diff multi_antiSMASH.xml @ 0:6a37d0a4510a default tip

initial uploaded
author bjoern-gruening
date Thu, 15 Mar 2012 05:23:03 -0400
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/multi_antiSMASH.xml	Thu Mar 15 05:23:03 2012 -0400
@@ -0,0 +1,119 @@
+<tool id="multi_antiSMASH" name="Secondary Metabolites" version="0.1">
+  <description>and Antibiotics Analysis (multi antiSMASH)</description>
+  <command interpreter="python">multi_antiSMASH_wrapper.py 
+## The command is a Cheetah template which allows some Python based syntax.
+## Lines starting hash hash are comments. Galaxy will turn newlines into spaces
+## ./antismash.py Tue6071_genome.fasta --geneclustertypes 1 --fullblast y --fullhmm y
+
+    #if $input_opts.input_opts_selector == "fasta":
+        --input $infile
+        --glimmer_prediction $glimmer_prediction
+    #else:
+        --input $infile
+    #end if
+
+    --input_format $input_opts.input_opts_selector
+
+    $eukaryotic 
+    $genecluster 
+    $smCOG 
+    $wg_blast 
+    --geneclustertypes $geneclustertypes
+    --geneclusterprots $geneclusterprots
+    --geneclusterprots_gff $geneclusterprots_gff
+    --embl_path $embl
+    > /dev/null 2> /dev/null
+  </command>
+  <inputs>
+
+    <conditional name="input_opts">
+        <param name="input_opts_selector" type="select" label="Input format">
+          <option value="fasta" selected="True">FASTA file (not annotated)</option>
+          <option value="genbank">GenBank file (annotated)</option>
+          <option value="embl">embl file (annotated)</option>
+        </param>
+        <when value="fasta">
+            <param name="infile" type="data" format="fasta" label="Sequence File"/>
+            <param name="glimmer_prediction" type="data" format="tabular" label="Glimmer Prediction File"/>
+        </when>
+        <when value="embl">
+            <param name="infile" type="data" format="embl" label="embl Sequence File"/>
+        </when>
+        <when value="genbank">
+            <param name="infile" type="data" format="embl" label="GenBank Sequence File"/>
+        </when>
+    </conditional>
+
+
+
+
+    <param name="eukaryotic" type="boolean" label="is the DNA of Eukaryotic origin" truevalue="--eukaryotic" falsevalue="" checked="false" />
+    <param name="smCOG" type="boolean" label="smCOG analysis for functional prediction and phylogenetic analysis of genes" falsevalue="" truevalue="--smcogs" checked="true" />
+    <param name="genecluster" type="boolean" label="Gene Cluster Blast Comparative Analysis" truevalue="--clusterblast" falsevalue="" checked="true" />
+    <param name="wg_blast" type="boolean" label="Whole genome BLAST results in EMBL output" truevalue="--fullblast" falsevalue="" checked="true" />
+    <param name="pfam" type="boolean" label="Whole genome PFAM results in EMBL output" truevalue="--fullhmm" falsevalue="" checked="true" />
+
+        <param name="geneclustertypes" type="select" display="checkboxes" multiple="true" label="Gene cluster types to search">
+            <option value="1" selected="True">all</option>
+            <option value="2">type I polyketide synthases</option>
+            <option value="3">type II polyketide synthases</option>
+            <option value="4">type III polyketide synthases</option>
+            <option value="5">nonribosomal peptide synthetases</option>
+            <option value="6">terpene synthases</option>
+            <option value="7">lantibiotics</option>
+            <option value="8">bacteriocins</option>
+            <option value="9">beta-lactams</option>
+            <option value="10">aminoglycosides / aminocyclitols</option>
+            <option value="11">aminocoumarins</option>
+            <option value="12">siderophores</option>
+            <option value="13">ectoines</option>
+            <option value="14">butyrolactones</option>
+            <option value="15">indoles</option>
+            <option value="16">nucleosides</option>
+            <option value="17">phosphoglycolipids</option>
+            <option value="18">melanins</option>
+            <option value="19">others</option>
+        </param>
+  </inputs>
+  <outputs>
+    <data format="fasta" name="geneclusterprots" label="${tool.name} on ${on_string} (Gen Cluster Proteins)" />
+    <data format="gff3" name="geneclusterprots_gff" label="${tool.name} on ${on_string} (Gen Cluster Proteins)" />
+    <data name="embl" format="text" label="${tool.name} on ${on_string} EMBL Output Format">
+    </data>
+  </outputs>
+  <help>
+    
+.. class:: infomark
+
+That version of antiSMASH can only handle multiple sequence files.
+It will run antiSMASH automatically on each sequence and aggregate the most important information from all runs.
+It will not provide an interactive HTML output file. If you need that please use the normal antiSMASH version on a single sequence.
+
+
+.. class:: warningmark
+
+**Warning on FASTA Header**
+
+The FASTA header should not contain any special letters, like '|'. Please replace them with the 'sed-tool'.
+
+
+**What it does**
+
+antiSMASH allows the rapid genome-wide identification, annotation and analysis of secondary metabolite biosynthesis gene clusters in bacterial and fungal genomes. 
+It integrates and cross-links with a large number of in silico secondary metabolite analysis tools that have been published earlier.
+
+
+**Input**
+
+If you don't have an annotated GenBank or embl file you also can provide a glimmer prediction output. Created with glimmer or glimmerHMM.
+
+
+**References**
+
+Marnix H. Medema, Kai Blin, Peter Cimermancic, Victor de Jager, Piotr Zakrzewski, Michael A. Fischbach, Tilmann Weber, 
+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.
+
+http://antismash.secondarymetabolites.org/help.html
+
+  </help>
+</tool>