Class: Ms::Sequest::Srf

Inherits:
Ident::Search
  • Object
show all
Includes:
Pepxml, Search, Sqt
Defined in:
lib/ms/sequest/srf.rb,
lib/ms/sequest/srf/sqt.rb,
lib/ms/sequest/srf/pepxml.rb,
lib/ms/sequest/srf/search.rb

Defined Under Namespace

Modules: Pepxml, Search, Sqt Classes: Dta, DtaGen, Header, NoSequestParamsError, Out

Constant Summary

Constants included from Pepxml

Pepxml::DEFAULT_OPTIONS, Pepxml::ModelToMsAnalyzer

Instance Attribute Summary collapse

Class Method Summary collapse

Instance Method Summary collapse

Methods included from Search

commandline, #to_dta, #to_mgf

Methods included from Pepxml

commandline, #to_pepxml

Methods included from Sqt

commandline, #to_sqt

Constructor Details

#initialize(filename = nil, opts = {}) ⇒ Srf

opts:

:filter_by_precursor_mass_tolerance => true | false (default true)
# this will filter by the sequest params prec tolerance as is
# typically done by Bioworks.

:link_protein_hits => true | false (default true)
# if true, generates the @protein attribute for the :protein method
#   and creates one protein per reference that is linked to each 
#   relevant peptide hit.
# if false, each protein for each peptide hit is a unique object 
# and the :proteins method returns nil.  If you are merging multiple
# searches then you probably want to set this to false to avoid
# recalculation.

:read_pephits => true | false (default true)
# will attempt to read peptide hit information (equivalent to .out
# files), otherwise, just reads the dta information.



103
104
105
106
107
108
109
110
111
 
# File 'lib/ms/sequest/srf.rb', line 103

def initialize(filename=nil, opts={})
  @peptide_hits = []

  @dta_files = []
  @out_files = []
  if filename
    from_file(filename, opts)
  end
end

Instance Attribute Details

#base_name ⇒ Object Also known as: base_name_noext

the base name of the file with no extension



37
38
39
 
# File 'lib/ms/sequest/srf.rb', line 37

def base_name
  @base_name
end

#dta_files ⇒ Object

Returns the value of attribute dta_files.



29
30
31
 
# File 'lib/ms/sequest/srf.rb', line 29

def dta_files
  @dta_files
end

#filtered_by_precursor_mass_tolerance ⇒ Object

a boolean to indicate if the results have been filtered by the sequest.params precursor mass tolerance



48
49
50
 
# File 'lib/ms/sequest/srf.rb', line 48

def filtered_by_precursor_mass_tolerance
  @filtered_by_precursor_mass_tolerance
end

#header ⇒ Object

Returns the value of attribute header.



28
29
30
 
# File 'lib/ms/sequest/srf.rb', line 28

def header
  @header
end

#index ⇒ Object

a parallel array to dta_files and out_files where each entry is:

first_scan, last_scan, charge 


34
35
36
 
# File 'lib/ms/sequest/srf.rb', line 34

def index
  @index
end

#out_files ⇒ Object

Returns the value of attribute out_files.



30
31
32
 
# File 'lib/ms/sequest/srf.rb', line 30

def out_files
  @out_files
end

#params ⇒ Object

Returns the value of attribute params.



31
32
33
 
# File 'lib/ms/sequest/srf.rb', line 31

def params
  @params
end

#resident_dir ⇒ Object

the directory the srf file was residing in when the filename was passed in. May not be available.



44
45
46
 
# File 'lib/ms/sequest/srf.rb', line 44

def resident_dir
  @resident_dir
end

#version ⇒ Object

a String: 3.5, 3.3 or 3.2



26
27
28
 
# File 'lib/ms/sequest/srf.rb', line 26

def version
  @version
end

Class Method Details

.get_sequest_params_and_finish_pos(filename) ⇒ Object

returns a Sequest::Params object or nil if none



55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
 
# File 'lib/ms/sequest/srf.rb', line 55

def self.get_sequest_params_and_finish_pos(filename)
  # split the file in half and only read the second half (since we can be
  # confident that the params file will be there!)

  params = nil
  finish_parsing_io_pos = nil
  File.open(filename, 'rb') do |handle|
    halfway = handle.stat.size / 2
    handle.seek halfway
    last_half = handle.read
    if sequest_start_from_last_half = last_half.rindex('[SEQUEST]')
      params_start_index =  sequest_start_from_last_half + halfway
      handle.seek(params_start_index)
      params = Ms::Sequest::Params.new.parse_io(handle)
      finish_parsing_io_pos = handle.pos
    else
      nil  # not found
    end
  end
  [params, finish_parsing_io_pos]
end

Instance Method Details

#dta_start_byte ⇒ Object 



77
78
79
80
81
82
83
 
# File 'lib/ms/sequest/srf.rb', line 77

def dta_start_byte
  case @version
  when '3.2' ; 3260
  when '3.3' ; 3644
  when '3.5' ; 3644
  end
end

#filter_by_precursor_mass_tolerance! ⇒ Object

  1. updates the out_file’s list of hits based on passing peptides (but not

the original hit id; rank is implicit in array ordering)

  1. recalculates deltacn values completely if number of hits changed (does

not touch deltacn orig)

This can spoil proper protein -> peptide linkages. Ms::Id::Search.merge! should be run after this method to ensure correct protein -> peptide linkages.



122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
 
# File 'lib/ms/sequest/srf.rb', line 122

def filter_by_precursor_mass_tolerance!
  pmt = params.peptide_mass_tolerance.to_f
  methd = nil  # the method to 

  case params.peptide_mass_units
  when '0'
    amu_based = true
    milli_amu = false
  when '1'
    amu_based = true
    milli_amu = true
  when '2'
    amu_based = false
  end

  self.filtered_by_precursor_mass_tolerance = true
  self.out_files.each do |out_file|
    hits = out_file.hits
    before = hits.size
    hits.reject! do |pep|
      if amu_based
        if milli_amu
          (pep.deltamass.abs > (pmt/1000))
        else
          (pep.deltamass.abs > pmt)
        end
      else
        (pep.ppm.abs > pmt)
      end
    end
    if hits.size != before
      out_file.hits = hits # <- is this necessary 
      Ms::Sequest::Srf::Out::Peptide.update_deltacns_from_xcorr(hits)
      out_file.num_hits = hits.size
    end
  end
  self
end

#from_file(filename, opts) ⇒ Object

returns self opts are the same as for ‘new’



178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
 
# File 'lib/ms/sequest/srf.rb', line 178

def from_file(filename, opts)
  @resident_dir = File.dirname(File.expand_path(filename))
  opts = { :filter_by_precursor_mass_tolerance => true, :link_protein_hits => true, :read_pephits => true}.merge(opts)

  (@params, after_params_io_pos) = Ms::Sequest::Srf.get_sequest_params_and_finish_pos(filename)
  return unless @params

  dup_references = 0
  dup_refs_gt_0 = false

  dup_references = @params.print_duplicate_references.to_i
  if dup_references == 0
    # warn %Q{
    #*****************************************************************************
    #WARNING: This srf file lists only 1 protein per peptide! (based on the
    #print_duplicate_references parameter in the sequest.params file used in its
    #creation)  So, downstream output will likewise only contain a single protein
    #for each peptide hit.  In many instances this is OK since downstream programs
    #will recalculate protein-to-peptide linkages from the database file anyway.
    #For complete protein lists per peptide hit, .srf files must be created with
    #print_duplicate_references > 0. HINT: to capture all duplicate references, 
    #set the sequest parameter 'print_duplicate_references' to 100 or greater.
    #*****************************************************************************
    #        }
  else
    dup_refs_gt_0 = true
  end

  File.open(filename, 'rb') do |fh|
    @header = Ms::Sequest::Srf::Header.from_io(fh)
    @version = @header.version

    unpack_35 = case @version
                when '3.2'
                  false
                when '3.3'
                  false
                when '3.5'
                  true
                end

    if @header.combined
      @base_name = File.basename(filename, '.*')
      # I'm not sure why this is the case, but the reported number is too
      # big by one on the 2 files I've seen so far, so we will correct it here!
      @header.dta_gen.num_dta_files = @header.dta_gen.num_dta_files - 1
      if opts[:read_pephits] == false
        raise NotImplementedError, "on combined files must read everything right now!"
      end
      (@dta_files, @out_files) = read_dta_and_out_interleaved(fh, @header.num_dta_files, unpack_35, dup_refs_gt_0)
    else
      @base_name = @header.raw_filename.scan(/[\\\/]([^\\\/]+)\.RAW$/).first.first

      @dta_files = read_dta_files(fh, @header.num_dta_files, unpack_35)
      if opts[:read_pephits]
        # need the params file to know if the duplicate_references is set > 0
        raise NoSequestParamsError, "no sequest params info in srf file!\npass in path to sequest.params file" if @params.nil?
        @out_files = read_out_files(fh,@header.num_dta_files, unpack_35, dup_refs_gt_0)

        # FOR DISPLAY ONLY!
        #@out_files.each do |f|
        #  if f.num_hits == 10
        #    p f.hits.last
        #  end
        #end

        if fh.eof?
          #warn "FILE: '#{filename}' appears to be an abortive run (no params in srf file)\nstill continuing..."
          @params = nil
          @index = []
        end
      end
    end

    fh.pos = after_params_io_pos

    # This is very sensitive to the grab_params method in sequest params
    fh.read(12)  ## gap between last params entry and index 

    @index = read_scan_index(fh,@header.num_dta_files)
  end


  ### UPDATE SOME THINGS:
  # give each hit a base_name, first_scan, last_scan
  if opts[:read_pephits] && !@header.combined
    @index.each_with_index do |ind,i|
      mass_measured = @dta_files[i][0]
      outfile = @out_files[i]
      outfile.first_scan = ind[0]
      outfile.last_scan = ind[1]
      outfile.charge = ind[2]

      pep_hits = @out_files[i].hits
      @peptide_hits.push( *pep_hits )
      pep_hits.each do |pep_hit|
        pep_hit[15] = @base_name
        pep_hit[16] = ind[0]
        pep_hit[17] = ind[1]
        pep_hit[18] = ind[2]
        # add the deltamass
        pep_hit[12] = pep_hit[0] - mass_measured  # real - measured (deltamass)
        pep_hit[13] = 1.0e6 * pep_hit[12].abs / mass_measured ## ppm
        pep_hit[19] = self  ## link with the srf object
      end
    end

    filter_by_precursor_mass_tolerance! if params

    if opts[:link_protein_hits]
      (@peptide_hits, @proteins) = merge!([self.peptide_hits]) do |_protein, _peptides|
        Ms::Sequest::Srf::Out::Protein.new(_protein.reference, _peptides)
      end
    end

  end

  self
end

#protein_class ⇒ Object 



50
51
52
 
# File 'lib/ms/sequest/srf.rb', line 50

def protein_class
  Ms::Sequest::Srf::Out::Protein
end

#read_dta_and_out_interleaved(fh, num_files, unpack_35, dup_refs_gt_0) ⇒ Object 



161
162
163
164
165
166
167
168
169
170
171
172
173
174
 
# File 'lib/ms/sequest/srf.rb', line 161

def read_dta_and_out_interleaved(fh, num_files, unpack_35, dup_refs_gt_0)
  dta_files = Array.new(num_files)
  out_files = Array.new(num_files)
  start = dta_start_byte
  fh.pos = start

  num_files.times do |i|
    dta_files[i] = Ms::Sequest::Srf::Dta.from_io(fh, unpack_35) 
    #p dta_files[i]
    out_files[i] = Ms::Sequest::Srf::Out.from_io(fh, unpack_35, dup_refs_gt_0)
    #p out_files[i]
  end
  [dta_files, out_files]
end

#read_dta_files(fh, num_files, unpack_35) ⇒ Object

returns an array of dta_files



320
321
322
323
324
325
326
327
328
329
 
# File 'lib/ms/sequest/srf.rb', line 320

def read_dta_files(fh, num_files, unpack_35)
  dta_files = Array.new(num_files)
  start = dta_start_byte
  fh.pos = start

  header.num_dta_files.times do |i|
    dta_files[i] = Ms::Sequest::Srf::Dta.from_io(fh, unpack_35) 
  end
  dta_files
end

#read_out_files(fh, number_files, unpack_35, dup_refs_gt_0) ⇒ Object

filehandle (fh) must be at the start of the outfiles. ‘read_dta_files’ will put the fh there.



333
334
335
336
337
338
339
 
# File 'lib/ms/sequest/srf.rb', line 333

def read_out_files(fh,number_files, unpack_35, dup_refs_gt_0)
  out_files = Array.new(number_files)
  header.num_dta_files.times do |i|
    out_files[i] = Ms::Sequest::Srf::Out.from_io(fh, unpack_35, dup_refs_gt_0)
  end
  out_files
end

#read_scan_index(fh, num) ⇒ Object

returns an index where each entry is [first_scan, last_scan, charge]



299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
 
# File 'lib/ms/sequest/srf.rb', line 299

def read_scan_index(fh, num)
  #string = fh.read(80)
  #puts "STRING: "
  #p string
  #puts string
  #File.open("tmp.tmp",'wb') {|out| out.print string }
  #abort 'her'
  ind_len = 24
  index = Array.new(num)
  unpack_string = 'III'
  st = ''
  ind_len.times do st << '0' end  ## create a 24 byte string to receive data
  num.times do |i|
    fh.read(ind_len, st)
    result = st.unpack(unpack_string)
    index[i] = st.unpack(unpack_string)
  end
  index
end