Mercurial > repos > yhoogstrate > featurecounts_valid_gff

changeset 34:21be93127c42

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author yhoogstrate
date Fri, 07 Feb 2014 11:42:01 -0500
parents f9574179f7ea
children 5669aa6422ef
files featurecounts_valid_gff.xml
diffstat 1 files changed, 25 insertions(+), 15 deletions(-) [+]
line wrap: on
line diff
--- a/featurecounts_valid_gff.xml	Fri Feb 07 11:28:24 2014 -0500
+++ b/featurecounts_valid_gff.xml	Fri Feb 07 11:42:01 2014 -0500
@@ -20,7 +20,9 @@
 			#else
 				featureCounts
 					-a 
-					#if $reference_gene_sets_source.source_select == "indexed"
+					#if $reference_gene_sets_source.source_select == "indexed_filtered"
+						"$reference_gene_sets_source.reference_gene_sets"
+					#else if $reference_gene_sets_source.source_select == "indexed_all"
 						"$reference_gene_sets_source.reference_gene_sets"
 					#else if $reference_gene_sets_source.source_select == "history"
 						"$reference_gene_sets_source.reference_gene_sets"
@@ -40,6 +42,8 @@
 						-b
 					#end if
 					
+					-T $extended_parameters.threads
+					
 					#if $extended_parameters.parameters == "extended"
 						-t $extended_parameters.gff_feature_type
 						-g $extended_parameters.gff_feature_attribute
@@ -47,7 +51,6 @@
 						$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
@@ -63,19 +66,15 @@
 					
 					2>&1
 				
-				<!-- #if $format == "complex" or $format.value == "complex" -->
-				<!-- ; mv tmp.txt $output -->
 				#if $format == "tabdel_default" or $format.value == "tabdel_default"
 					; cp $output tmp.txt
 					; 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"
 					; cp $output tmp.txt
 					; egrep -v "^#" tmp.txt | cut -f 1,7 > $output
-					<!-- ; rm tmp.txt -->
 				#end if
 			#end if
 		#end if
@@ -86,13 +85,14 @@
 		
 		<!-- Find out how to access the the GTF/GFF file(s) -->
 		<conditional name="reference_gene_sets_source">
-			<param name="source_select" type="select" label="Fasta Source">
-				<option value="indexed">Use a built-in index</option>
+			<param name="source_select" type="select" label="GFF/GTF Source">
+				<option value="indexed_filtered">Use a built-in index (which fit your reference)</option>
 				<option value="history">Use reference from the history</option>
-				<option value="attribute">Use a built-in index based on the 'metadata.dbkey' attribute of the input; select this if you design a workflow</option>
+				<option value="indexed_all">Use a built-in index (entire list) - only usefull if you design a workflow</option>
+				<option value="attribute">Use a built-in index based on the 'metadata.dbkey' attribute of the input - usefull if you design a workflow</option>
 			</param>
-			<when value="indexed">
-				<param name="reference_gene_sets" type="select" label="Reference Genome used during alignment (fasta)" >
+			<when value="indexed_filtered">
+				<param name="reference_gene_sets" type="select" label="Reference Gene Sets used during alignment (GFF/GTF)" >
 					<options from_file="gene_sets.loc">
 						<column name="name"  index="0"/>
 						<column name="dbkey" index="1"/>
@@ -102,6 +102,16 @@
 					</options>
 				</param>
 			</when>
+			<when value="indexed_all">
+				<param name="reference_gene_sets" type="select" label="Reference Gene Sets used during alignment (GFF/GTF)" >
+					<options from_file="gene_sets.loc">
+						<column name="name"  index="0"/>
+						<column name="dbkey" index="1"/>
+						<column name="value" index="2"/>
+						<validator type="no_options" message="No indexes are available for the selected input dataset" />
+					</options>
+				</param>
+			</when>
 			<when value="history">
 				<param name="reference_gene_sets" format="gff" type="data" label="Gene annotation file" help="The program assumes that the provided annotation file is in GTF format. Make sure that the gene annotaiton file corresponds to the same reference genome as used for the alignment." />
 			</when>
@@ -116,6 +126,8 @@
 			<option value="tabdel_short">Gene-name "\t" gene-count (tab-delimited)</option>
 		</param>
 		
+		<param name="threads" type="integer" value="2" min="1" label="Number of the CPU threads" />
+		
 		<conditional name="extended_parameters">
 			<param name="parameters" type="select" label="featureCounts parameters" help="For more advanced featureCounts settings.">
 				<option value="default">Default settings</option>
@@ -124,13 +136,13 @@
 			<when value="default">
 			</when>
 			<when value="extended">
-				<param name="gff_feature_type" type="text" 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_type" type="text" 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 ="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>
@@ -142,8 +154,6 @@
 				
 				<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." />