protk 1.2.6.pre5 → 1.3.0.pre1

data/ext/{protk/decoymaker → decoymaker}/decoymaker.c

@@ -24,7 +24,9 @@
 #define MAX_LINE_LENGTH 20000 /* large enough to read in long header lines */
 
 
-static VALUE decoymaker_make_decoys(VALUE self,VALUE input_file_in,VALUE db_length_in,VALUE output_file_in,char *prefix_string_in) {
+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);
   long sequences_to_generate = NUM2INT(db_length_in);
   char * output_file = RSTRING_PTR(output_file_in);
@@ -50,10 +52,26 @@ static VALUE decoymaker_make_decoys(VALUE self,VALUE input_file_in,VALUE db_leng
   /* 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 %s",infile);fflush(stdout);
+
+  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;
-  while (fgets(line, MAX_LINE_LENGTH, inp) != NULL) {i++; if(line[0]=='>') {if (!(n%1000)) printf(".");fflush(stdout); n++;} }
+
+  while (fgets(line, MAX_LINE_LENGTH, inp) != NULL) {
+    i++; 
+    if(line[0]=='>') {
+      if (!(n%1000)) {
+        printf(".");
+        fflush(stdout); 
+        n++;
+      }
+    } 
+  }
   
   n_sequences=n;
 
@@ -65,11 +83,17 @@ static VALUE decoymaker_make_decoys(VALUE self,VALUE input_file_in,VALUE db_leng
   index=(char**)malloc(sizeof(char*)*n_sequences);
   index[0]=sequence; /* 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;}
+  if ((inp = fopen(infile, "r"))==NULL) {
+    printf("error opening sequence database %s\n",infile);
+    return -1;
+  }
 
-  printf("done\nreading sequence database %s",infile);fflush(stdout);    
+  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) {
@@ -98,18 +122,21 @@ static VALUE decoymaker_make_decoys(VALUE self,VALUE input_file_in,VALUE db_leng
   }
 
   strcpy(index[n],temp_sequence);
+
   fclose(inp);
 
   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);
+
   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 */
 
@@ -124,7 +151,11 @@ static VALUE decoymaker_make_decoys(VALUE self,VALUE input_file_in,VALUE db_leng
 
   for(protein=0;protein<n_sequences;protein++)
   {
-    if (!(protein%1000)) {printf(".");fflush(stdout);}
+    if (!(protein%1000)) {
+      printf(".");
+      fflush(stdout);
+    }
+
     if (protein<(n_sequences-1)) 
     {
      strncpy(one_sequence,index[protein],(index[protein+1]-index[protein])/sizeof(char));
@@ -142,35 +173,56 @@ static VALUE decoymaker_make_decoys(VALUE self,VALUE input_file_in,VALUE db_leng
       {
         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]++;
+        a=20-strlen(strchr(AMINO_ACIDS,one_sequence[i])); // current amino acid
+        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
+    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 
     }
-    printf("done\n"); fflush(stdout);
+
+    printf("done\n"); 
+    fflush(stdout);
 
   
 
-  for(i=0;i<MAX_SEQUENCE_LENGTH;i++) row_sum[i]=0;
-    for(i=0;i<MAX_SEQUENCE_LENGTH;i++) for(j=0;j<=20;j++) row_sum[i]+=MP[j][i];
+  for(i=0;i<MAX_SEQUENCE_LENGTH;i++){
+     row_sum[i]=0;
+  }
+  
+  for(i=0;i<MAX_SEQUENCE_LENGTH;i++){ 
+    for(j=0;j<=20;j++){ 
+      row_sum[i]+=MP[j][i];
+    }
+  }
 
 
   /* 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;}
+  strcpy(outfile,output_file);
+
+    if ((outp = fopen(outfile, "w"))==NULL) {
+      printf("error opening output file %s\n",outfile); 
+      return -1;
+    }
+
     printf("generating %li random protein sequences",sequences_to_generate);fflush(stdout);
 
     strcpy(prefix_string,RSTRING_PTR(prefix_string_in));
 
     for(protein=0;protein<sequences_to_generate;protein++)
     {
-      if (!(protein%1000)) {printf(".");fflush(stdout);}
+      if (!(protein%1000)) {
+        printf(".");fflush(stdout);
+      }
+      
       i=0; j=0;
       while (1)
       {
@@ -213,9 +265,10 @@ static VALUE decoymaker_make_decoys(VALUE self,VALUE input_file_in,VALUE db_leng
 
   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("<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);
 
   return 0;
 

data/ext/decoymaker/extconf.rb

@@ -0,0 +1,3 @@
+require 'mkmf'
+
+create_makefile('decoymaker')

data/lib/protk/constants.rb

@@ -7,7 +7,6 @@
 require 'yaml'
 require 'logger'
 require 'pathname'
-require 'ftools'
 
 class Constants
 
@@ -77,6 +76,21 @@ class Constants
       "#{@protk_dir}/tools/tandem"
   end
 
+  def makeblastdb
+    makeblastdbpath=%x[which makeblastdb]
+    makeblastdbpath.chomp
+  end
+
+  def blastdbcmd
+    path=%x[which blastdbcmd]
+    path.chomp
+  end
+
+  def mascot2xml
+    path=%x[which Mascot2XML]
+    path.chomp
+  end
+
   def protein_database_root
     path=@env['protein_database_root']
     if ( path =~ /^\// )
@@ -154,7 +168,7 @@ class Constants
 
     ENV['PATH']=protk_paths.join(":")
 
-    
+    # puts "Path #{ENV['PATH']}"
     throw "No data found in config file" unless @env!=nil
     @info_level=default_config_yml['message_level']
     

data/lib/protk/data/default_config.yml

@@ -12,4 +12,5 @@ uniprot_sprot_annotation_database: swissprot_annotation
 uniprot_trembl_annotation_database: trembl_annotation
 galaxy_root: galaxy
 default_mascot_server: www.matrixscience.com
-log_file: Logs/protk.log
+log_file: Logs/protk.log
+

data/lib/protk/data/tandem_gpm_defaults.xml

@@ -0,0 +1,175 @@
+<?xml version="1.0"?>
+<?xml-stylesheet type="text/xsl" href="tandem-input-style.xsl"?>
+<bioml>
+
+<note>spectrum parameters</note>
+	<note type="input" label="spectrum, fragment monoisotopic mass error">0.4</note>
+	<note type="input" label="spectrum, parent monoisotopic mass error plus">100</note>
+	<note type="input" label="spectrum, parent monoisotopic mass error minus">100</note>
+	<note type="input" label="spectrum, parent monoisotopic mass isotope error">yes</note>
+	<note type="input" label="spectrum, fragment monoisotopic mass error units">Daltons</note>
+	<note>The value for this parameter may be 'Daltons' or 'ppm': all other values are ignored</note>
+	<note type="input" label="spectrum, parent monoisotopic mass error units">ppm</note>
+		<note>The value for this parameter may be 'Daltons' or 'ppm': all other values are ignored</note>
+	<note type="input" label="spectrum, fragment mass type">monoisotopic</note>
+		<note>values are monoisotopic|average </note>
+
+<note>spectrum conditioning parameters</note>
+	<note type="input" label="spectrum, dynamic range">100.0</note>
+		<note>The peaks read in are normalized so that the most intense peak
+		is set to the dynamic range value. All peaks with values of less that
+		1, using this normalization, are not used. This normalization has the
+		overall effect of setting a threshold value for peak intensities.</note>
+	<note type="input" label="spectrum, total peaks">50</note> 
+		<note>If this value is 0, it is ignored. If it is greater than zero (lets say 50),
+		then the number of peaks in the spectrum with be limited to the 50 most intense
+		peaks in the spectrum. X! tandem does not do any peak finding: it only
+		limits the peaks used by this parameter, and the dynamic range parameter.</note>
+	<note type="input" label="spectrum, maximum parent charge">4</note>
+	<note type="input" label="spectrum, use noise suppression">yes</note>
+	<note type="input" label="spectrum, minimum parent m+h">500.0</note>
+	<note type="input" label="spectrum, minimum fragment mz">150.0</note>
+	<note type="input" label="spectrum, minimum peaks">15</note> 
+	<note type="input" label="spectrum, threads">1</note>
+	<note type="input" label="spectrum, sequence batch size">1000</note>
+	
+<note>residue modification parameters</note>
+	<note type="input" label="residue, modification mass">57.022@C</note>
+		<note>The format of this parameter is m@X, where m is the modfication
+		mass in Daltons and X is the appropriate residue to modify. Lists of
+		modifications are separated by commas. For example, to modify M and C
+		with the addition of 16.0 Daltons, the parameter line would be
+		+16.0@M,+16.0@C
+		Positive and negative values are allowed.
+		</note>
+	<note type="input" label="residue, potential modification mass"></note>
+		<note>The format of this parameter is the same as the format
+		for residue, modification mass (see above).</note>
+	<note type="input" label="residue, potential modification motif"></note>
+		<note>The format of this parameter is similar to residue, modification mass,
+		with the addition of a modified PROSITE notation sequence motif specification.
+		For example, a value of 80@[ST!]PX[KR] indicates a modification
+		of either S or T when followed by P, and residue and the a K or an R.
+		A value of 204@N!{P}[ST]{P} indicates a modification of N by 204, if it
+		is NOT followed by a P, then either an S or a T, NOT followed by a P.
+		Positive and negative values are allowed.
+		</note>
+
+<note>protein parameters</note>
+	<note type="input" label="protein, taxon">other mammals</note>
+		<note>This value is interpreted using the information in taxonomy.xml.</note>
+	<note type="input" label="protein, cleavage site">[RK]|{P}</note>
+		<note>this setting corresponds to the enzyme trypsin. The first characters
+		in brackets represent residues N-terminal to the bond - the '|' pipe -
+		and the second set of characters represent residues C-terminal to the
+		bond. The characters must be in square brackets (denoting that only
+		these residues are allowed for a cleavage) or french brackets (denoting
+		that these residues cannot be in that position). Use UPPERCASE characters.
+		To denote cleavage at any residue, use [X]|[X] and reset the 
+		scoring, maximum missed cleavage site parameter (see below) to something like 50.
+		</note>
+	<note type="input" label="protein, modified residue mass file"></note>
+	<note type="input" label="protein, cleavage C-terminal mass change">+17.002735</note>
+	<note type="input" label="protein, cleavage N-terminal mass change">+1.007825</note>
+	<note type="input" label="protein, N-terminal residue modification mass">0.0</note>
+	<note type="input" label="protein, C-terminal residue modification mass">0.0</note>
+	<note type="input" label="protein, homolog management">no</note>
+		<note>if yes, an upper limit is set on the number of homologues kept for a particular spectrum</note>
+
+<note>model refinement parameters</note>
+	<note type="input" label="refine">yes</note>
+	<note type="input" label="refine, modification mass"></note>
+	<note type="input" label="refine, sequence path"></note>
+	<note type="input" label="refine, tic percent">20</note>
+	<note type="input" label="refine, spectrum synthesis">yes</note>
+	<note type="input" label="refine, maximum valid expectation value">0.1</note>
+	<note type="input" label="refine, potential N-terminus modifications">+42.010565@[</note>
+	<note type="input" label="refine, potential C-terminus modifications"></note>
+	<note type="input" label="refine, unanticipated cleavage">yes</note>
+	<note type="input" label="refine, potential modification mass"></note>
+	<note type="input" label="refine, point mutations">no</note>
+	<note type="input" label="refine, use potential modifications for full refinement">no</note>
+	<note type="input" label="refine, point mutations">no</note>
+	<note type="input" label="refine, potential modification motif"></note>
+	<note>The format of this parameter is similar to residue, modification mass,
+		with the addition of a modified PROSITE notation sequence motif specification.
+		For example, a value of 80@[ST!]PX[KR] indicates a modification
+		of either S or T when followed by P, and residue and the a K or an R.
+		A value of 204@N!{P}[ST]{P} indicates a modification of N by 204, if it
+		is NOT followed by a P, then either an S or a T, NOT followed by a P.
+		Positive and negative values are allowed.
+		</note>
+
+<note>scoring parameters</note>
+	<note type="input" label="scoring, minimum ion count">4</note>
+	<note type="input" label="scoring, maximum missed cleavage sites">1</note>
+	<note type="input" label="scoring, x ions">no</note>
+	<note type="input" label="scoring, y ions">yes</note>
+	<note type="input" label="scoring, z ions">no</note>
+	<note type="input" label="scoring, a ions">no</note>
+	<note type="input" label="scoring, b ions">yes</note>
+	<note type="input" label="scoring, c ions">no</note>
+	<note type="input" label="scoring, cyclic permutation">no</note>
+		<note>if yes, cyclic peptide sequence permutation is used to pad the scoring histograms</note>
+	<note type="input" label="scoring, include reverse">no</note>
+		<note>if yes, then reversed sequences are searched at the same time as forward sequences</note>
+	<note type="input" label="scoring, cyclic permutation">no</note>
+	<note type="input" label="scoring, include reverse">no</note>
+
+<note>output parameters</note>
+	<note type="input" label="output, log path"></note>
+	<note type="input" label="output, message">testing 1 2 3</note>
+	<note type="input" label="output, one sequence copy">no</note>
+	<note type="input" label="output, sequence path"></note>
+	<note type="input" label="output, path">output.xml</note>
+	<note type="input" label="output, sort results by">protein</note>
+		<note>values = protein|spectrum (spectrum is the default)</note>
+	<note type="input" label="output, path hashing">yes</note>
+		<note>values = yes|no</note>
+	<note type="input" label="output, xsl path">tandem-style.xsl</note>
+	<note type="input" label="output, parameters">yes</note>
+		<note>values = yes|no</note>
+	<note type="input" label="output, performance">yes</note>
+		<note>values = yes|no</note>
+	<note type="input" label="output, spectra">yes</note>
+		<note>values = yes|no</note>
+	<note type="input" label="output, histograms">yes</note>
+		<note>values = yes|no</note>
+	<note type="input" label="output, proteins">yes</note>
+		<note>values = yes|no</note>
+	<note type="input" label="output, sequences">yes</note>
+		<note>values = yes|no</note>
+	<note type="input" label="output, one sequence copy">no</note>
+		<note>values = yes|no, set to yes to produce only one copy of each protein sequence in the output xml</note>
+	<note type="input" label="output, results">valid</note>
+		<note>values = all|valid|stochastic</note>
+	<note type="input" label="output, maximum valid expectation value">0.1</note>
+		<note>value is used in the valid|stochastic setting of output, results</note>
+	<note type="input" label="output, histogram column width">30</note>
+		<note>values any integer greater than 0. Setting this to '1' makes cutting and pasting histograms
+		into spread sheet programs easier.</note>
+<note type="description">ADDITIONAL EXPLANATIONS</note>
+	<note type="description">Each one of the parameters for X! tandem is entered as a labeled note
+			node. In the current version of X!, keep those note nodes
+			on a single line.
+	</note>
+	<note type="description">The presence of the type 'input' is necessary if a note is to be considered
+			an input parameter.
+	</note>
+	<note type="description">Any of the parameters that are paths to files may require alteration for a 
+			particular installation. Full path names usually cause the least trouble,
+			but there is no reason not to use relative path names, if that is the
+			most convenient.
+	</note>
+	<note type="description">Any parameter values set in the 'list path, default parameters' file are
+			reset by entries in the normal input file, if they are present. Otherwise,
+			the default set is used.
+	</note>
+	<note type="description">The 'list path, taxonomy information' file must exist.
+		</note>
+	<note type="description">The directory containing the 'output, path' file must exist: it will not be created.
+		</note>
+	<note type="description">The 'output, xsl path' is optional: it is only of use if a good XSLT style sheet exists.
+		</note>
+
+</bioml>

data/lib/protk/data/tandem_isb_kscore_defaults.xml

@@ -0,0 +1,123 @@
+<bioml>
+
+<note>spectrum parameters</note>
+	<note type="input" label="spectrum, parent monoisotopic mass error minus">2.0</note>
+	<note type="input" label="spectrum, parent monoisotopic mass error plus">4.0</note>
+	        <note>PRECURSOR MASS TOLERANCE. This is monoisotopic mass, so for non-accurate-mass instruments, for which the precursor is often taken nearer to the isotopically averaged mass, an asymmetric tolerance (-2.0 Da to 4.0 Da) is preferable. This somewhat imitates a (-3.0 Da to 3.0 Da) window for averaged mass (but not exactly).</note>
+	<note type="input" label="spectrum, parent monoisotopic mass isotope error">no</note>
+	<note type="input" label="spectrum, fragment monoisotopic mass error units">Daltons</note>
+		<note>The value for this parameter may be 'Daltons' or 'ppm': all other values are ignored</note>
+	<note type="input" label="spectrum, parent monoisotopic mass error units">Daltons</note>
+		<note>The value for this parameter may be 'Daltons' or 'ppm': all other values are ignored</note>
+	<note type="input" label="spectrum, fragment monoisotopic mass error">0.4</note>
+	        <note>This parameter has no effect in k-score scoring.</note>
+	<note type="input" label="spectrum, fragment mass type">monoisotopic</note>
+		<note>values are monoisotopic|average </note>
+
+<note>spectrum conditioning parameters</note>
+        <note type="input" label="spectrum, use conditioning">no</note>
+		<note>For k-score scoring, it is recommended spectrum conditioning be turned OFF for best performance. All of the spectrum filtering and preprocessing options below in this section will be inactive.</note>
+	<note type="input" label="spectrum, dynamic range">10000.0</note>
+	<note type="input" label="spectrum, total peaks">400</note> 
+	<note type="input" label="spectrum, maximum parent charge">5</note>
+	<note type="input" label="spectrum, use noise suppression">yes</note>
+	<note type="input" label="spectrum, minimum parent m+h">600.0</note>
+	<note type="input" label="spectrum, minimum fragment mz">125.0</note>
+	<note type="input" label="spectrum, minimum peaks">10</note> 
+	<note type="input" label="spectrum, threads">1</note>
+	<note type="input" label="spectrum, sequence batch size">1000</note>
+	
+<note>residue modification parameters</note>
+	<note type="input" label="residue, modification mass"></note>
+		<note>STATIC MODIFICATION. The format of this parameter is m@X, where m is the modfication mass in Daltons and X is the appropriate residue to modify. Lists of modifications are separated by commas. For example, to modify M and C with the addition of 16.0 Daltons, the parameter line would be +16.0@M,+16.0@C. Positive and negative values are allowed.</note>
+	<note type="input" label="residue, potential modification mass"></note>
+		<note>VARIABLE MODIFICATION. The format of this parameter is the same as the format for residue, modification mass (see above).</note>
+	<note type="input" label="residue, potential modification motif"></note>
+		<note>VARIABLE MODIFICATION IN A MOTIF. The format of this parameter is similar to residue, modification mass, with the addition of a modified PROSITE notation sequence motif specification. For example, a value of 80@[ST!]PX[KR] indicates a modification of either S or T when followed by P, and residue and the a K or an R. A value of 204@N!{P}[ST]{P} indicates a modification of N by 204, if it is NOT followed by a P, then either an S or a T, NOT followed by a P. Positive and negative values are allowed. </note>
+
+<note>protein parameters</note>
+	<note type="input" label="protein, taxon">no default</note>
+		<note>SEQUENCE DATABASE TO SEARCH. This refers to identifiers in taxonomy.xml.</note>
+	<note type="input" label="protein, cleavage site">[RK]|{P}</note>
+		<note>ENZYME SPECIFICITY. This setting corresponds to the enzyme trypsin. The first characters in brackets represent residues N-terminal to the bond - the '|' pipe - and the second set of characters represent residues C-terminal to the bond. The characters must be in square brackets (denoting that only these residues are allowed for a cleavage) or french brackets (denoting that these residues cannot be in that position). Use UPPERCASE characters. To denote cleavage at any residue, use [X]|[X] and reset the scoring, maximum missed cleavage site parameter (see below) to something like 50. </note>
+	<note type="input" label="protein, modified residue mass file"></note>
+	<note type="input" label="protein, N-terminal residue modification mass"></note>
+	<note type="input" label="protein, C-terminal residue modification mass"></note>
+	<note type="input" label="protein, homolog management">no</note>
+		<note>if yes, an upper limit is set on the number of homologues kept for a particular spectrum</note>
+
+<note>model refinement parameters</note>
+	<note type="input" label="refine">no</note>
+	<note type="input" label="refine, modification mass"></note>
+	<note type="input" label="refine, sequence path"></note>
+	<note type="input" label="refine, tic percent">10</note>
+	<note type="input" label="refine, spectrum synthesis">yes</note>
+	<note type="input" label="refine, maximum valid expectation value">0.1</note>
+	<note type="input" label="refine, potential N-terminus modifications"></note>
+	<note type="input" label="refine, potential C-terminus modifications"></note>
+	<note type="input" label="refine, unanticipated cleavage">no</note>
+	<note type="input" label="refine, potential modification mass"></note>
+	<note type="input" label="refine, point mutations">no</note>
+	<note type="input" label="refine, use potential modifications for full refinement">no</note>
+	<note type="input" label="refine, point mutations">no</note>
+	<note type="input" label="refine, potential modification motif"></note>
+
+<note>scoring parameters</note>
+
+        <note type="input" label="scoring, algorithm">k-score</note>
+ 	<note type="input" label="scoring, minimum ion count">1</note>
+	<note type="input" label="scoring, maximum missed cleavage sites">2</note>
+	<note type="input" label="scoring, x ions">no</note>
+	<note type="input" label="scoring, y ions">yes</note>
+	<note type="input" label="scoring, z ions">no</note>
+	<note type="input" label="scoring, a ions">no</note>
+	<note type="input" label="scoring, b ions">yes</note>
+	<note type="input" label="scoring, c ions">no</note>
+	<note type="input" label="scoring, cyclic permutation">no</note>
+		<note>if yes, cyclic peptide sequence permutation is used to pad the scoring histograms</note>
+	<note type="input" label="scoring, include reverse">no</note>
+		<note>if yes, then reversed sequences are searched at the same time as forward sequences</note>
+	<note type="input" label="scoring, cyclic permutation">no</note>
+	<note type="input" label="scoring, include reverse">no</note>
+
+<note>output parameters</note>
+	<note type="input" label="output, log path"></note>
+	<note type="input" label="output, message">1234567890</note>
+	<note type="input" label="output, sequence path"></note>
+	<note type="input" label="output, path">output.xml</note>
+	<note type="input" label="output, sort results by">spectrum</note>
+		<note>values = protein|spectrum (spectrum is the default)</note>
+	<note type="input" label="output, path hashing">no</note>
+		<note>values = yes|no</note>
+	<note type="input" label="output, xsl path">tandem-style.xsl</note>
+	<note type="input" label="output, parameters">yes</note>
+		<note>values = yes|no</note>
+	<note type="input" label="output, performance">yes</note>
+		<note>values = yes|no</note>
+	<note type="input" label="output, spectra">no</note>
+		<note>values = yes|no</note>
+	<note type="input" label="output, histograms">no</note>
+		<note>values = yes|no</note>
+	<note type="input" label="output, proteins">yes</note>
+		<note>values = yes|no</note>
+	<note type="input" label="output, sequences">no</note>
+		<note>values = yes|no</note>
+	<note type="input" label="output, one sequence copy">no</note>
+		<note>values = yes|no, set to yes to produce only one copy of each protein sequence in the output xml</note>
+	<note type="input" label="output, results">all</note>
+		<note>values = all|valid|stochastic</note>
+	<note type="input" label="output, maximum valid expectation value">0.1</note>
+		<note>value is used in the valid|stochastic setting of output, results</note>
+	<note type="input" label="output, histogram column width">30</note>
+		<note>values any integer greater than 0. Setting this to '1' makes cutting and pasting histograms into spread sheet programs easier.</note>
+
+<note type="description">ADDITIONAL EXPLANATIONS</note>
+	<note type="description">Each one of the parameters for X! tandem is entered as a labeled note node. In the current version of X!, keep those note nodes on a single line.</note>
+	<note type="description">The presence of the type 'input' is necessary if a note is to be considered an input parameter. </note>
+	<note type="description">Any of the parameters that are paths to files may require alteration for a particular installation. Full path names usually cause the least trouble, but there is no reason not to use relative path names, if that is the most convenient.</note>
+	<note type="description">Any parameter values set in the 'list path, default parameters' file are reset by entries in the normal input file, if they are present. Otherwise, the default set is used. </note>
+	<note type="description">The 'list path, taxonomy information' file must exist.</note>
+	<note type="description">The directory containing the 'output, path' file must exist: it will not be created.</note>
+	<note type="description">The 'output, xsl path' is optional: it is only of use if a good XSLT style sheet exists.</note>
+
+</bioml>