Mercurial > repos > bgruening > antismash
comparison antismash.xml @ 4:e78e25d3b4bd draft
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/antismash commit f5f8e44e726c9f2cc57e0f0fe8182a73afa56669
author | bgruening |
---|---|
date | Tue, 31 May 2022 14:04:07 +0000 |
parents | 5784e268efca |
children | bc88856eddab |
comparison
equal
deleted
inserted
replaced
3:5784e268efca | 4:e78e25d3b4bd |
---|---|
1 <?xml version='1.0' encoding='utf-8'?> | 1 <tool id="antismash" name="Antismash" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="20.01"> |
2 <tool id="antismash" name="Antismash" version="5.1.2" profile="17.01"> | |
3 <description>allows the genome-wide identification, annotation and analysis of secondary metabolite biosynthesis gene clusters</description> | 2 <description>allows the genome-wide identification, annotation and analysis of secondary metabolite biosynthesis gene clusters</description> |
4 <requirements> | 3 <macros> |
5 <requirement type="package" version="5.1.2">antismash</requirement> | 4 <import>macros.xml</import> |
6 </requirements> | 5 </macros> |
6 <expand macro='requirements'/> | |
7 <expand macro="bio_tools"/> | |
7 <version_command>antismash --version</version_command> | 8 <version_command>antismash --version</version_command> |
8 <command detect_errors="aggressive"> | 9 <command detect_errors="aggressive"> |
9 <![CDATA[ | 10 <![CDATA[ |
10 export PYTHONWARNINGS="ignore::FutureWarning" && | 11 export PYTHONWARNINGS="ignore::FutureWarning" && |
11 | 12 |
16 #else: | 17 #else: |
17 #set $file_extension = $infile.ext | 18 #set $file_extension = $infile.ext |
18 #end if | 19 #end if |
19 | 20 |
20 ln -s '$infile' input_tempfile.$file_extension && | 21 ln -s '$infile' input_tempfile.$file_extension && |
22 #if $genefinding_gff3 | |
23 ln -s $genefinding_gff3 annotation.gff3 && | |
24 #end if | |
25 | |
21 | 26 |
22 ## create html folder | 27 ## create html folder |
23 mkdir -p '$htmloutputfolder' && | 28 mkdir -p '$htmloutputfolder' && |
24 | 29 |
25 antismash | 30 antismash |
26 --cpus "\${GALAXY_SLOTS:-12}" | 31 --cpus "\${GALAXY_SLOTS:-12}" |
27 --taxon '${cond_taxon.taxon}' | 32 --taxon '${cond_taxon.taxon}' |
28 | 33 #if $genefinding_gff3 |
34 --genefinding-gff3 annotation.gff3 | |
35 #end if | |
29 --genefinding-tool $cond_taxon.genefinding_tool | 36 --genefinding-tool $cond_taxon.genefinding_tool |
30 | 37 |
31 ${cb_general} | 38 ${cb_general} |
32 ${cb_subclusters} | 39 ${cb_subclusters} |
33 ${cb_knownclusters} | 40 ${cb_knownclusters} |
34 ${smcog_trees} | 41 ${smcog_trees} |
35 --tta-threshold ${tta_threshold} | 42 --tta-threshold ${tta_threshold} |
36 ${asf} | 43 ${asf} |
37 | 44 |
38 ${extra_cluster} | |
39 ${clusterhmmer} | 45 ${clusterhmmer} |
40 ${fullhmmer} | 46 ${fullhmmer} |
41 #if $cond_taxon.taxon == 'fungi': | 47 #if $cond_taxon.taxon == 'fungi': |
42 $cond_taxon.cassis | 48 $cond_taxon.cassis |
49 #else | |
50 $cond_taxon.tigrfam | |
43 #end if | 51 #end if |
52 | |
53 ${cc_mibig} | |
54 ${rre} | |
55 --logfile $log | |
56 | |
57 ## Advanced options | |
58 --minlength $advanced_options.minlength | |
59 --hmmdetection-strictness $advanced_options.hmmdetection_strictness | |
60 --cb-nclusters $advanced_options.cb_nclusters | |
61 --cb-min-homology-scale $advanced_options.cb_min_homology_scale | |
62 --rre-cutoff $advanced_options.rre_cutoff | |
63 --rre-minlength $advanced_options.rre_minlength | |
44 | 64 |
45 input_tempfile.$file_extension && | 65 input_tempfile.$file_extension && |
46 | 66 |
47 ## copy all content to html folder | 67 ## copy all content to html folder |
48 cp input_tempfile/index.html '${html}' 2> /dev/null && | 68 cp input_tempfile/index.html '${html}' 2> /dev/null && |
49 cp -r input_tempfile/* '${htmloutputfolder}' | 69 cp -r input_tempfile/* '${htmloutputfolder}' |
50 | |
51 ]]> | 70 ]]> |
52 </command> | 71 </command> |
53 <inputs> | 72 <inputs> |
54 <param name="infile" type="data" format="genbank,fasta,embl" label="Sequence file in GenBank,EMBL or FASTA format"/> | 73 <param name="infile" type="data" format="genbank,fasta,embl" label="Sequence file in GenBank,EMBL or FASTA format"/> |
74 <param argument="--genefinding-gff3" type="data" format="gff3" optional="true" label="GFF3 file" help="Specify GFF3 file to extract features from" /> | |
55 | 75 |
56 <conditional name="cond_taxon"> | 76 <conditional name="cond_taxon"> |
57 <param argument="--taxon" type="select" label="Origin of DNA"> | 77 <param argument="--taxon" type="select" label="Taxonomic classification of input sequence" help="Source of DNA"> |
58 <option value="bacteria" selected="True">Bacteria</option> | 78 <option value="bacteria" selected="True">Bacteria</option> |
59 <option value="fungi">Fungi</option> | 79 <option value="fungi">Fungi</option> |
60 </param> | 80 </param> |
61 <when value="bacteria"> | 81 <when value="bacteria"> |
62 <param argument="--genefinding-tool" type="select" label="Specify algorithm used for gene finding" | 82 <expand macro="genefinding"> |
63 help="The 'error' option will raise an error if genefinding is attempted. The 'none' option will not run genefinding"> | |
64 <option value="prodigal" selected="True">Prodigal</option> | 83 <option value="prodigal" selected="True">Prodigal</option> |
65 <option value="prodigal-m">Prodigal Metagenomic/Anonymous</option> | 84 <option value="prodigal-m">Prodigal Metagenomic/Anonymous</option> |
66 <option value="glimmerhmm">GlimmerHMM</option> | 85 </expand> |
67 <option value="none">None</option> | 86 <param argument="--tigrfam" type="boolean" truevalue="--tigrfam" falsevalue="" checked="false" |
68 <option value="error">Error</option> | 87 label="Annotate with TIGRFam" help="Annotate clusters using TIGRFam profiles. TIGRFAMs is a |
69 </param> | 88 collection of manually curated protein families focusing primarily on prokaryotic sequences" /> |
70 </when> | 89 </when> |
71 <when value="fungi"> | 90 <when value="fungi"> |
72 <param argument="--genefinding-tool" type="select" label="Specify algorithm used for gene finding" | 91 <expand macro="genefinding"/> |
73 help="The 'error' option will raise an error if genefinding is attempted. The 'none' option will not run genefinding"> | 92 <param argument="--cassis" type="boolean" truevalue="--cassis" falsevalue="" checked="false" |
74 <option value="glimmerhmm">GlimmerHMM</option> | 93 label="Motif based prediction of SM gene cluster regions" help="Improved prediction of gene cluster borders for fungal BGCs (CASSIS)"/> |
75 <option value="none">None</option> | |
76 <option value="error">Error</option> | |
77 </param> | |
78 <param argument="--cassis" type="boolean" truevalue="--cassis" falsevalue="" checked="False" | |
79 label="Motif based prediction of SM gene cluster regions" /> | |
80 </when> | 94 </when> |
81 </conditional> | 95 </conditional> |
82 | 96 <param argument="--fullhmmer" type="boolean" truevalue="--fullhmmer" falsevalue="" checked="false" |
83 | 97 label="Full genome PFAM anotation" help="Each gene product encoded in the detected BGCs is analyzed against the PFAM database. |
84 <param argument="--cb-general" type="boolean" truevalue="--cb-general" falsevalue="" checked="False" | 98 Hits are annotated in the final Genbank/EMBL files. Also, selecting this option normally increases the runtime"/> |
85 label="BLAST identified clusters against known clusters" | 99 |
86 help="Compare identified clusters against a database of antiSMASH-predicted clusters." /> | 100 <param argument="--clusterhmmer" type="boolean" truevalue="--clusterhmmer" falsevalue="" checked="false" |
87 <param argument="--cb-subclusters" type="boolean" truevalue="--cb-subclusters" falsevalue="" checked="True" | 101 label="PFAM anotation for only clusters" help="Run a cluster-limited HMMer analysis" /> |
88 label="Subcluster BLAST analysis" | 102 |
89 help="Compare identified clusters against known subclusters responsible for synthesising precursors." /> | 103 <param argument="--asf" type="boolean" truevalue="--asf" falsevalue="" checked="True" |
90 <param argument="--cb-knownclusters" type="boolean" truevalue="--cb-knownclusters" falsevalue="" checked="True" | 104 label="Run active site finder analysis" help="Active sites of several highly conserved biosynthetic enzymes are detected and variations of the active sites are reported"/> |
91 label="KnowCluster BLAST analysis" | 105 |
92 help="Compare identified clusters against known gene clusters from the MIBiG database."/> | 106 <param argument="--cc-mibig" type="boolean" truevalue="--cc-mibig" falsevalue="" checked="false" label="Comparison against MIBiG database" help="Run a comparison against the MIBiG database" /> |
107 | |
108 <param argument="--cb-general" type="boolean" truevalue="--cb-general" falsevalue="" checked="false" | |
109 label="BLAST identified clusters against known clusters" | |
110 help="Compare identified clusters against a database of antiSMASH-predicted clusters." /> | |
111 | |
112 <param argument="--cb-knownclusters" type="boolean" truevalue="--cb-knownclusters" falsevalue="" checked="true" | |
113 label="KnowCluster BLAST analysis" | |
114 help="Compare identified clusters against known gene clusters from the MIBiG database. MIBiG is a hand curated data collection of biosynthetic | |
115 gene clusters, which have been experimentally characterized"/> | |
116 | |
117 <param argument="--cb-subclusters" type="boolean" truevalue="--cb-subclusters" falsevalue="" checked="true" | |
118 label="Subcluster BLAST analysis" | |
119 help="The identified clusters are searched against a database containing operons involved in the biosynthesis of common secondary metabolite building | |
120 blocks (e.g. the biosynthesis of non-proteinogenic amino acids)" /> | |
121 | |
122 <param argument="--pfam2go" type="boolean" truevalue="--pfam2go" falsevalue="" checked="true" | |
123 label="Run Pfam to Gene Ontology mapping module" /> | |
124 | |
125 <param argument="--rre" type="boolean" truevalue="--rre" falsevalue="" checked="true" label="RREFinder precision mode" help="Run RREFinder precision mode on all RiPP gene clusters. Many ribosomally | |
126 synthesized and posttranslationally modified peptide classes (RiPPs) are reliant on a domain called the RiPP recognition element (RRE). The RRE binds specifically to a precursor peptide and directs | |
127 the posttranslational modification enzymes to their substrates" /> | |
128 | |
93 <param argument="--smcog-trees" type="boolean" checked="True" truevalue="--smcog-trees" falsevalue="" | 129 <param argument="--smcog-trees" type="boolean" checked="True" truevalue="--smcog-trees" falsevalue="" |
94 label="Analysis of secondary metabolism gene families (smCOGs)" | 130 label="Analysis of secondary metabolism gene families (smCOGs)" |
95 help="Look for sec. met. clusters of orthologous groups."/> | 131 help="It attempts to allocate each gene in the detected gene clusters to a secondary metabolism-specific gene family using profile hidden Markov models specific for |
96 <param argument="--asf" type="boolean" truevalue="--asf" falsevalue="" checked="True" | 132 the conserved sequence region characteristic of this family. In other words, each gene of the cluster is compared to a database of clusters of orthologous groups |
97 label="Run active site finder analysus" /> | 133 of proteins involved in secondary metabolism"/> |
98 <param argument="-pfam2go" type="boolean" truevalue="-pfam2go" falsevalue="" checked="True" | 134 |
99 label="Run Pfam to Gene Ontology mapping module" /> | 135 <param argument="--tta-threshold" type="float" value="0.65" label="Lowest GC content to annotate TTA codons at" |
100 <param argument="--tta-threshold" type="float" value="0.65" label="Lowest GC content to annotate TTA codons at" /> | 136 help="High-GC containing bacterial sequences contain the rare Leu-codon “TTA” as a mean for post-transcriptional regulation by limiting/controlling the amount of TTA-tNRA in the cell. |
101 | 137 This type of regulation is commonly found in secondary metabolite BGCs. This feature will annotate such TTA codons in the identified BGCs. Default: 0.65"/> |
102 <param argument="--clusterhmmer" type="boolean" truevalue="--clusterhmmer" falsevalue="" checked="False" | 138 <section name="advanced_options" title="Advanced options"> |
103 label="Run a cluster-limited HMMer analysis" /> | 139 <param argument="--minlength" type="integer" min="0" value="1000" label="Min length" help="Only process sequences larger than this value. Default: 1000" /> |
104 <param argument="--fullhmmer" type="boolean" truevalue="--fullhmmer" falsevalue="" checked="False" | 140 <param argument="--hmmdetection-strictness" type="select" label="HMM detection strictness" help="Defines which level of strictness to use for HMM-based cluster detection. Default: relaxed"> |
105 label="Run a whole-genome HMMer analysis" /> | 141 <option value="strict">Strict</option> |
106 | 142 <option value="relaxed" selected="true">Relaxed</option> |
107 <param name="extra_cluster" type="select" label="Clusters"> | 143 <option value="loose">Loose</option> |
108 <option value="--cf-create-clusters" selected="True">Find extra clusters</option> | 144 </param> |
109 <option value="--cf-borders-only">Only annotate borders of existing clusters</option> | 145 <param argument="--cb-nclusters" type="integer" min="0" max="50" value="10" label="Number of clusters from ClusterBlast to display" help="Default: 10" /> |
110 </param> | 146 <param argument="--cb-min-homology-scale" type="float" min="0" max="1" value="0" label="ClusterBlast minimum scaling factor" help="A minimum scaling factor |
147 for the query BGC in ClusterBlast results. Default: 0" /> | |
148 <param argument="--rre-cutoff" type="float" min="0" max="100" value="25" label="RRE cutoff" help="Bitscore cutoff for RRE pHMM detection. Default: 25.0" /> | |
149 <param argument="--rre-minlength" type="integer" min="0" max="100" value="50" label="RRE minlength" help="Minimum amino acid length of RRE domains. Default: 50" /> | |
150 </section> | |
111 | 151 |
112 <param name="outputs" type="select" multiple="true" label="Outputs"> | 152 <param name="outputs" type="select" multiple="true" label="Outputs"> |
113 <option value="html" selected="True">HTML file</option> | 153 <option value="html" selected="True">HTML file</option> |
114 <option value="all">All results</option> | 154 <option value="all">All results</option> |
115 <option value="embl">EMBL files</option> | 155 <option value="embl">EMBL files</option> |
116 <option value="gb">GenBank files</option> | 156 <option value="gb">GenBank files</option> |
117 <option value="genecluster_tabular">Gene clusters</option> | 157 <option value="genecluster_tabular">Gene clusters</option> |
158 <option value="log">Log file</option> | |
118 </param> | 159 </param> |
119 | 160 |
120 </inputs> | 161 </inputs> |
121 <outputs> | 162 <outputs> |
122 <collection type="list" name="genecluster_tabular" label="${tool.name} on ${on_string} (Gene Cluster)"> | 163 <collection type="list" name="genecluster_tabular" label="${tool.name} on ${on_string}: Gene Cluster"> |
123 <discover_datasets pattern="(?P<designation>.*)\.txt" directory="input_tempfile" ext="txt" visible="false" /> | 164 <discover_datasets pattern="(?P<designation>.*)\.txt" directory="input_tempfile" ext="txt" visible="false" /> |
124 <filter>'genecluster_tabular' in outputs</filter> | 165 <filter>'genecluster_tabular' in outputs</filter> |
125 </collection> | 166 </collection> |
126 <collection name="genbank" type="list" label="${tool.name} on ${on_string} (GenBank)"> | 167 <collection name="genbank" type="list" label="${tool.name} on ${on_string}: GenBank"> |
127 <discover_datasets pattern="(?P<designation>.*)\.gbk" directory="input_tempfile" ext="genbank" visible="false" /> | 168 <discover_datasets pattern="(?P<designation>.*)\.gbk" directory="input_tempfile" ext="genbank" visible="false" /> |
128 <filter>'gb' in outputs</filter> | 169 <filter>'gb' in outputs or fullhmmer</filter> |
129 </collection> | 170 </collection> |
130 <collection name="embl" type="list" label="${tool.name} on ${on_string} (EMBL)"> | 171 <collection name="embl" type="list" label="${tool.name} on ${on_string}: EMBL"> |
131 <discover_datasets pattern="(?P<designation>.*)\.gbk" directory="input_tempfile" ext="embl" visible="false" /> | 172 <discover_datasets pattern="(?P<designation>.*)\.gbk" directory="input_tempfile" ext="embl" visible="false" /> |
132 <filter>'embl' in outputs</filter> | 173 <filter>'embl' in outputs</filter> |
133 </collection> | 174 </collection> |
134 <collection name="archive" type="list" label="${tool.name} on ${on_string} (all files compressed)"> | 175 <collection name="archive" type="list" label="${tool.name} on ${on_string}: all files compressed"> |
135 <discover_datasets pattern="(?P<designation>.*)\.zip" directory="input_tempfile" ext="zip" visible="false" /> | 176 <discover_datasets pattern="(?P<designation>.*)\.zip" directory="input_tempfile" ext="zip" visible="false" /> |
136 <filter>'all' in outputs</filter> | 177 <filter>'all' in outputs</filter> |
137 </collection> | 178 </collection> |
138 <data format="html" name="html" label="${tool.name} on ${on_string} (html report)" /> | 179 <data format="html" name="html" label="${tool.name} on ${on_string}: HTML report" /> |
180 <data format="txt" name="log" label="${tool.name} on ${on_string}: log file"> | |
181 <filter>'log' in outputs</filter> | |
182 </data> | |
139 </outputs> | 183 </outputs> |
140 <tests> | 184 <tests> |
141 <test> | 185 <test expect_num_outputs="1"> |
142 <param name="infile" value="sequence.fasta"/> | 186 <param name="infile" value="sequence.fasta"/> |
143 <output name="html" file="index.html"/> | 187 <output name="html" file="index.html"/> |
144 </test> | 188 </test> |
145 <test> | 189 <test expect_num_outputs="2"> |
146 <param name="infile" value="sequence.gb"/> | 190 <param name="infile" value="sequence.gb"/> |
147 <param name="outputs" value="html,gb"/> | 191 <param name="outputs" value="html,gb"/> |
148 <param name="taxon" value="fungi"/> | 192 <param name="taxon" value="fungi"/> |
149 <param name="clusterhmmer" value="True"/> | 193 <param name="clusterhmmer" value="true"/> |
150 <param name="fullhmmer" value="True"/> | 194 <param name="fullhmmer" value="true"/> |
151 <param name="extra_cluster" value="--cf-create-clusters"/> | 195 <param name="cassis" value="true"/> |
152 <param name="cassis" value="True"/> | 196 <param name="cb_general" value="true"/> |
153 <param name="cb_general" value="True"/> | |
154 <output_collection name="genbank" type="list"> | 197 <output_collection name="genbank" type="list"> |
155 <element name="ARBH01000003.1.cluster001" file="ARBH01000003.1.cluster001" ftype="genbank" /> | 198 <element name="input_tempfile" file="test_02.genbank" ftype="genbank" lines_diff="2"/> |
156 <element name="ARBH01000003.1.final" file="ARBH01000003.1.final" ftype="genbank"/> | |
157 </output_collection> | 199 </output_collection> |
158 <output name="html" file="index.2.html"/> | 200 <output name="html" file="index.2.html" ftype="html"> |
201 <assert_contents> | |
202 <has_text text="No results found on input"/> | |
203 </assert_contents> | |
204 </output> | |
159 </test> | 205 </test> |
206 | |
207 <test expect_num_outputs="3"> | |
208 <param name="infile" value="sequence_long.fasta"/> | |
209 <param name="genefinding_gff3" value="annotation.gff3"/> | |
210 <param name="fullhmmer" value="true"/> | |
211 <param name="cc_mibig" value="true"/> | |
212 <param name="pfam2go" value="true"/> | |
213 <param name="rre" value="true"/> | |
214 <param name="outputs" value="html,gb,log"/> | |
215 <section name="advanced_options"> | |
216 <param name="minlength" value="1000"/> | |
217 <param name="hmmdetection_strictness" value="strict"/> | |
218 <param name="cb_nclusters" value="10"/> | |
219 <param name="cb_min_homology_scale" value="0.1"/> | |
220 <param name="rre_cutoff" value="10"/> | |
221 <param name="rre_minlength" value="50"/> | |
222 </section> | |
223 <output_collection name="genbank" type="list"> | |
224 <element name="input_tempfile" file="test_03.genbank" ftype="genbank" lines_diff="2"/> | |
225 </output_collection> | |
226 <output name="html" file="index.3.html" ftype="html"> | |
227 <assert_contents> | |
228 <has_text text="No results found on input"/> | |
229 </assert_contents> | |
230 </output> | |
231 <output name="log"> | |
232 <assert_contents> | |
233 <has_text text="antiSMASH status: SUCCESS"/> | |
234 <has_text text="HMM detection using strictness: strict"/> | |
235 </assert_contents> | |
236 </output> | |
237 </test> | |
238 | |
160 </tests> | 239 </tests> |
161 <help> | 240 <help> |
162 <![CDATA[ | 241 <![CDATA[ |
163 | 242 |
164 **What it does** | 243 **What it does** |
193 The downward-pointing arrow will open a menu offering to download the complete set of results from the antiSMASH run, a summary Excel file and to the summary EMBL/GenBank output file. | 272 The downward-pointing arrow will open a menu offering to download the complete set of results from the antiSMASH run, a summary Excel file and to the summary EMBL/GenBank output file. |
194 The EMBL/GenBank file can be viewed in a genome browser such as Artemis. | 273 The EMBL/GenBank file can be viewed in a genome browser such as Artemis. |
195 | 274 |
196 ]]> | 275 ]]> |
197 </help> | 276 </help> |
198 <citations> | 277 <expand macro="citations" /> |
199 <citation type="doi">10.1093/nar/gkv437</citation> | |
200 </citations> | |
201 </tool> | 278 </tool> |