# HG changeset patch
# User morinlab
# Date 1476210719 14400
# Node ID 73338a1805e7ad8ccce531775aa9238910f69115
planemo upload for repository https://github.com/morinlab/tools-morinlab/tree/master/tools/sequenza commit 4ef2d91b7c1686a2696b92fe538d4aec51d05e40-dirty
diff -r 000000000000 -r 73338a1805e7 create_seqz_file.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/create_seqz_file.xml Tue Oct 11 14:31:59 2016 -0400
@@ -0,0 +1,140 @@
+
+
+ extracts the common positions containing A and B allele frequencies
+
+
+ sequenza
+ pypy
+ SEQUENZA_INSTALL_DIR
+
+> $bytes;
+ #end if
+ for int in \$( cat $interval ); do
+ #end if
+
+ #if $interval and $order_file
+ if [ "\$int" != "\$( cat $order_file | head -n1)" ] ; then
+ skip=2;
+ else
+ skip=1;
+ fi ;
+ #end if
+
+ \$EXEC \$SEQUENZA_INSTALL_DIR/sequenza/exec/sequenza-utils.py bam2seqz
+ -n normal.bam
+ -t tumour.bam
+ -gc $gc_file
+ -F reference.fa
+
+ #if $interval
+ -C \$int
+ #end if
+
+ --hom $geno.hom
+ --het $geno.het
+ -q $qual.qlimit
+ -f $qual.qformat
+ -N $qual.depth
+
+ | \$EXEC \$SEQUENZA_INSTALL_DIR/sequenza/exec/sequenza-utils.py seqz-binning
+ -s -
+ -w $window
+
+ | awk '{ if (\$4 >= $min_depth && \$5 >= $min_depth) print \$_ }'
+
+ #if $gzip.gzip_selector == "yes":
+ #if $order_file and $interval:
+ | tail -n+\$skip | gzip >> $output_gzip;
+ #else
+ | gzip >> $output_gzip;
+ #end if
+
+ #if $interval:
+ echo \$(( \$( wc -c < $output_gzip ) + 1 )) >> $bytes;
+ #end if
+
+ #else:
+ >> $output;
+ #end if
+
+ #if $interval
+ done;
+ #end if
+
+]]>
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ gzip['gzip_selector'] == "no"
+
+
+ gzip['gzip_selector'] == "yes"
+
+
+ gzip['gzip_selector'] == "yes"
+
+
+
diff -r 000000000000 -r 73338a1805e7 sequenza_pipeline.R
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/sequenza_pipeline.R Tue Oct 11 14:31:59 2016 -0400
@@ -0,0 +1,37 @@
+#!/usr/bin/R
+
+# Script to Run Sequenza Pipeline in Galaxy
+library(sequenza);
+
+# INPUT FILE
+args=(commandArgs(TRUE));
+input.file <- args[1];
+
+ploidy <- args[4];
+
+cellularity <-args[5];
+
+# STEP ONE
+extract.data <- sequenza.extract(
+file=input.file,
+gz=TRUE
+);
+
+# STEP TWO
+fit.data <- sequenza.fit(
+extract.data
+);
+
+# STEP THREE
+if(length(args)>3){
+
+results.data <- sequenza.results(extract.data, cellularity=cellularity, ploidy=ploidy,out.dir = args[3],sample.id = args[2]);
+
+} else{
+ results.data <- sequenza.results(
+extract.data,
+ fit.data,
+out.dir = args[3],
+ sample.id = args[2]
+);
+}
diff -r 000000000000 -r 73338a1805e7 sequenza_pipeline.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/sequenza_pipeline.xml Tue Oct 11 14:31:59 2016 -0400
@@ -0,0 +1,60 @@
+
+
+ using general R sequenza pipeline
+
+
+ sequenza
+ SEQUENZA_INSTALL_DIR
+
+
+
+Rscript $__tool_directory__/sequenza_pipeline.R $input
+
+ #if $sampleid_source.sampleid_selector == "bamfile":
+ \$(basename $sampleid_source.id | sed 's/.bam$//g' )
+ #else:
+ $sampleid_source.id
+ #end if
+
+ output
+
+ #if $choose_fit_option.fit_option == "manual":
+
+ $ploidy $cellularity
+
+ #end if
+
+ 2>&1 ;
+
+ cat ./output/*segments.txt > $output;
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff -r 000000000000 -r 73338a1805e7 tool-data/fasta_indexes.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/fasta_indexes.loc.sample Tue Oct 11 14:31:59 2016 -0400
@@ -0,0 +1,29 @@
+#This is a sample file distributed with Galaxy that enables tools
+#to use a directory of Samtools indexed sequences data files. You will need
+#to create these data files and then create a fasta_indexes.loc file
+#similar to this one (store it in this directory) that points to
+#the directories in which those files are stored. The fasta_indexes.loc
+#file has this format (white space characters are TAB characters):
+#
+#
+#
+#So, for example, if you had hg19 Canonical indexed stored in
+#
+# /depot/data2/galaxy/hg19/sam/,
+#
+#then the fasta_indexes.loc entry would look like this:
+#
+#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /depot/data2/galaxy/hg19/sam/hg19canon.fa
+#
+#and your /depot/data2/galaxy/hg19/sam/ directory
+#would contain hg19canon.fa and hg19canon.fa.fai files.
+#
+#Your fasta_indexes.loc file should include an entry per line for
+#each index set you have stored. The file in the path does actually
+#exist, but it should never be directly used. Instead, the name serves
+#as a prefix for the index file. For example:
+#
+#hg18canon hg18 Human (Homo sapiens): hg18 Canonical /depot/data2/galaxy/hg18/sam/hg18canon.fa
+#hg18full hg18 Human (Homo sapiens): hg18 Full /depot/data2/galaxy/hg18/sam/hg18full.fa
+#hg19canon hg19 Human (Homo sapiens): hg19 Canonical /depot/data2/galaxy/hg19/sam/hg19canon.fa
+#hg19full hg19 Human (Homo sapiens): hg19 Full /depot/data2/galaxy/hg19/sam/hg19full.fa
diff -r 000000000000 -r 73338a1805e7 tool_data_table_conf.xml.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_data_table_conf.xml.sample Tue Oct 11 14:31:59 2016 -0400
@@ -0,0 +1,7 @@
+
+
+
+ value, dbkey, name, path
+
+
+
diff -r 000000000000 -r 73338a1805e7 tool_dependencies.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool_dependencies.xml Tue Oct 11 14:31:59 2016 -0400
@@ -0,0 +1,6 @@
+
+
+
+
+
+