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