# HG changeset patch
# User iracooke
# Date 1343017258 14400
# Node ID 418f42b34049bbe1b0cb329ea44af588c58d2a9e
# Parent deaedec14cc8566c3cd97469b55f2501e5655707
Reuploading
diff -r deaedec14cc8 -r 418f42b34049 display_applications/proteomics/PepXml.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/display_applications/proteomics/PepXml.xml Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,18 @@
+
+
+
+
+
+
+ ${site_url}/init_local?file=${encoded_filename.qp}&type=pepxml
+
+
+
+ #import binascii
+ ${binascii.hexlify( $pepxml_file.file_name )}
+
+
+ ${BASE_URL.split(":")[1][2:]}
+
+
+
diff -r deaedec14cc8 -r 418f42b34049 display_applications/proteomics/ProtXml.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/display_applications/proteomics/ProtXml.xml Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,18 @@
+
+
+
+
+
+
+ ${site_url}/init_local?file=${encoded_filename.qp}&type=protxml
+
+
+
+ #import binascii
+ ${binascii.hexlify( $protxml_file.file_name )}
+
+
+ ${BASE_URL.split(":")[1][2:]}
+
+
+
\ No newline at end of file
diff -r deaedec14cc8 -r 418f42b34049 display_applications/proteomics/mzML.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/display_applications/proteomics/mzML.xml Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,18 @@
+
+
+
+
+
+
+ ${site_url}/init_local?file=${encoded_filename.qp}&type=mzml
+
+
+
+ #import binascii
+ ${binascii.hexlify( $mzml_file.file_name )}
+
+
+ ${BASE_URL.split(":")[1][2:]}
+
+
+
\ No newline at end of file
diff -r deaedec14cc8 -r 418f42b34049 interprophet.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/interprophet.xml Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,55 @@
+
+ protk
+ Combine Peptide Prophet results from multiple search engines
+
+
+
+ interprophet_wrapper.rb $output $use_nss $use_nrs $use_nse $use_nsi $use_nsm --minprob $minprob
+
+
+ ## Inputs.
+ ${first_input}
+ #for $input_file in $input_files:
+ ${input_file.additional_input}
+ #end for
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+**What it does**
+
+Takes a set of pepXML files (possibly generated using different search engines) and calculates updated identification probabilities for each peptide. The updated probabilities are based on a statistical model that combines evidence from identifications across all of the input files, spectra, modified states and charge states.
+
+----
+
+**Citation**
+
+If you use this tool please read and cite the paper describing iProphet
+
+Shteynberg D, et al. “iProphet: Improved statistical validation of peptide identifications in shotgun proteomics.” *Molecular and Cellular Proteomics* 10, M111.007690 (2011).
+
+
+
+
diff -r deaedec14cc8 -r 418f42b34049 interprophet_wrapper.rb
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/interprophet_wrapper.rb Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,57 @@
+require 'pathname'
+
+$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
+
+interprophet_path=%x[which interprophet.rb]
+cmd << interprophet_path.chomp
+
+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}]
+
diff -r deaedec14cc8 -r 418f42b34049 lib/galaxy/datatypes/proteomics.py
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/lib/galaxy/datatypes/proteomics.py Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,275 @@
+"""
+Proteomics format classes
+"""
+import logging
+import re
+from galaxy.datatypes.data import *
+from galaxy.datatypes.xml import *
+from galaxy.datatypes.sniff import *
+from galaxy.datatypes.binary import *
+
+log = logging.getLogger(__name__)
+
+
+class Xls( Binary ):
+ """Class describing a binary excel spreadsheet file"""
+ file_ext = "xls"
+
+ def set_peek( self, dataset, is_multi_byte=False ):
+ if not dataset.dataset.purged:
+ dataset.peek = "Excel Spreadsheet file"
+ dataset.blurb = data.nice_size( dataset.get_size() )
+ else:
+ dataset.peek = 'file does not exist'
+ dataset.blurb = 'file purged from disk'
+ def display_peek( self, dataset ):
+ try:
+ return dataset.peek
+ except:
+ return "Binary xls file (%s)" % ( data.nice_size( dataset.get_size() ) )
+
+class PepXml(GenericXml):
+ """pepXML data"""
+ file_ext = "pepxml"
+
+ def set_peek( self, dataset, is_multi_byte=False ):
+ """Set the peek and blurb text"""
+ if not dataset.dataset.purged:
+ dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+ dataset.blurb = 'pepXML data'
+ else:
+ dataset.peek = 'file does not exist'
+ dataset.blurb = 'file purged from disk'
+ def sniff( self, filename ):
+ """
+ Determines whether the file is pepXML
+ """
+ #TODO - Use a context manager on Python 2.5+ to close handle
+ handle = open(filename)
+ xmlns_re = re.compile(".*pepXML\"")
+ for i in range(3):
+ line = handle.readline()
+ if xmlns_re.match(line.strip()):
+ handle.close()
+ return True
+
+ handle.close()
+ return False
+
+class MzML( GenericXml ):
+ """mzML data"""
+ file_ext = "mzml"
+
+ def set_peek( self, dataset, is_multi_byte=False ):
+ """Set the peek and blurb text"""
+ if not dataset.dataset.purged:
+ dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+ dataset.blurb = 'mzML Mass Spectrometry data'
+ else:
+ dataset.peek = 'file does not exist'
+ dataset.blurb = 'file purged from disk'
+
+ def sniff( self, filename ):
+ handle = open(filename)
+ xmlns_re = re.compile("^',
+ 'xmlns="http://regis-web.systemsbiology.net/protXML"' ]
+
+ for i, line in enumerate( file( filename ) ):
+ if i >= len( pepxml_header ):
+ return True
+ line = line.rstrip( '\n\r' )
+ if protxml_header[ i ] not in line:
+ return False
+
+
+
+class MzXML( Text ):
+ """mzXML data"""
+ file_ext = "mzXML"
+
+ def set_peek( self, dataset, is_multi_byte=False ):
+ """Set the peek and blurb text"""
+ if not dataset.dataset.purged:
+ dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+ dataset.blurb = 'mzXML Mass Spectrometry data'
+ else:
+ dataset.peek = 'file does not exist'
+ dataset.blurb = 'file purged from disk'
+ def sniff( self, filename ):
+ mzxml_header = [ '',
+ '' ]
+ for i, line in enumerate( file( filename ) ):
+ if i >= len( mzxml_header ):
+ return True
+ line = line.rstrip( '\n\r' )
+ if line != mzxml_header[ i ]:
+ return False
+
+class Mgf( Text ):
+ """Mascot Generic Format data"""
+ file_ext = "mgf"
+
+ def set_peek( self, dataset, is_multi_byte=False ):
+ """Set the peek and blurb text"""
+ if not dataset.dataset.purged:
+ dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+ dataset.blurb = 'mgf Mascot Generic Format'
+ else:
+ dataset.peek = 'file does not exist'
+ dataset.blurb = 'file purged from disk'
+
+
+ def sniff( self, filename ):
+ mgf_begin_ions = "BEGIN IONS"
+ max_lines=100
+
+ for i, line in enumerate( file( filename ) ):
+ line = line.rstrip( '\n\r' )
+ if line==mgf_begin_ions:
+ return True
+ if i>max_lines:
+ return False
+
+
+class MascotDat( Text ):
+ """Mascot search results """
+ file_ext = "mascotdat"
+
+ def set_peek( self, dataset, is_multi_byte=False ):
+ """Set the peek and blurb text"""
+ if not dataset.dataset.purged:
+ dataset.peek = data.get_file_peek( dataset.file_name, is_multi_byte=is_multi_byte )
+ dataset.blurb = 'mascotdat Mascot Search Results'
+ else:
+ dataset.peek = 'file does not exist'
+ dataset.blurb = 'file purged from disk'
+
+
+ def sniff( self, filename ):
+ mime_version = "MIME-Version: 1.0 (Generated by Mascot version 1.0)"
+ max_lines=10
+
+ for i, line in enumerate( file( filename ) ):
+ line = line.rstrip( '\n\r' )
+ if line==mime_version:
+ return True
+ if i>max_lines:
+ return False
+
+
+class RAW( Binary ):
+ """Class describing a Thermo Finnigan binary RAW file"""
+ file_ext = "raw"
+ def sniff( self, filename ):
+ # Thermo Finnigan RAW format is proprietary and hence not well documented.
+ # Files start with 2 bytes that seem to differ followed by F\0i\0n\0n\0i\0g\0a\0n
+ # This combination represents 17 bytes, but to play safe we read 20 bytes from
+ # the start of the file.
+ try:
+ header = open( filename ).read(20)
+ hexheader = binascii.b2a_hex( header )
+ finnigan = binascii.hexlify( 'F\0i\0n\0n\0i\0g\0a\0n' )
+ if hexheader.find(finnigan) != -1:
+ return True
+ return False
+ except:
+ return False
+ def set_peek( self, dataset, is_multi_byte=False ):
+ if not dataset.dataset.purged:
+ dataset.peek = "Thermo Finnigan RAW file"
+ dataset.blurb = data.nice_size( dataset.get_size() )
+ else:
+ dataset.peek = 'file does not exist'
+ dataset.blurb = 'file purged from disk'
+ def display_peek( self, dataset ):
+ try:
+ return dataset.peek
+ except:
+ return "Thermo Finnigan RAW file (%s)" % ( data.nice_size( dataset.get_size() ) )
+
+
+class Msp(Text):
+ """ Output of NIST MS Search Program chemdata.nist.gov/mass-spc/ftp/mass-spc/PepLib.pdf """
+ file_ext = "msp"
+
+ @staticmethod
+ def next_line_starts_with(contents, prefix):
+ next_line = contents.readline()
+ return next_line != None and next_line.startswith(prefix)
+
+ def sniff(self, filename):
+ """ Determines whether the file is a NIST MSP output file.
+
+ >>> fname = get_test_fname('test.msp')
+ >>> Msp().sniff(fname)
+ True
+ >>> fname = get_test_fname('test.mzXML')
+ >>> Msp().sniff(fname)
+ False
+ """
+ with open(filename, 'r') as contents:
+ return Msp.next_line_starts_with(contents, "Name:") and Msp.next_line_starts_with(contents, "MW:")
+
+class Ms2(Text):
+ file_ext = "ms2"
+
+ def sniff(self, filename):
+ """ Determines whether the file is a valid ms2 file.
+
+ >>> fname = get_test_fname('test.msp')
+ >>> Ms2().sniff(fname)
+ False
+ >>> fname = get_test_fname('test.ms2')
+ >>> Ms2().sniff(fname)
+ True
+ """
+
+ with open(filename, 'r') as contents:
+ header_lines = []
+ while True:
+ line = contents.readline()
+ if line == None or len(line) == 0:
+ pass
+ elif line.startswith('H\t'):
+ header_lines.append(line)
+ else:
+ break
+ for header_field in ['CreationDate', 'Extractor', 'ExtractorVersion', 'ExtractorOptions']:
+ found_header = False
+ for header_line in header_lines:
+ if header_line.startswith('H\t%s' % (header_field)):
+ found_header = True
+ break
+ if not found_header:
+ return False
+
+ return True
+
+# unsniffable binary format, should do something about this
+class XHunterAslFormat(Binary):
+ """ Annotated Spectra in the HLF format http://www.thegpm.org/HUNTER/format_2006_09_15.html """
+ file_ext = "hlf"
diff -r deaedec14cc8 -r 418f42b34049 make_decoy.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/make_decoy.xml Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,26 @@
+
+
+ protk
+
+
+ Creates a random protein database with similar properties to a real protein database
+
+ make_decoy.rb $input_file -o $output -L $length -P $prefix $append
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+ Create random protein sequences
+
+
+
diff -r deaedec14cc8 -r 418f42b34049 mzml_to_mgf.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/mzml_to_mgf.xml Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,25 @@
+
+
+ protk
+
+
+ Converts an mzML file to mgf suitable for searching by omssa
+
+ file_convert.rb $input_file -o $output $maldi
+
+
+
+
+
+
+
+
+
+
+
+
+
+ Convert line spectra to Mascot Generic Format
+
+
+
diff -r deaedec14cc8 -r 418f42b34049 omssa.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/omssa.xml Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,161 @@
+
+
+ protk
+
+
+ Run an OMSSA MS/MS Search
+
+ #if $database.source_select=="built_in":
+ omssa_search.rb -d $database.dbkey
+ #else #omssa_search.rb -d $database.fasta_file
+ #end if
+
+ --var-mods='
+ $variable_mods
+ '
+
+ --fix-mods='
+ $fixed_mods
+ '
+
+ --searched-ions='
+ $searched_ions
+ '
+
+ $input_file -o $output -r --enzyme=$enzyme --precursor-ion-tol-units=$precursor_tolu -v $missed_cleavages -f $fragment_ion_tol -p $precursor_ion_tol --num-peaks-for-multi-isotope-search $multi_isotope $use_average_mass $respect_precursor_charges --max-hit-expect $max_hit_expect --intensity-cut-off $intensity_cut_off
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+**What it does**
+
+Runs an MS/MS database search using the OMSSA search engine. Output is in the form of a pepXML file containing identified peptides along with their raw search scores.
+
+----
+
+**Citation**
+
+If you use this tool please read and cite the paper describing OMSSA.
+
+Geer L. Y., et al. “Open mass spectrometry search algorithm” *J. Proteome Res.* 3(5), 958-964 (2004).
+
+
+
diff -r deaedec14cc8 -r 418f42b34049 peptide_prophet.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/peptide_prophet.xml Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,79 @@
+
+ protk
+ Calculate Peptide Prophet statistics on search results
+
+ peptide_prophet_wrapper.rb ${output} ${input_file} -r $glyco $useicat $phospho $usepi $usert $accurate_mass $no_ntt $no_nmc $use_gamma $use_only_expect $force_fit $allow_alt_instruments $maldi
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+**What it does**
+
+Given raw search engine scores as inputs this tool estimates the accuracy of peptide assignments. From a practical perspective it estimates the probability that each peptide assignment is correct (providing probabilities as outputs), given raw scores (possibly on some arbitrary scale) as inputs.
+
+----
+
+**Citation**
+
+If you use this tool please read and cite the paper describing the statistical model implemented by Peptide Prophet
+
+Keller A., et al. “Empirical Statistical Model to Estimate the Accuracy of Peptide Identifications Made by MS/MS and Database Search” *Anal. Chem.* 74, 5383-5392 (2002).
+
+
+
+
+
+
+
+
diff -r deaedec14cc8 -r 418f42b34049 peptide_prophet_wrapper.rb
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/peptide_prophet_wrapper.rb Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,38 @@
+require 'pathname'
+
+$VERBOSE=nil
+
+peptide_prophet_path=%x[which peptide_prophet.rb]
+
+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 << peptide_prophet_path.chomp
+
+
+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"
+
+%x[#{cmd}]
diff -r deaedec14cc8 -r 418f42b34049 pepxml_to_table.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/pepxml_to_table.xml Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,23 @@
+
+ protk
+ Converts a pepXML file to a tab delimited text file
+
+
+
+pepxml_to_table.rb $input_file -o $output
+
+
+
+
+
+
+
+
+
+
+
+
+ Convert a pepXML file to Tab delimited text
+
+
+
diff -r deaedec14cc8 -r 418f42b34049 protein_prophet.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/protein_prophet.xml Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,67 @@
+
+ protk
+ Calculate Protein Prophet statistics on search results
+
+
+
+ protein_prophet.rb --galaxy $input_file -r $iproph $nooccam $groupwts $normprotlen $logprobs $confem $allpeps $unmapped $instances $delude --minprob=$minprob --minindep=$minindep
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+**What it does**
+
+Given a set of peptide assignments from MS/MS spectra in the form of a pepXML file, this tool estimates probabilities at the protein level. As output, the tool produces a protXML file, which contains proteins along with the estimated probabilities that those proteins were present. Probabilities are estimated using a statistical model based on the number of peptides corresponding to that protein and the confidence that each of those peptides were assigned correctly. It takes account of the fact that peptides may correspond to more than one protein.
+
+----
+
+**Citation**
+
+If you use this tool please read and cite the paper describing the statistical model implemented by Protein Prophet
+
+Nesvizhskii A., et al. “A Statistical Model for Identifying Proteins by Tandem Mass Spectrometry” *Anal. Chem.* 75, 4646-4658 (2003).
+
+
+
+
+
diff -r deaedec14cc8 -r 418f42b34049 protein_prophet_wrapper.rb
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/protein_prophet_wrapper.rb Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,37 @@
+require 'pathname'
+
+$VERBOSE=nil
+
+protein_prophet_path=%x[which protein_prophet.rb]
+
+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 << protein_prophet_path.chomp
+
+
+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}]
+
diff -r deaedec14cc8 -r 418f42b34049 tandem.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tandem.xml Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,128 @@
+
+ protk
+ Run an X!Tandem Search
+
+
+ #if $database.source_select=="built_in":
+ tandem_search.rb -d $database.dbkey
+ #else #tandem_search.rb -d $database.fasta_file
+ #end if
+
+ --var-mods='
+ $variable_mods
+ #for $custom_variable_mod in $custom_variable_mods:
+ ,${custom_variable_mod.custom_mod}
+ #end for
+ '
+
+ --fix-mods='
+ $fixed_mods
+ #for $custom_fix_mod in $custom_fix_mods:
+ ,${custom_fix_mod.custom_mod}
+ #end for
+ '
+
+ $input_file -o $output -r --enzyme=$enzyme --precursor-ion-tol-units=$precursor_tolu -v $missed_cleavages -f $fragment_ion_tol -p $precursor_ion_tol $allow_multi_isotope_search --keep-params-files
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+**What it does**
+
+Runs an MS/MS database search using the X!Tandem search engine. Output is in the form of a pepXML file containing identified peptides along with their raw search scores.
+
+----
+
+**References**
+
+Please see http://www.thegpm.org/GPM/references.html for details of references describing the X!Tandem search engine.
+
+
+
+
diff -r deaedec14cc8 -r 418f42b34049 tool-data/datatypes_conf.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/datatypes_conf.xml Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,42 @@
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff -r deaedec14cc8 -r 418f42b34049 tool-data/mascot_databases.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/mascot_databases.loc.sample Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,13 @@
+#This file lists the names of protein databases installed on Mascot
+#
+#In order to use interprophet to combine results from different search engines
+#it is important that all searches are performed on the same database
+#you should therefore ensure that each database installed on mascot has an equivalent
+#database installed in the Protk databases directory (databases used by omssa and x!tandem)
+#the mascot_to_pepxml tool will ask for this database when performing the conversion.
+#
+# Entries should follow the be structured as follows
+# Display_name dbkey dbNameOnMascot dbkey
+#
+Swissprot spall_ SPAll spall_
+Swissprot Human sphuman_ SPHuman sphuman_
\ No newline at end of file
diff -r deaedec14cc8 -r 418f42b34049 tool-data/mascot_mods.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/mascot_mods.loc.sample Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,77 @@
+#This file lists the names of chemical modifications acceptable for proteomics search engines
+#
+#
+Acetyl (K) acetyl_k_ Acetyl (K) acetyl_k_
+Acetyl (N-term) acetyl_n-term_ Acetyl (N-term) acetyl_n-term_
+Acetyl (Protein N-term) acetyl_proteinn-term_ Acetyl (Protein N-term) acetyl_proteinn-term_
+Amidated (C-term) amidated_c-term_ Amidated (C-term) amidated_c-term_
+Amidated (Protein C-term) amidated_proteinc-term_ Amidated (Protein C-term) amidated_proteinc-term_
+Ammonia-loss (N-term C) ammonia-loss_n-termc_ Ammonia-loss (N-term C) ammonia-loss_n-termc_
+Biotin (K) biotin_k_ Biotin (K) biotin_k_
+Biotin (N-term) biotin_n-term_ Biotin (N-term) biotin_n-term_
+Carbamidomethyl (C) carbamidomethyl_c_ Carbamidomethyl (C) carbamidomethyl_c_
+Carbamyl (K) carbamyl_k_ Carbamyl (K) carbamyl_k_
+Carbamyl (N-term) carbamyl_n-term_ Carbamyl (N-term) carbamyl_n-term_
+Carboxymethyl (C) carboxymethyl_c_ Carboxymethyl (C) carboxymethyl_c_
+Cation:Na (C-term) cation_na_c-term_ Cation:Na (C-term) cation_na_c-term_
+Cation:Na (DE) cation_na_de_ Cation:Na (DE) cation_na_de_
+Deamidated (NQ) deamidated_nq_ Deamidated (NQ) deamidated_nq_
+Deamidated-N (N) deamidated-n_n_ Deamidated-N (N) deamidated-n_n_
+Dehydrated (N-term C) dehydrated_n-termc_ Dehydrated (N-term C) dehydrated_n-termc_
+Dehydro (C) dehydro_c_ Dehydro (C) dehydro_c_
+Dioxidation (M) dioxidation_m_ Dioxidation (M) dioxidation_m_
+Ethanolyl (C) ethanolyl_c_ Ethanolyl (C) ethanolyl_c_
+ExacTagAmine (K) exactagamine_k_ ExacTagAmine (K) exactagamine_k_
+ExacTagThiol (C) exactagthiol_c_ ExacTagThiol (C) exactagthiol_c_
+Formyl (N-term) formyl_n-term_ Formyl (N-term) formyl_n-term_
+Formyl (Protein N-term) formyl_proteinn-term_ Formyl (Protein N-term) formyl_proteinn-term_
+Gln->pyro-Glu (N-term Q) gln_pyro-glu_n-termq_ Gln->pyro-Glu (N-term Q) gln_pyro-glu_n-termq_
+Glu->pyro-Glu (N-term E) glu_pyro-glu_n-terme_ Glu->pyro-Glu (N-term E) glu_pyro-glu_n-terme_
+Guanidinyl (K) guanidinyl_k_ Guanidinyl (K) guanidinyl_k_
+ICAT-C (C) icat-c_c_ ICAT-C (C) icat-c_c_
+ICAT-C:13C(9) (C) icat-c_13c_9__c_ ICAT-C:13C(9) (C) icat-c_13c_9__c_
+ICPL (K) icpl_k_ ICPL (K) icpl_k_
+ICPL (Protein N-term) icpl_proteinn-term_ ICPL (Protein N-term) icpl_proteinn-term_
+ICPL:13C(6) (K) icpl_13c_6__k_ ICPL:13C(6) (K) icpl_13c_6__k_
+ICPL:13C(6) (Protein N-term) icpl_13c_6__proteinn-term_ ICPL:13C(6) (Protein N-term) icpl_13c_6__proteinn-term_
+ICPL:13C(6)2H(4) (K) icpl_13c_6_2h_4__k_ ICPL:13C(6)2H(4) (K) icpl_13c_6_2h_4__k_
+ICPL:13C(6)2H(4) (N-term) icpl_13c_6_2h_4__n-term_ ICPL:13C(6)2H(4) (N-term) icpl_13c_6_2h_4__n-term_
+ICPL:13C(6)2H(4) (Protein N-term) icpl_13c_6_2h_4__proteinn-term_ ICPL:13C(6)2H(4) (Protein N-term) icpl_13c_6_2h_4__proteinn-term_
+ICPL:2H(4) (K) icpl_2h_4__k_ ICPL:2H(4) (K) icpl_2h_4__k_
+ICPL:2H(4) (Protein N-term) icpl_2h_4__proteinn-term_ ICPL:2H(4) (Protein N-term) icpl_2h_4__proteinn-term_
+iTRAQ4plex (K) itraq4plex_k_ iTRAQ4plex (K) itraq4plex_k_
+iTRAQ4plex (N-term) itraq4plex_n-term_ iTRAQ4plex (N-term) itraq4plex_n-term_
+iTRAQ4plex (Y) itraq4plex_y_ iTRAQ4plex (Y) itraq4plex_y_
+iTRAQ8plex (K) itraq8plex_k_ iTRAQ8plex (K) itraq8plex_k_
+iTRAQ8plex (N-term) itraq8plex_n-term_ iTRAQ8plex (N-term) itraq8plex_n-term_
+iTRAQ8plex (Y) itraq8plex_y_ iTRAQ8plex (Y) itraq8plex_y_
+Label:18O(1) (C-term) label_18o_1__c-term_ Label:18O(1) (C-term) label_18o_1__c-term_
+Label:18O(2) (C-term) label_18o_2__c-term_ Label:18O(2) (C-term) label_18o_2__c-term_
+Met->Hse (C-term M) met_hse_c-termm_ Met->Hse (C-term M) met_hse_c-termm_
+Met->Hsl (C-term M) met_hsl_c-termm_ Met->Hsl (C-term M) met_hsl_c-termm_
+Methyl (C-term) methyl_c-term_ Methyl (C-term) methyl_c-term_
+Methyl (DE) methyl_de_ Methyl (DE) methyl_de_
+Methylthio (C) methylthio_c_ Methylthio (C) methylthio_c_
+mTRAQ (K) mtraq_k_ mTRAQ (K) mtraq_k_
+mTRAQ (N-term) mtraq_n-term_ mTRAQ (N-term) mtraq_n-term_
+mTRAQ (Y) mtraq_y_ mTRAQ (Y) mtraq_y_
+mTRAQ:13C(3)15N(1) (K) mtraq_13c_3_15n_1__k_ mTRAQ:13C(3)15N(1) (K) mtraq_13c_3_15n_1__k_
+mTRAQ:13C(3)15N(1) (N-term) mtraq_13c_3_15n_1__n-term_ mTRAQ:13C(3)15N(1) (N-term) mtraq_13c_3_15n_1__n-term_
+mTRAQ:13C(3)15N(1) (Y) mtraq_13c_3_15n_1__y_ mTRAQ:13C(3)15N(1) (Y) mtraq_13c_3_15n_1__y_
+NIPCAM (C) nipcam_c_ NIPCAM (C) nipcam_c_
+Oxidation (HW) oxidation_hw_ Oxidation (HW) oxidation_hw_
+Oxidation (M) oxidation_m_ Oxidation (M) oxidation_m_
+Phospho (ST) phospho_st_ Phospho (ST) phospho_st_
+Phospho (Y) phospho_y_ Phospho (Y) phospho_y_
+Propionamide (C) propionamide_c_ Propionamide (C) propionamide_c_
+Pyridylethyl (C) pyridylethyl_c_ Pyridylethyl (C) pyridylethyl_c_
+Pyro-carbamidomethyl (N-term C) pyro-carbamidomethyl_n-termc_ Pyro-carbamidomethyl (N-term C) pyro-carbamidomethyl_n-termc_
+Sulfo (S) sulfo_s_ Sulfo (S) sulfo_s_
+Sulfo (T) sulfo_t_ Sulfo (T) sulfo_t_
+Sulfo (Y) sulfo_y_ Sulfo (Y) sulfo_y_
+TMT (K) tmt_k_ TMT (K) tmt_k_
+TMT (N-term) tmt_n-term_ TMT (N-term) tmt_n-term_
+TMT2plex (K) tmt2plex_k_ TMT2plex (K) tmt2plex_k_
+TMT2plex (N-term) tmt2plex_n-term_ TMT2plex (N-term) tmt2plex_n-term_
+TMT6plex (K) tmt6plex_k_ TMT6plex (K) tmt6plex_k_
+TMT6plex (N-term) tmt6plex_n-term_ TMT6plex (N-term) tmt6plex_n-term_
diff -r deaedec14cc8 -r 418f42b34049 tool-data/omssa_mods.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/omssa_mods.loc.sample Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,181 @@
+#This file lists the names of chemical modifications accepted by OMMSA
+#
+#
+2-amino-3-oxo-butanoic acid T 2-amino-3-oxo-butanoicacidt_ 23 2-amino-3-oxo-butanoicacidt_
+Asparagine HexNAc asparaginehexnac_ 182 asparaginehexnac_
+Asparagine dHexHexNAc asparaginedhexhexnac_ 183 asparaginedhexhexnac_
+CAMthiopropanoyl K camthiopropanoylk_ 131 camthiopropanoylk_
+CHD2-di-methylation of K chd2-di-methylationofk_ 189 chd2-di-methylationofk_
+CHD2-di-methylation of peptide n-term chd2-di-methylationofpeptiden-term_ 190 chd2-di-methylationofpeptiden-term_
+ICAT heavy icatheavy_ 130 icatheavy_
+ICAT light icatlight_ 129 icatlight_
+M cleavage from protein n-term mcleavagefromproteinn-term_ 9 mcleavagefromproteinn-term_
+MMTS on C mmtsonc_ 179 mmtsonc_
+Maleimide-PEO2-Biotin of C maleimide-peo2-biotinofc_ 191 maleimide-peo2-biotinofc_
+NEM C nemc_ 83 nemc_
+NIPCAM nipcam_ 84 nipcam_
+O18 on peptide n-term o18onpeptiden-term_ 87 o18onpeptiden-term_
+PNGasF in O18 water pngasfino18water_ 139 pngasfino18water_
+SeMet semet_ 113 semet_
+Serine HexNAc serinehexnac_ 184 serinehexnac_
+TMT 6-plex on K tmt6-plexonk_ 198 tmt6-plexonk_
+TMT 6-plex on n-term peptide tmt6-plexonn-termpeptide_ 199 tmt6-plexonn-termpeptide_
+Threonine HexNAc threoninehexnac_ 185 threoninehexnac_
+Uniblue A on K uniblueaonk_ 195 uniblueaonk_
+acetylation of K acetylationofk_ 24 acetylationofk_
+acetylation of protein n-term acetylationofproteinn-term_ 10 acetylationofproteinn-term_
+amidation of peptide c-term amidationofpeptidec-term_ 25 amidationofpeptidec-term_
+arginine to ornithine argininetoornithine_ 163 argininetoornithine_
+beta elimination of S betaeliminationofs_ 140 betaeliminationofs_
+beta elimination of T betaeliminationoft_ 141 betaeliminationoft_
+beta methythiolation of D betamethythiolationofd_ 13 betamethythiolationofd_
+beta-carboxylation of D beta-carboxylationofd_ 47 beta-carboxylationofd_
+beta-methylthiolation of D (duplicate of 13) beta-methylthiolationofd_duplicateof13__ 26 beta-methylthiolationofd_duplicateof13__
+carbamidomethyl C carbamidomethylc_ 3 carbamidomethylc_
+carbamylation of K carbamylationofk_ 31 carbamylationofk_
+carbamylation of n-term peptide carbamylationofn-termpeptide_ 32 carbamylationofn-termpeptide_
+carboxyamidomethylation of D carboxyamidomethylationofd_ 29 carboxyamidomethylationofd_
+carboxyamidomethylation of E carboxyamidomethylationofe_ 30 carboxyamidomethylationofe_
+carboxyamidomethylation of H carboxyamidomethylationofh_ 28 carboxyamidomethylationofh_
+carboxyamidomethylation of K carboxyamidomethylationofk_ 27 carboxyamidomethylationofk_
+carboxykynurenin of W carboxykynureninofw_ 165 carboxykynureninofw_
+carboxymethyl C carboxymethylc_ 2 carboxymethylc_
+carboxymethylated selenocysteine carboxymethylatedselenocysteine_ 207 carboxymethylatedselenocysteine_
+citrullination of R citrullinationofr_ 33 citrullinationofr_
+deamidation of N deamidationofn_ 196 deamidationofn_
+deamidation of N and Q deamidationofnandq_ 4 deamidationofnandq_
+dehydro of S and T dehydroofsandt_ 164 dehydroofsandt_
+di-O18 on peptide n-term di-o18onpeptiden-term_ 88 di-o18onpeptiden-term_
+di-iodination of Y di-iodinationofy_ 35 di-iodinationofy_
+di-methylation of K di-methylationofk_ 36 di-methylationofk_
+di-methylation of R di-methylationofr_ 37 di-methylationofr_
+di-methylation of peptide n-term di-methylationofpeptiden-term_ 38 di-methylationofpeptiden-term_
+farnesylation of C farnesylationofc_ 42 farnesylationofc_
+fluorophenylalanine fluorophenylalanine_ 46 fluorophenylalanine_
+formylation of K formylationofk_ 43 formylationofk_
+formylation of peptide n-term formylationofpeptiden-term_ 44 formylationofpeptiden-term_
+formylation of protein n-term formylationofproteinn-term_ 82 formylationofproteinn-term_
+gamma-carboxylation of E gamma-carboxylationofe_ 48 gamma-carboxylationofe_
+gammathiopropionylation of K gammathiopropionylationofk_ 40 gammathiopropionylationofk_
+gammathiopropionylation of peptide n-term gammathiopropionylationofpeptiden-term_ 41 gammathiopropionylationofpeptiden-term_
+geranyl-geranyl geranyl-geranyl_ 49 geranyl-geranyl_
+glucuronylation of protein n-term glucuronylationofproteinn-term_ 50 glucuronylationofproteinn-term_
+glutathione disulfide glutathionedisulfide_ 51 glutathionedisulfide_
+guanidination of K guanidinationofk_ 53 guanidinationofk_
+heavy arginine-13C6 heavyarginine-13c6_ 136 heavyarginine-13c6_
+heavy arginine-13C6-15N4 heavyarginine-13c6-15n4_ 137 heavyarginine-13c6-15n4_
+heavy lysine - 13C6 15N2 heavylysine-13c615n2_ 181 heavylysine-13c615n2_
+heavy lysine - 2H4 heavylysine-2h4_ 180 heavylysine-2h4_
+heavy lysine-13C6 heavylysine-13c6_ 138 heavylysine-13c6_
+homoserine homoserine_ 56 homoserine_
+homoserine lactone homoserinelactone_ 57 homoserinelactone_
+hydroxylation of Y hydroxylationofy_ 64 hydroxylationofy_
+hydroxylation of D hydroxylationofd_ 59 hydroxylationofd_
+hydroxylation of F hydroxylationoff_ 63 hydroxylationoff_
+hydroxylation of K hydroxylationofk_ 60 hydroxylationofk_
+hydroxylation of N hydroxylationofn_ 61 hydroxylationofn_
+hydroxylation of P hydroxylationofp_ 62 hydroxylationofp_
+iTRAQ114 on K itraq114onk_ 168 itraq114onk_
+iTRAQ114 on Y itraq114ony_ 169 itraq114ony_
+iTRAQ114 on nterm itraq114onnterm_ 167 itraq114onnterm_
+iTRAQ115 on K itraq115onk_ 171 itraq115onk_
+iTRAQ115 on Y itraq115ony_ 172 itraq115ony_
+iTRAQ115 on nterm itraq115onnterm_ 170 itraq115onnterm_
+iTRAQ116 on K itraq116onk_ 174 itraq116onk_
+iTRAQ116 on Y itraq116ony_ 175 itraq116ony_
+iTRAQ116 on nterm itraq116onnterm_ 173 itraq116onnterm_
+iTRAQ117 on K itraq117onk_ 177 itraq117onk_
+iTRAQ117 on Y itraq117ony_ 178 itraq117ony_
+iTRAQ117 on nterm itraq117onnterm_ 176 itraq117onnterm_
+iTRAQ8plex itraq8plex_ 204 itraq8plex_
+iTRAQ8plex itraq8plex_ 205 itraq8plex_
+iTRAQ8plex itraq8plex_ 203 itraq8plex_
+iTRAQ8plex itraq8plex_ 201 itraq8plex_
+iTRAQ8plex itraq8plex_ 202 itraq8plex_
+iTRAQ8plex itraq8plex_ 200 itraq8plex_
+iodination of Y iodinationofy_ 65 iodinationofy_
+lipoyl K lipoylk_ 67 lipoylk_
+methyl C methylc_ 73 methylc_
+methyl H methylh_ 74 methylh_
+methyl N methyln_ 75 methyln_
+methyl R methylr_ 77 methylr_
+methyl ester of D methylesterofd_ 69 methylesterofd_
+methyl ester of E (duplicate of 17) methylesterofe_duplicateof17__ 70 methylesterofe_duplicateof17__
+methyl ester of S methylesterofs_ 71 methylesterofs_
+methyl ester of Y methylesterofy_ 72 methylesterofy_
+methyl ester of peptide c-term (duplicate of 18) methylesterofpeptidec-term_duplicateof18__ 68 methylesterofpeptidec-term_duplicateof18__
+methylation of D methylationofd_ 16 methylationofd_
+methylation of E methylationofe_ 17 methylationofe_
+methylation of K methylationofk_ 0 methylationofk_
+methylation of Q methylationofq_ 14 methylationofq_
+methylation of peptide c-term methylationofpeptidec-term_ 18 methylationofpeptidec-term_
+methylation of peptide n-term methylationofpeptiden-term_ 76 methylationofpeptiden-term_
+methylation of protein n-term methylationofproteinn-term_ 11 methylationofproteinn-term_
+myristoleylation of G myristoleylationofg_ 78 myristoleylationofg_
+myristoyl-4H of G myristoyl-4hofg_ 79 myristoyl-4hofg_
+myristoylation of K myristoylationofk_ 81 myristoylationofk_
+myristoylation of peptide n-term G myristoylationofpeptiden-termg_ 80 myristoylationofpeptiden-termg_
+n-acyl diglyceride cysteine n-acyldiglyceridecysteine_ 118 n-acyldiglyceridecysteine_
+n-formyl met addition n-formylmetaddition_ 22 n-formylmetaddition_
+oxidation of C oxidationofc_ 193 oxidationofc_
+oxidation of C to cysteic acid oxidationofctocysteicacid_ 34 oxidationofctocysteicacid_
+oxidation of C to sulfinic acid oxidationofctosulfinicacid_ 162 oxidationofctosulfinicacid_
+oxidation of F to dihydroxyphenylalanine oxidationofftodihydroxyphenylalanine_ 39 oxidationofftodihydroxyphenylalanine_
+oxidation of H oxidationofh_ 89 oxidationofh_
+oxidation of H to D oxidationofhtod_ 55 oxidationofhtod_
+oxidation of H to N oxidationofhton_ 54 oxidationofhton_
+oxidation of M oxidationofm_ 1 oxidationofm_
+oxidation of P to pyroglutamic acid oxidationofptopyroglutamicacid_ 111 oxidationofptopyroglutamicacid_
+oxidation of W oxidationofw_ 90 oxidationofw_
+oxidation of W to formylkynurenin oxidationofwtoformylkynurenin_ 45 oxidationofwtoformylkynurenin_
+oxidation of W to hydroxykynurenin oxidationofwtohydroxykynurenin_ 58 oxidationofwtohydroxykynurenin_
+oxidation of W to kynurenin oxidationofwtokynurenin_ 66 oxidationofwtokynurenin_
+oxidation of W to nitro oxidationofwtonitro_ 85 oxidationofwtonitro_
+oxidation of Y (duplicate of 64) oxidationofy_duplicateof64__ 194 oxidationofy_duplicateof64__
+oxidation of Y to nitro oxidationofytonitro_ 86 oxidationofytonitro_
+palmitoleyl of C palmitoleylofc_ 187 palmitoleylofc_
+palmitoleyl of S palmitoleylofs_ 186 palmitoleylofs_
+palmitoleyl of T palmitoleyloft_ 188 palmitoleyloft_
+palmitoylation of C palmitoylationofc_ 92 palmitoylationofc_
+palmitoylation of K palmitoylationofk_ 93 palmitoylationofk_
+palmitoylation of S palmitoylationofs_ 94 palmitoylationofs_
+palmitoylation of T palmitoylationoft_ 95 palmitoylationoft_
+phosphopantetheine S phosphopantetheines_ 91 phosphopantetheines_
+phosphorylation of H phosphorylationofh_ 192 phosphorylationofh_
+phosphorylation of S phosphorylationofs_ 6 phosphorylationofs_
+phosphorylation of S with ETD loss phosphorylationofswithetdloss_ 134 phosphorylationofswithetdloss_
+phosphorylation of S with prompt loss phosphorylationofswithpromptloss_ 96 phosphorylationofswithpromptloss_
+phosphorylation of T phosphorylationoft_ 7 phosphorylationoft_
+phosphorylation of T with ETD loss phosphorylationoftwithetdloss_ 135 phosphorylationoftwithetdloss_
+phosphorylation of T with prompt loss phosphorylationoftwithpromptloss_ 97 phosphorylationoftwithpromptloss_
+phosphorylation of Y phosphorylationofy_ 8 phosphorylationofy_
+phosphorylation with neutral loss on C phosphorylationwithneutrallossonc_ 99 phosphorylationwithneutrallossonc_
+phosphorylation with neutral loss on D phosphorylationwithneutrallossond_ 100 phosphorylationwithneutrallossond_
+phosphorylation with neutral loss on H phosphorylationwithneutrallossonh_ 101 phosphorylationwithneutrallossonh_
+phosphorylation with neutral loss on S phosphorylationwithneutrallossons_ 132 phosphorylationwithneutrallossons_
+phosphorylation with neutral loss on T phosphorylationwithneutrallossont_ 133 phosphorylationwithneutrallossont_
+phosphorylation with prompt loss on Y phosphorylationwithpromptlossony_ 98 phosphorylationwithpromptlossony_
+propionamide C propionamidec_ 5 propionamidec_
+propionyl heavy K propionylheavyk_ 104 propionylheavyk_
+propionyl heavy peptide n-term propionylheavypeptiden-term_ 105 propionylheavypeptiden-term_
+propionyl light K propionyllightk_ 102 propionyllightk_
+propionyl light on peptide n-term propionyllightonpeptiden-term_ 103 propionyllightonpeptiden-term_
+pyridyl K pyridylk_ 106 pyridylk_
+pyridyl peptide n-term pyridylpeptiden-term_ 107 pyridylpeptiden-term_
+pyro-cmC pyro-cmc_ 108 pyro-cmc_
+pyro-glu from n-term E pyro-glufromn-terme_ 109 pyro-glufromn-terme_
+pyro-glu from n-term Q pyro-glufromn-termq_ 110 pyro-glufromn-termq_
+s-pyridylethylation of C s-pyridylethylationofc_ 112 s-pyridylethylationofc_
+selenocysteine selenocysteine_ 206 selenocysteine_
+sulfation of Y sulfationofy_ 114 sulfationofy_
+sulphone of M sulphoneofm_ 115 sulphoneofm_
+sumoylation of K sumoylationofk_ 166 sumoylationofk_
+tri-deuteromethylation of D tri-deuteromethylationofd_ 19 tri-deuteromethylationofd_
+tri-deuteromethylation of E tri-deuteromethylationofe_ 20 tri-deuteromethylationofe_
+tri-deuteromethylation of peptide c-term tri-deuteromethylationofpeptidec-term_ 21 tri-deuteromethylationofpeptidec-term_
+tri-iodination of Y tri-iodinationofy_ 116 tri-iodinationofy_
+tri-methylation of K tri-methylationofk_ 15 tri-methylationofk_
+tri-methylation of R tri-methylationofr_ 117 tri-methylationofr_
+tri-methylation of protein n-term tri-methylationofproteinn-term_ 12 tri-methylationofproteinn-term_
+trideuteration of L (SILAC) trideuterationofl_silac__ 197 trideuterationofl_silac__
+ubiquitinylation residue ubiquitinylationresidue_ 52 ubiquitinylationresidue_
diff -r deaedec14cc8 -r 418f42b34049 tool-data/pepxml_databases.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/pepxml_databases.loc.sample Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,13 @@
+#This file lists the names of protein databases installed locally in protk.
+# These are used by omssa and x!tandem as well as the "mascot to pepxml" tool
+# In order to combine search results with Interprophet searches must be run against an identical database
+#
+# Entries should follow the be structured as follows
+# Display_name omssa_tandem_dbname dbkey
+#
+#
+Swissprot spall_ spall spall_
+Combined PlasmboDB (falciparum) and Swissprot Human plasmodb_pfalciparum_sphuman_ plasmodb_pfalciparum_sphuman plasmodb_pfalciparum_sphuman_
+Swissprot Human sphuman_ sphuman sphuman_
+Combined Swissprot/TRembl Human sptrhuman_ sptrhuman sptrhuman_
+Swissprot Mouse spmouse_ spmouse spmouse_
diff -r deaedec14cc8 -r 418f42b34049 tool-data/protk_display_site.txt.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/protk_display_site.txt.sample Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,3 @@
+#Proteomic Visualization application should be hosted on the same server as galaxy
+#Entries in this file are of the format "site_id" site_url
+Proteomics Visualize http://127.0.0.1:8500
diff -r deaedec14cc8 -r 418f42b34049 tool-data/tandem_mods.loc.sample
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/tool-data/tandem_mods.loc.sample Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,6 @@
+#This file lists the names of inbuilt chemical modifications accepted by X!Tandem
+#
+#
+Carbamidomethyl C carbamidomethyl_c_ 57.021464@C carbamidomethyl_c_
+Glycocapture-N glycocapture_n_ 0.998@N!{P}[ST] glycocapture_n_
+Oxidation M oxidation_m_ 15.994915@M oxidation_m_
\ No newline at end of file
diff -r deaedec14cc8 -r 418f42b34049 xls_to_table.xml
--- /dev/null Thu Jan 01 00:00:00 1970 +0000
+++ b/xls_to_table.xml Mon Jul 23 00:20:58 2012 -0400
@@ -0,0 +1,23 @@
+
+ protk
+ Converts an excel spreadsheet to a tab delimited text file
+
+
+
+xls_to_table.rb $input_file -o $output
+
+
+
+
+
+
+
+
+
+
+
+
+ Convert an Excel Spreadsheet to Tab delimited text
+
+
+