|
0
|
1 <tool id="antismash" name="Secondary Metabolites" version="2.0.2.0">
|
|
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>
|
|
5
|
7 <requirement type="package" version="2.0.2">antismash_python_deps</requirement>
|
|
4
|
8 <requirement type="package" version="2.0.2">antismash</requirement>
|
|
|
9 </requirements>
|
|
|
10 <command>
|
|
15
|
11 #import os, glob
|
|
|
12 #set $outputfolder = os.path.join($html.files_path, 'antismash')
|
|
|
13 ln -s $infile #echo 'input_tempfile.' + $infile.ext#;
|
|
|
14 mkdir -p $outputfolder;
|
|
4
|
15 run_antismash.py
|
|
|
16 --cpus 4
|
|
13
|
17 --enable $types
|
|
15
|
18 --input-type 'nucl'
|
|
4
|
19 $smcogs
|
|
|
20 $clusterblast
|
|
|
21 $subclusterblast
|
|
|
22 $inclusive
|
|
|
23 $full_hmmer
|
|
|
24 $full_blast
|
|
0
|
25
|
|
15
|
26 #if str($pfam_database) != "None":
|
|
|
27 --pfamdir $pfam_database.fields.path
|
|
|
28 #end if
|
|
|
29
|
|
|
30 --disable-embl
|
|
|
31 --outputfolder $outputfolder
|
|
|
32
|
|
|
33
|
|
|
34 #echo 'input_tempfile.' + $infile.ext#
|
|
0
|
35
|
|
9
|
36 ## leave out the start and end features, it can be easily replaced with Galaxy tools
|
|
|
37 ##--from START Start analysis at nucleotide specified
|
|
15
|
38 ##--to END
|
|
|
39
|
|
|
40 ;
|
|
|
41 ## shuffling files to create the correct outputs for Galaxy
|
|
|
42
|
|
|
43 ## html output
|
|
16
|
44 #if 'html' in str($outputs).split(','):
|
|
15
|
45 cp #echo os.path.join($outputfolder, 'index.html')# $html;
|
|
|
46 #end if
|
|
|
47
|
|
|
48 ## gene clusters
|
|
16
|
49 #if 'geneclusterprots_tabular' in str($outputs).split(','):
|
|
15
|
50 cp #echo os.path.join($outputfolder, 'geneclusters.txt')# $geneclusterprots;
|
|
|
51 #end if
|
|
|
52
|
|
|
53 ##SVG images
|
|
16
|
54 #if 'archive_svgs' in str($outputs).split(','):
|
|
15
|
55 cd #echo os.path.join($outputfolder, 'svg')#;
|
|
16
|
56 tar cfz $archive_svgs *_all.svg genecluster*;
|
|
15
|
57 #end if
|
|
|
58
|
|
|
59 ##all files in a archive
|
|
16
|
60 #if 'archive' in str($outputs).split(','):
|
|
15
|
61 cd $outputfolder;
|
|
|
62 tar cf $archive *.zip;
|
|
|
63 #end if
|
|
|
64
|
|
|
65 ## genbank
|
|
16
|
66 #if 'gb' in str($outputs).split(','):
|
|
15
|
67 #for $gb_file in glob.glob( os.path.join($outputfolder, '*.gbk') ):
|
|
|
68 cat $gb_file >> $genbank;
|
|
|
69 #end for
|
|
|
70 #end if
|
|
0
|
71
|
|
|
72 </command>
|
|
|
73 <inputs>
|
|
|
74 <param name="infile" type="data" format="gb,embl" label="Nucleotide sequence file in GenBank or EMBL format"/>
|
|
|
75
|
|
11
|
76 <param name="clusterblast" type="boolean" label="BLAST identified clusters against known clusters" truevalue="--clusterblast" falsevalue="" checked="True" />
|
|
|
77 <param name="smcogs" type="boolean" label="analysis of secondary metabolism gene families (smCOGs)"
|
|
|
78 falsevalue="" truevalue="--smcogs" checked="True" />
|
|
|
79
|
|
|
80 <param name="full_blast" type="boolean" label="Run a whole-genome BLAST analysis" truevalue="--full-blast" falsevalue="" checked="False" />
|
|
|
81 <param name="subclusterblast" type="boolean" label="Subcluster Blast analysis" truevalue="--subclusterblast" falsevalue="" checked="false" />
|
|
|
82 <param name="full_hmmer" type="boolean" label="Run a whole-genome Pfam analysis" truevalue="--full-hmmer" falsevalue="" checked="false" />
|
|
0
|
83
|
|
|
84 <param name="inclusive" type="boolean" label="Use inclusive algorithm for cluster detection" truevalue="--inclusive" falsevalue="" checked="false" />
|
|
|
85
|
|
15
|
86 <param name="pfam_database" type="select" optional="true" label="Pfam database" help="Pfam Covariance models">
|
|
4
|
87 <options from_file="antismash.loc">
|
|
|
88 <column name="value" index="0"/>
|
|
|
89 <column name="name" index="1"/>
|
|
|
90 <column name="path" index="2"/>
|
|
|
91 </options>
|
|
|
92 </param>
|
|
|
93
|
|
0
|
94 <param name="types" type="select" display="checkboxes" multiple="true" label="Gene cluster types to search">
|
|
9
|
95 <option value="t1pks" selected="True">type I polyketide synthases</option>
|
|
|
96 <option value="t2pks" selected="True">type II polyketide synthases</option>
|
|
|
97 <option value="t3pks" selected="True">type III polyketide synthases</option>
|
|
|
98 <option value="t4pks" selected="True">type IV polyketide synthases</option>
|
|
|
99 <option value="transatpks" selected="True">trans-AT PKS</option>
|
|
|
100 <option value="nrps" selected="True">nonribosomal peptide synthetases</option>
|
|
|
101 <option value="terpene" selected="True">terpene synthases</option>
|
|
|
102 <option value="lantipeptide" selected="True">lantipeptides</option>
|
|
|
103 <option value="bacteriocin" selected="True">bacteriocins</option>
|
|
|
104 <option value="blactam" selected="True">beta-lactams</option>
|
|
|
105 <option value="amglyccycl" selected="True">aminoglycosides / aminocyclitols</option>
|
|
|
106 <option value="aminocoumarin" selected="True">aminocoumarins</option>
|
|
|
107 <option value="siderophore" selected="True">siderophores</option>
|
|
|
108 <option value="ectoine" selected="True">ectoines</option>
|
|
|
109 <option value="butyrolactone" selected="True">butyrolactones</option>
|
|
|
110 <option value="indole" selected="True">indoles</option>
|
|
|
111 <option value="nucleoside" selected="True">nucleosides</option>
|
|
|
112 <option value="phosphoglycolipid" selected="True">phosphoglycolipids</option>
|
|
|
113 <option value="oligosaccharide" selected="True">oligosaccharides</option>
|
|
|
114 <option value="furan" selected="True">furans</option>
|
|
|
115 <option value="hserlactone" selected="True">hserlactones</option>
|
|
|
116 <option value="thiopeptide" selected="True">thiopeptides</option>
|
|
|
117 <option value="phenazine" selected="True">phenazines</option>
|
|
|
118 <option value="phosphonate" selected="True">phosphonates</option>
|
|
15
|
119 <option value="other" selected="True">others</option>
|
|
|
120 </param>
|
|
|
121
|
|
|
122 <param name="outputs" type="select" multiple="true" label="Output formats">
|
|
|
123 <option value="geneclusterprots_fasta" selected="True">Gene cluster proteins (FASTA)</option>
|
|
|
124 <option value="geneclusterprots_tabular">Gene cluster proteins (Tabular)</option>
|
|
|
125 <option value="html" selected="True">Interactive summary page (html)</option>
|
|
|
126 <option value="archive_svgs">All clusters as image (compressed)</option>
|
|
|
127 <option value="archive">All files compressed</option>
|
|
|
128 <option value="gb">Annotated genome (GenBank)</option>
|
|
0
|
129 </param>
|
|
|
130
|
|
|
131 </inputs>
|
|
|
132 <outputs>
|
|
15
|
133 <data format="fasta" name="geneclusterprots" label="${tool.name} on ${on_string} (Gen Cluster Proteins)">
|
|
|
134 <filter>'geneclusterprots_fasta' in outputs</filter>
|
|
|
135 </data>
|
|
|
136 <data format="fasta" name="geneclusterprots" label="${tool.name} on ${on_string} (Gen Cluster Proteins)">
|
|
|
137 <filter>'geneclusterprots_tabular' in outputs</filter>
|
|
|
138 </data>
|
|
|
139 <data format="gzipped" name="archive" label="${tool.name} on ${on_string} (all files compressed)">
|
|
|
140 <filter>'archive' in outputs</filter>
|
|
|
141 </data>
|
|
|
142 <data format="gzipped" name="archive_svgs" label="${tool.name} on ${on_string} (SVG images)">
|
|
|
143 <filter>'archive_svgs' in outputs</filter>
|
|
|
144 </data>
|
|
|
145 <data format="html" name="html" label="${tool.name} on ${on_string} (html report)">
|
|
|
146 <filter>'html' in outputs</filter>
|
|
|
147 </data>
|
|
|
148 <data name="genbank" format="genbank" label="${tool.name} on ${on_string} (genbank)">
|
|
|
149 <filter>'gb' in outputs</filter>
|
|
0
|
150 </data>
|
|
|
151 </outputs>
|
|
|
152 <help>
|
|
|
153
|
|
|
154 .. class:: infomark
|
|
|
155
|
|
|
156 **What it does**
|
|
|
157
|
|
|
158 antiSMASH allows the rapid genome-wide identification, annotation and analysis of secondary metabolite biosynthesis gene clusters in bacterial and fungal genomes.
|
|
|
159 It integrates and cross-links with a large number of in silico secondary metabolite analysis tools that have been published earlier.
|
|
|
160
|
|
|
161
|
|
|
162 **Input**
|
|
|
163
|
|
11
|
164 The ideal input for antiSMASH is an annotated nucleotide file in Genbank format or EMBL format. If no annotation is available,
|
|
|
165 we recommend running your sequence through an annotation pipeline like RAST are one included in Galaxy.
|
|
|
166
|
|
|
167
|
|
|
168 There are several optional analyses that may or may not be run on your sequence.
|
|
|
169 Highly recommended is the Gene Cluster Blast Comparative Analysis, which runs BlastP using each amino acid sequence from a detected gene cluster as a
|
|
|
170 query on a large database of predicted protein sequences from secondary metabolite biosynthetic gene clusters, and pools the results to identify
|
|
|
171 the gene clusters that are most homologous to the gene cluster that was detected in your query nucleotide sequence.
|
|
|
172
|
|
|
173
|
|
|
174 Also available is the analysis of secondary metabolism gene families (smCOGs).
|
|
|
175 This analysis attempts to allocate each gene in the detected gene clusters to a secondary metabolism-specific gene
|
|
|
176 family using profile hidden Markov models specific for the conserved sequence region characteristic of this family.
|
|
|
177 Additionally, a phylogenetic tree is constructed of each gene together with the (max. 100) sequences of the smCOG seed alignment.
|
|
|
178
|
|
|
179
|
|
|
180 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.
|
|
|
181 Of course, some regions important to secondary metabolism may have been missed in the gene cluster identification stage
|
|
|
182 (e.g. because they represent the biosynthetic pathway of a yet unknown secondary metabolite).
|
|
|
183 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
|
184
|
|
|
185
|
|
|
186 **References**
|
|
|
187
|
|
|
188 Marnix H. Medema, Kai Blin, Peter Cimermancic, Victor de Jager, Piotr Zakrzewski, Michael A. Fischbach, Tilmann Weber,
|
|
|
189 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.
|
|
|
190
|
|
|
191 http://antismash.secondarymetabolites.org/help.html
|
|
|
192
|
|
|
193 </help>
|
|
|
194 </tool>
|
