diff pyCRAC/pyBarcodeFilter.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/pyBarcodeFilter.xml	Tue Jun 18 09:11:00 2013 -0400
@@ -0,0 +1,125 @@
+ <tool id ="pyBarcodeFilter" name="pyBarcodeFilter" force_history_refresh="True">
+        <requirements>
+            <requirement type="package">pyCRAC</requirement>
+        </requirements>
+	<command interpreter="perl"> 
+	/usr/local/bin/pyBarcodeFilter.pl
+	--file_type $ftype.type
+	-f $ftype.f
+	-b $barcode
+	-m $mismatch
+	$index
+	--out $out
+	--id $out.id 
+	--output_path $__new_file_path__ 
+	#if $ftype.reverse.rev == "yes":
+        -r=$ftype.reverse.r
+		$ftype.reverse.both
+    #end if#
+	</command>
+	<version_command>pyBarcodeFilter.py --version</version_command>
+	<inputs>
+		<conditional name="ftype">
+		<param name="type" type="select" label="File type">
+			<option value="fastq" selected="true">FASTQ</option>
+			<option value="fasta">FASTA</option>
+		</param>
+		<when value="fastq">
+			<param format="fastq" name="f" type="data" label="FastQ File -f" help="FastQ format" />
+			<conditional name="reverse">
+                <param name="rev" type="select"  label="Add a reverse or paired FastQ file">
+                    <option value="no" selected="true">NO</option>
+                    <option value="yes">YES</option>
+                </param>        
+                <when value="yes">
+                    <param format="fastq" name="r" type="data" label="Reverse FastQ File -f" help="FastQ format" />
+                    <param name="both" type="select"  label="Search for barcode in both reads">
+                        <option value="" selected="true">NO</option>
+                        <option value="--both">YES</option>
+                    </param>
+				</when>
+				<when value="no">
+				</when>
+			</conditional>
+		</when>
+		<when value="fasta">
+			<param format="fasta" name="f" type="data" label="FastA File -f" help="FastA format" />
+			<conditional name="reverse">
+                <param name="rev" type="select"  label="Add a reverse or paired FastA file">
+                    <option value="no" selected="true">NO</option>
+                    <option value="yes">YES</option>
+                </param>        
+                <when value="yes">
+                    <param format="fasta" name="r" type="data" label="Reverse FastA File -f" help="FastA format" />
+                    <param name="both" type="select"  label="Search for barcode in both reads">
+                        <option value="" selected="true">NO</option>
+                        <option value="--both">YES</option>
+				    </param>
+				</when>
+				<when value="no">
+				</when>
+			</conditional>
+		</when>
+		</conditional>
+		<param format="tabular" name="barcode" type="data" label="Barcode File -f" help="Tab delimited file with barcodes and barcode names" />
+		<param format="integer" name="mismatch" type="integer" label="Mismatches -m" value="0" size="3" help="Set the number of allowed mismatches in a barcode">
+			<validator type="in_range" min="0" max="100" message="Please enter a value between 0 and 100"/>
+		</param>      
+		<param name="index" type="select"  label="Split data using Illumina indexing barcode information -i">
+            <option value="" selected="true">NO</option>
+            <option value="-i">YES</option>
+		</param> 
+	</inputs>
+	<outputs>
+		<data format="text" name="out" label="pyBarcodeFilter"/>
+	</outputs>
+	<help>
+
+.. class:: infomark
+
+**pySolexaBarcodeFilter**
+
+pySolexaBarcodeFilter is part of the pyCRAC_ package. Filters sequence files by barcodes.
+
+This tool requires FASTA or FASTQ input files containing the raw data and a text file containing barcode information.
+To process paired end data, use -f and the -r flags to indicate the path to the forward and reverse sequencing reactions, respectively. 
+The barcodes file should two columns separated by a tab (see the table below). The first column should contain the barcode nucleotide sequences. 
+The second column should contain an identifier, for example, the name of the barcode or the name of the experiment.
+The ā€™Nā€™ in the barcode sequence indicates a random nucleotide. Make sure to use a simple text editor like TextEdit (MacOS X), gedit (Linux/Unix) or use a text editor in the terminal. 
+The program is case sensitive: all the nucleotide sequences should be upper case. 
+You can freely combine different barcodes but if you are mixing samples containing random nucleotide barcodes and normal barcodes.
+**NOTE!** make sure to place the regular barcode sequence below the sequence with random nucleotides and make sure the shortest sequence is ALWAYS at the bottom in the column (see below)
+
+Example of a barcode text file::
+
+    NNNCGCTTAGC mutant2
+    NNNGCGCAGC  mutant1
+    NNNATTAG    control
+    NNNTAAGC    myfavprotein
+    AGC         oldcontrol
+    AC          veryfirstbarcodedsample 
+   
+.. _pyCRAC: http://sandergranneman.bio.ed.ac.uk/Granneman_Lab/pyCRAC_software.html
+        
+------
+
+**Parameter list**
+
+Options::
+
+  -f FILE, --input_file=FILE		
+                            name of the FASTQ or FASTA input file
+  -r FILE, --reverse_input_file=FILE	
+                            name of the paired (or reverse) FASTQ or FASTA input file
+  --file_type=FASTQ     		
+                            type of file, uncompressed (fasta or fastq) or compressed (fasta.gz or fastq.gz, gzip/gunzip 
+					        compressed). Default is fastq
+  -b FILE, --barcode_list=FILE		
+                            name of tab-delimited file containing barcodes and barcode names
+  -m 1, --mismatches=1  		
+                            to set the number of allowed mismatches in a barcode. A maximum of one mismatch is allowed. Default = 0
+  -i, --index           		
+                            use this option if you want to split the data using the Illumina indexing barcode information
+
+	</help>
+</tool>