Mercurial > repos > oinizan > frogs
diff preprocess.xml @ 7:76dcbe930b1d draft
"planemo upload for repository https://github.com/geraldinepascal/FROGS-wrappers/ commit 0a8dfe386b79711c479cf8a2bc8e9677e521b9e5-dirty"
| author | oinizan |
|---|---|
| date | Wed, 18 Aug 2021 15:43:00 +0000 |
| parents | 192cac570229 |
| children | 7bf54edaba24 |
line wrap: on
line diff
--- a/preprocess.xml Mon Jun 21 14:09:38 2021 +0000 +++ b/preprocess.xml Wed Aug 18 15:43:00 2021 +0000 @@ -15,42 +15,47 @@ # 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_preprocess" name="FROGS Pre-process" version="3.2.3.1"> +<tool id="FROGS_preprocess" name="FROGS Pre-process" version="@TOOL_VERSION@+galaxy2"> <description>merging, denoising and dereplication.</description> - <requirements> - <requirement type="package" version="3.2.3">frogs</requirement> - <requirement type="package" version="2.17.0">vsearch</requirement> - <requirement type="package" version="1.2.11">flash</requirement> - <requirement type="package" version="2.10">cutadapt</requirement> - </requirements> + + <macros> + <import>macros.xml</import> + </macros> + + <expand macro="requirements" > + <requirement type="package" version="2.17.0">vsearch</requirement> + <requirement type="package" version="1.2.11">flash</requirement> + <requirement type="package" version="2.10">cutadapt</requirement> + </expand> + <stdio> <exit_code range="1:" /> <exit_code range=":-1" /> </stdio> <command> - preprocess.py $sequencer_type.sequencer_selected - --output-dereplicated $dereplicated_file --output-count $count_file --summary $summary_file + preprocess.py '$sequencer_type.sequencer_selected' + --output-dereplicated '$dereplicated_file' --output-count '$count_file' --summary '$summary_file' --nb-cpus \${GALAXY_SLOTS:-1} - --min-amplicon-size $sequencer_type.min_amplicon_size --max-amplicon-size $sequencer_type.max_amplicon_size - + --min-amplicon-size $sequencer_type.min_amplicon_size --max-amplicon-size $sequencer_type.max_amplicon_size + #if $sequencer_type.sequencer_selected == "illumina" #if $sequencer_type.sequencing_protocol.sequencing_protocol_selected == "standard" - --five-prim-primer $sequencer_type.sequencing_protocol.five_prim_primer --three-prim-primer $sequencer_type.sequencing_protocol.three_prim_primer + --five-prim-primer '$sequencer_type.sequencing_protocol.five_prim_primer' --three-prim-primer '$sequencer_type.sequencing_protocol.three_prim_primer' #else --without-primers #end if #else - --five-prim-primer $sequencer_type.five_prim_primer --three-prim-primer $sequencer_type.three_prim_primer + --five-prim-primer '$sequencer_type.five_prim_primer' --three-prim-primer '$sequencer_type.three_prim_primer' #end if - - #if $sequencer_type.input_type.input_type_selected == "archive" - --input-archive $sequencer_type.input_type.archive_file + + #if $sequencer_type.input_type.input_type_selected == "archive" + --input-archive '$sequencer_type.input_type.archive_file' #if $sequencer_type.sequencer_selected == "illumina" and $sequencer_type.input_type.archive_type.archive_type_selected == "already_merged" --already-contiged #elif $sequencer_type.sequencer_selected == "illumina" - --R1-size $sequencer_type.input_type.archive_type.R1_size --R2-size $sequencer_type.input_type.archive_type.R2_size + --R1-size $sequencer_type.input_type.archive_type.R1_size --R2-size $sequencer_type.input_type.archive_type.R2_size --mismatch-rate $sequencer_type.input_type.archive_type.mm_rate - --merge-software $sequencer_type.input_type.archive_type.merge_software_type.merge_software_selected + --merge-software '$sequencer_type.input_type.archive_type.merge_software_type.merge_software_selected' #if $sequencer_type.input_type.archive_type.merge_software_type.merge_software_selected == "flash" --expected-amplicon-size $sequencer_type.input_type.archive_type.merge_software_type.expected_amplicon_size #end if @@ -61,22 +66,22 @@ #else #set $sep = ' ' #if $sequencer_type.sequencer_selected == "illumina" - --samples-names - #for $current in $sequencer_type.input_type.files_by_samples_type.samples + --samples-names + #for $current in $sequencer_type.input_type.files_by_samples_type.samples $sep'${current.name.strip()}' #end for - --input-R1 - #for $current in $sequencer_type.input_type.files_by_samples_type.samples - $sep${current.R1_file} + --input-R1 + #for $current in $sequencer_type.input_type.files_by_samples_type.samples + $sep'${current.R1_file}' #end for #if $sequencer_type.input_type.files_by_samples_type.files_by_samples_type_selected == "already_merged" --already-contiged #else --input-R2 - #for $current in $sequencer_type.input_type.files_by_samples_type.samples - $sep${current.R2_file} + #for $current in $sequencer_type.input_type.files_by_samples_type.samples + $sep'${current.R2_file}' #end for - --R1-size $sequencer_type.input_type.files_by_samples_type.R1_size --R2-size $sequencer_type.input_type.files_by_samples_type.R2_size + --R1-size $sequencer_type.input_type.files_by_samples_type.R1_size --R2-size $sequencer_type.input_type.files_by_samples_type.R2_size --mismatch-rate $sequencer_type.input_type.files_by_samples_type.mm_rate --merge-software $sequencer_type.input_type.files_by_samples_type.merge_software_type.merge_software_selected #if $sequencer_type.input_type.files_by_samples_type.merge_software_type.merge_software_selected == "flash" @@ -87,12 +92,12 @@ #end if #end if #else - --input-R1 - #for $current in $sequencer_type.input_type.samples - $sep${current.R1_file} + --input-R1 + #for $current in $sequencer_type.input_type.samples + $sep'${current.R1_file}' #end for - --samples-names - #for $current in $sequencer_type.input_type.samples + --samples-names + #for $current in $sequencer_type.input_type.samples $sep'${current.name.strip()}' #end for #end if @@ -123,7 +128,7 @@ <!-- Reads size --> <param name="R1_size" type="integer" label="Reads 1 size" help="The maximum read1 size." value="" optional="false" /> <param name="R2_size" type="integer" label="Reads 2 size" help="The maximum read2 size." value="" optional="false" /> - <param name="mm_rate" type="float" label="Mismatch rate." help="The maximum rate of mismatch in the overlap region" value="0.1" optional="false" /> + <param name="mm_rate" type="float" label="Mismatch rate." help="The maximum rate of mismatch in the overlap region" value="0.1" optional="false" /> <conditional name="merge_software_type"> <param name="merge_software_selected" type="select" label="Merge software" help="Select the software to merge paired-end reads."> <option value="vsearch" selected="true">Vsearch</option> @@ -201,7 +206,7 @@ <when value="without_primers"></when> </conditional> </when> - + <when value="454"> <!-- Samples --> <conditional name="input_type"> @@ -296,14 +301,11 @@ <output name="dereplicated_file" file="references/01-prepro-vsearch.fasta" compare="diff" lines_diff="0" /> <output name="count_file" file="references/01-prepro-vsearch.tsv" compare="diff" lines_diff="0" /> <output name="summary_file" file="references/01-prepro-vsearch.html" compare="sim_size" delta="0"/> - </test> + </test> </tests> <help> -.. image:: static/images/FROGS_logo.png - :height: 144 - :width: 110 - +@HELP_LOGO@ .. class:: infomark page-header h2 @@ -361,14 +363,14 @@ **Summary file** (report.html): This file reports the number of remaining sequences after each filter (format `HTML <https://en.wikipedia.org/wiki/HTML>`_). Depending of the tool configuration there will be more or less filtering steps so more or less bars in the barplot. - - .. image:: static/images/FROGS_preprocess_summary_v3.png + + .. image:: static/images/FROGS_preprocess_summary_v3.png :height: 850 - :width: 831 + :width: 831 It also presents the length distribution of the full amplicon sequences after merging step and after filtering steps. - - .. image:: static/images/FROGS_preprocess_lengthsSamples_v3.png + + .. image:: static/images/FROGS_preprocess_lengthsSamples_v3.png :height: 379 :width: 364 @@ -376,14 +378,14 @@ How it works -.. csv-table:: +.. csv-table:: :header: "Steps", "Illumina", "454" :widths: 5, 150, 150 :class: table table-striped - "1", "For un-merged data: Merges R1 and R2 with a maximum of M% mismatch in the overlaped region(`VSEARCH <https://github.com/torognes/vsearch/>`_ or `FLASH <https://ccb.jhu.edu/software/FLASH/>`_ or optionnaly `PEAR <https://sco.h-its.org/exelixis/web/software/pear/>`_) with a minimum of 10 bp in the overlap region. Resulting un-merged reads may optionnaly be artificially combined by adding 100 N between the reads", "/" + "1", "For un-merged data: Merges R1 and R2 with a maximum of M% mismatch in the overlaped region(`VSEARCH <https://github.com/torognes/vsearch/>`_ or `FLASH <http://ccb.jhu.edu/software/FLASH/>`_ or optionnaly `PEAR <https://sco.h-its.org/exelixis/web/software/pear/>`_) with a minimum of 10 bp in the overlap region. Resulting un-merged reads may optionnaly be artificially combined by adding 100 N between the reads", "/" "2", "If sequencing protocol is the illumina standard protocol : Removes sequences where the two primers are not present and removes primers in the remaining sequence (`cutadapt <http://cutadapt.readthedocs.org/en/latest/guide.html>`_). The primer search accepts 10% of differences", "Removes sequences where the two primers are not present, removes primers sequence from amplicon sequence and reverse complement the sequences on strand - (`cutadapt <http://cutadapt.readthedocs.org/en/latest/guide.html>`_). The primer search accepts 10% of differences" - "3", "Filters sequences with ambiguous nucleotides and for merged sequences filters on their length which must be range between 'Minimum amplicon size - primer length' and 'Maximum amplicon size - primer length'", "Removes sequences with at least one homopolymer with more than seven nucleotides and with a distance of less than or equal to 10 nucleo-tides between two poor quality positions, i.e. with a Phred quality score lesser than 10" + "3", "Filters sequences with ambiguous nucleotides and for merged sequences filters on their length which must be range between 'Minimum amplicon size - primer length' and 'Maximum amplicon size - primer length'", "Removes sequences with at least one homopolymer with more than seven nucleotides and with a distance of less than or equal to 10 nucleo-tides between two poor quality positions, i.e. with a Phred quality score lesser than 10" "4", "Dereplicates sequences", "Dereplicates sequences" @@ -435,16 +437,16 @@ The (`Kozich et al. 2013 <http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3753973/>`_ ) protocol uses custom sequencing primers which are also the PCR primers. In this case the reads do not contain the PCR primers. -In case of Illumina standard protocol, the primers must be provided in 5' to 3' orientation. +In case of Illumina standard protocol, the primers must be provided in 5' to 3' orientation. .. role:: alert-info Example: 5' :alert-info:`ATGCCC` GTCGTCGTAAAATGC :alert-info:`ATTTCAG` 3' - + Value for parameter 5' primer: ATGCCC - + Value for parameter 3' primer: ATTTCAG .. class:: h3 @@ -460,7 +462,7 @@ .. image:: static/images/FROGS_preprocess_ampliconSize_unimodal_v3.png :height: 415 :width: 676 - + .. image:: static/images/FROGS_preprocess_ampliconSize_multimodal_v3.png :height: 415 :width: 676 @@ -472,20 +474,16 @@ If the filter 'merged' reduce drasticaly the number of sequences: In un-merged Illumina data, and targeted amplicon size in the range of R1+R2-10, the reduction of dataset by the merged filter is classicaly inferior than 20%. A loss of more than 20% in all samples can highlight a quality problem. - + If the overlap between R1 and R2 is superior to 50 nucleotides and the quality of the end of the sequences is poor (see `FastQC <http://www.bioinformatics.babraham.ac.uk/projects/fastqc/>`_) you can try to cut the end of your sequences and relaunch the preprocess tool. You can either raise the mismatch percent in the overlapped region, but not too much! ----- -**Contact** - -Contacts: frogs-support@inrae.fr - -Repositories: https://github.com/geraldinepascal/FROGS, https://github.com/geraldinepascal/FROGS-wrappers - -Website: http://frogs.toulouse.inrae.fr/ - -Please cite the **FROGS article**: `Escudie F., et al. Bioinformatics, 2018. FROGS: Find, Rapidly, OTUs with Galaxy Solution. <https://doi.org/10.1093/bioinformatics/btx791>`_ +@HELP_CONTACT@ </help> + + <citations> + <expand macro="citations" /> + </citations> + </tool>