Mercurial > repos > iuc > featurecounts

changeset 3:dae123c03a74 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/featurecounts commit 1c0d28b6cefe154e8cf037c9f36200e8f52a838f
author iuc
date Thu, 10 Nov 2016 03:05:17 -0500
parents a80f96e55958
children d417fb66494e
files featurecounts.xml tool-data/gene_sets.loc.sample tool_data_table_conf.xml.sample
diffstat 3 files changed, 61 insertions(+), 13 deletions(-) [+]
line wrap: on
line diff
--- a/featurecounts.xml	Mon Oct 31 07:26:54 2016 -0400
+++ b/featurecounts.xml	Thu Nov 10 03:05:17 2016 -0500
@@ -8,7 +8,12 @@
     <command><![CDATA[
         ## Check whether all alignments are from the same type (bam || sam)
         featureCounts
-            -a "$reference_gene_sets"
+            #if $gtf_source.ref_source=="history":
+                -a "$gtf_source.reference_gene_sets"
+            #else:
+                -a "$gtf_source.reference_gene_sets_builtin.fields.path"
+            #end if
+
             -o "output"
             -T \${GALAXY_SLOTS:-2}
 
@@ -25,7 +30,7 @@
 
             -Q  $extended_parameters.mapping_quality
                 $extended_parameters.largest_overlap
-  --minOverlap  $extended_parameters.min_overlap
+            --minOverlap  $extended_parameters.min_overlap
                 $extended_parameters.read_reduction
                 $extended_parameters.primary
                 $extended_parameters.ignore_dup
@@ -87,11 +92,27 @@
                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 must be in the same format" />
         
-        <param name="reference_gene_sets"
-               format="gff,gtf,gff3"
-               type="data"
-               label="Gene annotation file"
-               help="The program assumes that the provided annotation file is in GTF format. Make sure that the gene annotation file corresponds to the same reference genome as used for the alignment" />
+        <conditional name="gtf_source">
+            <param name="ref_source" type="select" label="Gene annotation file">
+                <option value="cached">locally cached</option>
+                <option value="history">in your history</option>
+            </param>
+            <when value="cached">
+                <param name="reference_gene_sets_builtin" type="select" label="Using locally cached annotation" help="If the annotation file you require is not listed here, please contact the Galaxy administrator">
+                    <options from_data_table="gene_sets">
+                        <filter type="sort_by" column="1" />
+                        <validator type="no_options" message="No annotations are available." />
+                    </options>
+                </param>
+            </when>
+            <when value="history">
+                <param name="reference_gene_sets"
+                       format="gff,gtf,gff3"
+                       type="data"
+                       label="Gene annotation file"
+                       help="The program assumes that the provided annotation file is in GTF format. Make sure that the gene annotation file corresponds to the same reference genome as used for the alignment" />
+            </when>
+        </conditional>
         
         <param name="format"
                type="select"
@@ -208,7 +229,7 @@
                 falsevalue=""
                 argument="-O"
                 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)" />
+                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="strand_specificity"
                    type="select"
@@ -281,7 +302,7 @@
                    type="select"
                    label="Reduce read to single position"
                    argument="--read2pos"
-                   help="The read is reduced to its 5' most base or 3'most base. Read summarization is then performed based on thesingle base which the read is reduced to.">
+                   help="The read is reduced to its 5' most base or 3'most base. Read summarization is then performed based on the single base the the read is reduced to.">
                 <option value="" selected="true">Leave the read as it is</option>
                 <option value="--read2pos 5">Reduce it to the 5' end</option>
                 <option value="--read2pos 3">Reduce it to the 3' end</option>
@@ -293,7 +314,7 @@
                    falsevalue=""
                    argument="--primary"
                    label="Only count primary alignments"
-                   help="If specified, only primary alignments will be counted. Primaryand secondary alignments are identified using bit 0x100 in theFlag field of SAM/BAM files. All primary alignments in a datasetwill be counted no matter they are from multi-mapping reads ornot ('-M' is ignored)." />
+                   help="If specified, only primary alignments will be counted. Primary and secondary alignments are identified using bit 0x100 in theFlag field of SAM/BAM files. All primary alignments in a dataset will be counted regardless of whether they are from multi-mapping reads or not ('-M' is ignored)." />
             
             <param name="ignore_dup"
                    type="boolean"
@@ -301,15 +322,15 @@
                    falsevalue=""
                    argument="--ignoreDup"
                    label="Ignore reads marked as duplicate"
-                   help="If specified, reads that were marked asduplicates will be ignored. Bit Ox400 in FLAG field of SAM/BAMfile is used for identifying duplicate reads. In paired enddata, the entire read pair will be ignored if at least one endis found to be a duplicate read." />
+                   help="If specified, reads that were marked as duplicates will be ignored. Bit Ox400 in the FLAG field of a SAM/BAM file is used for identifying duplicate reads. In paired end data, the entire read pair will be ignored if at least one end is found to be a duplicate read." />
             
             <param name="count_split_alignments_only"
                    type="boolean"
                    truevalue=" --countSplitAlignmentsOnly"
                    falsevalue=""
                    argument="--countSplitAlignmentsOnly"
-                   label="Ignore reads marked as duplicate"
-                   help="If specified, only split alignments (CIGARstrings containing letter `N') will be counted. All the otheralignments will be ignored. An example of split alignments isthe exon-spanning reads in RNA-seq data." />
+                   label="Ignore unspliced alignments"
+                   help="If specified, only split alignments (CIGAR strings containing the letter `N') will be counted. All the other alignments will be ignored. An example of split alignments are exon-spanning reads in RNA-seq data." />
         </section>
     </inputs>
     <outputs>
@@ -364,6 +385,7 @@
             <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" />
             <param name="format" value="tabdel_short" />
             <param name="include_feature_length_file" value="true"/>
+            <param name="ref_source" value="history" />
             <output name="output" file="output_1_short.tab"/>
             <output name="output_summary" file="output_1_summary.tab"/>
         </test>
@@ -372,6 +394,7 @@
             <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" />
             <param name="format" value="tabdel_medium" />
             <param name="include_feature_length_file" value="true"/>
+            <param name="ref_source" value="history" />
             <output name="output" file="output_1_medium.tab"/>
             <output name="output_summary" file="output_1_summary.tab"/>
         </test>
@@ -380,6 +403,7 @@
             <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" />
             <param name="format" value="tabdel_full" />
             <param name="include_feature_length_file" value="true"/>
+            <param name="ref_source" value="history" />
             <output name="output" file="output_1_full.tab"/>
             <output name="output_summary" file="output_1_summary.tab"/>
             <output name="output_feature_lengths" file="output_feature_lengths.tab"/>
@@ -390,6 +414,7 @@
             <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" />
             <param name="format" value="tabdel_short" />
             <param name="include_feature_length_file" value="true"/>
+            <param name="ref_source" value="history" />
             <output name="output" file="output_2_short.tab"/>
             <output name="output_summary" file="output_2_summary.tab"/>
         </test>
@@ -398,6 +423,7 @@
             <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" />
             <param name="format" value="tabdel_medium" />
             <param name="include_feature_length_file" value="true"/>
+            <param name="ref_source" value="history" />
             <output name="output" file="output_2_medium.tab"/>
             <output name="output_summary" file="output_2_summary.tab"/>
         </test>
@@ -406,6 +432,7 @@
             <param name="reference_gene_sets" value="featureCounts_guide.gff" ftype="gff" />
             <param name="format" value="tabdel_full" />
             <param name="include_feature_length_file" value="true"/>
+            <param name="ref_source" value="history" />
             <output name="output" file="output_2_full.tab"/>
             <output name="output_summary" file="output_2_summary.tab"/>
             <output name="output_feature_lengths" file="output_feature_lengths.tab"/>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/gene_sets.loc.sample	Thu Nov 10 03:05:17 2016 -0500
@@ -0,0 +1,14 @@
+# This is a sample file distributed with featureCounts that enables it and other# tools to use gene/exon annotations in the GFF/GTF format.
+# 
+# The gene_sets.loc file syntax is:
+#<unique_build_id>	<dbkey>	<display_name>	<path>
+# 
+# Please ensure that the above fields are tab separated.
+# 
+# In case you have TWO or MORE providers PER dbkey, the one mentioned
+# first in the file, should have the "default" priority.
+#
+#Example:
+#
+#Homo_sapiens.GRCh37.74	hg19	GRCh37 (hg19) annotation from Ensembl, release 74	/depot/data2/galaxy/hg19/gene_sets/Homo_sapiens.GRCh37.74.gtf
+#Homo_sapiens.NCBI36.54	hg18	hg18 annotation from Ensembl, release 54	/depot/data2/galaxy/hg18/gene_sets/Homo_sapiens.NCBI36.54.gtf
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample	Thu Nov 10 03:05:17 2016 -0500
@@ -0,0 +1,7 @@
+<tables>
+    <!-- Location of all GFF/GTF files -->
+    <table name="gene_sets" comment_char="#">
+        <columns>value, dbkey, name, path</columns>
+        <file path="tool-data/gene_sets.loc" />
+    </table>
+</tables>