protk 1.3.0.pre3 → 1.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 704282a21d38fd8d3a536fbbba9ab90eabd54355
-  data.tar.gz: d325658a001939d222bfb7c942836df25ae9790b
+  metadata.gz: 5e8f8a571cb43ed61984a34b6e1fb51caf979593
+  data.tar.gz: b53857f75c1ff6ca850859c3985aee36533e437f
 SHA512:
-  metadata.gz: f9902d7d48b5171470b073ab94089481f0a9125d0e65e4a33b600ed86cf622bafa774335a0c33520e955d49dd0f195ed7ae82fcab6ad18bf35a42dafe030aea3
-  data.tar.gz: 253cabdf8bfcf009516cc2675ebe12bb9b43ec15515625eabd3701c0761be9f3fc78dcc58dc731c7f89f642f8c11cf1bd8889c5f68a565cda0d04de06fb273c3
+  metadata.gz: 9450fccc4a5ce59f064927d62fbc6a4342a1710c3b82707e0908dea52af7d0b50f215e64073bb067a506d204701acea11b6d28f302447494b8a30b1e7af2df2d
+  data.tar.gz: 1b8bc78fc09b4c81eee72fad169a6aee7145a16312c01bc95a5dd590f08cb98194b26115a166a759b9c52c7c67204a767747642e5e9331de4562d52f31eb1e11

data/bin/make_decoy.rb

@@ -36,7 +36,6 @@ input_file=ARGV[0]
 db_length=tool.db_length
 if ( db_length==0) #If no db length was specified use the number of entries in the input file
   db_length=Bio::FastaFormat.open(input_file).count
-  puts "Found #{db_length} entries in input file"
 end
 
 output_file = tool.explicit_output if tool.explicit_output!=nil
@@ -65,6 +64,7 @@ end
 
 if ( tool.append )
 	cmd ="awk 'FNR==1{print \"\"}1' #{input_file} #{decoys_tmp_file} > #{output_file};"
+	cmd << "sed -i.bak '/^$/d' #{output_file};"
 	cmd << "rm #{decoys_tmp_file}"
 else
 	cmd = "mv #{decoys_tmp_file} #{output_file}"

data/bin/msgfplus_search.rb

@@ -83,16 +83,17 @@ database_path=db_info.path
 
 # Database must have fasta extension
 if Pathname.new(database_path).extname.to_s.downcase != ".fasta"
-  make_msgfdb_cmd << "ln -s #{database_path} #{database_path}.fasta;"
+  File.symlink(database_path,"#{database_path}.fasta") unless File.exists?("#{database_path}.fasta")
+  # make_msgfdb_cmd << "ln -s #{database_path} #{database_path}.fasta;"
   database_path="#{database_path}.fasta"
-  db_info.path=database_path
+  database_path
 end
 
 # Database must be indexed
 unless FileTest.exists?("#{database_path}.canno")
-  dbdir = Pathname.new(database_path).dirname.realpath.to_s
+  dbdir = Pathname.new(database_path).dirname.to_s
   tdavalue=search_tool.decoy_search ? 1 : 0;
-  make_msgfdb_cmd << "cd #{dbdir}; java -Xmx3500M -cp #{genv.msgfplusjar} edu.ucsd.msjava.msdbsearch.BuildSA -d #{database_path} -tda #{tdavalue}; "
+  make_msgfdb_cmd << "java -Xmx3500M -cp #{genv.msgfplusjar} edu.ucsd.msjava.msdbsearch.BuildSA -d #{database_path} -tda #{tdavalue}; "
 end
 
 
@@ -214,7 +215,6 @@ ARGV.each do |filename|
     else
       cmd << "; mv #{mzid_output_path} #{output_path}"
     end
-      
 
     # Up to here we've formulated the command. The rest is cleanup
     p "Running:#{cmd}"

data/bin/omssa_search.rb

@@ -12,8 +12,6 @@ require 'protk/command_runner'
 require 'protk/search_tool'
 require 'protk/galaxy_util'
 
-for_galaxy = GalaxyUtil.for_galaxy?
-
 # Setup specific command-line options for this tool. Other options are inherited from SearchTool
 #
 search_tool=SearchTool.new([
@@ -94,22 +92,6 @@ ARGV.each do |filename|
     #
     cmd << " -v #{search_tool.missed_cleavages}"
 
-    # If this is for Galaxy and a data directory has been specified
-    # look for a common unimod.xml file.
-    if for_galaxy
-      galaxy_index_dir = search_tool.galaxy_index_dir
-      if galaxy_index_dir
-        galaxy_mods = File.join(galaxy_index_dir, "mods.xml")
-        if( FileTest.exists?(galaxy_mods) )      
-          cmd << " -mx #{galaxy_mods}"
-        end
-        galaxy_usermods = File.join(galaxy_index_dir, "usermods.xml")
-        if( FileTest.exists?(galaxy_usermods) )
-          cmd << " -mux #{galaxy_usermods}"
-        end
-      end
-    end
-
     if ( search_tool.omx_output )
       cmd << " -ox #{search_tool.omx_output} "
     end

data/bin/peptide_prophet.rb

@@ -51,10 +51,11 @@ throw "When --output and -F options are set only one file at a time can be run"
 # Obtain a global environment object
 genv=Constants.new
 
-
+input_stagers=[]
 inputs=ARGV.collect { |file_name| file_name.chomp}
 if for_galaxy
-  inputs = inputs.collect {|ip| GalaxyUtil.stage_pepxml(ip) }
+  input_stagers = inputs.collect {|ip| GalaxyUtil.stage_pepxml(ip) }
+  inputs=input_stagers.collect { |sg| sg.staged_path }
 end
 
 # Interrogate all the input files to obtain the database and search engine from them
@@ -212,7 +213,13 @@ else
 
   cmd=generate_command(genv,prophet_tool,inputs,output_file_name,database,engine)
   run_peptide_prophet(genv,prophet_tool,cmd,output_file_name,engine)
-    
+  
 end
 
+if (for_galaxy)
+  input_stagers.each do |sg|
+    sg.restore_references(output_file_name)
+    sg.restore_references(output_file_name,{:base_only => true})
+  end
+end
 

data/bin/protein_prophet.rb

@@ -40,7 +40,13 @@ exit unless prophet_tool.check_options(true)
 # Obtain a global environment object
 genv=Constants.new
 
-inputs = ARGV.collect {|file_name| file_name.chomp }
+input_stagers=[]
+inputs=ARGV.collect { |file_name| file_name.chomp}
+if for_galaxy
+  input_stagers = inputs.collect {|ip| GalaxyUtil.stage_pepxml(ip) }
+  inputs=input_stagers.collect { |sg| sg.staged_path }
+end
+
 
 if ( prophet_tool.explicit_output )
   output_file=prophet_tool.explicit_output
@@ -52,11 +58,6 @@ if ( !Pathname.new(output_file).exist? || prophet_tool.over_write )
 
   cmd="ProteinProphet "
 
-  if for_galaxy
-    inputs = inputs.collect {|ip| GalaxyUtil.stage_pepxml(ip) }
-  end
-
-
   cmd << " #{inputs.join(" ")} #{output_file}"
 
   if ( prophet_tool.glyco )
@@ -71,11 +72,13 @@ else
   genv.log("Protein Prophet output file #{output_file} already exists. Run with -r option to replace",:warn)   
 end
 
-# if for_galaxy
-  # Restore references to peptide prophet xml so downstream tools like 
-  # libra can find it.
-  # input_stager.restore_references("protein_prophet_results.prot.xml")
-# end
+
+if (for_galaxy)
+  input_stagers.each do |sg|
+    sg.restore_references(output_file)
+    sg.restore_references(output_file,{:base_only => true})
+  end
+end
 
 
 

data/bin/protxml_to_psql.rb

@@ -0,0 +1,399 @@
+#!/usr/bin/env ruby
+#
+# This file is part of protk
+# Created by Ira Cooke 18/1/2011
+#
+# Convert a protein/peptide xml file to sqlite database
+#
+#
+
+require 'libxml'
+require 'protk/constants'
+require 'protk/command_runner'
+require 'protk/tool'
+require 'protk/fastadb'
+require 'sqlite3'
+require 'protk/mzml_parser'
+
+include LibXML
+
+def prepare_fasta(database_path,type)
+
+  db_filename = nil
+  case
+  when Pathname.new(database_path).exist? # It's an explicitly named db  
+    db_filename = Pathname.new(database_path).expand_path.to_s
+  else
+    db_filename=Constants.new.current_database_for_name(database_path)
+  end
+
+  db_indexfilename = "#{db_filename}.pin"
+
+  if File.exist?(db_indexfilename)
+    puts "Using existing indexed database"
+    orf_lookup = FastaDB.new(db_filename)
+  else
+    puts "Indexing database"
+    orf_lookup = FastaDB.create(db_filename,db_filename,type)
+  end
+  orf_lookup
+end
+
+def get_fasta_record(protein_name,fastadb)
+#  puts "Looking up #{protein_name}"
+  entry = fastadb.get_by_id protein_name
+  if ( entry == nil)
+    puts "Failed lookup for #{protein_name}"
+    raise KeyError
+  end
+  entry
+end
+
+def initialize_db()
+	result = $outputdb.execute <<-SQL
+	  CREATE TABLE ProteinGroups (
+	    ID INT, 
+	    Probability REAL
+	  );
+	SQL
+
+	result = $outputdb.execute <<-SQL
+	  CREATE TABLE Proteins (
+	    ID INT,
+	    ProteinGroupID INT,
+	    Probability REAL,
+	    Name TEXT,
+	    Description TEXT,
+	    Coverage REAL,
+	    NumPeptides INT,
+	    Indistinguishables TEXT,
+	    Sequence TEXT
+	  );
+	SQL
+
+	result = $outputdb.execute <<-SQL
+	  CREATE TABLE Peptides (
+	    ID INT,
+	    ProteinID INT,
+	    Probability REAL,
+	    Sequence TEXT,
+	    Start INT,
+	    End INT,
+	    ModifiedSequence TEXT
+	  );
+	SQL
+
+	# This has the role of a join table for the Peptides <-> Spectra many to many relationship
+	result = $outputdb.execute <<-SQL
+		CREATE TABLE PeptideSpectrumMatches (
+	    PeptideSequence TEXT,
+	    PeptideModifiedSequence TEXT,
+	    SpectrumID INT,
+	    ScanNum INT,
+	    RetentionTime REAL,
+	    PrecursorNeutralMass REAL,
+	    MassDeviation REAL,
+	    PrevAA TEXT,
+	    NextAA TEXT
+	  );
+	SQL
+
+	result = $outputdb.execute <<-SQL
+		CREATE TABLE Spectra (
+			ID INTEGER PRIMARY KEY,
+			MZData TEXT,
+			IntensityData TEXT,
+			PrecursorMass REAL,
+			PrecursorCharge INT,
+			SpectrumType INT,
+			SpectrumTitle TEXT
+		);
+	SQL
+
+end
+
+def insert_protein_group(group_node)
+	group_number=group_node.attributes['group_number']
+	group_prob=group_node.attributes['probability']
+	$outputdb.execute <<-SQL
+		INSERT INTO ProteinGroups(ID,Probability) VALUES(
+			#{group_number},#{group_prob}
+		);
+	SQL
+
+	proteins=group_node.find("./#{$protxml_ns_prefix}protein", $protxml_ns)
+
+	proteins.each do |protein|
+		insert_protein(protein,group_number)
+	end
+end
+
+def protein_dbid_from_name(protein_name)
+	protein_name #TODO: Allow user defined regex to parse this
+end
+
+def insert_protein(protein,group_id)
+
+	indis_proteins=protein.find("./#{$protxml_ns_prefix}indistinguishable_protein", $protxml_ns)
+	indis_proteins_summary=""
+	indis_proteins.each { |iprot| indis_proteins_summary<<"#{iprot.attributes['protein_name']};" }
+
+	annot_descr=protein.find("./#{$protxml_ns_prefix}annotation[@protein_description]", $protxml_ns)
+
+
+	protein_prob=protein.attributes['probability']
+	protein_name=protein.attributes['protein_name']
+
+	begin
+		protein_description=annot_descr[0].attributes['protein_description'].chomp.gsub("'","")
+	rescue
+		puts "No protein_description"
+	end
+	protein_coverage=protein.attributes['percent_coverage']
+	protein_npep = protein.attributes['total_number_peptides']
+	protein_indis = indis_proteins_summary
+
+	protein_coverage="NULL" unless protein_coverage
+	protein_indis="NULL" unless protein_indis
+	protein_description="NULL" unless protein_description
+
+	if $fasta_lookup
+		begin
+			entry=get_fasta_record(protein_name,$fasta_lookup)
+			protein_seq=entry.aaseq
+		rescue
+			puts "Warning: No entry found for #{protein_name}"
+			protein_seq="NULL"
+		end
+	end
+
+	begin
+		$outputdb.execute <<-SQL
+		INSERT INTO Proteins(ID,ProteinGroupID,Probability,Name,Description,Coverage,NumPeptides,Indistinguishables,Sequence) 
+		VALUES(#{$protein_id},#{group_id},#{protein_prob},\'#{protein_name}\',\'#{protein_description}\',#{protein_coverage},
+		#{protein_npep},\'#{protein_indis}\','#{protein_seq}');
+		SQL
+	rescue
+		throw "Unable to insert #{protein_description}\n"
+	end
+	peptides=protein.find("./#{$protxml_ns_prefix}peptide",$protxml_ns)
+
+	peptides.each do |peptide|  
+		insert_peptide(peptide,$protein_id,protein_seq)
+	end
+	$protein_id+=1
+end
+
+def insert_peptide(peptide,protein_id,protein_seq)
+	nsp_adjusted_probability=peptide.attributes['nsp_adjusted_probability']
+	sequence=peptide.attributes['peptide_sequence']
+
+	start_pos="NULL"
+	end_pos="NULL"
+	begin
+		if protein_seq!="NULL"
+			start_pos = protein_seq.index(sequence)
+			end_pos = start_pos+sequence.length
+		end
+	rescue
+		puts "Unable to locate peptide #{sequence} in protein #{protein_seq} for #{$protein_id}\n"
+		start_pos="NULL"
+		end_pos="NULL"
+	end
+	mod_info=peptide.find("./#{$protxml_ns_prefix}modification_info",$protxml_ns)
+
+	throw "More than one modification_info object for a peptide" unless mod_info.length<=1
+	mod_seq=format_modified_peptide(mod_info)
+
+	$outputdb.execute <<-SQL
+		INSERT INTO Peptides(ID,ProteinID,Probability,Sequence,Start,End,ModifiedSequence)
+		VALUES(#{$peptide_id},#{protein_id},#{nsp_adjusted_probability},\'#{sequence}\',
+		#{start_pos},#{end_pos},\'#{mod_seq}\')
+	SQL
+	$peptide_id+=1
+
+end
+
+def format_modified_peptide(mod_info)
+	mod_seq="NULL"
+	if mod_info.length==1
+		mod_seq=mod_info[0].attributes['modified_peptide']
+		mod_seq.gsub!(/\[/,"\{")
+		mod_seq.gsub!(/\]/,"\}")
+	end
+	mod_seq
+end
+
+def insert_psms_from_file(filepath)
+	$pepxml_ns_prefix="xmlns:"
+	$pepxml_ns="xmlns:http://regis-web.systemsbiology.net/pepXML"
+
+	pepxml_parser=XML::Parser.file("#{filepath}")
+	puts "Parsing #{filepath}"
+	pepxml_doc=pepxml_parser.parse
+	if not pepxml_doc.root.namespaces.default
+  		$pepxml_ns_prefix=""
+  		$pepxml_ns=nil
+	end
+
+	matched_spectra=[]
+
+	spectrum_queries=pepxml_doc.find("//#{$pepxml_ns_prefix}spectrum_query", $pepxml_ns)
+
+	spectrum_queries.each do |query| 
+
+		spectrum_name = query.attributes['spectrum'].chomp.gsub("0","").sub(/\.\d+$/,"")
+
+		start_scan=query.attributes['start_scan'].to_i
+		end_scan=query.attributes['end_scan'].to_i
+		throw "Don't know how to deal with multi scan spectra" unless start_scan==end_scan
+
+		retention_time=query.attributes['retention_time_sec'].chomp.to_f
+		neutral_mass=query.attributes['precursor_neutral_mass'].to_f
+		assumed_charge=query.attributes['assumed_charge'].to_i
+
+
+		top_search_hit=query.find("./#{$pepxml_ns_prefix}search_result/#{$pepxml_ns_prefix}search_hit",$pepxml_ns)[0]
+		peptide=top_search_hit.attributes['peptide']
+
+		mod_info=top_search_hit.find("./#{$protxml_ns_prefix}modification_info",$protxml_ns)
+
+		throw "More than one modification_info object for a peptide" unless mod_info.length<=1
+		modified_peptide=format_modified_peptide(mod_info)
+
+		calc_neutral_pep_mass=top_search_hit.attributes['calc_neutral_pep_mass'].to_f
+		massdiff = top_search_hit.attributes['massdiff'].to_f
+		prevaa = top_search_hit.attributes['peptide_prev_aa']
+		nextaa = top_search_hit.attributes['peptide_next_aa']
+
+		spectrum_name="NULL" unless spectrum_name
+		retention_time="NULL" unless retention_time
+		assumed_charge="NULL" unless assumed_charge
+		calc_neutral_pep_mass="NULL" unless calc_neutral_pep_mass
+		massdiff = "NULL" unless massdiff
+		prevaa = "NULL" unless prevaa
+		nextaa = "NULL" unless nextaa
+
+
+		$outputdb.execute <<-SQL
+			INSERT INTO PeptideSpectrumMatches(PeptideSequence,PeptideModifiedSequence,SpectrumID,ScanNum,RetentionTime,PrecursorNeutralMass,MassDeviation,PrevAA,NextAA)
+			VALUES('#{peptide}','#{modified_peptide}','#{spectrum_name}','#{start_scan}','#{retention_time.to_f}'\
+			,'#{calc_neutral_pep_mass}','#{massdiff}','#{prevaa}','#{nextaa}')
+		SQL
+
+		matched_spectra<<{:name => spectrum_name, :scan_num => start_scan}
+
+	end
+
+	matched_spectra
+end
+
+
+def lookup_spectra_from_files(file_list,matched_spectra)
+
+	titles_to_match = matched_spectra.collect { |s| s[:name] }
+
+	# require 'debugger';debugger
+
+	queries_with_spectra=Array.new.replace(titles_to_match)
+
+	num_matched=0
+	total_spectra=0
+
+	file_list.each do |file|
+		mzml_parser = MzMLParser.new(file)
+
+		spec = mzml_parser.next_spectrum
+
+
+		while (spec) do
+			total_spectra+=1
+			if titles_to_match.include? spec[:title]
+				num_matched+=1
+				queries_with_spectra.delete(spec[:title])
+
+				$outputdb.execute <<-SQL
+					INSERT INTO Spectra(MZData,IntensityData,SpectrumTitle,PrecursorMass)
+					VALUES('#{spec[:mz]}','#{spec[:intensity]}','#{spec[:title]}','#{spec[:precursormz]}')
+				SQL
+
+			else
+
+			end
+			spec = mzml_parser.next_spectrum
+		end
+
+	end
+	puts "Found #{num_matched} matching spectra"
+	puts "Total in spectrum files #{total_spectra}"
+	puts "Total psms #{titles_to_match.length}"
+	puts "Unmatched psms #{queries_with_spectra.length}"
+
+
+
+end
+
+# Setup specific command-line options for this tool. Other options are inherited from ProphetTool
+#
+tool=Tool.new([:explicit_output,:over_write])
+tool.option_parser.banner = "Convert a protXML file to a sqlite database.\n\nUsage: protxml_to_psql.rb [options] file1.protXML"
+
+tool.add_value_option(:database,nil,['-d','--database path','A Fasta file where full protein sequences can be looked up'])
+
+# require 'debugger';debugger
+
+exit unless tool.check_options(true,[:explicit_output])
+
+input_file=ARGV.shift
+
+
+if File.exists? tool.explicit_output
+	throw "Cant overwrite existing db #{tool.explicit_output}" unless tool.over_write
+	File.delete(tool.explicit_output)		
+end
+
+$fasta_lookup=nil
+if tool.database
+	$fasta_lookup=prepare_fasta(tool.database,'prot')
+end
+
+$outputdb = SQLite3::Database.new tool.explicit_output
+
+initialize_db
+
+XML::Error.set_handler(&XML::Error::QUIET_HANDLER)
+
+protxml_parser=XML::Parser.file("#{input_file}")
+
+$protxml_ns_prefix="xmlns:"
+$protxml_ns="xmlns:http://regis-web.systemsbiology.net/protXML"
+
+
+protxml_doc=protxml_parser.parse
+if not protxml_doc.root.namespaces.default
+  $protxml_ns_prefix=""
+  $protxml_ns=nil
+end
+
+$protein_id=0
+$peptide_id=0
+
+headers_with_inputs=protxml_doc.find("//#{$protxml_ns_prefix}protein_summary_header[@source_files]",$protxml_ns)
+
+matched_spectra=[]
+
+headers_with_inputs.each do |header|  
+	pepxml_files = header.attributes['source_files'].split(",")
+	pepxml_files.each do |pepxml_file|
+		matched_spectra.concat insert_psms_from_file(pepxml_file)
+	end
+end
+
+lookup_spectra_from_files(ARGV.collect { |file| file.chomp },matched_spectra)
+
+protein_groups=protxml_doc.find("//#{$protxml_ns_prefix}protein_group", $protxml_ns)
+
+protein_groups.each do |g| 
+	insert_protein_group(g)
+end
+

data/ext/decoymaker/decoymaker.c

@@ -20,24 +20,40 @@
 
 #define AMINO_ACIDS "ARNDCEQGHILKMFPSTWYV"
 #define NOT_AMINO_ACIDS "BJOUXZ*"
-#define MAX_SEQUENCE_LENGTH 20000
-#define MAX_LINE_LENGTH 20000 /* large enough to read in long header lines */
+#define MAX_SEQUENCE_LENGTH 2000
+#define MAX_LINE_LENGTH 200000 /* large enough to read in long header lines */
+
+void RemoveSpaces(char* source)
+{
+  char* i = source;
+  char* j = source;
+  while(*j != 0)
+  {
+    *i = *j++;
+    if(*i != ' ')
+      i++;
+  }
+  *i = 0;
+}
 
 
 static VALUE decoymaker_make_decoys(VALUE self,VALUE input_file_in,
-  VALUE db_length_in,VALUE output_file_in,char *prefix_string_in) {
-  
-  char *input_file = RSTRING_PTR(input_file_in);
+  VALUE db_length_in,VALUE output_file_in,VALUE prefix_string_in) 
+{
+
+  char *infile = StringValueCStr(input_file_in);
   long sequences_to_generate = NUM2INT(db_length_in);
-  char * output_file = RSTRING_PTR(output_file_in);
+  char * outfile = StringValueCStr(output_file_in);
+  char *prefix_string = StringValueCStr(prefix_string_in);
 
   char line[MAX_LINE_LENGTH];      
-  char settings_line[60][70];
-  char infile[255], outfile[255]; /* for reading input and writing output */
-  char prefix_string[255];
+  // char settings_line[60][70];
+
   char *p,**index;
-  char *sequence; 
-  char one_sequence[MAX_SEQUENCE_LENGTH],random_sequence[(int)(MAX_SEQUENCE_LENGTH*1.5)],random_sequence_output[(int)(MAX_SEQUENCE_LENGTH*1.5)];
+  
+  char one_sequence[MAX_SEQUENCE_LENGTH];
+  char random_sequence[(int)(MAX_SEQUENCE_LENGTH*1.5)];
+  char random_sequence_output[(int)(MAX_SEQUENCE_LENGTH*1.5)];
   char *temp_sequence;
   int a;
   FILE *inp, *outp;
@@ -50,63 +66,57 @@ static VALUE decoymaker_make_decoys(VALUE self,VALUE input_file_in,
   double x;
 
   /* scanning sequence database */
-  
-  strcpy(infile,input_file);
 
   if ((inp = fopen(infile, "r"))==NULL) {
     printf("error opening sequence database %s\n",infile);return -1;
   }
 
-  printf("scanning sequence database \n%s\n",infile);
-  fflush(stdout);
-
-  i=0;n=0;k=0;
+  long total_sequence_len=0;
+  n=0;
 
   while (fgets(line, MAX_LINE_LENGTH, inp) != NULL) {
-    i++; 
-    if(line[0]=='>') {
-      if (!(n%1000)) {
-        printf(".");
-        fflush(stdout); 
-        n++;
-      }
-    } 
+    total_sequence_len+=strlen(line);
+
+    // printf("%ld\n",i);fflush(stdout);
+    if (line[0]=='>') { n++; } 
   }
-  
+    
   n_sequences=n;
 
 
   /* reading sequence database */      
   
   temp_sequence=(char*)calloc(sizeof(char),MAX_SEQUENCE_LENGTH);
-  sequence=(char*)malloc(sizeof(char)*(i*80)); /* allocate enough memory for 80 characters per line in FASTA database */
+
+  char *sequence_block=(char*)malloc(sizeof(char)*(total_sequence_len+2));
+
   index=(char**)malloc(sizeof(char*)*n_sequences);
-  index[0]=sequence; /* set first index pointer to beginning of first database sequence */
+  index[0]=sequence_block; /* set first index pointer to beginning of first database sequence */
   
   if ((inp = fopen(infile, "r"))==NULL) {
     printf("error opening sequence database %s\n",infile);
     return -1;
   }
 
-  printf("done\nreading sequence database \n%s\n",infile);
-  fflush(stdout);    
-  
   n=-1;
   strcpy(temp_sequence,"\0");
   
   while (fgets(line, MAX_LINE_LENGTH, inp) != NULL)
-  { 
-    if (strcmp(line,"\n")==0) {
+  {
+    RemoveSpaces(line);
+
+    if (strcmp(line,"\n")==0) { // Skips blank lines
       continue;
     }
+
     if (line[0]=='>') { 
       if (n>=0) { 
-        if (!(n%1000)&&n>0) { 
-          printf(".");fflush(stdout);
-        }
+
         strcpy(index[n],temp_sequence);
-        n++; index[n]=index[n-1]+sizeof(char)*strlen(temp_sequence);
+        n++; 
+        index[n]=index[n-1]+sizeof(char)*strlen(temp_sequence);
         strcpy(temp_sequence,"\0");
+
       }
       else 
       {
@@ -116,7 +126,9 @@ static VALUE decoymaker_make_decoys(VALUE self,VALUE input_file_in,
     }
     else 
     {
-      if ( (strlen(temp_sequence)+strlen(line))>=MAX_SEQUENCE_LENGTH ) continue; 
+      if ( (strlen(temp_sequence)+strlen(line))>=MAX_SEQUENCE_LENGTH ) { 
+        continue;
+      } 
       strncat(temp_sequence,line,strlen(line)-1);
     }   
   }
@@ -127,16 +139,18 @@ static VALUE decoymaker_make_decoys(VALUE self,VALUE input_file_in,
 
   n_sequences=n+1;
 
-  printf("done [read %li sequences (%li amino acids)]\n",n_sequences,(int)(index[n_sequences-1]-index[0])/sizeof(char)+strlen(temp_sequence));fflush(stdout);
+  // printf("done [read %li sequences (%li amino acids)]\n",n_sequences,(int)(index[n_sequences-1]-index[0])/sizeof(char)+strlen(temp_sequence));fflush(stdout);
+
+  // measured_pl_sum=(int)(index[n_sequences-1]-index[0])/sizeof(char)+strlen(temp_sequence);
+
 
-  measured_pl_sum=(int)(index[n_sequences-1]-index[0])/sizeof(char)+strlen(temp_sequence);
 
 
 
   /* generating Markov probabilities */
 
-  printf("generating Markov probability matrix...");
-  fflush(stdout);
+  // printf("generating Markov probability matrix...");
+  // fflush(stdout);
 
   srand(time(0)); /* replace with constant to re-generate identical random databases */
 
@@ -146,52 +160,53 @@ static VALUE decoymaker_make_decoys(VALUE self,VALUE input_file_in,
     }
   }
   for(j=0;j<=20;j++) {
-    measured_aa_freq[j]=0;generated_aa_freq[j]=0;
+    measured_aa_freq[j]=0;
+    generated_aa_freq[j]=0;
   }
 
+
   for(protein=0;protein<n_sequences;protein++)
   {
-    if (!(protein%1000)) {
-      printf(".");
-      fflush(stdout);
+    if (protein<(n_sequences-1)) 
+    {
+      long len_one_seq = (index[protein+1]-index[protein])/sizeof(char);
+      if ( len_one_seq > MAX_SEQUENCE_LENGTH ){
+        printf("Seq is longer than max len \n");fflush(stdout);
+        len_one_seq=MAX_SEQUENCE_LENGTH;
+      }
+      strncpy(one_sequence,index[protein],len_one_seq);
+
+      one_sequence[len_one_seq]='\0'; // NULL terminate the string
+
+    } else { 
+      strcpy(one_sequence,index[protein]);
     }
 
-    if (protein<(n_sequences-1)) 
+    pl=strlen(one_sequence);
+    n=1;
+    one_index=0;
+
+    for(i=0;i<pl;i++)
     {
-     strncpy(one_sequence,index[protein],(index[protein+1]-index[protein])/sizeof(char));
-     one_sequence[(index[protein+1]-index[protein])/sizeof(char)]='\0';
-   }
-   else strcpy(one_sequence,index[protein]);
-   pl=strlen(one_sequence);
-   n=1;one_index=0;
-
-   for(i=0;i<pl;i++)
-   {
-     if(strpbrk(NOT_AMINO_ACIDS,(const char *)&one_sequence)==NULL)
-     {
-      if ( strchr(AMINO_ACIDS,one_sequence[i])==NULL)
+      if(strpbrk(NOT_AMINO_ACIDS,(const char *)&one_sequence)==NULL)
       {
-        printf("Unknown amino acid %c",one_sequence[i]);                
+        if ( strchr(AMINO_ACIDS,one_sequence[i])==NULL)
+        {
+          printf("Unknown amino acid %c",one_sequence[i]);                
+        } else {
+          a=20-strlen(strchr(AMINO_ACIDS,one_sequence[i])); // current amino acid
+          MP[a][i]++;
+          measured_aa_freq[a]++;
+        }
       } else {
-        a=20-strlen(strchr(AMINO_ACIDS,one_sequence[i])); // current amino acid
-        MP[a][i]++;
+        a=floor(20*(float)rand()/RAND_MAX);
+        MP[a][i]++; 
         measured_aa_freq[a]++;
-      }
-  }
-    else {
-    a=floor(20*(float)rand()/RAND_MAX);
-    MP[a][i]++; 
-    measured_aa_freq[a]++;
-    } // replace B, X, Z etc. with random amino acid to preserve size distribution
-  }
-  MP[20][pl]++;
-      measured_aa_freq[20]++; // MP[20][n] is the number of sequences of length n in the database 
+      } // replace B, X, Z etc. with random amino acid to preserve size distribution
     }
-
-    printf("done\n"); 
-    fflush(stdout);
-
-  
+    MP[20][pl]++;
+    measured_aa_freq[20]++; // MP[20][n] is the number of sequences of length n in the database 
+  }  
 
   for(i=0;i<MAX_SEQUENCE_LENGTH;i++){
      row_sum[i]=0;
@@ -204,41 +219,38 @@ static VALUE decoymaker_make_decoys(VALUE self,VALUE input_file_in,
   }
 
 
-  /* generate random protein sequences through Markov chain */
-
-  strcpy(outfile,output_file);
 
-    if ((outp = fopen(outfile, "w"))==NULL) {
-      printf("error opening output file %s\n",outfile); 
-      return -1;
-    }
+  /* generate random protein sequences through Markov chain */
 
-    printf("generating %li random protein sequences",sequences_to_generate);fflush(stdout);
 
-    strcpy(prefix_string,RSTRING_PTR(prefix_string_in));
+  if ((outp = fopen(outfile, "w"))==NULL) {
+    printf("error opening output file %s\n",outfile); 
+    return -1;
+  }
 
-    for(protein=0;protein<sequences_to_generate;protein++)
-    {
-      if (!(protein%1000)) {
-        printf(".");fflush(stdout);
-      }
+  for(protein=0;protein<sequences_to_generate;protein++)
+  {
       
-      i=0; j=0;
-      while (1)
+    i=0; j=0;
+    while (1)
+    {
+      x=(double)row_sum[j]*((double)rand()/RAND_MAX);
+      partial_sum=MP[0][j]; i=1;
+       
+      while (partial_sum<x) {partial_sum+=MP[i][j]; i++;}
+
+      if (j>=MAX_SEQUENCE_LENGTH) { i=21; }/* terminate when sequence has reached MAX_SEQUENCE_LENGTH */
+     
+      if (i<21)
       {
-       x=(double)row_sum[j]*((double)rand()/RAND_MAX);
-       partial_sum=MP[0][j]; i=1;
-       while (partial_sum<x) {partial_sum+=MP[i][j]; i++;}
-    if (j>=MAX_SEQUENCE_LENGTH) i=21; /* terminate when sequence has reached MAX_SEQUENCE_LENGTH */
-       if (i<21)
-       {
-         random_sequence[j]=AMINO_ACIDS[i-1];j++;generated_aa_freq[i-1]++;
-       }
-    else /* i==21, i.e. protein sequence terminated */
-       {
-         k=0; generated_aa_freq[20]++; generated_pl_sum+=j;
-         for(l=0;l<j;l++) 
-         {
+        random_sequence[j]=AMINO_ACIDS[i-1];j++;generated_aa_freq[i-1]++;
+      } else { /* i==21, i.e. protein sequence terminated */ 
+        k=0; 
+        generated_aa_freq[20]++; 
+        generated_pl_sum+=j;
+        
+        for(l=0;l<j;l++) 
+        {
           random_sequence_output[k]=random_sequence[l]; k++;
           if (!((k+1)%61))
           {
@@ -256,19 +268,13 @@ static VALUE decoymaker_make_decoys(VALUE self,VALUE input_file_in,
   
   fclose(outp);
 
-
-  /* freeing some memory... */
-
-  free(index);  
   
-  printf("done (wrote %li random protein sequences to %s)\n",sequences_to_generate,outfile);
+  // printf("done (wrote %li random protein sequences to %s)\n",sequences_to_generate,outfile);
 
   k=0;l=0;
   for(i=0;i<=20;i++) {k+=measured_aa_freq[i];l+=generated_aa_freq[i];}
-    // printf("<f(aa) in %s> <f(aa) in %s>\n",infile,outfile);
-  // for(i=0;i<=20;i++) printf("%f %f\n",(float)measured_aa_freq[i]/k,(float)generated_aa_freq[i]/l);
 
-  printf("<average sequence length in %s> = %f\n<average sequence length in %s> = %f\n",infile,measured_pl_sum/(float)n_sequences,outfile,generated_pl_sum/(float)sequences_to_generate);
+  // printf("<average sequence length in %s> = %f\n<average sequence length in %s> = %f\n",infile,measured_pl_sum/(float)n_sequences,outfile,generated_pl_sum/(float)sequences_to_generate);
 
   return 0;
 

data/lib/protk/galaxy_stager.rb

@@ -20,14 +20,13 @@ class GalaxyStager
     end
   end
 
-  def replace_references(in_file, options = {})
-    options = { :base_only => false }.merge(options)
-    replacement = options[:base_only] ? @staged_base : @staged_path
+  def replace_references(in_file)
     GalaxyStager.replace_references(in_file, @original_path, replacement)
   end
 
-  def restore_references(in_file)
-    GalaxyStager.replace_references(in_file, @staged_path, @original_path)
+  def restore_references(in_file, options = {})
+    path = options[:base_only] ? @staged_path.gsub(/#{@extension}/,"") : @staged_path
+    GalaxyStager.replace_references(in_file, path, @original_path)
   end
 
   def self.replace_references(in_file, from_path, to_path)

data/lib/protk/galaxy_util.rb

@@ -14,7 +14,7 @@ class GalaxyUtil
 
   def self.stage_pepxml(input_pepxml_path)
     stager = GalaxyStager.new(input_pepxml_path, :extension => ".pep.xml")
-    stager.staged_path
+    stager
   end
 
   def self.stage_protxml(input_protxml_path)

data/lib/protk/mzml_parser.rb

@@ -0,0 +1,67 @@
+require 'libxml'
+
+include LibXML
+
+class MzMLParser < Object
+
+
+	def initialize(path)
+		@namespace=
+		@mzml_ns_prefix="xmlns:"
+		@mzml_ns="xmlns:http://psi.hupo.org/ms/mzml"
+
+		doc=XML::Document.file(path)
+		@file_reader=XML::Reader.document(doc)
+	end
+
+	def next_spectrum()
+
+		until @file_reader.name=="spectrum" 
+			if !@file_reader.read()
+				return nil
+			end
+		end
+
+		this_spect=spectrum_as_hash(@file_reader.expand)
+
+		@file_reader.next_sibling
+
+		return this_spect
+	end
+
+	def spectrum_as_hash(spectrum)
+		index=spectrum.attributes['index']
+		sid = spectrum.attributes['id']
+		precursor_mz_param = spectrum.find(".//#{@mzml_ns_prefix}cvParam[@accession=\"MS:1000744\"]",@mzml_ns)[0]
+		mslevel_param = spectrum.find("./#{@mzml_ns_prefix}cvParam[@accession=\"MS:1000511\"]",@mzml_ns)[0]
+
+		title_param = spectrum.find("./#{@mzml_ns_prefix}cvParam[@accession=\"MS:1000796\"]",@mzml_ns)[0]
+
+		# prec_mz = spectrum.find(".//#{@mz}")
+
+		precursor_mz_mz = precursor_mz_param.attributes['value'] if precursor_mz_param
+		mslevel = mslevel_param.attributes['value'] if mslevel_param
+		spectrum_title = title_param['value'] if title_param
+
+		data_arrays = spectrum.find("./#{@mzml_ns_prefix}binaryDataArrayList/#{@mzml_ns_prefix}binaryDataArray",@mzml_ns)
+
+		data={}
+		data_arrays.each do |arr|
+			the_data = arr.find("./#{@mzml_ns_prefix}binary",@mzml_ns)[0].content
+			mzaccession = arr.find("./#{@mzml_ns_prefix}cvParam[@accession=\"MS:1000514\"]",@mzml_ns)
+			if ( mzaccession.length==1 )
+				data[:mz] = the_data
+			else 
+				data[:intensity] = the_data
+			end
+		end
+		data[:title]=spectrum_title
+		data[:mzlevel]=mslevel
+		data[:index]=index
+		data[:precursormz]=precursor_mz_mz
+		data[:id]=sid
+
+		data
+	end
+
+end

data/lib/protk/tool.rb

@@ -53,7 +53,7 @@ class Tool
   end
   
   
-  def add_value_option(symbol,default_value,opts)
+  def add_value_option(symbol,default_value,opts)    
     @options[symbol]=default_value
     @option_parser.on(*opts) do |val|
       @options[symbol]=val
@@ -108,6 +108,8 @@ class Tool
       add_value_option(:threads,1,['-n','--threads num','Number of processing threads to use. Set to 0 to autodetect an appropriate value'])
     end
 
+
+
   end
 
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: protk
 version: !ruby/object:Gem::Version
-  version: 1.3.0.pre3
+  version: 1.3.0
 platform: ruby
 authors:
 - Ira Cooke
@@ -152,6 +152,20 @@ dependencies:
     - - ~>
       - !ruby/object:Gem::Version
         version: '0'
+- !ruby/object:Gem::Dependency
+  name: sqlite3
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ~>
+      - !ruby/object:Gem::Version
+        version: '0'
 description: A bunch of tools for proteomics
 email: iracooke@gmail.com
 executables:
@@ -195,6 +209,7 @@ files:
 - bin/protein_prophet.rb
 - bin/protk_setup.rb
 - bin/protxml_to_gff.rb
+- bin/protxml_to_psql.rb
 - bin/protxml_to_table.rb
 - bin/repair_run_summary.rb
 - bin/sixframe.rb
@@ -237,6 +252,7 @@ files:
 - lib/protk/manage_db_rakefile.rake
 - lib/protk/manage_db_tool.rb
 - lib/protk/mascot_util.rb
+- lib/protk/mzml_parser.rb
 - lib/protk/omssa_util.rb
 - lib/protk/openms_defaults.rb
 - lib/protk/pepxml.rb
@@ -266,9 +282,9 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
-  - - '>'
+  - - '>='
     - !ruby/object:Gem::Version
-      version: 1.3.1
+      version: '0'
 requirements: []
 rubyforge_project: 
 rubygems_version: 2.2.1