mspire 0.4.9 → 0.5.0

data/bin/bioworks_to_pepxml_gui.rb

@@ -1,225 +0,0 @@
-#!/usr/bin/ruby -w
-
-tmp = $VERBOSE ; $VERBOSE = nil
-require 'fox16'
-$VERBOSE = tmp
-
-include Fox
-
-
-class Opt
-  attr_accessor :flag, :value
-  def initialize(flag, value=nil)
-    @flag = flag
-    @value = value
-  end
-
-  def self.[](flag, value=nil)
-    self.new(flag, value)
-  end
-
-  def to_s
-    st = @flag
-    if @value
-      st << " " << @value
-    end
-    st
-  end
-  
-end
-
-
-NCOLS = 40
-
-srf_dir = nil
-output_dir = '.'
-msdata_dir = '.'
-$progname = 'bioworks_to_pepxml.rb'
-$sequest_folder = '/project/marcotte/marcotte/ms/john/sequest'
-$data_folder = '/project/marcotte/marcotte/ms/john/data'
-$isb_folder = '/var/www/tpp'
-
-# This is a directory selector consisting of: Label | FieldText | BrowseButton
-# if you pass in patterns, then you can select multiple files!
-class DirSelector 
-  attr_writer :directory
-
-  def directory
-    @directory_data.to_s
-  end
-
-  # You should pass in the frame that you want filled up!
-  def initialize(parent, label='select directory', init_dir='.', text_field_width=30)
-    @directory_data = FXDataTarget.new(init_dir)
-
-    FXLabel.new(parent, label , nil, LAYOUT_CENTER_Y|LAYOUT_RIGHT|JUSTIFY_RIGHT)
-    srf_field = FXTextField.new(parent, text_field_width, @directory_data) do |tf|
-      tf.text = @directory_data.to_s
-    end
-    srf_field.connect(SEL_COMMAND) do |sender, sel, message|
-      @directory_data.value = message
-    end
-    but = FXButton.new(parent, "Browse")
-    but.connect(SEL_COMMAND) do |sender, sel, message|
-      @directory_data.value = FXFileDialog.getOpenDirectory(parent, "Open directory_data", @directory_data.to_s)
-      srf_field.text = @directory_data.value
-    end
-  end
-end
-
-# This is a directory selector consisting of: Label | FieldText | BrowseButton
-# if you pass in patterns, then you can select multiple files!
-class MultipleFilesSelector
-  # an array of filenames
-  attr_writer :files
-
-  # You should pass in the frame that you want filled up!
-  def initialize(parent, label='select multiple files', init_dir='.', text_field_width=30, patterns=["All Files (*)"])
-    @directory_data = FXDataTarget.new(init_dir)
-
-    FXLabel.new(parent, label , nil, LAYOUT_CENTER_Y|LAYOUT_RIGHT|JUSTIFY_RIGHT)
-    srf_field = FXTextField.new(parent, text_field_width, @directory_data) do |tf|
-      tf.text = @directory_data.to_s
-    end
-    srf_field.connect(SEL_COMMAND) do |sender, sel, message|
-      @directory_data.value = message
-    end
-    but = FXButton.new(parent, "Browse")
-    if patterns.is_a?(Array)
-      pattern_string = patterns.join("\n") 
-    else
-      pattern_string = patterns
-    end
-    but.connect(SEL_COMMAND) do |sender, sel, message|
-      reply = FXFileDialog.getOpenFilenames(parent, "Open directory_data", @directory_data.to_s, pattern_string)
-      p reply
-      abort
-      srf_field.text = @directory_data.value
-    end
-  end
-end
-
-
-class MainWindow < FXMainWindow
-
-  def action(*args)
-    p args
-
-    cmd = []
-    cmd << $progname
-    #cmd << args
-    #cmd << Opt['-o', output_dir]
-
-    puts cmd.join(" ")
-  end
-
-  def initialize(anApp)
-    labels = ["&SRF files (select multiple)", "&Output Directory (ISB)", "&Directory with RAW files"]
-    super(anApp, "bioworks_to_pepxml", nil, nil, DECOR_ALL)
-
-    gb = FXGroupBox.new(self, "Specify input/output", FRAME_RIDGE)
-    mat = FXMatrix.new(gb, 3, MATRIX_BY_COLUMNS|LAYOUT_SIDE_TOP)
-
-    srf_files_selector = MultipleFilesSelector.new(mat, labels[0], $sequest_folder, NCOLS, ["SRF files (*.srf)"])
-
-    isb_files_selector = DirSelector.new(mat, labels[1], $isb_folder, NCOLS)
-
-    hf = FXHorizontalFrame.new(self)
-    create_mzxml = FXCheckButton.new(hf, 'create mzXML files')
-    copy_mzxml = FXCheckButton.new(hf, 'copy mzXML files to ISB dir') {|v| v.checkState = TRUE }
-    copy_mzxml.hide
-
-    @mat2 = FXMatrix.new(self, 3, MATRIX_BY_COLUMNS|LAYOUT_SIDE_TOP)
-    srf_dir_selector = DirSelector.new(@mat2, labels[2], $data_folder, NCOLS)
-
-    submit = FXButton.new(self, "Submit")
-    submit.connect(SEL_COMMAND) do |sender, sel, message|
-      action(srf_dir_selector.files)
-    end
-
-    create_mzxml.connect(SEL_COMMAND) do |button,b,checked|
-      if checked 
-        copy_mzxml.show
-        @mat2.show
-        self.resize(self.width, @large_height)
-      else
-        copy_mzxml.hide
-        @mat2.hide
-        self.resize(self.width, @small_height)
-      end
-    end
-
-  end
-
-  def create
-    super
-    show(PLACEMENT_SCREEN)
-    @large_height = self.height
-
-    # setup hidden state
-    @mat2.hide 
-    @small_height = @large_height - @mat2.height
-    self.resize(self.width, @small_height)
-  end
-
-end
-
-
-application = FXApp.new("Hello", "FXRuby") do |theApp|
-  MainWindow.new(theApp)
-  theApp.create
-  theApp.run
-end
-
-
-application.run()
-
-
-
-
-=begin
-
-
----------------------------------
-class MyMainWindow < FXMainWindow
-
-   attr :advancedFrame
-
-   def initialize(app)
-      super(app, "MyMainWindow")
-      
-      contents = FXVerticalFrame.new(self,
-         LAYOUT_FILL_X|LAYOUT_FILL_Y)
-
-      advancedButton = FXButton.new(contents, "Advanced >>",
-         nil, self, 0, FRAME_RAISED|FRAME_THICK)
-
-      advancedButton.connect(SEL_COMMAND) do
-         if @advancedFrame.shown?
-            self.height -= @advancedFrame.height
-            @advancedFrame.hide
-            advancedButton.text = "Advanced >>"
-         else
-            self.height += @advancedFrame.height
-            @advancedFrame.show
-            advancedButton.text = "<< Basic"
-         end
-         
-         self.recalc
-      end
-   end
-end
-#---------------------------
-app = FXApp.new
-
-mainWindow = MyMainWindow.new(app)
-
-app.create
-mainWindow.advancedFrame.hide
-mainWindow.height -= mainWindow.advancedFrame.height
-
-mainWindow.show(PLACEMENT_SCREEN)
-
-app.run
-
-=end

data/bin/fasta_shaker.rb

@@ -1,5 +0,0 @@
-#!/usr/bin/ruby
-
-
-require 'fasta'
-FastaShaker.shake_from_argv(ARGV)

data/bin/filter_and_validate.rb

@@ -1,5 +0,0 @@
-#!/usr/bin/ruby
-
-require 'spec_id/precision/filter'
-
-SpecID::Precision::Filter.new.filter_and_validate_cmdline(ARGV)

data/bin/gi2annot.rb

@@ -1,14 +0,0 @@
-#!/usr/bin/ruby -w
-
-require 'gi'
-
-if ARGV.size < 1
-  puts "usage: #{File.basename(__FILE__)} <gi> ..."
-  puts "calls NCBI for the annotation of the gi"
-end
-
-
-gis = ARGV.to_a.dup
-
-puts( GI.gi2annot(gis).join("\n") )
-

data/bin/id_class_anal.rb

@@ -1,112 +0,0 @@
-#!/usr/bin/ruby -w
-
-require 'spec_id'
-require 'generator'
-require 'optparse'
-require 'ostruct'
-require 'roc'
-
-def file_noext(file)
-  file.sub(/#{Regexp.escape(File.extname(file))}$/, '')
-end
-
-delimiter = "\t"
-def_pre = "SHUFF_"
-
-opt = OpenStruct.new
-opt.p = def_pre
-
-jtplot_base = 'class_anal'
-jtplot_file = jtplot_base + '.toplot'
-
-OptionParser.new do |op|
-  op.on("-p", "--prefix PREFIX", "prefix for false positive proteins") {|v| opt.p = v.split(',') }
-  op.on("-j", "--jtplot", "output file '#{jtplot_file}' for jtp plotting program") {|v| opt.j = v }
-#  op.on("-e", "--peptides", "runs a full analysis on peptides") {|v| opt.e = v }
-  op.on("-a", "--area", "outputs area under the curve") {|v| opt.a = v }
-end.parse!
-
-if ARGV.size < 1
-  puts "
-  usage: #{File.basename(__FILE__)} [options] protein_file.xml ...
-
-  Protein ID classification analysis.  Takes either a bioworks.xml (v3.2 with
-  probabilities) or protein_prophet-prot.xml file which has been run with
-  decoy proteins.  
-  
-  Outputs tp's and precision.  
-  [The false positive predictive rate (FPPR) is 1 - precision]  
-  The two columns will be labeled at the top. 
-  (delimited by '\\t') to STDOUT.  To capture to file:
-  #{File.basename(__FILE__)} protein_file.xml > out.csv
-
-  OPTIONS:
-  <s> = string
-  -p  --prefix <s[,s...]>  Prefix(s) by which to determine decoy proteins (default #{def_pre})
-  -j  --jtplot        outputs #{jtplot_file} for plotting by plot.rb
-                      [% plot.rb -w lp --yrange n0.1:1.1 --noenhanced <file> ]
-  -a  --area          outputs area under the curve instead of tps/precision
-  
-  NOTE: protein prophet files not yet functional!!!
-  ABBR:
-    TP = True Positives
-    FP = False Positives
-    Prec = Precision = TP/(TP+FP)
-  "
-  exit
-end
-
-###########################################################
-# I DON"T think option -e is functional yet...
-###########################################################
-
-files = ARGV.to_a
-
-out = nil
-if opt.j
-  out = File.open(jtplot_file, "w")
-  lines = ['XYData', jtplot_base, "Classification Analysis", "Num Hits", "Precision"]
-  lines.each {|l| out.puts l}
-end
-
-headings = files.collect do |file|
-  %w(TP Precision).collect {|v| v + " (#{file_noext(file)})" }
-end
-
-all_arrs = []
-files.each_with_index do |file,i|
-  sp = SpecID.new(file)
-  headers = [file_noext(file)]
-  arrs = sp.num_hits_and_ppv_for_prob(opt.p[i])
-  
-  if opt.a
-    (num_hits, prec) = arrs
-    roc = ROC.new
-    prec_area = roc.area_under_curve(num_hits, prec)
-    puts "#{file} (area under curve [num_hits, precision])"
-    puts "Prec [#TPPrec = TP/(TP+FP)]:\t#{prec_area}"
-  end
-
-  all_arrs.push(*arrs)
-
-  lns = []
-  if opt.j
-    xs = arrs.shift
-    arrs.zip(headers).each do |ar|
-      lns << ar[1] << xs.join(" ") << ar[0].join(" ")
-    end
-    lns.each do |line|
-      out.puts line
-    end
-  end
-end
-
-
-unless opt.a
-  puts headings.flatten.join(delimiter)
-  SyncEnumerator.new(*all_arrs).each do |row|
-    puts row.join(delimiter)
-  end
-end
-
-out.close if opt.j

data/bin/id_precision.rb

@@ -1,172 +0,0 @@
-#!/usr/bin/ruby -w
-
-require 'spec_id'
-require 'roc'
-require 'generator'
-require 'optparse'
-
-################################################
-$AREAS_ONLY = false
-################################################
-
-opts = OptionParser.new do |op|
-  op.banner = "usage: #{File.basename(__FILE__)} prefix bioworks.xml"
-  op.separator ""
-  op.separator "takes Bioworks 3.2 xml output files (with probabilities)"
-  op.separator "rank orders the probabilities and outputs num hits and precision"
-  op.separator "Also takes gzipped (xml.gz) files labeled as such"
-  op.separator ""
-  op.separator "Outputs a comma separated value to STDOUT (.csv)"
-  op.separator ""
-  op.separator "To capture:"
-  op.separator "   #{File.basename(__FILE__)} bioworks.xml > out.csv"
-  op.on("-a", "--area", "outputs the area under the curve instead") do |v| $AREAS_ONLY = true end
-end
-
-opts.parse!
-
-if ARGV.size < 2
-  puts opts
-  exit
-end
-
-fp_prefix = ARGV[0]
-file = ARGV[1]
-
-obj = SpecID.new(file)
-re_prefix = /^#{Regexp.escape(fp_prefix)}/o
-prc = proc {|it| it.prots.first.reference =~ re_prefix }
-#(match, nomatch) = obj.classify(:peps, prc)
-obj.peps = obj.pep_prots
-(fp, tp) = obj.classify(:peps, prc)
-
-
-#puts fp.size.to_s
-#puts tp.size.to_s
-fp_obj = SpecID.new
-fp_obj.peps = fp
-tp_obj = SpecID.new
-tp_obj.peps = tp
-
-two_lists = [tp_obj, fp_obj].map do |obj|
-  list = []
-  list.push( obj.pep_probs_by_pep_prots )
-
-  list.push( obj.pep_probs_by_bn_seq_charge )
-  # These each have a by_min and a by_top10
-  list.push(*( obj.pep_probs_by_bn_scan ) )
-  list.push(*( obj.pep_probs_by_bn_scan_charge ) )
-  list
-end
-
-
-headings = ["PepProts", "SeqCharge", "Scan(TopHit)", "Scan(Top10)", "ScanCharge(TopHit)", "ScanCharge(Top10)"]
-csv_headings = []
-headings.each do |head|
-  csv_headings << head + ": NH"
-  csv_headings << head + ": PR"
-end
-
-pairs = two_lists[0].zip two_lists[1]
-
-roc = DecoyROC.new
-x_y= []
-area_under_curve = []
-#start_x = []
-#end_x = []
-pairs.each do |pair|
-  #x,y = roc.pred_and_tps_and_ppv(pair[0], pair[1])
-  (num_hits, tps, ppv) = roc.pred_and_tps_and_ppv(pair[0], pair[1])
-  x = num_hits
-  y = ppv
-  if $AREAS_ONLY
-    x.unshift 0
-    y.unshift 1.0
-    area_under_curve << roc.area_under_curve(x,y)
-    #start_x << x.first
-    #end_x << x.last
-  else
-    x_y.push(x, y)   # <- normal output
-  end
-end
-
-if $AREAS_ONLY
-  headings.unshift "Filename"
-  puts headings.join(" ")
-  area_under_curve.unshift file
-  puts area_under_curve.join(" ")
-  #puts start_x.join(" ")
-  #puts end_x.join(" ")
-  exit           ### <--------------  ABORT HERE
-end
-
-
-# X axis is the number of peptides id# (i.e., # of peps in TP db)
-# Y axis is the precision = TP/(TP+FP)
-
-puts "#  NH = number of hits"
-puts "#  TP = true positives"
-puts "#  FP = false positives"
-puts "#  PR = precision = TP/(TP+FP)"
-puts csv_headings.join(",")
-
-SyncEnumerator.new(*x_y).each do |row|
-  #items_as_string = row.collect do |item|
-  #  sprintf("%.18f", item)
-  #end
-
-  ## THIS IS THE NORMAL OUTPUT:
-  puts row.join(", ")
-   
-
-  #puts items_as_string.join(", ")
-end
-
-=begin
-
-files = ARGV.to_a
-
-two_lists = files.collect do |file|
-  obj = Bioworks.new(file)
-  list = []
-  list.push( obj.pep_probs_by_pep_prots )
-  list.push( obj.pep_probs_by_seq_charge )
-  # These each have a by_min and a by_top10
-  list.push(*( obj.pep_probs_by_scan ) )
-  list.push(*( obj.pep_probs_by_scan_charge ) )
-  list
-end
-
-
-headings = ["PepProts: TP", "PepProts: PR", "SeqCharge: TP", "SeqCharge: PR",
-  "Scan(TopHit): TP", "Scan(TopHit): PR", "Scan(Top10): TP", "Scan(Top10): PR",
-  "ScanCharge(TopHit): TP", "ScanCharge(TopHit): PR",
-  "ScanCharge(Top10): TP", "ScanCharge(Top10): PR"]
-
-pairs = two_lists[0].zip two_lists[1]
-
-roc = ROC.new
-x_y= []
-pairs.each do |pair|
-  x,y = roc.tps_and_precision(pair[0], pair[1])
-  x_y.push(x, y)
-end
-
-# X axis is the number of peptides id# (i.e., # of peps in TP db)
-# Y axis is the precision = TP/(TP+FP)
-
-puts "#  TP = true positives"
-puts "#  FP = false positives"
-puts "#  PR = precision = TP/(TP+FP)"
-puts headings.join(",")
-
-SyncEnumerator.new(*x_y).each do |row|
-  #items_as_string = row.collect do |item|
-  #  sprintf("%.18f", item)
-  #end
-  puts row.join(", ")
-  #puts items_as_string.join(", ")
-end
-
-=end
-

data/bin/ms_to_lmat.rb

@@ -1,67 +0,0 @@
-#!/usr/bin/ruby
-
-require 'ms/msrun'
-require 'optparse'
-require 'ostruct'
-require 'lmat'
-
-
-# defaults:
-opt = {}
-opt[:baseline] = 0.0
-opt[:newext] = ".lmat"
-opt[:inc_mz] = 1.0
-
-# get options:
-opts = OptionParser.new do |op|
-  op.banner = "usage: #{File.basename(__FILE__)} [options] <msfile> ..."
-  op.separator "input: .mzdata or .mzXML (versions 1.x and 2.x)"
-  op.separator ""
-  op.separator "(sums m/z values that round to the same bin)"
-  op.separator ""
-  op.on("--mz_inc N", Float, "m/z increment (def: 1.0)") {|n| opt[:mz_inc] = n.to_f}
-  op.on("--mz_start N", Float, "m/z start (def: start of 1st full scan)") {|n| opt[:start_mz] = n.to_f}
-  op.on("--mz_end N", Float, "m/z end (def: end of 1st full scan)") {|n| opt[:end_mz] = n.to_f}
-  op.on("--baseline N", Float, "value for missing indices (def: #{opt[:baseline]})") {|n| opt[:baseline] = n.to_f}
-  op.on("--ascii", "generates an lmata file instead") {opt[:ascii] = true}
-  op.on("-v", "--verbose") {$VERBOSE = true}
-end
-opts.parse!
-
-if ARGV.size < 1 
-  puts opts
-end
-
-ARGV.each do |file|
-  msrun = MS::MSRun.new(file)
-  mslevel = 1
-  (start_mz, end_mz) = msrun.start_and_end_mz(mslevel)
-  (times, spectra) = msrun.times_and_spectra(mslevel)
-  args = {
-    :start_mz => start_mz,
-    :end_mz => end_mz,
-
-    :start_tm => times.first,
-    :end_tm => times.last,
-    :inc_tm => nil,
-  }
-  args.merge!(opt)
-  lmat = LMat.new.from_times_and_spectra(times, spectra, args)
-  ext = File.extname(file)
-  outfile = file.sub(/#{Regexp.escape(ext)}$/, opt[:newext])
-  if args[:ascii]
-    outfile << "a"
-    lmat.print(outfile)
-  else
-    lmat.write(outfile)
-  end
-  puts("OUTPUT: #{outfile}") if $VERBOSE
-end
-
-
-
-
-
-
-
-

data/bin/pepproph_filter.rb

@@ -1,16 +0,0 @@
-#!/usr/bin/ruby -w
-
-require 'spec_id/proph'
-
-if ARGV.size < 1
-  puts "usage: #{File.basename(__FILE__)} <prob_cutoff> <pepproph.xml> ..."
-  puts "     For each file outputs 'pepproph_min<prob_cutoff>.xml'"
-  puts "     deleting all search_hits with peptides less than prob_cutoff"
-end
-
-files = ARGV.to_a
-cutoff = files.shift
-files.each do |file|
-  outfile = file.gsub(/\.xml/, "_min#{cutoff}.xml")
-  Proph::Pep::Parser.new.filter_by_min_pep_prob(file, outfile, cutoff.to_f)
-end

data/bin/prob_validate.rb

@@ -1,6 +0,0 @@
-#!/usr/bin/ruby
-
-require 'spec_id/precision/prob'
-
-SpecID::Precision::Prob.new.precision_vs_num_hits_cmdline(ARGV)
-

data/bin/protein_summary.rb

@@ -1,6 +0,0 @@
-#!/usr/bin/ruby -w
-
-require 'spec_id/protein_summary'
-
-ProteinSummary.new.create_from_command_line_args(ARGV)
-

data/bin/protxml2prots_peps.rb

@@ -1,32 +0,0 @@
-#!/usr/bin/ruby -w
-
-require 'prot'
-require 'pep'
-
-if ARGV.size < 4
-  usage = <<HERE
-usage: protxml2prots_peps.rb run-prot.xml prot_prob nsp_pep_prob init_pep_prob
-       takes all proteins and peptides passing prob cutoffs and
-       outputs 'run-prot.xml.<prot_prob>_<nsp_prob>_<init_prob>.protpep' 
-       which is a marshalled array of proteins (containing peptides)
-HERE
-  puts usage
-  exit(1);
-end
-
-file = ARGV[0]
-outfile = file + '.' + ARGV[1] +'_'+ ARGV[2] +'_'+ ARGV[3] + ".protpep"
-
-proteins = Protein.get_prots_and_peps_fast(*ARGV)
-#puts "proteins"
-#proteins.each do |pr|
-#  puts pr
-#  pr.peptides.each do |pep|
-#    puts "\n\t" + pep.to_s 
-#  end
-#end
-#proteins = Protein.get_prots_and_peps(*ARGV)
-File.open(outfile, "w") do |f|
-  Marshal.dump(proteins, f)
-end
-