Mercurial > repos > iuc > roary

comparison roary.xml @ 7:78608ec02d62 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/roary commit 442b1247ee31ec9872633be18784f346e4762486"
author iuc
date Sat, 13 Feb 2021 11:59:15 +0000
parents 15ac71df11a0
children e88a7de55d6e
comparison
equal deleted inserted replaced
6:15ac71df11a0 7:78608ec02d62
1 <tool id="roary" name="Roary" version="3.13.0+galaxy0"> 1 <tool id="roary" name="Roary" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
2 <description>the pangenome pipeline - Quickly generate a core gene alignment from gff3 files</description> 2 <description>the pangenome pipeline - Quickly generate a core gene alignment from gff3 files</description>
3 3 <macros>
4 <token name="@TOOL_VERSION@">3.13.0</token>
5 <token name="@VERSION_SUFFIX@">1</token>
6 </macros>
4 <requirements> 7 <requirements>
5 <requirement type="package" version="3.13.0">roary</requirement> 8 <requirement type="package" version="@TOOL_VERSION@">roary</requirement>
6 </requirements> 9 </requirements>
7 10
8 <command detect_errors="exit_code"><![CDATA[ 11 <command detect_errors="exit_code"><![CDATA[
9 #set $filenames = list() 12 #set $filenames = list()
10 #for $gff in $gff_input.gffs 13 #for $gff in $gff_input.gffs
11 cp '$gff' '${gff.element_identifier}.gff' && 14 cp '$gff' '${gff.element_identifier}.gff' &&
12 #set $filename = str($gff.element_identifier) + '.gff' 15 #set $filename = str($gff.element_identifier) + '.gff'
13 $filenames.append(str($filename)) 16 $filenames.append(str($filename))
14 #end for 17 #end for
15 18
16 roary 19 roary
17 -f out 20 -f out
18 -p \${GALAXY_SLOTS:-1} 21 -p \${GALAXY_SLOTS:-1}
27 30
28 #for $f in $filenames 31 #for $f in $filenames
29 '$f' 32 '$f'
30 #end for 33 #end for
31 34
32 ]]></command> 35 ]]> </command>
33 36
34 <inputs> 37 <inputs>
35 <conditional name="gff_input"> 38 <conditional name="gff_input">
36 <param name="gff_input_selector" type="select" label="Individual gff files or a dataset collection" help="Select between individual gff files or a collection of gff files"> 39 <param name="gff_input_selector" type="select" label="Individual gff files or a dataset collection" help="Select between individual gff files or a collection of gff files">
37 <option value="individual">Individual</option> 40 <option value="individual">Individual</option>
38 <option value="collection">Collection</option> 41 <option value="collection">Collection</option>
42 </param>
43 <when value="individual">
44 <param name="gffs" type="data" multiple="true" min="2" format="gff,gff3" label="select gff inputs to Roary" help="Select the files you wish to send to Roary, must be in gff3 format with the sequence data at the end of the file." />
45 </when>
46 <when value='collection'>
47 <param name="gffs" type="data_collection" collection_type="list" format="gff,gff3" label="Dataset collection to submit to Roary" help="A dataset list collection of gff3 files to send to Roary for analysis." />
48 </when>
49 </conditional>
50 <param name="percent_ident" type="integer" value="95" label="minimum percentage identity for blastp" help="Sets the minimum percentage identity for protein matches" />
51 <param name="core_diff" type="float" value="99.0" label="percentage of isolates a gene must be in to be core" help="The total percentage of the isolates that must have the gene for it to be considered a core gene." />
52
53 <param name="outputs" type="select" multiple="true" display="checkboxes" label="Additional outputs" help="Summary statistics, core gene alignments and Gene Presence/Absence tables are always produced.">
54 <option value="abg_nw">Accessory binary genes in newick format</option>
55 <option value="abg_fa">Accessory binary genes in fasta format</option>
56 <option value="accgraph">Accessory graph in dot format</option>
57 <option value="acchead_embl">Accessory header file in embl format</option>
58 <option value="acctab">Accessory gene table in tabular format</option>
59 <option value="blastfreq">Blast Identity Frequency Rtab file</option>
60 <option value="clust">Clustered proteins file</option>
61 <option value="coreaccgraph">Core Accessory Graph in dot format</option>
62 <option value="coreaccembl">Core Accessory table in embl format</option>
63 <option value="coreacctab">Core Accessory table in tabular format</option>
64 <option value="genepa_rtab">Gene Presence Absence file in Rtab format</option>
65 <option value="numcons_rtab">Number of Conserved Genes in Rtab format</option>
66 <option value="numpangene_rtab">Number of Genes in Pan Genome in Rtab format</option>
67 <option value="numnew_rtab">Number of New Genes in Rtab format</option>
68 <option value="numuniq_rtab">Number of Unique Genes in Rtab format</option>
69 <option value="pangenomeref">FASTA file which contains a single representative nucleotide sequence from each of the clusters in the pan genome (core and accessory)</option>
39 </param> 70 </param>
40 <when value="individual">
41 <param name="gffs" type="data" multiple="true" format="gff,gff3" label="select gff inputs to Roary" help="Select the files you wish to send to Roary, must be in gff3 format with the sequence data at the end of the file." />
42 </when>
43 <when value='collection'>
44 <param name="gffs" type="data_collection" collection_type="list" format="gff,gff3" label="Dataset collection to submit to Roary" help="A dataset list collection of gff3 files to send to Roary for analysis." />
45 </when>
46 </conditional>
47 <param name="percent_ident" type="integer" label="minimum percentage identity for blastp" help="Sets the minimum percentage identity for protein matches" value="95"/>
48 <param name="core_diff" type="float" label="percentage of isolates a gene must be in to be core" help="The total percentage of the isolates that must have the gene for it to be considered a core gene." value="99.0"/>
49 71
50 <param name="outputs" type="select" multiple="true" display="checkboxes" label="Additional outputs" help="Summary statistics, core gene alignments and Gene Presence/Absence tables are always produced."> 72 <section name="advanced" title="Advanced options" expanded="false">
51 <option value="abg_nw">Accessory binary genes in newick format</option> 73 <param name="maxclust" type="integer" value="50000" label="Maximum number of clusters" help="The maximum number of clusters to assign proteins" />
52 <option value="abg_fa">Accessory binary genes in fasta format</option> 74 <param name="split_para" type="boolean" checked="False" truevalue="-s" falsevalue="" label="Don't split paralogs" help="Click yes so that paralogs aren't split." />
53 <option value="accgraph">Accessory graph in dot format</option> 75 <param name="trans_tab" type="integer" value="11" label="Translation table to use [1 or 4 or 11]" help="DNA -> RNA translation table to use. Roary is designed for prokaryotes and so tables 1, 4 or 11 will work, others could be problematic." />
54 <option value="acchead_embl">Accessory header file in embl format</option> 76 <param name="mcl" type="float" value="1.5" label="MCL inflation value" help="This is an advanced setting, change only if you know what you are doing and then at your own risk!" />
55 <option value="acctab">Accessory gene table in tabular format</option> 77 </section>
56 <option value="blastfreq">Blast Identity Frequency Rtab file</option>
57 <option value="clust">Clustered proteins file</option>
58 <option value="coreaccgraph">Core Accessory Graph in dot format</option>
59 <option value="coreaccembl">Core Accessory table in embl format</option>
60 <option value="coreacctab">Core Accessory table in tabular format</option>
61 <option value="genepa_rtab">Gene Presence Absence file in Rtab format</option>
62 <option value="numcons_rtab">Number of Conserved Genes in Rtab format</option>
63 <option value="numpangene_rtab">Number of Genes in Pan Genome in Rtab format</option>
64 <option value="numnew_rtab">Number of New Genes in Rtab format</option>
65 <option value="numuniq_rtab">Number of Unique Genes in Rtab format</option>
66 <option value="pangenomeref">FASTA file which contains a single representative nucleotide sequence from each of the clusters in the pan genome (core and accessory)</option>
67 </param>
68
69 <section name="advanced" title="Advanced options" expanded="false">
70 <param name="maxclust" type="integer" value="50000" label="Maximum number of clusters" help="The maximum number of clusters to assign proteins" />
71 <param name="split_para" type="boolean" checked="False" truevalue="-s" falsevalue="" label="Don't split paralogs" help="Click yes so that paralogs aren't split."/>
72 <param name="trans_tab" type="integer" value="11" label="Translation table to use [1 or 4 or 11]" help="DNA -> RNA translation table to use. Roary is designed for prokaryotes and so tables 1, 4 or 11 will work, others could be problematic." />
73 <param name="mcl" type="float" value="1.5" label="MCL inflation value" help="This is an advanced setting, change only if you know what you are doing and then at your own risk!" />
74 </section>
75 78
76 </inputs> 79 </inputs>
77 80
78 <outputs> 81 <outputs>
79 <data format="tabular" name="sumstats" label="${tool.name} on ${on_string} Summary statistics" from_work_dir="out/summary_statistics.txt" /> 82 <data format="tabular" name="sumstats" label="${tool.name} on ${on_string} Summary statistics" from_work_dir="out/summary_statistics.txt" />
80 <data format="fasta" name="core_gene_aln" label="${tool.name} on ${on_string} Core Gene Alignment" from_work_dir="out/core_gene_alignment.aln" /> 83 <data format="fasta" name="core_gene_aln" label="${tool.name} on ${on_string} Core Gene Alignment" from_work_dir="out/core_gene_alignment.aln" />
81 <data format="csv" name="gene_p_a" label="${tool.name} on ${on_string} Gene Presence Absence" from_work_dir="out/gene_presence_absence.csv" /> 84 <data format="csv" name="gene_p_a" label="${tool.name} on ${on_string} Gene Presence Absence" from_work_dir="out/gene_presence_absence.csv" />
82 <data format="fasta" name="acc_bin" label="${tool.name} on ${on_string} Accessory Binary Genes" from_work_dir="out/accessory_binary_genes.fa" > 85 <data format="fasta" name="acc_bin" label="${tool.name} on ${on_string} Accessory Binary Genes" from_work_dir="out/accessory_binary_genes.fa">
83 <filter>outputs and 'abg_fa' in outputs</filter> 86 <filter>outputs and 'abg_fa' in outputs</filter>
84 </data> 87 </data>
85 <data format="nhx" name="acc_bin_new" label="${tool.name} on ${on_string} Accessory Binary Genes (Newick)" from_work_dir="out/accessory_binary_genes.fa.newick" > 88 <data format="nhx" name="acc_bin_new" label="${tool.name} on ${on_string} Accessory Binary Genes (Newick)" from_work_dir="out/accessory_binary_genes.fa.newick">
86 <filter>outputs and 'abg_nw' in outputs</filter> 89 <filter>outputs and 'abg_nw' in outputs</filter>
87 </data> 90 </data>
88 <data format="dot" name="acc_graph" label="${tool.name} on ${on_string} Acsessory Graph" from_work_dir="out/accessory_graph.dot"> 91 <data format="dot" name="acc_graph" label="${tool.name} on ${on_string} Acsessory Graph" from_work_dir="out/accessory_graph.dot">
89 <filter>outputs and 'accgraph' in outputs</filter> 92 <filter>outputs and 'accgraph' in outputs</filter>
90 </data> 93 </data>
91 <data format="embl" name="acc_head_embl" label="${tool.name} on ${on_string} Accessory Header" from_work_dir="out/accessory.header.embl" > 94 <data format="embl" name="acc_head_embl" label="${tool.name} on ${on_string} Accessory Header" from_work_dir="out/accessory.header.embl">
92 <filter>outputs and 'acchead_embl' in outputs</filter> 95 <filter>outputs and 'acchead_embl' in outputs</filter>
93 </data> 96 </data>
94 <data format="tabular" name="acc_tab" label="${tool.name} on ${on_string} Accessory Gene Table" from_work_dir="out/accessory.tab" > 97 <data format="tabular" name="acc_tab" label="${tool.name} on ${on_string} Accessory Gene Table" from_work_dir="out/accessory.tab">
95 <filter>outputs and 'acctab' in outputs</filter> 98 <filter>outputs and 'acctab' in outputs</filter>
96 </data> 99 </data>
97 <data format="txt" name="blast_freq" label="${tool.name} on ${on_string} Blast Identity Frequencies" from_work_dir="out/blast_identity_frequency.Rtab" > 100 <data format="txt" name="blast_freq" label="${tool.name} on ${on_string} Blast Identity Frequencies" from_work_dir="out/blast_identity_frequency.Rtab">
98 <filter>outputs and 'blastfreq' in outputs</filter> 101 <filter>outputs and 'blastfreq' in outputs</filter>
99 </data> 102 </data>
100 <data format="txt" name="clust_file" label="${tool.name} on ${on_string} Clustered Proteins" from_work_dir="out/clustered_proteins" > 103 <data format="txt" name="clust_file" label="${tool.name} on ${on_string} Clustered Proteins" from_work_dir="out/clustered_proteins">
101 <filter>outputs and 'clust' in outputs</filter> 104 <filter>outputs and 'clust' in outputs</filter>
102 </data> 105 </data>
103 <data format="dot" name="core_acc_graph" label="${tool.name} on ${on_string} Core Accessory Graph" from_work_dir="out/core_accessory_graph.dot" > 106 <data format="dot" name="core_acc_graph" label="${tool.name} on ${on_string} Core Accessory Graph" from_work_dir="out/core_accessory_graph.dot">
104 <filter>outputs and 'coreaccgraph' in outputs</filter> 107 <filter>outputs and 'coreaccgraph' in outputs</filter>
105 </data> 108 </data>
106 <data format="embl" name="core_acc_embl" label="${tool.name} on ${on_string} Core Accessory EMBL" from_work_dir="out/core_accessory.header.embl" > 109 <data format="embl" name="core_acc_embl" label="${tool.name} on ${on_string} Core Accessory EMBL" from_work_dir="out/core_accessory.header.embl">
107 <filter>outputs and 'coreaccembl' in outputs</filter> 110 <filter>outputs and 'coreaccembl' in outputs</filter>
108 </data> 111 </data>
109 <data format="tabular" name="core_acc_tab" label="${tool.name} on ${on_string} Core Accessory Table" from_work_dir="out/core_accessory.tab" > 112 <data format="tabular" name="core_acc_tab" label="${tool.name} on ${on_string} Core Accessory Table" from_work_dir="out/core_accessory.tab">
110 <filter>outputs and 'coreacctab' in outputs</filter> 113 <filter>outputs and 'coreacctab' in outputs</filter>
111 </data> 114 </data>
112 <data format="txt" name="gene_p_a_rtab" label="${tool.name} on ${on_string} Gene Presence Absence Rtab" from_work_dir="out/gene_presence_absence.Rtab" > 115 <data format="txt" name="gene_p_a_rtab" label="${tool.name} on ${on_string} Gene Presence Absence Rtab" from_work_dir="out/gene_presence_absence.Rtab">
113 <filter>outputs and 'genepa_rtab' in outputs</filter> 116 <filter>outputs and 'genepa_rtab' in outputs</filter>
114 </data> 117 </data>
115 <data format="txt" name="num_cons_rtab" label="${tool.name} on ${on_string} Number of Conserved Genes" from_work_dir="out/number_of_conserved_genes.Rtab" > 118 <data format="txt" name="num_cons_rtab" label="${tool.name} on ${on_string} Number of Conserved Genes" from_work_dir="out/number_of_conserved_genes.Rtab">
116 <filter>outputs and 'numcons_rtab' in outputs</filter> 119 <filter>outputs and 'numcons_rtab' in outputs</filter>
117 </data> 120 </data>
118 <data format="txt" name="num_pangene_rtab" label="${tool.name} on ${on_string} Number of Genes in Pan Geneome" from_work_dir="out/number_of_genes_in_pan_genome.Rtab" > 121 <data format="txt" name="num_pangene_rtab" label="${tool.name} on ${on_string} Number of Genes in Pan Geneome" from_work_dir="out/number_of_genes_in_pan_genome.Rtab">
119 <filter>outputs and 'numpangene_rtab' in outputs</filter> 122 <filter>outputs and 'numpangene_rtab' in outputs</filter>
120 </data> 123 </data>
121 <data format="txt" name="num_new_rtab" label="${tool.name} on ${on_string} Number of New Genes" from_work_dir="out/number_of_new_genes.Rtab" > 124 <data format="txt" name="num_new_rtab" label="${tool.name} on ${on_string} Number of New Genes" from_work_dir="out/number_of_new_genes.Rtab">
122 <filter>outputs and 'numnew_rtab' in outputs</filter> 125 <filter>outputs and 'numnew_rtab' in outputs</filter>
123 </data> 126 </data>
124 <data format="txt" name="num_uniq_rtab" label="${tool.name} on ${on_string} Number of Unique Genes" from_work_dir="out/number_of_unique_genes.Rtab" > 127 <data format="txt" name="num_uniq_rtab" label="${tool.name} on ${on_string} Number of Unique Genes" from_work_dir="out/number_of_unique_genes.Rtab">
125 <filter>outputs and 'numuniq_rtab' in outputs</filter> 128 <filter>outputs and 'numuniq_rtab' in outputs</filter>
126 </data> 129 </data>
127 <data format="fasta" name="pan_genome_ref" label="${tool.name} on ${on_string} pan-genome reference" from_work_dir="out/pan_genome_reference.fa" > 130 <data format="fasta" name="pan_genome_ref" label="${tool.name} on ${on_string} pan-genome reference" from_work_dir="out/pan_genome_reference.fa">
128 <filter>outputs and 'pangenomeref' in outputs</filter> 131 <filter>outputs and 'pangenomeref' in outputs</filter>
129 </data> 132 </data>
130 </outputs> 133 </outputs>
131 134
132 <tests> 135 <tests>
133 <test> 136 <test>
134 <param name="gff_input_selector" value="individual"/> 137 <param name="gff_input_selector" value="individual" />
135 <param name="gffs" value="ex1.gff,ex2.gff" ftype="gff3"/> 138 <param name="gffs" value="ex1.gff,ex2.gff" ftype="gff3" />
136 <output name="sumstats" file="out/summary_statistics.txt" ftype="tabular"/> 139 <output name="sumstats" file="out/summary_statistics.txt" ftype="tabular" />
137 </test> 140 </test>
138 <test> 141 <test>
139 <param name="gff_input_selector" value="individual"/> 142 <param name="gff_input_selector" value="individual" />
140 <param name="gffs" value="ex1.gff,ex2.gff" ftype="gff3"/> 143 <param name="gffs" value="ex1.gff,ex2.gff" ftype="gff3" />
141 <param name="percent_ident" value="50"/> 144 <param name="percent_ident" value="50" />
142 <param name="core_diff" value="50.0"/> 145 <param name="core_diff" value="50.0" />
143 <output name="sumstats" file="test2/summary_statistics.txt" ftype="tabular"/> 146 <output name="sumstats" file="test2/summary_statistics.txt" ftype="tabular" />
144 </test> 147 </test>
145 </tests> 148 </tests>
146 149
147 <help><![CDATA[ 150 <help><![CDATA[
148 **Roary** 151 **Roary**
149 152
174 - Change the MCL inflation value - a float, default is [1.5] 177 - Change the MCL inflation value - a float, default is [1.5]
175 178
176 179
177 For further info see: http://sanger-pathogens.github.io/Roary/ 180 For further info see: http://sanger-pathogens.github.io/Roary/
178 181
179 ]]></help> 182 ]]> </help>
180 183
181 <citations> 184 <citations>
182 <citation type="doi">10.1093/bioinformatics/btv421</citation> 185 <citation type="doi">10.1093/bioinformatics/btv421</citation>
183 </citations> 186 </citations>
184 187