diff pyCRAC/pySelectMotifsFromGTF.xml @ 0:19b20927172d draft

Uploaded
author swebb
date Tue, 18 Jun 2013 09:11:00 -0400
parents
children
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/pyCRAC/pySelectMotifsFromGTF.xml	Tue Jun 18 09:11:00 2013 -0400
@@ -0,0 +1,75 @@
+ <tool id ="pySelectMotifsFromGTF" name="pySelectMotifsFromGTF">
+	<requirements>
+        	<requirement type="package">pyCRAC</requirement>
+    	</requirements>
+	<command interpreter="python"> 
+	/usr/local/bin/pySelectMotifsFromGTF.py
+	--gtf $input
+	-m $motif
+	-o $out
+	-l $length
+	-z $zscore	
+	</command>
+	<version_command>/usr/local/bin/pySelectMotifsFromGTF.py --version</version_command>
+	<inputs>
+		<param format="gtf" name="input" type="data" label="Input File -f" help="pyMotif gtf output files" />
+		<param format="txt" name="motif" type="text" size="200" value="KBCTTG" label="motif string" help="Enter motif (all uppercase) you want to extract from the pyMotif gtf output file">
+			<validator type="empty_field" />
+		</param>
+		<param format="integer" type="integer" value="6" size="5" name="length" label="Length --length" help="Set a Kmer Length. Note that the length has to be at least as long as your k-mer sequence, otherwise the program will not run correctly" />
+		<param format="float" type="float" value="0" size="5" name="zscore" label="Z Score --Z_score" help="Set a minimum Kmer Z_score" />
+		<param name="label" type="text" format="txt" size="30" value="pySelectMotifsFromGTF" label="Enter output file label -o" />
+	</inputs>
+
+	<outputs>
+		<data format="gtf" name="out" label="${label.value}_${motif.value}.gtf"/>
+	</outputs>
+	<help>
+
+
+.. class:: infomark
+
+**pySelectMotifsFromGTF**
+
+pySelectMotifsFromGTF is part of the pyCRAC_ package. Extracts your favourite k-mer sequence from pyMotif GTF output files.
+Note that you can include degenerate nucleotides in your motif string::
+
+    N = A, G, C or T
+    R = A or G = puRine
+    Y = C or T = pYrimidine
+    M = A or C = aroMatic
+    S = G or C
+    W = A or T
+    K = G or T = Keto
+    V = A, C or G = Not T (letter after)
+    D = A, G or T = Not C
+    H = A, C or T = Not G
+    B = C, G or T = Not A
+
+So if you enter KBCTTG as search string and length=6, then the program will extract a large number of six-mers from your data.
+If you set length = 8, it will look for this pattern in a stretch of 8 nucleotides.
+   
+.. _pyCRAC: http://sandergranneman.bio.ed.ac.uk/Granneman_Lab/pyCRAC_software.html
+        
+------
+
+**Parameter list**
+
+Options::
+
+    --gtf=Yourfavoritegtf.gtf
+                        type the path to the gtf file that you want to use. By
+                        default it expects data from the standard input
+    -o FILE, --output=FILE
+                        Optional.Specify the name of the output file. Default
+                        is standard output. Make sure it has the .gtf
+                        extension!
+    -m KBCTTG, --motif=KBCTTG
+                        Specify the motif you want extract from the GTF file.
+    -z 15.0, --Z_score=15.0
+                        Set a minimum k-mer Z-score. Default=0
+    -l 4, --length=4      
+                        Set a k-mer length. Default is no length filtering
+
+	</help>
+</tool>