
|
133 Expected feature compositions
|
|
|
134 observed_features : FeatureTable[RelativeFrequency]
|
|
|
135 Observed feature compositions
|
|
|
136 depth : Int, optional
|
|
|
137 Maximum depth of semicolon-delimited taxonomic ranks to test (e.g., 1 =
|
|
|
138 root, 7 = species for the greengenes reference sequence database).
|
|
|
139 palette : Str % Choices('Set1', 'Set2', 'Set3', 'Pastel1', 'Pastel2', 'Paired', 'Accent', 'Dark2', 'tab10', 'tab20', 'tab20b', 'tab20c', 'viridis', 'plasma', 'inferno', 'magma', 'terrain', 'rainbow'), optional
|
|
|
140 Color palette to utilize for plotting.
|
|
|
141 plot_tar : Bool, optional
|
|
|
142 Plot taxon accuracy rate (TAR) on score plot. TAR is the number of true
|
|
|
143 positive features divided by the total number of observed features (TAR
|
|
|
144 = true positives / (true positives + false positives)).
|
|
|
145 plot_tdr : Bool, optional
|
|
|
146 Plot taxon detection rate (TDR) on score plot. TDR is the number of
|
|
|
147 true positive features divided by the total number of expected features
|
|
|
148 (TDR = true positives / (true positives + false negatives)).
|
|
|
149 plot_r_value : Bool, optional
|
|
|
150 Plot expected vs. observed linear regression r value on score plot.
|
|
|
151 plot_r_squared : Bool, optional
|
|
|
152 Plot expected vs. observed linear regression r-squared value on score
|
|
|
153 plot.
|
|
|
154 plot_bray_curtis : Bool, optional
|
|
|
155 Plot expected vs. observed Bray-Curtis dissimilarity scores on score
|
|
|
156 plot.
|
|
|
157 plot_jaccard : Bool, optional
|
|
|
158 Plot expected vs. observed Jaccard distances scores on score plot.
|
|
|
159 plot_observed_features : Bool, optional
|
|
|
160 Plot observed features count on score plot.
|
|
|
161 plot_observed_features_ratio : Bool, optional
|
|
|
162 Plot ratio of observed:expected features on score plot.
|
|
|
163 metadata : MetadataColumn[Categorical], optional
|
|
|
164 Optional sample metadata that maps observed_features sample IDs to
|
|
|
165 expected_features sample IDs.
|
|
|
166
|
|
|
167 Returns
|
|
|
168 -------
|
|
|
169 visualization : Visualization
|
|
|
170 ]]></help>
|
|
|
171 <macros>
|
|
|
172 <import>qiime_citation.xml</import>
|
|
|
173 </macros>
|
|
|
174 <expand macro="qiime_citation"/>
|
|
|
175 </tool>
|
