# HG changeset patch
# User yhoogstrate
# Date 1384348520 18000
# Node ID d065dcf46babe8aaf867c9857c781198b18deb30

Uploaded

diff -r 000000000000 -r d065dcf46bab featureCounts.xml
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/featureCounts.xml	Wed Nov 13 08:15:20 2013 -0500
@@ -0,0 +1,136 @@
+<?xml version="1.4.0" encoding="UTF-8"?>
+<tool id="featureCounts-valid-gff" name="featureCounts-valid-gff">
+	<description>Count reads aligned to (valid GTF/GFF) annotated genes in a reference genome from SAM or BAM files.</description>
+	
+	<command>
+		<!--
+			The following script is written in the "Cheetah" language:
+			http://www.cheetahtemplate.org/docs/users_guide_html_multipage/contents.html
+		-->
+		featureCounts
+			-a $input_annotation
+			-o tmp.txt
+			
+			#if $alignments[0].file.extension == "bam"
+				-b
+			#end if
+			
+			#if $extended_parameters.parameters == "extended"
+				-t $extended_parameters.gff_feature_type
+				-g $extended_parameters.gff_feature_attribute
+				$extended_parameters.summarization_level
+				$extended_parameters.contribute_to_multiple_features
+				$extended_parameters.protocol
+				-Q $extended_parameters.mapping_quality
+				-T $extended_parameters.threads
+				$extended_parameters.fragment_counting
+				$extended_parameters.check_distance
+				-d $extended_parameters.minimum_fragment_length
+				-D $extended_parameters.maximum_fragment_length
+				$extended_parameters.only_both_ends
+				$extended_parameters.exclude_chimerics
+				$extended_parameters.namesort
+			#end if
+			
+			#for $alignment in $alignments
+				${alignment.file}
+			#end for
+			
+			> /dev/null 2> /dev/null
+		
+		
+		
+		#if $format == "complex" or $format.value == "complex"
+			; mv tmp.txt $output
+		#elif $format == "tabdel_default" or $format.value == "tabdel_default"
+			; egrep -v "^#" tmp.txt > tmp2.txt
+			; cut -f 1,7 tmp2.txt > tmp_left.txt
+			; cut -f 6 tmp2.txt > tmp_right.txt
+			; paste tmp_left.txt tmp_right.txt > $output
+			; rm tmp.txt tmp2.txt tmp_left.txt tmp_right.txt
+		#elif $format == "tabdel_short" or $format.value == "tabdel_short"
+			; egrep -v "^#" tmp.txt | cut -f 1,7 > $output
+			; rm tmp.txt
+		#end if
+	</command>
+	
+	<inputs>
+		<param name="input_annotation" type="data" format="gff" label="Annotation file" help="The annotation file. The program assumes that the provided annotation file is in GTF format." />
+		
+		<repeat name="alignments" title="Alignment file" default="1" min="1">
+			<param name="file" type="data" format="bam,sam" label="Alignment file" help="The input alignment file(s) where the gene expression has to be counted. The file can have a SAM or BAM format; but ALL files in the series must be in THE SAME format." />
+		</repeat>
+		
+		<param name="format" type="select" label="Output format">
+			<option value="complex">featureCounts 1.4.0+ default (extensive; complex)</option>
+			<option value="tabdel_default" selected="true">Gene-name "\t" gene-count "\t" gene-length (tab-delimited)</option>
+			<option value="tabdel_short">Gene-name "\t" gene-count (tab-delimited)</option>
+		</param>
+		
+		<conditional name="extended_parameters">
+			<param name="parameters" type="select" label="featureCounts parameters" help="For more advanced featureCounts settings.">
+				<option value="default">Default settings</option>
+				<option value="extended">Extended settings</option>
+			</param>
+			<when value="default">
+			</when>
+			<when value="extended">
+				<param name="gff_feature_type" type="boolean" value="exon" label="GFF feature type filter." help="Specify the feature type. Only rows which have the matched matched feature type in the provided GTF annotation file will be included for read counting. `exon' by default." />
+				
+				<param name="gff_feature_attribute" type="text" value="gene_id" label="GFF gene identifier" help="Specify the attribute type used to group features (eg. exons) into meta-features (eg. genes), when GTF annotation is provided. `gene_id' by default. This attribute type is usually the gene identifier. This argument is useful for the meta-feature level summarization." />
+				
+				<param name ="summarization_level" type="boolean" truevalue=" -f" falsevalue="" label="On feature level" help="If specified, read summarization will be performed at the feature level. By default (-f is not specified), the read summarization is performed at the meta-feature level." />
+				
+				<param name ="contribute_to_multiple_features" type="boolean" truevalue=" -O" falsevalue="" label="Allow read to contribute to multiple features." help="If specified, reads (or fragments if -p is specified) will be allowed to be assigned to more than one matched meta- feature (or matched feature if -f is specified)." />
+				
+				<param name="protocol" type="select" label="Strand specific protocol" help="Indicate if strand-specific read counting should be performed. It has three possible values: 0 (unstranded), 1 (stranded) and 2 (reversely stranded). 0 by default.">
+					<option value=" -s 0" selected="true">Unstranded</option>
+					<option value=" -s 1">Stranded (forwards)</option>
+					<option value=" -s 2">Stranded (reverse)</option>
+				</param>
+				
+				<param name="multimaping_counts" type="boolean" truevalue=" -M" falsevalue="" label="Count multi-mapping reads/fragments" help="If specified, multi-mapping reads/fragments will be counted (ie. a multi-mapping read will be counted up to N times if it has N reported mapping locations). The program uses the `NH' tag to find multi-mapping reads." />
+				
+				<param name="mapping_quality" type="integer" value="0" label="Minimum read quality" help="The minimum mapping quality score a read must satisfy in order to be counted. For paired-end reads, at least one end should satisfy this criteria. 0 by default." />
+				
+				<param name="threads" type="integer" value="1" min="1" label="Number of the CPU threads." />
+				
+				<param name="fragment_counting" type="boolean" truevalue=" -p" falsevalue="" label="PE: Count fragments instead of reads" help="Paired-end specific: If specified, fragments (or templates) will be counted instead of reads. The two reads from the same fragment must be adjacent to each other in the provided SAM/BAM file. If SAM/BAM input does not meet this requirement, the -S (sorting) option should be provided as well." />
+				
+				<param name="check_distance" type="boolean" truevalue=" -P" falsevalue="" label="PE: Check paired-end distance" help="Paired-end specific: If specified, paired-end distance will be checked when assigning fragments to meta-features or features. This option is only applicable when -p (Count fragments instead of reads) is specified. The distance thresholds should be specified using -d and -D (minimum and maximum fragment/template length) options." />
+				
+				<param name="minimum_fragment_length" type="integer" value="50" label="PE: Minimum fragment/template length." />
+				<param name="maximum_fragment_length" type="integer" value="600" label="PE: Maximum fragment/template length." />
+				
+				<param name="only_both_ends" type="boolean" truevalue=" -B" falsevalue="" label="PE: only allow fragments with both reads aligned"  help="Paired-end specific: If specified, only fragments that have both ends successfully aligned will be considered for summarization. This option is only applicable for paired-end reads." />
+				
+				<param name="exclude_chimerics" type="boolean" truevalue=" -C" falsevalue="" label="PE: Exclude chimeric fragments"  help="Paired-end specific: If specified, the chimeric fragments (those fragments that have their two ends aligned to different chromosomes) will NOT be included for summarization. This option is only applicable for paired-end read data." />
+				
+				<param name="namesort" type="boolean" truevalue=" -S" falsevalue="" label="PE: Name-sort reads (slow!)"  help="Paired-end specific: If specified, the program will reorder input reads according to their names and make reads from the same pair be adjacent to each other. This option should be provided when reads from the same pair are not adjacent to each other in input SAM/BAM files (for instance sorting reads by chromosomal locations could decouple reads from the same pair)." />
+			</when>
+		</conditional>
+	</inputs>
+	
+	<outputs>
+		<data format="tabular" name="output" label="${tool.name} on ${alignments[0].file.hid}: ${alignments[0].file.name}" />
+	</outputs>
+	
+	<help>
+featureCounts-valid-gff:
+	This application count reads aligned to annotated genes in a reference genome from SAM or BAM files.
+	This is similar to tools like DEXSeq-count, HTSeq-count, etc.
+	The tool is written in pure C, without the requirement of third party sorting software.
+	Therefore this tool is incredibly fast and takes about 7 minutes on a single average CPU for a 10GB alignment to a Homo Sapiens genome!
+	
+	---
+	
+	Remark that this is a fork of the original "featureCounts" package, which can be found at:
+	http://subread.sourceforge.net/
+	
+	---
+	
+	This fork is able to read GTF/GFF files according to the provided standard by Ensembl, which can be found at:
+	http://www.ensembl.org/info/website/upload/gff.html
+	The fork is maintained by: Youri Hoogstrate
+	</help>
+</tool>