Mercurial > repos > frogs > frogs_2_0_0
comparison remove_chimera.xml @ 0:76c750c5f0d1 draft default tip
planemo upload for repository https://github.com/oinizan/FROGS-wrappers commit 0b900a51e220ce6f17c1e76292c06a5f4d934055-dirty
author | frogs |
---|---|
date | Thu, 25 Oct 2018 05:01:13 -0400 |
parents | |
children |
comparison
equal
deleted
inserted
replaced
-1:000000000000 | 0:76c750c5f0d1 |
---|---|
1 <?xml version="1.0"?> | |
2 <!-- | |
3 # Copyright (C) 2015 INRA | |
4 # | |
5 # This program is free software: you can redistribute it and/or modify | |
6 # it under the terms of the GNU General Public License as published by | |
7 # the Free Software Foundation, either version 3 of the License, or | |
8 # (at your option) any later version. | |
9 # | |
10 # This program is distributed in the hope that it will be useful, | |
11 # but WITHOUT ANY WARRANTY; without even the implied warranty of | |
12 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the | |
13 # GNU General Public License for more details. | |
14 # | |
15 # You should have received a copy of the GNU General Public License | |
16 # along with this program. If not, see <http://www.gnu.org/licenses/>. | |
17 --> | |
18 <tool id="FROGS_remove_chimera" name="FROGS Remove chimera" version="1.3.0"> | |
19 <description>Step 3 in metagenomics analysis : Remove PCR chimera in each sample.</description> | |
20 <requirements> | |
21 <requirement type="package" version="2.0.1">frogs</requirement> | |
22 </requirements> | |
23 <stdio> | |
24 <exit_code range="1:" /> | |
25 <exit_code range=":-1" /> | |
26 </stdio> | |
27 <command> | |
28 remove_chimera.py | |
29 --nb-cpus $nb_cpus | |
30 --input-fasta $sequence_file --non-chimera $non_chimera_fasta | |
31 --summary $summary_file | |
32 #if $abundance_type.abundance_type_selected == "biom" | |
33 --input-biom $abundance_biom | |
34 --out-abundance $out_abundance_biom | |
35 #else | |
36 --input-count $abundance_count | |
37 --out-abundance $out_abundance_count | |
38 #end if | |
39 </command> | |
40 <inputs> | |
41 <!-- Files --> | |
42 <param format="fasta" name="sequence_file" type="data" label="Sequences file" help="The sequences file (format: fasta)." optional="false" /> | |
43 <conditional name="abundance_type"> | |
44 <param name="abundance_type_selected" type="select" label="Abundance type" help="Select the type of file where the abundance of each sequence by sample is stored."> | |
45 <option value="biom" selected="true">BIOM file</option> | |
46 <option value="count">TSV file</option> | |
47 </param> | |
48 <when value="biom"> | |
49 <param format="biom1" name="abundance_biom" type="data" label="Abundance file" help="It contains the count by sample for each sequence." optional="false" /> | |
50 </when> | |
51 <when value="count"> | |
52 <param format="tabular" name="abundance_count" type="data" label="Count file" help="It contains the count by sample for each sequence (see below)." optional="false" /> | |
53 </when> | |
54 </conditional> | |
55 <!-- Parameters --> | |
56 <param name="nb_cpus" type="hidden" label="CPU number" help="The maximum number of CPUs used." value="1" /> | |
57 <!-- | |
58 <param name="size_separator" type="text" label="Size separator" help="Fill this input only if the IDs of sequences in fasta store the abundance as suffix. Example: 'Cluster_1;size=10' => ';size='" value="" optional="true" /> | |
59 --> | |
60 </inputs> | |
61 <outputs> | |
62 <data format="fasta" name="non_chimera_fasta" label="${tool.name}: non_chimera.fasta" from_work_dir="non_chimera.fasta"/> | |
63 <data format="biom1" name="out_abundance_biom" label="${tool.name}: non_chimera_abundance.biom" from_work_dir="non_chimera_abundance.biom"> | |
64 <filter>abundance_type['abundance_type_selected'] == "biom"</filter> | |
65 </data> | |
66 <data format="tabular" name="out_abundance_count" label="${tool.name}: non_chimera_abundance.tsv" from_work_dir="non_chimera_abundance.tsv"> | |
67 <filter>abundance_type['abundance_type_selected'] == "count"</filter> | |
68 </data> | |
69 <data format="html" name="summary_file" label="${tool.name}: report.html" from_work_dir="report.html"/> | |
70 </outputs> | |
71 <tests> | |
72 <test> | |
73 <param name="sequence_file" value="references/02-clustering.fasta"/> | |
74 <conditional name="abundance_type"> | |
75 <param name="abundance_type_selected" value="biom"/> | |
76 <param name="abundance_biom" value="references/02-clustering.biom" /> | |
77 </conditional> | |
78 <output name="non_chimera_fasta" file="references/03-chimera.fasta"/> | |
79 </test> | |
80 </tests> | |
81 <help> | |
82 | |
83 .. image:: static/images/FROGS_logo.png | |
84 :height: 144 | |
85 :width: 110 | |
86 | |
87 | |
88 .. class:: infomark page-header h2 | |
89 | |
90 What it does | |
91 | |
92 Remove chimeric sequences by sample. | |
93 | |
94 | |
95 .. class:: infomark page-header h2 | |
96 | |
97 Context | |
98 | |
99 Chimeras are sequences formed from two or more biological sequences joined together. | |
100 | |
101 The majority of these anomalous sequences are formed from an incomplete extension during a PCR cycle. During subsequent cycles, a partially extended strand can bind to a template derived from a different but similar sequence. | |
102 | |
103 This phenomena is particularly common in amplicon sequencing where closely related sequences are amplified. | |
104 | |
105 | |
106 .. class:: infomark page-header h2 | |
107 | |
108 Inputs/Outputs | |
109 | |
110 .. class:: h3 | |
111 | |
112 Inputs | |
113 | |
114 **Sequence file**: | |
115 | |
116 The sequences (format `FASTA <https://en.wikipedia.org/wiki/FASTA_format>`_). | |
117 | |
118 **Abundance file**: | |
119 | |
120 The abundance of each cluster in each sample (format `BIOM <http://biom-format.org/>`_). | |
121 | |
122 OR | |
123 | |
124 The abundance of each sequence in each sample (format `TSV <https://en.wikipedia.org/wiki/Tab-separated_values>`_). This type of file is produced by *FROGS pre-process*. | |
125 | |
126 Example:: | |
127 | |
128 #id splA splB | |
129 seq1 1289 2901 | |
130 seq2 3415 0 | |
131 | |
132 .. class:: h3 | |
133 | |
134 Outputs | |
135 | |
136 **Sequence file** (non_chimera.fasta): | |
137 | |
138 The sequence file with only non-chimera (format `FASTA <https://en.wikipedia.org/wiki/FASTA_format>`_). | |
139 | |
140 **Abundance file** (non_chimera.biom or non_chimera.tsv): | |
141 | |
142 The abundance file with only non-chimera (format the same of the abundance input). | |
143 | |
144 **Summary file** (report.html): | |
145 | |
146 This file presents the number of removed elements (format `HTML <https://en.wikipedia.org/wiki/HTML>`_). | |
147 | |
148 | |
149 .. class:: infomark page-header h2 | |
150 | |
151 How it works | |
152 | |
153 .. csv-table:: | |
154 :header: "Steps", "Description" | |
155 :widths: 10, 90 | |
156 :class: table table-striped | |
157 | |
158 "1", "Split input data by sample (classicaly the PCR is realised by sample)." | |
159 "2", "Find chimera in each sample (`vsearch <https://github.com/torognes/vsearch>`_)." | |
160 "3", "Remove the sequences identify as chimera in all samples where they are present." | |
161 | |
162 | |
163 ---- | |
164 | |
165 **Contact** | |
166 | |
167 Contacts: frogs@inra.fr | |
168 | |
169 Repository: https://github.com/geraldinepascal/FROGS | |
170 | |
171 Please cite the FROGS Publication: *Escudie F., Auer L., Bernard M., Cauquil L., Vidal K., Maman S., Mariadassou M., Hernadez-Raquet G., Pascal G., 2015. FROGS: Find Rapidly OTU with Galaxy Solution. In: The environmental genomic Conference, Montpellier, France,* http://bioinfo.genotoul.fr/fileadmin/user_upload/FROGS_2015_GE_Montpellier_poster.pdf | |
172 | |
173 Depending on the help provided you can cite us in acknowledgements, references or both. | |
174 </help> | |
175 <citations> | |
176 <citation type="doi">10.7287/peerj.preprints.386v1</citation> | |
177 </citations> | |
178 </tool> |