Mercurial > repos > iracooke > tpp_prophets

changeset 9:c04896f31ff7

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Added bash wrapper scripts and protxml to table
author Ira Cooke <iracooke@gmail.com>
date Mon, 10 Jun 2013 04:58:03 -0500
parents d19a95abf2e4
children 0ad9b29c22e5
files interprophet_wrapper.rb interprophet_wrapper.sh peptide_prophet_wrapper.rb peptide_prophet_wrapper.sh protein_prophet_wrapper.rb protein_prophet_wrapper.sh protxml_to_table.xml
diffstat 7 files changed, 112 insertions(+), 127 deletions(-) [+]
line wrap: on
line diff
--- a/interprophet_wrapper.rb	Sun Jun 09 08:19:01 2013 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,56 +0,0 @@
-require 'pathname'
-
-$VERBOSE=nil
-
-# Hard-Coded argument order and number of arguments
-#
-actual_output_path_string=ARGV[0]
-use_nss=ARGV[1]
-use_nrs=ARGV[2]
-use_nse=ARGV[3]
-use_nsi=ARGV[4]
-use_nsm=ARGV[5]
-minprob=ARGV[6]
-minprob_val=ARGV[7]
-
-wd= Dir.pwd
-original_input_files=ARGV.drop(7)
-# End hard coded args #
-
-cmd=""
-
-output_substitution_cmds=""
-
-input_files=original_input_files.collect do |input|
-
-  # We append ".pep.xml" to the input file name because interprophet can't handle anything else
-  # In order for this to work properly we need to create a symbolic link our working directory
-  #
-  original_input_path=Pathname.new("#{input}")
-  actual_input_path_string="#{wd}/#{original_input_path.basename}.pep.xml"
-
-  cmd << "ln -s #{input} #{actual_input_path_string};"
-  output_substitution_cmds << "ruby -pi -e \"gsub('#{actual_input_path_string}', '#{input}.pep.xml')\" interprophet_output.pep.xml;"
-  actual_input_path_string
-end
-
-cmd << "rvm 1.9.3@protk-1.2.0 do interprophet.rb"
-
-cmd << " --no-nss" unless use_nss=="blank"
-cmd << " --no-nrs" unless use_nrs=="blank"
-cmd << " --no-nse" unless use_nse=="blank"
-cmd << " --no-nsi" unless use_nsi=="blank"
-cmd << " --no-nsm" unless use_nsm=="blank"
-
-
-input_files.each { |input|
-  cmd << " #{input}"
-}
-
-
-cmd << " -o interprophet_output.pep.xml -r"
-
-cmd << ";#{output_substitution_cmds}"
-
-%x[#{cmd}]
-
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/interprophet_wrapper.sh	Mon Jun 10 04:58:03 2013 -0500
@@ -0,0 +1,33 @@
+#!/usr/bin/env bash
+#
+
+# Hard-Coded argument order
+# Args 0-4 are like (eg --no-nss)
+# Args 5 and 6 are like (eg --minprob 0.5)
+# Remaining args are filenames
+#
+actual_output_path_string=$1;shift
+for i in {0 1 2 3 4}; do
+	if [ $1 != "blank" ]; then cmd_args[$i]=$1; fi;shift
+done	
+cmd_args+=($1);shift
+cmd_args+=($1);shift
+
+wd=`pwd`
+
+for original_input_file in $@; do
+	input_file_name=`basename $original_input_file`
+	actual_input_path_string=$wd/$input_file_name.pep.xml
+	ln -s $original_input_file $actual_input_path_string
+	cmd_args+=($actual_input_path_string)
+done
+
+rvm 1.9.3@protk-1.2.2 do interprophet.rb ${cmd_args[@]} -o interprophet_output.pep.xml -r;
+
+if [ -f interprophet_output.pep.xml ]; then
+	for original_input_file in $@; do
+		actual_input_path_string=$wd/`basename $original_input_file`.pep.xml
+		sed -i.bak s%$actual_input_path_string%$original_input_file%g interprophet_output.pep.xml
+	done
+fi
+
--- a/peptide_prophet_wrapper.rb	Sun Jun 09 08:19:01 2013 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,36 +0,0 @@
-require 'pathname'
-
-$VERBOSE=nil
-
-actual_output_path_string=ARGV.shift
-
-# Second argument is the original input file name ... we'll change this below
-original_input_file=ARGV[0]
-
-# Before doing anything we append create a link to the input file in our working dir with ".pep.xml" appended to the input 
-# name because peptide prophet can't handle anything else
-
-wd= Dir.pwd
-
-original_input_path=Pathname.new("#{original_input_file}")
-actual_input_path_string="#{wd}/#{original_input_path.basename}.pep.xml"
-full_tmp_output_path_string="#{wd}/peptide_prophet_output.pep.xml"
-
-cmd = "ln -s #{original_input_file} #{actual_input_path_string};"
-
-cmd << "rvm 1.9.3@protk-1.2.0 do peptide_prophet.rb"
-
-
-ARGV[0]="#{actual_input_path_string}"
-
-ARGV.each { |a|    
-  cmd << " #{a}" 
-}
-
-cmd << " -o peptide_prophet_output.pep.xml"
-
-# Finally we need to fix up the output file so any references to the temporary working file are changed to refs to the original input file
-cmd << ";ruby -pi -e \"gsub('#{actual_input_path_string}', '#{original_input_file}')\" peptide_prophet_output.pep.xml"
-cmd << ";ruby -pi -e \"gsub('#{full_tmp_output_path_string}', '#{actual_output_path_string}')\" peptide_prophet_output.pep.xml"
-
-p %x[#{cmd}]
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/peptide_prophet_wrapper.sh	Mon Jun 10 04:58:03 2013 -0500
@@ -0,0 +1,23 @@
+#!/usr/bin/env bash
+
+actual_output_path_string=$1;shift
+
+original_input_file=$1;shift
+
+# Before doing anything we append create a link to the input file in our working dir with ".pep.xml" appended to the input 
+# name because peptide prophet can't handle anything else
+
+wd=`pwd`
+
+actual_input_path_string=$wd/`basename $original_input_file`.pep.xml
+
+full_tmp_output_path_string=$wd/peptide_prophet_output.pep.xml
+
+ln -s $original_input_file $actual_input_path_string
+
+
+rvm 1.9.3@protk-1.2.2 do peptide_prophet.rb $actual_input_path_string $@ -o peptide_prophet_output.pep.xml;
+
+sed -i.bak s%$actual_input_path_string%$original_input_file%g peptide_prophet_output.pep.xml
+sed -i.bak s%$full_tmp_output_path_string%$actual_output_path_string%g peptide_prophet_output.pep.xml
+
--- a/protein_prophet_wrapper.rb	Sun Jun 09 08:19:01 2013 -0500
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,35 +0,0 @@
-require 'pathname'
-
-$VERBOSE=nil
-
-actual_output_path_string=ARGV.shift
-
-# Second argument is the original input file name ... we'll change this below
-original_input_file=ARGV[0]
-
-# Before doing anything we append create a link to the input file in our working dir with ".pep.xml" appended to the input 
-# name because peptide prophet can't handle anything else
-
-wd= Dir.pwd
-
-original_input_path=Pathname.new("#{original_input_file}")
-actual_input_path_string="#{wd}/#{original_input_path.basename}.pep.xml"
-
-cmd = "ln -s #{original_input_file} #{actual_input_path_string};"
-
-cmd << "rvm 1.9.3@protk-1.2.0 do protein_prophet.rb"
-
-
-ARGV[0]="#{actual_input_path_string}"
-
-ARGV.each { |a| 
-    
-  cmd << " #{a}" 
-}
-
-cmd << " -o protein_prophet_results.prot.xml"
-
-cmd << ";ruby -pi -e \"gsub('#{actual_input_path_string}', '#{original_input_file}.pep.xml')\" protein_prophet_results.prot.xml"
-
-%x[#{cmd}]
-
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/protein_prophet_wrapper.sh	Mon Jun 10 04:58:03 2013 -0500
@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+#
+
+actual_output_path_string=$1;shift
+original_input_file=$1;shift
+
+# Before doing anything we append create a link to the input file in our working dir with ".pep.xml" appended to the input 
+# name because peptide prophet can't handle anything else
+
+wd=`pwd`
+
+actual_input_path_string=$wd/`basename $original_input_file`.pep.xml
+
+ln -s $original_input_file $actual_input_path_string
+
+rvm 1.9.3@protk-1.2.2 do protein_prophet.rb $actual_input_path_string $@ -o protein_prophet_results.prot.xml
+
+if [ -f protein_prophet_results.prot.xml ]; then
+	sed -i.bak s%$actual_input_path_string%$original_input_file.pep.xml%g protein_prophet_results.prot.xml
+fi
+
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/protxml_to_table.xml	Mon Jun 10 04:58:03 2013 -0500
@@ -0,0 +1,35 @@
+<tool id="protxml_to_table_1" name="ProtXML to Table" version="1.0.1">
+	<requirements>
+	    <requirement type="package" version="1.2.2">galaxy_protk</requirement>
+   </requirements>
+
+	<description>Converts a ProtXML file to a table</description>
+
+	<command>
+		rvm 1.9.3@protk-1.2.2 do protxml_to_table.rb 
+
+		$input_file 
+		-o $output 
+	</command>
+
+	<inputs>	
+		
+		<param format="protxml" name="input_file" type="data" label="ProtXML File to Convert"/>
+
+	</inputs>
+
+
+	<outputs>
+		<data format="tabular" name="output" />
+	</outputs>
+
+
+  <help>
+
+**What it does**
+
+Converts a ProtXML file to a tab separated table 
+
+  </help>
+
+</tool>