Mercurial > repos > iuc > bioext_bealign

comparison bealign.xml @ 3:fb4975b507c6 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"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
comparison
equal deleted inserted replaced
2:d8b6f0adaa79 3:fb4975b507c6
1 <?xml version="1.0"?> 1 <?xml version="1.0"?>
2 <tool id="bioext_bealign" name="Align sequences" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@"> 2 <tool id="bioext_bealign" name="Align sequences" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
3 <description>to a reference using a codon alignment algorithm</description> 3 <description>to a reference using a codon alignment algorithm</description>
4 <macros> 4 <macros>
5 <import>macros.xml</import> 5 <import>macros.xml</import>
6 <token name="@VERSION_SUFFIX@">0</token> 6 <token name="@VERSION_SUFFIX@">1</token>
7 </macros> 7 </macros>
8 <expand macro="requirements" /> 8 <expand macro="requirements">
9 <requirement type="package" version="5.1.0">gawk</requirement>
10 </expand>
9 <version_command>bealign --version</version_command> 11 <version_command>bealign --version</version_command>
10 <command detect_errors="exit_code"> 12 <command detect_errors="exit_code">
11 <![CDATA[ 13 <![CDATA[
12 ## Some downstream tools, such as the TN-93 clustering tool and RAxML, might 14 ## Some downstream tools, such as the TN-93 clustering tool and RAxML, might
13 ## break if there are non-standard characters in the sequences or text other 15 ## break if there are non-standard characters in the sequences or text other
14 ## than alphanumerics in the sequence names, so we run the input dataset 16 ## than alphanumerics in the sequence names, so we run the input dataset
15 ## through a simple awk script to remove any non-IUPAC-standard nucleotides 17 ## through a simple awk script to remove any non-IUPAC-standard nucleotides
16 ## and replace any unwanted characters in the sequence names with underscores. 18 ## and replace any unwanted characters in the sequence names with underscores.
17 ## This should not affect the actual alignment, since any non-standard character 19 ## This should not affect the actual alignment, since any non-standard character
18 ## in the sequences is already ignored, but the possibility remains. 20 ## in the sequences is already ignored, but the possibility remains.
19 cat '$input' | awk '{ if (\$0 ~ "^[^>]") {a = gensub(/[^ACGTURYKMSWBDHVNacgturykmswbdhvn?-]/, "", "g"); } else {a=gensub(/[^>A-Za-z0-9_]/, "_", "g"); }; print a } ' | 21 cat '$input' @SANITIZE@ reads.fa &&
20 sed 's,_\\+,_,g' > reads.fa &&
21 bealign --reference '$select_reference.reference' --alphabet $advanced.alphabet 22 bealign --reference '$select_reference.reference' --alphabet $advanced.alphabet
22 #if $advanced.expected_identity: 23 #if $advanced.expected_identity:
23 --expected-identity $advanced.expected_identity 24 --expected-identity $advanced.expected_identity
24 #end if 25 #end if
25 --score-matrix $advanced.score_matrix $advanced.reverse_complement $advanced.keep_reference
26 #if $advanced.discard: 26 #if $advanced.discard:
27 $advanced.discard '$advanced.discarded_reads' 27 $advanced.discard '$advanced.discarded_reads'
28 #end if 28 #end if
29 reads.fa alignment.bam 29 --score-matrix $advanced.score_matrix
30 $advanced.reverse_complement
31 $advanced.keep_reference
32 reads.fa '$output'
33 #set $input_background = False
34 #if $background_source.selection == 'history':
35 #if $background_source.sequences:
36 #set $input_background = $background_source.sequences
37 #end if
38 #else:
39 #if $background_source.sequences:
40 #set $input_background = $background_source.sequences.fields.path
41 #end if
42 #end if
43 #if $input_background:
44 && cat '$input_background' @SANITIZE@ background.fa &&
45 bealign --reference '$select_reference.reference' --alphabet $advanced.alphabet
46 #if $advanced.expected_identity:
47 --expected-identity $advanced.expected_identity
48 #end if
49 --keep-reference --score-matrix $advanced.score_matrix $advanced.reverse_complement
50 background.fa '$background'
51 #end if
52 #set $reference_name = str($select_reference.reference)
53 #if $select_reference.reference_type == 'preset' and $select_reference.save_reference:
54 && python '$__tool_directory__/copy_reference.py' --reference '$reference_name' --dataset '$saved_reference'
55 #end if
30 ]]> 56 ]]>
31 </command> 57 </command>
32 <inputs> 58 <inputs>
33 <param name="input" type="data" format="fasta" label="Input reads" help="For the benefit of certain tools that depend on this aligner, such as the TN-93 clustering tool, this dataset's sequence names will have non-alphanumeric characters replaced with underscores, and the sequences will be restricted to the set of IUPAC nucleotide characters." /> 59 <param name="input" type="data" format="fasta" label="Input reads" help="For the benefit of certain tools that depend on this aligner, such as the TN-93 clustering tool, this dataset's sequence names will have non-alphanumeric characters replaced with underscores, and the sequences will be restricted to the set of IUPAC nucleotide characters." />
34 <conditional name="select_reference"> 60 <conditional name="select_reference">
79 <option value="CoV2-ORF7b">SARS-CoV-2: ORF7b</option> 105 <option value="CoV2-ORF7b">SARS-CoV-2: ORF7b</option>
80 <option value="CoV2-ORF8">SARS-CoV-2: ORF8</option> 106 <option value="CoV2-ORF8">SARS-CoV-2: ORF8</option>
81 <option value="CoV2-ORF10">SARS-CoV-2: ORF10</option> 107 <option value="CoV2-ORF10">SARS-CoV-2: ORF10</option>
82 <option value="CoV2-RdRp">SARS-CoV-2: RNA-dependent RNA polymerase</option> 108 <option value="CoV2-RdRp">SARS-CoV-2: RNA-dependent RNA polymerase</option>
83 </param> 109 </param>
110 <param name="save_reference" type="boolean" display="radio" label="Save this reference to your history" />
84 </when> 111 </when>
85 <when value="dataset"> 112 <when value="dataset">
86 <param argument="--reference" type="data" format="fasta" label="Reference sequences" /> 113 <param argument="--reference" type="data" format="fasta" label="Reference sequences" />
87 </when> 114 </when>
88 </conditional> 115 </conditional>
116 <conditional name="background_source">
117 <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">
118 <option value="data_table">Use a predefined background</option>
119 <option value="history">Select a dataset from your history</option>
120 </param>
121 <when value="data_table">
122 <param name="sequences" type="select" optional="true" label="Select sequences from data table">
123 <options from_data_table="bealign_selection" />
124 </param>
125 </when>
126 <when value="history">
127 <param name="sequences" type="data" format="fasta" optional="true" label="Select dataset with sequences" />
128 </when>
129 </conditional>
89 <section name="advanced" title="Advanced options" expanded="False"> 130 <section name="advanced" title="Advanced options" expanded="False">
90 <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" /> 131 <param argument="--expected-identity" type="float" min="0" max="1" optional="True" label="Discard sequences that are insufficiently identical to the reference" />
91 <param argument="--alphabet" type="select" label="Alphabet to use for alignment"> 132 <param argument="--alphabet" type="select" label="Alphabet to use for alignment">
92 <option value="codon" selected="True">Codon</option> 133 <option value="codon" selected="True">Codon</option>
93 <option value="dna">DNA</option> 134 <option value="dna">DNA</option>
94 <option value="amino">Amino acids</option> 135 <option value="amino">Amino acids</option>
95 </param> 136 </param>
108 <param name="reverse_complement" argument="--reverse-complement" type="boolean" checked="False" truevalue="--reverse-complement" falsevalue="" label="Also try to align against reverse complement of reference" /> 149 <param name="reverse_complement" argument="--reverse-complement" type="boolean" checked="False" truevalue="--reverse-complement" falsevalue="" label="Also try to align against reverse complement of reference" />
109 <param name="keep_reference" argument="--keep-reference" type="boolean" checked="False" truevalue="--keep-reference" falsevalue="" label="Include reference as first sequence in aligned BAM" /> 150 <param name="keep_reference" argument="--keep-reference" type="boolean" checked="False" truevalue="--keep-reference" falsevalue="" label="Include reference as first sequence in aligned BAM" />
110 </section> 151 </section>
111 </inputs> 152 </inputs>
112 <outputs> 153 <outputs>
113 <data name="output" format="bam" from_work_dir="alignment.bam" /> 154 <data name="output" format="bam" label="${tool.name} on ${on_string} - Aligned Sequences" />
155 <data name="background" format="bam" label="${tool.name} on ${on_string} - Background" >
156 <filter>background_source['sequences']</filter>
157 </data>
158 <data name="saved_reference" format="fasta" label="${tool.name} on ${on_string} - Reference" >
159 <filter>select_reference['save_reference']</filter>
160 </data>
114 <data name="discarded_reads" format="fasta"> 161 <data name="discarded_reads" format="fasta">
115 <filter>advanced['discard']</filter> 162 <filter>advanced['discard']</filter>
116 </data> 163 </data>
117 </outputs> 164 </outputs>
118 <tests> 165 <tests>
119 <test> 166 <test>
120 <param name="input" ftype="fasta" value="bealign-in1.fa" /> 167 <param name="input" ftype="fasta" value="query.fa" />
121 <param name="reference_type" value="dataset" /> 168 <param name="reference_type" value="dataset" />
122 <param name="score_matrix" value="HIV_BETWEEN_F" /> 169 <param name="score_matrix" value="HIV_BETWEEN_F" />
123 <param name="reference" ftype="fasta" value="bealign-in-ref-1.fa" /> 170 <param name="reference" ftype="fasta" value="reference.fa" />
124 <output name="output" file="bealign-out1.bam" ftype="bam" lines_diff="2" /> 171 <output name="output" file="bealign-out1.bam" ftype="bam" lines_diff="2" />
125 </test> 172 </test>
126 <test> 173 <test>
127 <param name="input" ftype="fasta" value="bealign-in2.fa" /> 174 <param name="input" ftype="fasta" value="query.fa" />
128 <param name="reference_type" value="dataset" /> 175 <param name="reference_type" value="preset" />
129 <param name="score_matrix" value="BLOSUM62" /> 176 <param name="reference" value="CoV2-nsp8" />
130 <param name="reference" ftype="fasta" value="bealign-in-ref-2.fa" /> 177 <param name="score_matrix" value="HIV_BETWEEN_F" />
131 <output name="output" file="bealign-out2.bam" ftype="bam" lines_diff="2"/> 178 <output name="output" file="bealign-out2.bam" ftype="bam" lines_diff="2"/>
132 </test> 179 </test>
133 <test> 180 <test expect_num_outputs="2">
134 <param name="input" ftype="fasta" value="bealign-in2.fa" /> 181 <param name="input" ftype="fasta" value="query.fa" />
135 <param name="reference_type" value="dataset" /> 182 <param name="reference_type" value="preset" />
136 <param name="expected_identity" value="0.9" /> 183 <param name="reference" value="CoV2-nsp8" />
137 <param name="score_matrix" value="BLOSUM62" /> 184 <param name="add_background" value="Yes" />
138 <param name="reference" ftype="fasta" value="bealign-in-ref-2.fa" /> 185 <param name="background_source" value="data_table" />
186 <param name="sequences" value="CoV2-nsp8" />
187 <param name="alphabet" value="codon" />
188 <param name="score_matrix" value="HIV_BETWEEN_F" />
139 <output name="output" file="bealign-out3.bam" ftype="bam" lines_diff="2"/> 189 <output name="output" file="bealign-out3.bam" ftype="bam" lines_diff="2"/>
190 <output name="background" file="bealign-out3-background.bam" ftype="bam" lines_diff="2"/>
191 </test>
192 <test expect_num_outputs="2">
193 <param name="input" ftype="fasta" value="query.fa" />
194 <param name="reference_type" value="preset" />
195 <param name="reference" value="CoV2-nsp8" />
196 <param name="save_reference" value="true" />
197 <param name="add_background" value="No" />
198 <param name="alphabet" value="codon" />
199 <param name="score_matrix" value="HIV_BETWEEN_F" />
200 <output name="output" file="bealign-out4.bam" ftype="bam" lines_diff="2"/>
201 <output name="saved_reference" file="reference.fa" ftype="fasta"/>
140 </test> 202 </test>
141 </tests> 203 </tests>
142 <help> 204 <help>
143 <![CDATA[ 205 <![CDATA[
144 bealign 206 bealign