Mercurial > repos > iuc > bioext_bealign
diff bealign.xml @ 3:fb4975b507c6 draft
"planemo upload for repository https://github.com/davebx/bioext-gx/ commit af3bfbbd3f1236bf96a25bcb8483f2889295ec0c"
author | iuc |
---|---|
date | Fri, 20 Aug 2021 21:04:17 +0000 |
parents | d8b6f0adaa79 |
children | a287431cdf4f |
line wrap: on
line diff
--- a/bealign.xml Fri Jul 09 15:19:05 2021 +0000 +++ b/bealign.xml Fri Aug 20 21:04:17 2021 +0000 @@ -3,9 +3,11 @@ <description>to a reference using a codon alignment algorithm</description> <macros> <import>macros.xml</import> - <token name="@VERSION_SUFFIX@">0</token> + <token name="@VERSION_SUFFIX@">1</token> </macros> - <expand macro="requirements" /> + <expand macro="requirements"> + <requirement type="package" version="5.1.0">gawk</requirement> + </expand> <version_command>bealign --version</version_command> <command detect_errors="exit_code"> <![CDATA[ @@ -16,17 +18,41 @@ ## and replace any unwanted characters in the sequence names with underscores. ## This should not affect the actual alignment, since any non-standard character ## in the sequences is already ignored, but the possibility remains. - cat '$input' | awk '{ if (\$0 ~ "^[^>]") {a = gensub(/[^ACGTURYKMSWBDHVNacgturykmswbdhvn?-]/, "", "g"); } else {a=gensub(/[^>A-Za-z0-9_]/, "_", "g"); }; print a } ' | - sed 's,_\\+,_,g' > reads.fa && + cat '$input' @SANITIZE@ reads.fa && bealign --reference '$select_reference.reference' --alphabet $advanced.alphabet #if $advanced.expected_identity: --expected-identity $advanced.expected_identity #end if - --score-matrix $advanced.score_matrix $advanced.reverse_complement $advanced.keep_reference #if $advanced.discard: $advanced.discard '$advanced.discarded_reads' #end if - reads.fa alignment.bam + --score-matrix $advanced.score_matrix + $advanced.reverse_complement + $advanced.keep_reference + reads.fa '$output' + #set $input_background = False + #if $background_source.selection == 'history': + #if $background_source.sequences: + #set $input_background = $background_source.sequences + #end if + #else: + #if $background_source.sequences: + #set $input_background = $background_source.sequences.fields.path + #end if + #end if + #if $input_background: + && cat '$input_background' @SANITIZE@ background.fa && + bealign --reference '$select_reference.reference' --alphabet $advanced.alphabet + #if $advanced.expected_identity: + --expected-identity $advanced.expected_identity + #end if + --keep-reference --score-matrix $advanced.score_matrix $advanced.reverse_complement + background.fa '$background' + #end if + #set $reference_name = str($select_reference.reference) + #if $select_reference.reference_type == 'preset' and $select_reference.save_reference: + && python '$__tool_directory__/copy_reference.py' --reference '$reference_name' --dataset '$saved_reference' + #end if ]]> </command> <inputs> @@ -81,13 +107,28 @@ <option value="CoV2-ORF10">SARS-CoV-2: ORF10</option> <option value="CoV2-RdRp">SARS-CoV-2: RNA-dependent RNA polymerase</option> </param> + <param name="save_reference" type="boolean" display="radio" label="Save this reference to your history" /> </when> <when value="dataset"> <param argument="--reference" type="data" format="fasta" label="Reference sequences" /> </when> </conditional> + <conditional name="background_source"> + <param name="selection" type="select" label="Source for the background" help="You can use a predefined background cached on this Galaxy server or select a dataset from your history"> + <option value="data_table">Use a predefined background</option> + <option value="history">Select a dataset from your history</option> + </param> + <when value="data_table"> + <param name="sequences" type="select" optional="true" label="Select sequences from data table"> + <options from_data_table="bealign_selection" /> + </param> + </when> + <when value="history"> + <param name="sequences" type="data" format="fasta" optional="true" label="Select dataset with sequences" /> + </when> + </conditional> <section name="advanced" title="Advanced options" expanded="False"> - <param name="expected_identity" argument="--expected-identity" type="float" min="0" max="1" optional="True" label="Discard sequences that are insufficiently identical to the reference" /> + <param argument="--expected-identity" type="float" min="0" max="1" optional="True" label="Discard sequences that are insufficiently identical to the reference" /> <param argument="--alphabet" type="select" label="Alphabet to use for alignment"> <option value="codon" selected="True">Codon</option> <option value="dna">DNA</option> @@ -110,33 +151,54 @@ </section> </inputs> <outputs> - <data name="output" format="bam" from_work_dir="alignment.bam" /> + <data name="output" format="bam" label="${tool.name} on ${on_string} - Aligned Sequences" /> + <data name="background" format="bam" label="${tool.name} on ${on_string} - Background" > + <filter>background_source['sequences']</filter> + </data> + <data name="saved_reference" format="fasta" label="${tool.name} on ${on_string} - Reference" > + <filter>select_reference['save_reference']</filter> + </data> <data name="discarded_reads" format="fasta"> <filter>advanced['discard']</filter> </data> </outputs> <tests> <test> - <param name="input" ftype="fasta" value="bealign-in1.fa" /> + <param name="input" ftype="fasta" value="query.fa" /> <param name="reference_type" value="dataset" /> <param name="score_matrix" value="HIV_BETWEEN_F" /> - <param name="reference" ftype="fasta" value="bealign-in-ref-1.fa" /> + <param name="reference" ftype="fasta" value="reference.fa" /> <output name="output" file="bealign-out1.bam" ftype="bam" lines_diff="2" /> </test> <test> - <param name="input" ftype="fasta" value="bealign-in2.fa" /> - <param name="reference_type" value="dataset" /> - <param name="score_matrix" value="BLOSUM62" /> - <param name="reference" ftype="fasta" value="bealign-in-ref-2.fa" /> + <param name="input" ftype="fasta" value="query.fa" /> + <param name="reference_type" value="preset" /> + <param name="reference" value="CoV2-nsp8" /> + <param name="score_matrix" value="HIV_BETWEEN_F" /> <output name="output" file="bealign-out2.bam" ftype="bam" lines_diff="2"/> </test> - <test> - <param name="input" ftype="fasta" value="bealign-in2.fa" /> - <param name="reference_type" value="dataset" /> - <param name="expected_identity" value="0.9" /> - <param name="score_matrix" value="BLOSUM62" /> - <param name="reference" ftype="fasta" value="bealign-in-ref-2.fa" /> + <test expect_num_outputs="2"> + <param name="input" ftype="fasta" value="query.fa" /> + <param name="reference_type" value="preset" /> + <param name="reference" value="CoV2-nsp8" /> + <param name="add_background" value="Yes" /> + <param name="background_source" value="data_table" /> + <param name="sequences" value="CoV2-nsp8" /> + <param name="alphabet" value="codon" /> + <param name="score_matrix" value="HIV_BETWEEN_F" /> <output name="output" file="bealign-out3.bam" ftype="bam" lines_diff="2"/> + <output name="background" file="bealign-out3-background.bam" ftype="bam" lines_diff="2"/> + </test> + <test expect_num_outputs="2"> + <param name="input" ftype="fasta" value="query.fa" /> + <param name="reference_type" value="preset" /> + <param name="reference" value="CoV2-nsp8" /> + <param name="save_reference" value="true" /> + <param name="add_background" value="No" /> + <param name="alphabet" value="codon" /> + <param name="score_matrix" value="HIV_BETWEEN_F" /> + <output name="output" file="bealign-out4.bam" ftype="bam" lines_diff="2"/> + <output name="saved_reference" file="reference.fa" ftype="fasta"/> </test> </tests> <help>