|
0
|
1 <tool id="copyrighter" name="CopyRighter" version="0.45">
|
|
|
2
|
|
|
3 <description>trait bias corrector for microbial profiles</description>
|
|
|
4
|
|
|
5 <requirements>
|
|
|
6 <requirement type="binary">copyrighter</requirement>
|
|
|
7 </requirements>
|
|
|
8
|
|
|
9 <version_string>copyrighter --version</version_string>
|
|
|
10
|
|
|
11 <command>
|
|
|
12 copyrighter
|
|
|
13 -i $input
|
|
|
14 -d $database.value
|
|
|
15 #if str($lookup):
|
|
|
16 -l $lookup
|
|
|
17 #end if
|
|
|
18 #if str($total) != "None":
|
|
|
19 -t $total
|
|
|
20 #end if
|
|
|
21 #if str($verbose):
|
|
|
22 -v
|
|
|
23 #end if
|
|
|
24 </command>
|
|
|
25
|
|
|
26 <inputs>
|
|
|
27 <param name="input" type="data" format="txt" label="Input community file" help="Text file obtained from 16S rRNA microarray, 16S rRNA amplicon sequencing or metagenomic sequencing, in biom, QIIME, GAAS, Unifrac, or generic (tabular site-by-species) format. The file must contain read counts (not percentages) and taxa must have UNALTERED taxonomic assignments." />
|
|
|
28 <conditional name="database">
|
|
|
29 <param name="specify" type="select" label="Trait database" help="Tab-delimited file of traits: 16S copy number, genome length, ...">
|
|
|
30 <option value="builtin">Built-in file</option>
|
|
|
31 <option value="uploaded">Uploaded file</option>
|
|
|
32 </param>
|
|
|
33 <when value="builtin">
|
|
|
34 <param name="value" type="select" label="Built-in file">
|
|
|
35 <options from_data_table="trait_db" />
|
|
|
36 <validator type="no_options" message="No built-in trait database is available"/>
|
|
|
37 </param>
|
|
|
38 </when>
|
|
|
39 <when value="uploaded">
|
|
|
40 <param name="value" type="data" format="tabular" label="Uploaded file" />
|
|
|
41 </when>
|
|
|
42 </conditional>
|
|
|
43 <param name="lookup" type="select" display="radio" value="desc" label="Lookup method" help="What to match when looking up the trait value of a taxon.">
|
|
|
44 <option value="desc">OTU name</option>
|
|
|
45 <option value="id">OTU ID (if recorded in your input community file)</option>
|
|
|
46 </param>
|
|
|
47 <param name="total" type="data" format="tabular" optional="true" label="Total abundance file" help="Tab-delimited file containing the total microbial abundance of each community, e.g. 16S rRNA quantitative PCR numbers to be corrected by the average 16S rRNA copy number." />
|
|
|
48 <param name="verbose" type="boolean" checked="no" truevalue="1" falsevalue="0" format="txt" label="Verbose" help="Display trait value assignments." />
|
|
|
49 </inputs>
|
|
|
50
|
|
|
51 <outputs>
|
|
|
52 <data format="txt" name="relative" from_work_dir="out_copyrighted.txt" label="${tool.name} from ${on_string} (relative)"/>
|
|
|
53 <data format="tabular" name="absolute" from_work_dir="out_copyrighted_total.tsv" label="${tool.name} from ${on_string} (absolute)">
|
|
|
54 <filter>str(total) != "None"</filter>
|
|
|
55 </data>
|
|
|
56 <data format="txt" name="combined" from_work_dir="out_copyrighted_combined.txt" label="${tool.name} from ${on_string} (combined)">
|
|
|
57 <filter>str(total) != "None"</filter>
|
|
|
58 </data>
|
|
|
59 </outputs>
|
|
|
60
|
|
|
61 <stdio>
|
|
|
62 <exit_code range="1:" level="fatal" />
|
|
|
63 <regex match="error|exception|invalid" source="stderr" level="fatal" />
|
|
|
64 </stdio>
|
|
|
65
|
|
|
66 <tests>
|
|
|
67 <test>
|
|
|
68 <param name="input" value="test_data/in.qiime" />
|
|
|
69 <param name="specify" value="uploaded"/>
|
|
|
70 <param name="value" value="test_data/in_db.tsv"/>
|
|
|
71 <output name="relative" file="test_data/out.qiime"/>
|
|
|
72 </test>
|
|
|
73 <test>
|
|
|
74 <param name="input" value="test_data/in.biom"/>
|
|
|
75 <param name="specify" value="uploaded"/>
|
|
|
76 <param name="value" value="test_data/in_db.tsv"/>
|
|
|
77 <output name="relative" file="test_data/out.biom" lines_diff="2"/>
|
|
|
78 </test>
|
|
|
79 <test>
|
|
|
80 <param name="input" value="test_data/in.qiime"/>
|
|
|
81 <param name="specify" value="uploaded"/>
|
|
|
82 <param name="value" value="test_data/in_db.tsv"/>
|
|
|
83 <param name="verbose" value="yes"/>
|
|
|
84 <output name="relative" file="test_data/out.qiime"/>
|
|
|
85 </test>
|
|
|
86 <test>
|
|
|
87 <param name="input" value="test_data/in.biom"/>
|
|
|
88 <param name="specify" value="uploaded"/>
|
|
|
89 <param name="value" value="test_data/in_db.tsv"/>
|
|
|
90 <param name="lookup" value="id"/>
|
|
|
91 <output name="relative" file="test_data/out2.biom" lines_diff="2"/>
|
|
|
92 </test>
|
|
|
93 <test>
|
|
|
94 <param name="input" value="test_data/in.qiime"/>
|
|
|
95 <param name="specify" value="uploaded"/>
|
|
|
96 <param name="value" value="test_data/in_db.tsv"/>
|
|
|
97 <param name="total" value="test_data/in_total.tsv"/>
|
|
|
98 <output name="relative" file="test_data/out.qiime"/>
|
|
|
99 <output name="absolute" file="test_data/out_total.tsv"/>
|
|
|
100 <output name="combined" file="test_data/out_combined.qiime"/>
|
|
|
101 </test>
|
|
|
102 <!--<test>
|
|
|
103 <param name="input" value="test_data/in.biom"/>
|
|
|
104 <param name="specify" value="builtin"/>
|
|
|
105 <param name="value" value="test_data/in_db.tsv"/>
|
|
|
106 <output name="relative" file="test_data/out.biom" lines_diff="2"/>
|
|
|
107 </test>-->
|
|
|
108 </tests>
|
|
|
109
|
|
|
110 <help>
|
|
|
111 **What CopyRighter does**
|
|
|
112
|
|
|
113 The genome of Bacteria and Archaea often contains several copies of the
|
|
|
114 16S rRNA gene. This can lead to significant biases when estimating the
|
|
|
115 composition of microbial communities using 16S rRNA amplicons or
|
|
|
116 microarrays or their total abundance using 16S rRNA quantitative PCR,
|
|
|
117 since species with a large number of copies will contribute
|
|
|
118 disproportionally more 16S amplicons than species with a unique copy.
|
|
|
119 Fortunately, it is possible to infer the copy number of unsequenced
|
|
|
120 microbial species, based on that of close relatives that have been fully
|
|
|
121 sequenced. Using this information, CopyRigher corrects microbial
|
|
|
122 relative abundance by applying a weight proportional to the inverse of
|
|
|
123 the estimated copy number to each species.
|
|
|
124
|
|
|
125 In metagenomic surveys, a similar problem arises due to genome length
|
|
|
126 variations between species, and can be corrected by CopyRighter as well.
|
|
|
127
|
|
|
128 In all cases, a community file is used as input and a corrected community
|
|
|
129 file with trait-corrected (16S rRNA gene copy number or genome length)
|
|
|
130 relative abundances is generated. Total abundance can optionally be
|
|
|
131 provided, corrected and combined with relative abundance estimates to
|
|
|
132 get the absolute abundance of each species. Also the average trait value
|
|
|
133 in each community is reported on standard output.
|
|
|
134 </help>
|
|
|
135
|
|
|
136 </tool>
|
|
|
137
|
