Mercurial > repos > dsobral > breseq

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/breseq.xml	Sat Mar 03 11:47:47 2018 -0500
@@ -0,0 +1,160 @@
+<tool id="breseq" name="Breseq Variant Report" version="0.31.1" hidden="false">
+    <description>Runs Breseq software on a set of fastq files</description>
+
+    <requirements>
+        <requirement type="package" version="0.31.1">breseq</requirement>
+    </requirements>
+
+    <command interpreter="python">
+        breseq_wrapper.py
+
+        $outfile
+        $outfile.files_path
+
+        --num-processors \${GALAXY_SLOTS:-4}
+
+        #if str($reference.source) == "history":
+	    #for $i, $s in enumerate( $reference.ref_series )
+            	-r $s.own_genome
+            #end for
+        #else:
+            -r $reference.fixed_genome.fields.path
+        #end if
+        #for $i, $s in enumerate( $read_series )
+            ${s.input}
+        #end for
+
+        #if str($polymorphism.selection) == "yes":
+            --polymorphism-prediction
+            --polymorphism-reject-indel-homopolymer-length $polymorphism.indel_homopolymer_length
+            --polymorphism-reject-surrounding-homopolymer-length $polymorphism.surrounding_homopolymer_length
+            --polymorphism-minimum-coverage-each-strand $polymorphism.strand_coverage
+            --polymorphism-bias-cutoff $polymorphism.bias_pvalue
+        #end if
+
+        #if str($junction_reference.selection) == "yes":
+            #for $i, $s in enumerate( $junction_reference.j_series )
+                --junction-only-reference $s.jc_genome
+            #end for
+        #end if
+
+        ${cnv_evidence}
+
+        -b $minqvalue
+
+    </command>
+
+    <stdio>
+        <exit_code range="1:"  level="fatal"   description="Fatal ERROR exit code greater than 1" />
+    </stdio>
+
+    <inputs>
+        <!-- reference genome -->
+        <conditional name="reference">
+            <param name="source" type="select" label="Will you select a reference genome from your history or use a built-in genome?" >
+                <option value="indexed">Use a built-in genome</option>
+                <option value="history">Use one from the history</option>
+            </param>
+            <when value="indexed">
+                <param name="fixed_genome" type="select" label="Select a reference genome" help="If your genome of interest is not listed, contact the Bioinformatics team">
+                    <options from_data_table="genbank_files">
+                        <filter type="sort_by" column="2"/>
+                        <validator type="no_options" message="No indexes are available for the selected input dataset"/>
+                    </options>
+                </param>
+            </when>
+            <when value="history">
+                <!-- <param name="own_genome" type="data" label="Select the reference genome (fasta or genbank)" /> -->
+                <repeat name="ref_series" title="Reference Genome" min="1">
+                        <param name="own_genome" type="data" label="Select the reference genome (fasta or genbank)" />
+                </repeat>
+            </when>
+        </conditional>
+
+
+        <!-- input Fastq files -->
+        <repeat name="read_series" title="Read File" min="1">
+            <param name="input" type="data" format="fastq" label="Dataset" />
+        </repeat>
+
+
+        <!-- select polymorphism -->
+        <conditional name="polymorphism">
+            <param name="selection" type="select" label="Perform polimorphism detection" help="Do you want to perform polimorphism detection in a population">
+                <option value="no">Do not perform polymorphism detection</option>
+                <option value="yes">Perform polymorphism detection</option>
+            </param>
+            <when value="yes">
+                <param name="indel_homopolymer_length" type="integer" value="0" label="Reject insertion/deletion polymorphisms due to homopolymer repeats with this length or greater" />
+                <param name="surrounding_homopolymer_length" type="integer" value="0" label="Do not predict polymorphic base substitutions that create a homopolymer with this length on each side (with 2 TTATT->TTTTT is rejected)" />
+                <param name="strand_coverage" type="integer" value="3" label="Only accept polymorphisms if coverage in each strand is at least this" />
+                <param name="bias_pvalue" type="float" value="0.05" label="Only accept polymorphisms if pvalue of strand or read quality bias is greater than this" />
+            </when>
+            <when value="no" />
+        </conditional>
+
+        <!-- junction only reference(s) -->
+        <conditional name="junction_reference">
+            <param name="selection" type="select" label="Detect external sequence insertion" help="You can select external sequences to detect insertions">
+                <option value="no">Do not detect external sequence insertion</option>
+                <option value="yes">Detect external sequence insertions</option>
+            </param>
+            <when value="yes">
+        	<repeat name="j_series" title="Junction-only references" min="1">
+            		<param name="jc_genome" type="data" label="Select an external sequence (fasta or genbank)" />
+        	</repeat>
+            </when>
+            <when value="no" />
+        </conditional>
+
+        <!-- Copy Number Evidence -->
+        <param name="cnv_evidence" type="select" label="Copy number variation prediction (experimental option)" help="Do you want to perform copy number variation prediction">
+         <option value="">Do not perform copy number variaion prediction</option>
+         <option value="--cnv">Perform copy number variation prediction (--cnv)</option>
+        </param>
+
+        <param name="minqvalue" type="integer" value="3" label="Minimum Phred Q for a base to be considered" />
+
+
+    </inputs>
+
+    <outputs>
+        <data format="prezip.html" name="outfile" label="Breseq HTML report" />
+    </outputs>
+
+    <help>
+**Breseq**
+
+Breseq_ is a computational pipeline for finding mutations relative to a reference sequence in short-read DNA re-sequencing data for microbial sized genomes.
+
+.. _Breseq: http://barricklab.org/twiki/bin/view/Lab/ToolsBacterialGenomeResequencing
+
+------
+
+**Inputs**
+
+Breseq accepts files in FASTQ format. It does not take pair-end information into account.
+
+You can either run in clonal (consensus) mode or search for polymorphisms in a population.
+
+You can also select an external sequence (eg. a transposon) to detect for insertions or horizontal transfer.
+
+
+------
+
+**Outputs**
+
+Breseq outputs a number of files. These are all condensed in a single zipped file.
+
+It contains output files with the final results, accessible through ``output/index.html``
+
+It also contains data files with accessory data, including:
+
+- ``data/reference.fasta`` (file with reference genome: can be used in eg. IGV browser)
+- ``data/reference.gff`` (file with genomic annotations: can be used in eg. IGV browser)
+- ``data/areference.bam`` (file with read alignments: can be used in eg. IGV browser)
+- ``data/unmatched.*`` (files with read that failed to align: can be used to build an assembly or to eg. blast against NCBI)
+
+    </help>
+</tool>
+