diff seqid_uncollapser.xml @ 0:78a7d28f2a15 draft

Uploaded
author idot
date Wed, 10 Jul 2013 06:13:48 -0400
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/seqid_uncollapser.xml	Wed Jul 10 06:13:48 2013 -0400
@@ -0,0 +1,75 @@
+<tool id="cshl_seqid_uncollapser" name="Uncollapse rows">
+	<description>containing collapsed sequence IDs</description>
+	<command>
+cat '$input' |
+fastx_uncollapser -c $idcol -v -o '$output'
+</command>
+	<inputs>
+		<param format="tabular,pslx" name="input" type="data" label="Library to uncollapse" />
+	    <param name="idcol" label="Column with collased sequence-identifier" type="data_column" data_ref="input" accept_default="false" >
+ 		  <help>This column contains the sequence id from a collapsed FASTA file in the form of "(seq number)-(read count)" (e.g. 15-4). Use 10 if you're analyzing BLAT output</help>
+		</param>
+	</inputs>
+	<tests>
+		<test>
+			<param name="input" value="fastx_seqid_uncollapse1.psl" />
+			<param name="idcol" value="10" />
+			<param name="output" file="fastx_seqid_uncollapse1.out" />
+		</test>
+	</tests>
+
+	<outputs>
+		<data format="input" name="output" metadata_source="input"
+		/>
+	</outputs>
+  <help>
+
+**What it does**
+
+This tool reads a row (in a table) containing a collapsed sequence ID, and duplicates the .
+
+.. class:: warningmark
+
+You must specify the column containing the collapsed sequence ID (e.g. 15-4).
+
+--------
+
+**Example Input File**
+
+The following input file contains two collapsed sequence identifiers at column 10: *84-2* and *87-5*
+
+(meaning the first has multiplicity-count of 2 and the second has multiplicity count of 5)::
+
+
+  23    0    0    0    0    0    0    0    +    84-2 ...
+  22    0    0    0    0    0    0    0    +    87-5 ...
+
+
+**Output Example**
+
+After **uncollapsing** (on column 10), the line of the first sequence-identifier is repeated *twice*, and the line of the second sequence-identifier is repeated *five* times::
+
+  23    0    0    0    0    0    0    0    +    84-2 ...
+  23    0    0    0    0    0    0    0    +    84-2 ...
+  22    0    0    0    0    0    0    0    +    87-5 ...
+  22    0    0    0    0    0    0    0    +    87-5 ...
+  22    0    0    0    0    0    0    0    +    87-5 ...
+  22    0    0    0    0    0    0    0    +    87-5 ...
+  22    0    0    0    0    0    0    0    +    87-5 ...
+
+
+Uncollapsing a text file allows analsys of collapsed FASTA files to be used with any tool which doesn't 'understand' collapsed multiplicity counts.
+
+.. class:: infomark
+
+See the *Collapse* tool in the *FASTA Manipulation* category for more details about collapsing FASTA files.
+
+-----
+
+This tool is based on `FASTX-toolkit`__ by Assaf Gordon.
+
+ .. __: http://hannonlab.cshl.edu/fastx_toolkit/
+    
+</help>
+</tool>
+<!-- FASTX-Uncollapser is part of the FASTX-toolkit, by A.Gordon (gordon@cshl.edu) -->