changeset 9:328a1e3b5261 draft

planemo upload for repository https://github.com/galaxyproteomics/tools-galaxyp/tools/bumbershoot/customProDB commit 98f3323d4b92a4a3668788b3e1bad1a6529fd6df-dirty
author galaxyp
date Wed, 08 Jun 2016 14:04:54 -0400
parents fa6aa0d5a27c
children ed65d110c1b5
files customProDB.R customProDB.xml
diffstat 2 files changed, 53 insertions(+), 7 deletions(-) [+]
line wrap: on
line diff
--- a/customProDB.R	Mon May 09 12:55:26 2016 -0400
+++ b/customProDB.R	Wed Jun 08 14:04:54 2016 -0400
@@ -23,7 +23,12 @@
 option_list$proteinseq <- make_option('--proteinseq', type='character')
 option_list$procodingseq <- make_option('--procodingseq', type='character')
 option_list$ids <- make_option('--ids', type='character')
+option_list$dbsnpinCoding <- make_option('--dbsnpinCoding', type='character')
+option_list$cosmic <- make_option('--cosmic', type='character')
+option_list$annotationFromHistory <- make_option('--annotationFromHistory', type='logical', action="store_true", default=FALSE)
 option_list$rpkmCutoff <- make_option('--rpkmCutoff', type='character')
+#option_list$outputIndels <- make_option('--outputIndels', type='logical', action="store_true", default=FALSE)
+#option_list$outputNovelJunctions <- make_option('--outputNovelJunctions', type='logical', action="store_true", default=FALSE)
 option_list$outputFile <- make_option('--outputFile', type='character')
 
 
@@ -37,14 +42,39 @@
 	exon_anno_file = GalaxyInputFile(required=TRUE),
 	proteinseq_file = GalaxyInputFile(required=TRUE),
 	procodingseq_file = GalaxyInputFile(required=TRUE),
+	ids_file = GalaxyInputFile(required=TRUE),
+	dbsnpinCoding_file = GalaxyInputFile(required=FALSE),
+	cosmic_file = GalaxyInputFile(required=FALSE),
+	annotationFromHistory = GalaxyLogicalParam(required=FALSE),
 	rpkmCutoff = GalaxyNumericParam(required=TRUE),
-	ids_file = GalaxyInputFile(required=TRUE),
+	#outputIndels = GalaxyLogicalParam(required=FALSE),
+	#outputNovelJunctions = GalaxyLogicalParam(required=FALSE),
 	outputFile = GalaxyOutput("FASTA","fasta"))
 {
-    file.symlink(exon_anno_file, "exon_anno.RData")
-    file.symlink(proteinseq_file, "proseq.RData")
-    file.symlink(procodingseq_file, "procodingseq.RData")
-    file.symlink(ids_file, "ids.RData")
+    file.symlink(exon_anno_file, paste(getwd(), "exon_anno.RData", sep="/"))
+    file.symlink(proteinseq_file, paste(getwd(), "proseq.RData", sep="/"))
+    file.symlink(procodingseq_file, paste(getwd(), "procodingseq.RData", sep="/"))
+    file.symlink(ids_file, paste(getwd(), "ids.RData", sep="/"))
+
+    if (length(dbsnpinCoding_file) > 0)
+    {
+        file.symlink(dbsnpinCoding_file, paste(getwd(), "dbsnpinCoding.RData", sep="/"))
+        labelrsid = T
+    }
+    else
+    {
+        labelrsid = F
+    }
+
+    if (length(cosmic_file) > 0)
+    {
+        file.symlink(cosmic_file, paste(getwd(), "cosmic.RData", sep="/"))
+        cosmic = T
+    }
+    else
+    {
+        cosmic = F
+    }
 
     bamLink = "input.bam"
     file.symlink(bam_file, bamLink)
@@ -52,9 +82,9 @@
 
     suppressPackageStartupMessages(library(customProDB))
 
-    easyRun(bamFile=bamLink, vcfFile=vcf_file, annotation_path=dirname(exon_anno_file),
+    easyRun(bamFile=bamLink, vcfFile=vcf_file, annotation_path=getwd(),
             rpkm_cutoff=rpkmCutoff, outfile_path=".", outfile_name="output",
-            nov_junction=F, INDEL=T, lablersid=F, COSMIC=F)
+            nov_junction=F, INDEL=T, lablersid=labelrsid, COSMIC=cosmic)
 }
 
 
--- a/customProDB.xml	Mon May 09 12:55:26 2016 -0400
+++ b/customProDB.xml	Wed Jun 08 14:04:54 2016 -0400
@@ -16,12 +16,24 @@
             --proteinseq="$genome_annotation.proteinSeq"
             --procodingseq="$genome_annotation.proCodingSeq"
             --ids="$genome_annotation.ids"
+            #if str($genome_annotation.dbsnpInCoding) != "None":
+                --dbsnpinCoding="$genome_annotation.dbsnpInCoding"
+            #end if
+            #if str($genome_annotation.cosmic) != "None":
+                --cosmic="$genome_annotation.cosmic"
+            #end if
        #else:
             #set index_path = $genome_annotation.builtin.fields.path
             --exon_anno="$index_path/exon_anno.RData"
             --proteinseq="$index_path/proseq.RData"
             --procodingseq="$index_path/procodingseq.RData"
             --ids="$index_path/ids.RData"
+            #if $genome_annotation.dbsnpInCoding:
+                --dbsnpinCoding="$index_path/dbsnpinCoding.RData"
+            #end if
+            #if $genome_annotation.cosmic:
+                --cosmic="$index_path/cosmic.RData"
+            #end if
        #end if
 
 2&gt;&amp;1</command>
@@ -50,6 +62,8 @@
             <validator type="unspecified_build" />
             <validator message="Sequences are not currently available for the specified build." metadata_column="1" metadata_name="dbkey" table_name="customProDB" type="dataset_metadata_in_data_table" />
         </param>
+        <param name="labelrsid" type="boolean" value="" label="Annotate SNPs with rsid from dbSNP (select organisms only)" />
+        <param name="cosmic" type="boolean" value="" label="Annotate somatic SNPs from COSMIC (human only)" />
       </when>
       <when value="history">
         <param name="exonAnno" type="data" format="RData" metadata_name="dbkey" help="A dataframe of exon annotations in an RData file" label="Exon Annotations" />
@@ -63,6 +77,8 @@
             <validator check="dbkey" message="Metadata missing, click the pencil icon in the history item and use the auto-detect feature to correct this issue." type="metadata" />
         </param>
         <param name="vcfInput" type="data" format="vcf" label="VCF file" />
+        <param name="dbsnpInCoding" type="data" format="RData" label="A dataframe containing dbSNP rsids" optional="true" />
+        <param name="cosmic" type="data" format="RData" label="A dataframe containing somatic SNPs from COSMIC (human only)" optional="true" />
       </when>
     </conditional>
     <param name="rpkmCutoff" type="float" value="1" min="0" label="Transcript Expression Cutoff (RPKM)" help="If non-zero, if a transcript does not meet this expression cutoff (based on RPKM) then it will not be included in the output database." />