diff tools/mira4/mira4_mapping.xml @ 5:ffefb87bd414 draft

Uploaded v0.0.1 preview 5, using MIRA 4.0 RC4, supports segment_placement (pairing type)

--- a/tools/mira4/mira4_mapping.xml	Fri Oct 11 04:28:45 2013 -0400
+++ b/tools/mira4/mira4_mapping.xml	Tue Oct 15 12:07:34 2013 -0400
@@ -5,7 +5,7 @@
         <requirement type="binary">mira</requirement>
         <requirement type="package" version="4.0">MIRA</requirement>
     </requirements>
-    <version_command interpreter="python">mira4.py -v</version_command>
+    <version_command interpreter="python">mira4.py --version</version_command>
     <command interpreter="python">
 mira4.py $manifest $out_maf $out_fasta $out_log
     </command>
@@ -38,6 +38,13 @@
                 <option value="pcbiohq">PacBio high quality (corrected)</option>
                 <option value="text">Synthetic reads (database entries, consensus sequences, artifical reads, etc)</option>
             </param>
+            <param name="segment_placement" type="select" label="Pairing type (segment placing)">
+                <option value="">None (e.g. single end sequencing)</option>
+                <option value="FR">---&gt; &lt;--- (e.g. Sanger capillary or Solexa/Illumina paired-end library)</option>
+                <option value="RF">&lt;--- ---&gt; (e.g. Solexa/Illumina mate-pair library)</option>
+                <option value="SB">2---&gt; 1---&gt; (e.g. Roche 454 paired-end libraries or IonTorrent long-mate; see note)</option>
+                <option value="?">Unknown or not relevant (e.g. primer walking with Sanger capillary sequencing)</option>
+            </param>
             <param name="filenames" type="data" format="fastq,mira" multiple="true" required="true" label="Read file(s)"
                    help="Multiple files allowed, for example paired reads can be given as two files (MIRA looks at read names to identify pairs)." />
         </repeat>
@@ -97,6 +104,10 @@
 ##This is perhaps redundant as MIRA defaults to StrainX for the reads:
 strain = StrainX
 #end if
+#if str($rg.segment_placement) != ""
+##Record the segment placement (if any)
+segmentplacement = ${rg.segment_placement}
+#end if
 ##MIRA will accept multiple filenames on one data line, or multiple data lines
 #for $f in $rg.filenames
 ##Must now map Galaxy datatypes to MIRA file types...
@@ -149,6 +160,19 @@
 
 It is particularly suited to small genomes such as bacteria.
 
+**Notes**
+
+.. class:: warningmark
+
+Note that the raw data for Roche 454 and Ion Torrent paired-end libraries
+sequences a circularised fragment such that the raw data starts with the
+end of the fragment, a linker, then the start of the fragment. This means
+both the start and end are sequenced from the same strand, and thus should
+be given to MIRA as orientation "2---&gt; 1---&gt;". However, in order to
+use this data with traditional tools expecting Sanger capillary style
+libraries which expect "---&gt; &lt;---" your FASTQ files may have been
+pre-processed to mimic this by reverse complementing one of the pair.
+
 **Citation**
 
 If you use this Galaxy tool in work leading to a scientific publication please