Mercurial > repos > frogs > frogs
view remove_chimera.xml @ 3:8edcbafb3b4e draft
"planemo upload for repository https://github.com/geraldinepascal/FROGS-wrappers/ commit 2024a13846ea6f9bd94ae62e3b2a5a3aba8cd304-dirty"
author | frogs |
---|---|
date | Tue, 24 Aug 2021 08:21:23 +0000 |
parents | 094a2469204d |
children | 445b04a65ed8 |
line wrap: on
line source
<?xml version="1.0"?> <!-- # Copyright (C) 2015 INRA # # This program is free software: you can redistribute it and/or modify # it under the terms of the GNU General Public License as published by # the Free Software Foundation, either version 3 of the License, or # (at your option) any later version. # # This program is distributed in the hope that it will be useful, # but WITHOUT ANY WARRANTY; without even the implied warranty of # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the # GNU General Public License for more details. # # You should have received a copy of the GNU General Public License # along with this program. If not, see <http://www.gnu.org/licenses/>. --> <tool id="FROGS_remove_chimera" name="FROGS Remove chimera" version="@TOOL_VERSION@+galaxy2"> <description>Remove PCR chimera in each sample.</description> <macros> <import>macros.xml</import> </macros> <expand macro="requirements" > <requirement type="package" version="2.17.0">vsearch</requirement> </expand> <stdio> <exit_code range="1:" /> <exit_code range=":-1" /> </stdio> <command> remove_chimera.py --nb-cpus \${GALAXY_SLOTS:-1} --input-fasta '$sequence_file' --non-chimera '$non_chimera_fasta' --summary '$summary_file' #if $abundance_type.abundance_type_selected == "biom" --input-biom '$abundance_biom' --out-abundance '$out_abundance_biom' #else --input-count '$abundance_count' --out-abundance '$out_abundance_count' #end if </command> <inputs> <!-- Files --> <param format="fasta" name="sequence_file" type="data" label="Sequences file" help="The sequences file (format: fasta)." optional="false" /> <conditional name="abundance_type"> <param name="abundance_type_selected" type="select" label="Abundance type" help="Select the type of file where the abundance of each sequence by sample is stored."> <option value="biom" selected="true">BIOM file</option> <option value="count">TSV file</option> </param> <when value="biom"> <param format="biom1" name="abundance_biom" type="data" label="Abundance file" help="It contains the count by sample for each sequence." optional="false" /> </when> <when value="count"> <param format="tabular" name="abundance_count" type="data" label="Count file" help="It contains the count by sample for each sequence (see below)." optional="false" /> </when> </conditional> </inputs> <outputs> <data format="fasta" name="non_chimera_fasta" label="${tool.name}: non_chimera.fasta" from_work_dir="non_chimera.fasta"/> <data format="biom1" name="out_abundance_biom" label="${tool.name}: non_chimera_abundance.biom" from_work_dir="non_chimera_abundance.biom"> <filter>abundance_type['abundance_type_selected'] == "biom"</filter> </data> <data format="tabular" name="out_abundance_count" label="${tool.name}: non_chimera_abundance.tsv" from_work_dir="non_chimera_abundance.tsv"> <filter>abundance_type['abundance_type_selected'] == "count"</filter> </data> <data format="html" name="summary_file" label="${tool.name}: report.html" from_work_dir="report.html"/> </outputs> <tests> <test> <param name="sequence_file" value="references/02-clustering_fastidious.fasta"/> <conditional name="abundance_type"> <param name="abundance_type_selected" value="biom"/> <param name="abundance_biom" value="references/02-clustering_fastidious.biom" /> </conditional> <output name="non_chimera_fasta" file="references/03-chimera.fasta" compare="diff" lines_diff="0"/> <output name="summary_file" file="references/03-chimera.html" compare="diff" lines_diff="0"/> <output name="out_abundance_biom" file="references/03-chimera.biom" compare="sim_size" delta="0"/> </test> </tests> <help> @HELP_LOGO@ .. class:: infomark page-header h2 What it does Remove chimeric sequences by sample. .. class:: infomark page-header h2 Context Chimeras are sequences formed from two or more biological sequences joined together. 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. This phenomena is particularly common in amplicon sequencing where closely related sequences are amplified. .. class:: infomark page-header h2 Inputs/Outputs .. class:: h3 Inputs **Sequence file**: The sequences (format `FASTA <https://en.wikipedia.org/wiki/FASTA_format>`_). **Abundance file**: The abundance of each cluster in each sample (format `BIOM <http://biom-format.org/>`_). OR 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*. Example: .. csv-table:: :header: "#id", "splA","splB" :widths: 10,10,10 :class: table table-striped "seq1", "1289", "2901" "seq2", "3415", "0" .. class:: h3 Outputs **Sequence file** (non_chimera.fasta): The sequence file with only non-chimera (format `FASTA <https://en.wikipedia.org/wiki/FASTA_format>`_). **Abundance file** (non_chimera.biom or non_chimera.tsv): The abundance file with only non-chimera (format the same of the abundance input). **Summary file** (report.html): This file presents the number of removed elements (format `HTML <https://en.wikipedia.org/wiki/HTML>`_). .. class:: infomark page-header h2 How it works .. csv-table:: :header: "Steps", "Description" :widths: 10, 90 :class: table table-striped "1", "Split input data by sample (classicaly the PCR is realised by sample)." "2", "Find chimera in each sample (`vsearch <https://github.com/torognes/vsearch>`_)." "3", "Remove the sequences identify as chimera in all samples where they are present." @HELP_CONTACT@ </help> <citations> <expand macro="citations" /> </citations> </tool>