|
20
|
1 <tool id="antismash" name="Secondary Metabolites" version="2.0.2.1">
|
|
4
|
2 <description>and Antibiotics Analysis (antiSMASH)</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package" version="3.0">hmmer</requirement>
|
|
25
|
5 <requirement type="package">hmmer</requirement>
|
|
4
|
6 <requirement type="package" version="2.2.28">blast+</requirement>
|
|
25
|
7 <requirement type="package">blast+</requirement>
|
|
4
|
8 <requirement type="package" version="3.8.31">muscle</requirement>
|
|
25
|
9 <requirement type="package">muscle</requirement>
|
|
17
|
10 <requirement type="package" version="1.4.0-post-1">straight.plugin</requirement>
|
|
19
|
11 <requirement type="package" version="1.62">biopython</requirement>
|
|
|
12 <requirement type="package" version="1.2.6">pyquery</requirement>
|
|
17
|
13 <requirement type="package" version="0.1.2">helperlibs</requirement>
|
|
21
|
14 <requirement type="package" version="0.9">cssselect</requirement>
|
|
4
|
15 <requirement type="package" version="2.0.2">antismash</requirement>
|
|
25
|
16 <requirement type="package">antismash</requirement>
|
|
4
|
17 </requirements>
|
|
|
18 <command>
|
|
15
|
19 #import os, glob
|
|
22
|
20 #set $outputfolder = $html.files_path
|
|
23
|
21 #if str($infile.ext) == 'genbank':
|
|
|
22 #set $file_extension = 'gb'
|
|
|
23 #else:
|
|
|
24 ## TODO add embl as input file
|
|
22
|
25 #set $file_extension = 'gb'
|
|
|
26 #end if
|
|
|
27
|
|
|
28 ln -s $infile #echo 'input_tempfile.' + $file_extension#;
|
|
15
|
29 mkdir -p $outputfolder;
|
|
4
|
30 run_antismash.py
|
|
25
|
31 --cpus 12
|
|
13
|
32 --enable $types
|
|
15
|
33 --input-type 'nucl'
|
|
4
|
34 $smcogs
|
|
|
35 $clusterblast
|
|
|
36 $subclusterblast
|
|
|
37 $inclusive
|
|
|
38 $full_hmmer
|
|
|
39 $full_blast
|
|
25
|
40 $eukaryotic
|
|
|
41
|
|
0
|
42
|
|
15
|
43 #if str($pfam_database) != "None":
|
|
|
44 --pfamdir $pfam_database.fields.path
|
|
|
45 #end if
|
|
|
46
|
|
25
|
47 --debug
|
|
|
48
|
|
15
|
49 --disable-embl
|
|
|
50 --outputfolder $outputfolder
|
|
|
51
|
|
22
|
52 #echo 'input_tempfile.' + $file_extension#
|
|
0
|
53
|
|
9
|
54 ## leave out the start and end features, it can be easily replaced with Galaxy tools
|
|
|
55 ##--from START Start analysis at nucleotide specified
|
|
15
|
56 ##--to END
|
|
|
57
|
|
25
|
58 2>&1
|
|
|
59
|
|
|
60 ##
|
|
15
|
61 ## shuffling files to create the correct outputs for Galaxy
|
|
25
|
62 ##
|
|
|
63
|
|
15
|
64 ## html output
|
|
25
|
65 ;
|
|
|
66 cp #echo os.path.join($outputfolder, 'index.html')# $html 2> /dev/null
|
|
15
|
67
|
|
|
68 ## gene clusters
|
|
16
|
69 #if 'geneclusterprots_tabular' in str($outputs).split(','):
|
|
25
|
70 ;
|
|
|
71 cp #echo os.path.join($outputfolder, 'geneclusters.txt')# $geneclusterprots_tabular 2> /dev/null
|
|
15
|
72 #end if
|
|
|
73
|
|
22
|
74 #if 'geneclusterprots_fasta' in str($outputs).split(','):
|
|
25
|
75 ;
|
|
|
76 cp #echo os.path.join($outputfolder, '*_genecluster_proteins.fa')# $geneclusterprots_fasta 2> /dev/null
|
|
22
|
77 #end if
|
|
|
78
|
|
|
79
|
|
15
|
80 ##SVG images
|
|
16
|
81 #if 'archive_svgs' in str($outputs).split(','):
|
|
25
|
82 ;
|
|
|
83 cd #echo os.path.join($outputfolder, 'svg')#
|
|
22
|
84 #if $clusterblast:
|
|
25
|
85 ;
|
|
|
86 tar cfz $archive_svgs *_all.svg genecluster* 2> /dev/null
|
|
22
|
87 #else:
|
|
25
|
88 ;
|
|
|
89 tar cfz $archive_svgs genecluster*
|
|
22
|
90 #end if
|
|
15
|
91 #end if
|
|
|
92
|
|
|
93 ##all files in a archive
|
|
16
|
94 #if 'archive' in str($outputs).split(','):
|
|
25
|
95 ;
|
|
15
|
96 cd $outputfolder;
|
|
25
|
97 tar cf $archive *.zip 2> /dev/null
|
|
15
|
98 #end if
|
|
|
99
|
|
|
100 ## genbank
|
|
16
|
101 #if 'gb' in str($outputs).split(','):
|
|
25
|
102 ;
|
|
|
103 cat #echo os.path.join($outputfolder, '*.gbk')# > $genbank 2> /dev/null
|
|
15
|
104 #end if
|
|
0
|
105
|
|
|
106 </command>
|
|
|
107 <inputs>
|
|
22
|
108 <param name="infile" type="data" format="genbank" label="Nucleotide sequence file in GenBank format"/>
|
|
0
|
109
|
|
25
|
110 <param name="eukaryotic" type="select" label="Origin of DNA">
|
|
|
111 <option value="" selected="True">Prokaryotic</option>
|
|
|
112 <option value="--eukaryotic">Eukaryotic</option>
|
|
|
113 </param>
|
|
|
114
|
|
22
|
115 <param name="clusterblast" type="boolean" label="BLAST identified clusters against known clusters"
|
|
|
116 help="(--clusterblast)"
|
|
|
117 truevalue="--clusterblast" falsevalue="" checked="True" />
|
|
|
118 <param name="subclusterblast" type="boolean" label="Subcluster BLAST analysis"
|
|
|
119 help="(--subclusterblast)"
|
|
|
120 truevalue="--subclusterblast" falsevalue="" checked="false" />
|
|
|
121 <param name="smcogs" type="boolean" label="Analysis of secondary metabolism gene families (smCOGs)"
|
|
11
|
122 falsevalue="" truevalue="--smcogs" checked="True" />
|
|
|
123
|
|
22
|
124 <param name="full_blast" type="boolean" label="Run a whole-genome BLAST analysis"
|
|
|
125 help="(--full-blast)"
|
|
|
126 truevalue="--full-blast" falsevalue="" checked="False" />
|
|
|
127 <param name="full_hmmer" type="boolean" label="Run a whole-genome Pfam analysis"
|
|
|
128 help="(--full-hmmer)"
|
|
|
129 truevalue="--full-hmmer" falsevalue="" checked="false" />
|
|
0
|
130
|
|
22
|
131 <param name="inclusive" type="boolean" label="Use inclusive algorithm for cluster detection"
|
|
|
132 help="(--inclusive)"
|
|
|
133 truevalue="--inclusive" falsevalue="" checked="false" />
|
|
0
|
134
|
|
15
|
135 <param name="pfam_database" type="select" optional="true" label="Pfam database" help="Pfam Covariance models">
|
|
4
|
136 <options from_file="antismash.loc">
|
|
|
137 <column name="value" index="0"/>
|
|
|
138 <column name="name" index="1"/>
|
|
|
139 <column name="path" index="2"/>
|
|
|
140 </options>
|
|
|
141 </param>
|
|
|
142
|
|
0
|
143 <param name="types" type="select" display="checkboxes" multiple="true" label="Gene cluster types to search">
|
|
9
|
144 <option value="t1pks" selected="True">type I polyketide synthases</option>
|
|
|
145 <option value="t2pks" selected="True">type II polyketide synthases</option>
|
|
|
146 <option value="t3pks" selected="True">type III polyketide synthases</option>
|
|
|
147 <option value="t4pks" selected="True">type IV polyketide synthases</option>
|
|
|
148 <option value="transatpks" selected="True">trans-AT PKS</option>
|
|
|
149 <option value="nrps" selected="True">nonribosomal peptide synthetases</option>
|
|
|
150 <option value="terpene" selected="True">terpene synthases</option>
|
|
|
151 <option value="lantipeptide" selected="True">lantipeptides</option>
|
|
|
152 <option value="bacteriocin" selected="True">bacteriocins</option>
|
|
|
153 <option value="blactam" selected="True">beta-lactams</option>
|
|
|
154 <option value="amglyccycl" selected="True">aminoglycosides / aminocyclitols</option>
|
|
|
155 <option value="aminocoumarin" selected="True">aminocoumarins</option>
|
|
|
156 <option value="siderophore" selected="True">siderophores</option>
|
|
|
157 <option value="ectoine" selected="True">ectoines</option>
|
|
|
158 <option value="butyrolactone" selected="True">butyrolactones</option>
|
|
|
159 <option value="indole" selected="True">indoles</option>
|
|
|
160 <option value="nucleoside" selected="True">nucleosides</option>
|
|
|
161 <option value="phosphoglycolipid" selected="True">phosphoglycolipids</option>
|
|
|
162 <option value="oligosaccharide" selected="True">oligosaccharides</option>
|
|
|
163 <option value="furan" selected="True">furans</option>
|
|
|
164 <option value="hserlactone" selected="True">hserlactones</option>
|
|
|
165 <option value="thiopeptide" selected="True">thiopeptides</option>
|
|
|
166 <option value="phenazine" selected="True">phenazines</option>
|
|
|
167 <option value="phosphonate" selected="True">phosphonates</option>
|
|
15
|
168 <option value="other" selected="True">others</option>
|
|
|
169 </param>
|
|
|
170
|
|
25
|
171 <param name="outputs" type="select" multiple="true" label="Additional outputs">
|
|
15
|
172 <option value="geneclusterprots_fasta" selected="True">Gene cluster proteins (FASTA)</option>
|
|
|
173 <option value="geneclusterprots_tabular">Gene cluster proteins (Tabular)</option>
|
|
|
174 <option value="archive_svgs">All clusters as image (compressed)</option>
|
|
|
175 <option value="archive">All files compressed</option>
|
|
|
176 <option value="gb">Annotated genome (GenBank)</option>
|
|
0
|
177 </param>
|
|
|
178
|
|
|
179 </inputs>
|
|
|
180 <outputs>
|
|
22
|
181 <data format="fasta" name="geneclusterprots_fasta" label="${tool.name} on ${on_string} (Gen Cluster Proteins)">
|
|
15
|
182 <filter>'geneclusterprots_fasta' in outputs</filter>
|
|
|
183 </data>
|
|
22
|
184 <data format="tabular" name="geneclusterprots_tabular" label="${tool.name} on ${on_string} (Gen Cluster Proteins)">
|
|
15
|
185 <filter>'geneclusterprots_tabular' in outputs</filter>
|
|
|
186 </data>
|
|
22
|
187 <data format="tar" name="archive" label="${tool.name} on ${on_string} (all files compressed)">
|
|
15
|
188 <filter>'archive' in outputs</filter>
|
|
|
189 </data>
|
|
22
|
190 <data format="tar.gz" name="archive_svgs" label="${tool.name} on ${on_string} (SVG images)">
|
|
15
|
191 <filter>'archive_svgs' in outputs</filter>
|
|
|
192 </data>
|
|
|
193 <data format="html" name="html" label="${tool.name} on ${on_string} (html report)">
|
|
25
|
194 <!-- html is default output at any time.
|
|
15
|
195 <filter>'html' in outputs</filter>
|
|
25
|
196 -->
|
|
15
|
197 </data>
|
|
|
198 <data name="genbank" format="genbank" label="${tool.name} on ${on_string} (genbank)">
|
|
|
199 <filter>'gb' in outputs</filter>
|
|
0
|
200 </data>
|
|
|
201 </outputs>
|
|
|
202 <help>
|
|
|
203
|
|
|
204 .. class:: infomark
|
|
|
205
|
|
|
206 **What it does**
|
|
|
207
|
|
|
208 antiSMASH allows the rapid genome-wide identification, annotation and analysis of secondary metabolite biosynthesis gene clusters in bacterial and fungal genomes.
|
|
|
209 It integrates and cross-links with a large number of in silico secondary metabolite analysis tools that have been published earlier.
|
|
|
210
|
|
|
211
|
|
|
212 **Input**
|
|
|
213
|
|
22
|
214 The ideal input for antiSMASH is an annotated nucleotide file in Genbank format. If no annotation is available,
|
|
|
215 we recommend running your sequence through an annotation pipeline like RAST are the one included in Galaxy.
|
|
11
|
216
|
|
|
217
|
|
|
218 There are several optional analyses that may or may not be run on your sequence.
|
|
|
219 Highly recommended is the Gene Cluster Blast Comparative Analysis, which runs BlastP using each amino acid sequence from a detected gene cluster as a
|
|
|
220 query on a large database of predicted protein sequences from secondary metabolite biosynthetic gene clusters, and pools the results to identify
|
|
|
221 the gene clusters that are most homologous to the gene cluster that was detected in your query nucleotide sequence.
|
|
|
222
|
|
|
223
|
|
|
224 Also available is the analysis of secondary metabolism gene families (smCOGs).
|
|
|
225 This analysis attempts to allocate each gene in the detected gene clusters to a secondary metabolism-specific gene
|
|
|
226 family using profile hidden Markov models specific for the conserved sequence region characteristic of this family.
|
|
|
227 Additionally, a phylogenetic tree is constructed of each gene together with the (max. 100) sequences of the smCOG seed alignment.
|
|
|
228
|
|
|
229
|
|
|
230 For the most thorough genome analysis, we provide genome-wide PFAM HMM analysis of all genes in the genome through modules of the CLUSEAN pipeline.
|
|
|
231 Of course, some regions important to secondary metabolism may have been missed in the gene cluster identification stage
|
|
|
232 (e.g. because they represent the biosynthetic pathway of a yet unknown secondary metabolite).
|
|
|
233 Therefore, when genome-wide PFAM HMM analysis is selected, the PFAM frequencies are also used to find all genome regions in which PFAM domains typical for secondary metabolism are overrepresented.
|
|
0
|
234
|
|
|
235
|
|
|
236 **References**
|
|
|
237
|
|
|
238 Marnix H. Medema, Kai Blin, Peter Cimermancic, Victor de Jager, Piotr Zakrzewski, Michael A. Fischbach, Tilmann Weber,
|
|
|
239 Rainer Breitling and Eriko Takano (2011). antiSMASH: Rapid identification, annotation and analysis of secondary metabolite biosynthesis gene clusters. Nucleic Acids Research, doi: 10.1093/nar/gkr466.
|
|
|
240
|
|
|
241 http://antismash.secondarymetabolites.org/help.html
|
|
|
242
|
|
25
|
243
|
|
|
244 Bjoern A. Gruening: https://github.com/bgruening/galaxytools/tree/master/antismash
|
|
|
245
|
|
0
|
246 </help>
|
|
|
247 </tool>
|
