ms-sequest 0.0.11 → 0.0.12
Sign up to get free protection for your applications and to get access to all the features.
- data/.autotest +14 -0
- data/.gitignore +8 -0
- data/.gitmodules +9 -0
- data/History +8 -0
- data/{MIT-LICENSE → LICENSE} +1 -0
- data/README.rdoc +77 -0
- data/Rakefile +110 -0
- data/VERSION +1 -0
- data/lib/ms/sequest.rb +1 -1
- data/lib/ms/sequest/bioworks.rb +498 -0
- data/lib/ms/sequest/pepxml.rb +1458 -0
- data/lib/ms/sequest/srf.rb +4 -3
- data/lib/ms/sequest/srf/search.rb +1 -1
- data/lib/ms/sequest/srf/search/tap.rb +1 -1
- data/script/fasta_ipi_to_ncbi-ish.rb +29 -0
- data/spec/ms/sequest/bioworks_spec.rb +153 -0
- data/spec/ms/sequest/params_spec.rb +131 -0
- data/spec/ms/sequest/pepxml_spec.rb +376 -0
- data/spec/ms/sequest/sqt_spec.rb +78 -0
- data/spec/ms/sequest/sqt_spec_helper.rb +34 -0
- data/spec/ms/sequest/srf/search_spec.rb +53 -0
- data/spec/ms/sequest/srf/search_spec_helper.rb +341 -0
- data/spec/ms/sequest/srf/sqt_spec.rb +142 -0
- data/spec/ms/sequest/srf_spec.rb +182 -0
- data/spec/ms/sequest/srf_spec_helper.rb +172 -0
- data/spec/spec_helper.rb +51 -0
- data/spec/testfiles/7MIX_STD_110802_1.sequest_params_fragment.srf +0 -0
- data/spec/testfiles/bioworks31.params +77 -0
- data/spec/testfiles/bioworks32.params +62 -0
- data/spec/testfiles/bioworks33.params +63 -0
- data/spec/testfiles/corrupted_900.srf +0 -0
- data/spec/testfiles/small.sqt +87 -0
- data/spec/testfiles/small2.sqt +176 -0
- data/tap.yml +0 -0
- metadata +74 -21
- data/README +0 -23
@@ -0,0 +1,1458 @@
|
|
1
|
+
|
2
|
+
require 'sample_enzyme'
|
3
|
+
require 'ms/parser/mzxml'
|
4
|
+
require 'hash_by'
|
5
|
+
require 'set_from_hash'
|
6
|
+
require 'spec_id/bioworks'
|
7
|
+
require 'instance_var_set_from_hash'
|
8
|
+
require 'ms/msrun'
|
9
|
+
require 'spec_id/srf'
|
10
|
+
require 'spec_id/sequest/params'
|
11
|
+
require 'fileutils'
|
12
|
+
|
13
|
+
class Numeric
|
14
|
+
# returns a string with a + or - on the front
|
15
|
+
def to_plus_minus_string
|
16
|
+
if self >= 0
|
17
|
+
'+' << self.to_s
|
18
|
+
else
|
19
|
+
self.to_s
|
20
|
+
end
|
21
|
+
end
|
22
|
+
end
|
23
|
+
|
24
|
+
|
25
|
+
module Sequest ; end
|
26
|
+
class Sequest::PepXML; end
|
27
|
+
|
28
|
+
class Sequest::PepXML::MSMSPipelineAnalysis
|
29
|
+
include SpecIDXML
|
30
|
+
# Version 1.2.3
|
31
|
+
attr_writer :date
|
32
|
+
attr_writer :xmlns, :xmlns_xsi, :xsi_schemaLocation
|
33
|
+
attr_accessor :summary_xml
|
34
|
+
# Version 2.3.4
|
35
|
+
attr_writer :xmlns, :xmlns_xsi, :xsi_schema_location
|
36
|
+
attr_accessor :pepxml_version
|
37
|
+
attr_accessor :msms_run_summary
|
38
|
+
|
39
|
+
# if block given, sets msms_run_summary to block
|
40
|
+
def initialize(hash=nil)
|
41
|
+
@xmlns = nil
|
42
|
+
@xmlns_xsi = nil
|
43
|
+
@xsi_schema_location = nil
|
44
|
+
if hash
|
45
|
+
self.set_from_hash(hash)
|
46
|
+
end
|
47
|
+
if block_given?
|
48
|
+
@msms_run_summary = yield
|
49
|
+
end
|
50
|
+
end
|
51
|
+
|
52
|
+
# if no date string given, then it will set to Time.now
|
53
|
+
def date
|
54
|
+
if @date ; @date
|
55
|
+
else
|
56
|
+
case Sequest::PepXML.pepxml_version
|
57
|
+
when 18 ; tarr = Time.now.to_a ; tarr[3..5].reverse.join('-') + "T#{tarr[0..2].reverse.join(':')}"
|
58
|
+
end
|
59
|
+
end
|
60
|
+
end
|
61
|
+
|
62
|
+
def xmlns
|
63
|
+
if @xmlns ; @xmlns
|
64
|
+
else ; "http://regis-web.systemsbiology.net/pepXML"
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
def xmlns_xsi
|
69
|
+
if @xmlns_xsi ; @xmlns_xsi
|
70
|
+
else ; "http://www.w3.org/2001/XMLSchema-instance"
|
71
|
+
end
|
72
|
+
end
|
73
|
+
|
74
|
+
def xsi_schema_location
|
75
|
+
if @xsi_schema_location ; @xsi_schema_location
|
76
|
+
else ; "http://regis-web.systemsbiology.net/pepXML /tools/bin/TPP/tpp/schema/pepXML_v18.xsd"
|
77
|
+
end
|
78
|
+
end
|
79
|
+
|
80
|
+
def to_pepxml
|
81
|
+
case Sequest::PepXML.pepxml_version
|
82
|
+
when 18
|
83
|
+
element_xml_and_att_string(:msms_pipeline_analysis, "date=\"#{date}\" xmlns=\"#{xmlns}\" xmlns:xsi=\"#{xmlns_xsi}\" xsi:schemaLocation=\"#{xsi_schema_location}\" summary_xml=\"#{summary_xml}\"") do
|
84
|
+
@msms_run_summary.to_pepxml
|
85
|
+
end
|
86
|
+
else
|
87
|
+
abort "Don't know how to deal with version: #{Sequest::PepXML.pepxml_version}"
|
88
|
+
end
|
89
|
+
end
|
90
|
+
|
91
|
+
end
|
92
|
+
|
93
|
+
class Sequest::PepXML::MSMSRunSummary
|
94
|
+
include SpecID
|
95
|
+
include SpecIDXML
|
96
|
+
|
97
|
+
# the version of TPP you are using (determines xml output)
|
98
|
+
# The name of the pep xml file (without extension) (but this is a long
|
99
|
+
# filename!!!)
|
100
|
+
attr_accessor :base_name
|
101
|
+
# The name of the mass spec manufacturer
|
102
|
+
attr_accessor :ms_manufacturer
|
103
|
+
attr_accessor :ms_model
|
104
|
+
attr_accessor :ms_mass_analyzer
|
105
|
+
attr_accessor :ms_detector
|
106
|
+
attr_accessor :raw_data_type
|
107
|
+
attr_accessor :raw_data
|
108
|
+
attr_accessor :ms_ionization
|
109
|
+
attr_accessor :pepxml_version
|
110
|
+
|
111
|
+
# A SampleEnzyme object (responds to: name, cut, no_cut, sense)
|
112
|
+
attr_accessor :sample_enzyme
|
113
|
+
# A SearchSummary object
|
114
|
+
attr_accessor :search_summary
|
115
|
+
# An array of spectrum_queries
|
116
|
+
attr_accessor :spectrum_queries
|
117
|
+
|
118
|
+
# takes a hash of name, value pairs
|
119
|
+
# if block given, spectrum_queries (should be array of spectrum queries) is
|
120
|
+
# set to the return value of the block
|
121
|
+
def initialize(hash=nil)
|
122
|
+
@spectrum_queries = []
|
123
|
+
if hash
|
124
|
+
instance_var_set_from_hash(hash)
|
125
|
+
end
|
126
|
+
if block_given? ; @spectrum_queries = yield end
|
127
|
+
end
|
128
|
+
|
129
|
+
def to_pepxml
|
130
|
+
case Sequest::PepXML.pepxml_version
|
131
|
+
when 18
|
132
|
+
element_xml_and_att_string(:msms_run_summary, "base_name=\"#{base_name}\" msManufacturer=\"#{ms_manufacturer}\" msModel=\"#{ms_model}\" msIonization=\"#{ms_ionization}\" msMassAnalyzer=\"#{ms_mass_analyzer}\" msDetector=\"#{ms_detector}\" raw_data_type=\"#{raw_data_type}\" raw_data=\"#{raw_data}\"") do
|
133
|
+
sample_enzyme.to_pepxml +
|
134
|
+
search_summary.to_pepxml +
|
135
|
+
spectrum_queries.map {|sq| sq.to_pepxml }.join
|
136
|
+
end
|
137
|
+
end
|
138
|
+
end
|
139
|
+
|
140
|
+
def search_hit_class
|
141
|
+
Sequest::PepXML::SearchHit
|
142
|
+
end
|
143
|
+
|
144
|
+
def self.from_pepxml_node(node)
|
145
|
+
self.new.from_pepxml_node(node)
|
146
|
+
end
|
147
|
+
|
148
|
+
# peps correspond to search_results
|
149
|
+
def from_pepxml_node(node)
|
150
|
+
@base_name = node['base_name']
|
151
|
+
@ms_manufacturer = node['msManufacturer']
|
152
|
+
@ms_model = node['msModel']
|
153
|
+
@ms_manufacturer = node['msIonization']
|
154
|
+
@ms_mass_analyzer = node['msMassAnalyzer']
|
155
|
+
@ms_detector = node['msDetector']
|
156
|
+
@raw_data_type = node['raw_data_type']
|
157
|
+
@raw_data = node['raw_data']
|
158
|
+
self
|
159
|
+
end
|
160
|
+
end
|
161
|
+
|
162
|
+
|
163
|
+
|
164
|
+
class Sequest::PepXML
|
165
|
+
include SpecIDXML
|
166
|
+
|
167
|
+
## CREATE a default version for the entire class
|
168
|
+
class << self
|
169
|
+
attr_accessor :pepxml_version
|
170
|
+
end
|
171
|
+
DEF_VERSION = 18
|
172
|
+
self.pepxml_version = DEF_VERSION # default version
|
173
|
+
|
174
|
+
attr_accessor :pepxml_version, :msms_pipeline_analysis
|
175
|
+
## the full path name (no extension)
|
176
|
+
attr_accessor :base_name
|
177
|
+
attr_accessor :h_plus
|
178
|
+
attr_accessor :avg_parent
|
179
|
+
|
180
|
+
#attr_accessor :spectrum_queries, :params, :base_name, :search_engine, :database, :raw_data_type, :raw_data, :out_data_type, :out_data, :sample_enzyme, :pepxml_version
|
181
|
+
|
182
|
+
# returns an array of spectrum queries
|
183
|
+
def spectrum_queries
|
184
|
+
msms_pipeline_analysis.msms_run_summary.spectrum_queries
|
185
|
+
end
|
186
|
+
|
187
|
+
# msms_pipeline_analysis is set to the result of the yielded block
|
188
|
+
# and set_mono_or_avg is called with params if given
|
189
|
+
def initialize(pepxml_version=DEF_VERSION, sequest_params_obj=nil)
|
190
|
+
self.class.pepxml_version = pepxml_version
|
191
|
+
if sequest_params_obj
|
192
|
+
set_mono_or_avg(sequest_params_obj)
|
193
|
+
end
|
194
|
+
if block_given?
|
195
|
+
@msms_pipeline_analysis = yield
|
196
|
+
@base_name = @msms_pipeline_analysis.msms_run_summary.base_name
|
197
|
+
end
|
198
|
+
end
|
199
|
+
|
200
|
+
# sets @h_plus and @avg_parent from the sequest params object
|
201
|
+
def set_mono_or_avg(sequest_params_obj)
|
202
|
+
case sequest_params_obj.precursor_mass_type
|
203
|
+
when "monoisotopic" ; @avg_parent = false
|
204
|
+
else ; @avg_parent = true
|
205
|
+
end
|
206
|
+
|
207
|
+
case @avg_parent
|
208
|
+
when true ; @h_plus = SpecID::AVG[:h_plus]
|
209
|
+
when false ; @h_plus = SpecID::MONO[:h_plus]
|
210
|
+
end
|
211
|
+
end
|
212
|
+
|
213
|
+
def date
|
214
|
+
Time.new.to_s
|
215
|
+
end
|
216
|
+
|
217
|
+
def xml_version
|
218
|
+
'<?xml version="1.0" encoding="UTF-8"?>' + "\n"
|
219
|
+
end
|
220
|
+
|
221
|
+
# for pepxml_version == 0
|
222
|
+
def doctype
|
223
|
+
'<!DOCTYPE msms_pipeline_analysis SYSTEM "/usr/bin/msms_analysis3.dtd">' + "\n"
|
224
|
+
end
|
225
|
+
|
226
|
+
def style_sheet
|
227
|
+
case self.class.pepxml_version
|
228
|
+
when 18
|
229
|
+
'<?xml-stylesheet type="text/xsl" href="/tools/bin/TPP/tpp/schema/pepXML_std.xsl"?>'
|
230
|
+
end
|
231
|
+
end
|
232
|
+
|
233
|
+
def header
|
234
|
+
case self.class.pepxml_version
|
235
|
+
when 18 ; xml_version + style_sheet
|
236
|
+
end
|
237
|
+
end
|
238
|
+
|
239
|
+
# updates the private attrs _num_prots and _first_prot on bioworks pep
|
240
|
+
# objects. Ideally, we'd like these attributes to reside elsewhere, but for
|
241
|
+
# memory concerns, this is best for now.
|
242
|
+
def self._prot_num_and_first_prot_by_pep(pep_array)
|
243
|
+
pep_array.hash_by(:aaseq).each do |aasq, pep_arr|
|
244
|
+
prts = []
|
245
|
+
pep_arr.each { |pep| prts.push( *(pep.prots) ) }
|
246
|
+
prts.uniq!
|
247
|
+
_size = prts.size
|
248
|
+
pep_arr.each do |pep|
|
249
|
+
pep._num_prots = _size
|
250
|
+
pep._first_prot = prts.first
|
251
|
+
end
|
252
|
+
end
|
253
|
+
end
|
254
|
+
|
255
|
+
|
256
|
+
Default_Options = {
|
257
|
+
:out_path => '.',
|
258
|
+
#:backup_db_path => '.',
|
259
|
+
# a PepXML option
|
260
|
+
:pepxml_version => DEF_VERSION,
|
261
|
+
## MSMSRunSummary options:
|
262
|
+
# string must be recognized in sample_enzyme.rb
|
263
|
+
# or create your own SampleEnzyme object
|
264
|
+
:ms_manufacturer => 'ThermoFinnigan',
|
265
|
+
:ms_model => 'LCQ Deca XP Plus',
|
266
|
+
:ms_ionization => 'ESI',
|
267
|
+
:ms_mass_analyzer => 'Ion Trap',
|
268
|
+
:ms_detector => 'UNKNOWN',
|
269
|
+
:ms_data => '.', # path to ms data files (raw or mzxml)
|
270
|
+
:raw_data_type => "raw",
|
271
|
+
:raw_data => ".mzXML", ## even if you don't have it?
|
272
|
+
## SearchSummary options:
|
273
|
+
:out_data_type => "out", ## may be srf?? don't think pepxml recognizes this yet
|
274
|
+
:out_data => ".tgz", ## may be srf??
|
275
|
+
:copy_mzxml => false, # copy the mzxml file to the out_path (create it if necessary)
|
276
|
+
:print => false, # print the objects to file
|
277
|
+
}
|
278
|
+
|
279
|
+
# will dynamically set :ms_model and :ms_mass_analyzer from srf info
|
280
|
+
# (ignoring defaults or anything passed in) for LTQ Orbitrap
|
281
|
+
# and LCQ Deca XP
|
282
|
+
# See SRF::Sequest::PepXML::Default_Options hash for defaults
|
283
|
+
# unless given, the out_path will be given as the path of the srf_file
|
284
|
+
# srf may be an object or a filename
|
285
|
+
def self.new_from_srf(srf, opts={})
|
286
|
+
opts = Default_Options.merge(opts)
|
287
|
+
|
288
|
+
## read the srf file
|
289
|
+
if srf.is_a? String
|
290
|
+
srf = SRF.new(srf)
|
291
|
+
end
|
292
|
+
|
293
|
+
## set the outpath
|
294
|
+
out_path = opts.delete(:out_path)
|
295
|
+
|
296
|
+
params = srf.params
|
297
|
+
|
298
|
+
## check to see if we need backup_db
|
299
|
+
backup_db_path = opts.delete(:backup_db_path)
|
300
|
+
if !File.exist?(params.database) && backup_db_path
|
301
|
+
params.database_path = backup_db_path
|
302
|
+
end
|
303
|
+
|
304
|
+
#######################################################################
|
305
|
+
# PREPARE THE OPTIONS:
|
306
|
+
#######################################################################
|
307
|
+
## remove items from the options hash that don't belong to
|
308
|
+
ppxml_version = opts.delete(:pepxml_version)
|
309
|
+
out_data_type = opts.delete(:out_data_type)
|
310
|
+
out_data = opts.delete(:out_data)
|
311
|
+
|
312
|
+
## Extract meta info from srf
|
313
|
+
bn_noext = base_name_noext(srf.header.raw_filename)
|
314
|
+
opts[:ms_model] = srf.header.model
|
315
|
+
case opts[:ms_model]
|
316
|
+
when /Orbitrap/
|
317
|
+
opts[:ms_mass_analyzer] = 'Orbitrap'
|
318
|
+
when /LCQ Deca XP/
|
319
|
+
opts[:ms_mass_analyzer] = 'Ion Trap'
|
320
|
+
end
|
321
|
+
|
322
|
+
## Create the base name
|
323
|
+
full_base_name_no_ext = make_base_name( File.expand_path(out_path), bn_noext)
|
324
|
+
opts[:base_name] = full_base_name_no_ext
|
325
|
+
|
326
|
+
## Create the search summary:
|
327
|
+
search_summary_options = {
|
328
|
+
:search_database => Sequest::PepXML::SearchDatabase.new(params),
|
329
|
+
:base_name => full_base_name_no_ext,
|
330
|
+
:out_data_type => out_data_type,
|
331
|
+
:out_data => out_data
|
332
|
+
}
|
333
|
+
modifications_string = srf.header.modifications
|
334
|
+
search_summary = Sequest::PepXML::SearchSummary.new( params, modifications_string, search_summary_options)
|
335
|
+
|
336
|
+
# create the sample enzyme from the params object:
|
337
|
+
sample_enzyme_obj =
|
338
|
+
if opts[:sample_enzyme]
|
339
|
+
opts[:sample_enzyme]
|
340
|
+
else
|
341
|
+
params.sample_enzyme
|
342
|
+
end
|
343
|
+
opts[:sample_enzyme] = sample_enzyme_obj
|
344
|
+
|
345
|
+
## Create the pepxml obj and top level objects
|
346
|
+
pepxml_obj = Sequest::PepXML.new(ppxml_version, params)
|
347
|
+
pipeline = Sequest::PepXML::MSMSPipelineAnalysis.new({:date=>nil,:summary_xml=> bn_noext +'.xml'})
|
348
|
+
pepxml_obj.msms_pipeline_analysis = pipeline
|
349
|
+
pipeline.msms_run_summary = Sequest::PepXML::MSMSRunSummary.new(opts)
|
350
|
+
pipeline.msms_run_summary.search_summary = search_summary
|
351
|
+
modifications_obj = search_summary.modifications
|
352
|
+
|
353
|
+
## name some common variables we'll need
|
354
|
+
h_plus = pepxml_obj.h_plus
|
355
|
+
avg_parent = pepxml_obj.avg_parent
|
356
|
+
|
357
|
+
|
358
|
+
## COPY MZXML FILES IF NECESSARY
|
359
|
+
if opts[:copy_mzxml]
|
360
|
+
mzxml_pathname_noext = File.join(opts[:ms_data], bn_noext)
|
361
|
+
to_copy = MS::Converter::MzXML.file_to_mzxml(mzxml_pathname_noext)
|
362
|
+
if to_copy
|
363
|
+
FileUtils.cp to_copy, out_path
|
364
|
+
else
|
365
|
+
puts "Couldn't file mzXML file with base: #{mzxml_pathname_noext}"
|
366
|
+
puts "Perhaps you need to specifiy the location of the raw data"
|
367
|
+
puts "or need an mzXML converter (readw or t2x)"
|
368
|
+
exit
|
369
|
+
end
|
370
|
+
end
|
371
|
+
|
372
|
+
|
373
|
+
#######################################################################
|
374
|
+
# CREATE the spectrum_queries_ar
|
375
|
+
#######################################################################
|
376
|
+
srf_index = srf.index
|
377
|
+
out_files = srf.out_files
|
378
|
+
spectrum_queries_arr = Array.new(srf.dta_files.size)
|
379
|
+
files_with_hits_index = 0 ## will end up being 1 indexed
|
380
|
+
|
381
|
+
deltacn_orig = opts[:deltacn_orig]
|
382
|
+
deltacn_index =
|
383
|
+
if deltacn_orig ; 20
|
384
|
+
else 19
|
385
|
+
end
|
386
|
+
|
387
|
+
srf.dta_files.each_with_index do |dta_file,dta_i|
|
388
|
+
next if out_files[dta_i].num_hits == 0
|
389
|
+
files_with_hits_index += 1
|
390
|
+
|
391
|
+
precursor_neutral_mass = dta_file.mh - h_plus
|
392
|
+
|
393
|
+
(start_scan, end_scan, charge) = srf_index[dta_i]
|
394
|
+
sq_hash = {
|
395
|
+
:spectrum => [bn_noext, start_scan, end_scan, charge].join('.'),
|
396
|
+
:start_scan => start_scan,
|
397
|
+
:end_scan => end_scan,
|
398
|
+
:precursor_neutral_mass => precursor_neutral_mass,
|
399
|
+
:assumed_charge => charge.to_i,
|
400
|
+
:pepxml_version => ppxml_version,
|
401
|
+
:index => files_with_hits_index,
|
402
|
+
}
|
403
|
+
|
404
|
+
spectrum_query = Sequest::PepXML::SpectrumQuery.new(sq_hash)
|
405
|
+
|
406
|
+
|
407
|
+
hits = out_files[dta_i].hits
|
408
|
+
|
409
|
+
search_hits =
|
410
|
+
if opts[:all_hits]
|
411
|
+
Array.new(out_files[dta_i].num_hits) # all hits
|
412
|
+
else
|
413
|
+
Array.new(1) # top hit only
|
414
|
+
end
|
415
|
+
|
416
|
+
(0...(search_hits.size)).each do |hit_i|
|
417
|
+
hit = hits[hit_i]
|
418
|
+
# under the modified deltacn schema (like bioworks)
|
419
|
+
# Get proper deltacn and deltacnstar
|
420
|
+
# under new srf, deltacn is already corrected for what prophet wants,
|
421
|
+
# deltacn_orig_updated is how to access the old one
|
422
|
+
# Prophet deltacn is not the same as the native Sequest deltacn
|
423
|
+
# It is the deltacn of the second best hit!
|
424
|
+
|
425
|
+
## mass calculations:
|
426
|
+
calc_neutral_pep_mass = hit[0] - h_plus
|
427
|
+
|
428
|
+
|
429
|
+
sequence = hit.sequence
|
430
|
+
|
431
|
+
# NEED TO MODIFY SPLIT SEQUENCE TO DO MODS!
|
432
|
+
## THIS IS ALL INNER LOOP, so we make every effort at speed here:
|
433
|
+
(prevaa, pepseq, nextaa) = SpecID::Pep.prepare_sequence(sequence)
|
434
|
+
# 0=mh 1=deltacn_orig 2=sp 3=xcorr 4=id 5=num_other_loci 6=rsp 7=ions_matched 8=ions_total 9=sequence 10=prots 11=deltamass 12=ppm 13=aaseq 14=base_name 15=first_scan 16=last_scan 17=charge 18=srf 19=deltacn 20=deltacn_orig_updated
|
435
|
+
|
436
|
+
sh_hash = {
|
437
|
+
:hit_rank => hit_i+1,
|
438
|
+
:peptide => pepseq,
|
439
|
+
:peptide_prev_aa => prevaa,
|
440
|
+
:peptide_next_aa => nextaa,
|
441
|
+
:protein => hit[10].first.reference.split(" ").first,
|
442
|
+
:num_tot_proteins => hit[10].size,
|
443
|
+
:num_matched_ions => hit[7],
|
444
|
+
:tot_num_ions => hit[8],
|
445
|
+
:calc_neutral_pep_mass => calc_neutral_pep_mass,
|
446
|
+
:massdiff => precursor_neutral_mass - calc_neutral_pep_mass,
|
447
|
+
:num_tol_term => sample_enzyme_obj.num_tol_term(sequence),
|
448
|
+
:num_missed_cleavages => sample_enzyme_obj.num_missed_cleavages(pepseq),
|
449
|
+
:is_rejected => 0,
|
450
|
+
# These are search score attributes:
|
451
|
+
:xcorr => hit[3],
|
452
|
+
:deltacn => hit[deltacn_index],
|
453
|
+
:spscore => hit[2],
|
454
|
+
:sprank => hit[6],
|
455
|
+
:modification_info => modifications_obj.modification_info(SpecID::Pep.split_sequence(sequence)[1]),
|
456
|
+
}
|
457
|
+
unless deltacn_orig
|
458
|
+
sh_hash[:deltacnstar] =
|
459
|
+
if hits[hit_i+1].nil? # no next hit? then its deltacnstar == 1
|
460
|
+
'1'
|
461
|
+
else
|
462
|
+
'0'
|
463
|
+
end
|
464
|
+
end
|
465
|
+
search_hits[hit_i] = Sequest::PepXML::SearchHit.new(sh_hash) # there can be multiple hits
|
466
|
+
end
|
467
|
+
|
468
|
+
search_result = Sequest::PepXML::SearchResult.new
|
469
|
+
search_result.search_hits = search_hits
|
470
|
+
spectrum_query.search_results = [search_result]
|
471
|
+
spectrum_queries_arr[files_with_hits_index] = spectrum_query
|
472
|
+
end
|
473
|
+
spectrum_queries_arr.compact!
|
474
|
+
|
475
|
+
pipeline.msms_run_summary.spectrum_queries = spectrum_queries_arr
|
476
|
+
pepxml_obj.base_name = pipeline.msms_run_summary.base_name
|
477
|
+
pipeline.msms_run_summary.spectrum_queries = spectrum_queries_arr
|
478
|
+
|
479
|
+
pepxml_obj
|
480
|
+
end
|
481
|
+
|
482
|
+
# takes an .srg or bioworks.xml file
|
483
|
+
# if possible, ensures that an mzXML file is present for each pepxml file
|
484
|
+
# :print => true, will print files
|
485
|
+
# NOTES: num_tol_term and num_missing_cleavages are both calculated from the
|
486
|
+
# sample_enzyme. Thus, a No_Enzyme search may still pass in a
|
487
|
+
# :sample_enzyme option to get these calculated.
|
488
|
+
def self.set_from_bioworks(bioworks_file, opts={})
|
489
|
+
opts = Default_Options.merge(opts)
|
490
|
+
## Create the out_path directory if necessary
|
491
|
+
|
492
|
+
unless File.exist? opts[:out_path]
|
493
|
+
FileUtils.mkpath(opts[:out_path])
|
494
|
+
end
|
495
|
+
unless File.directory? opts[:out_path]
|
496
|
+
abort "#{opts[:out_path]} must be a directory!"
|
497
|
+
end
|
498
|
+
|
499
|
+
spec_id = SpecID.new(bioworks_file)
|
500
|
+
pepxml_objs =
|
501
|
+
if spec_id.is_a? Bioworks
|
502
|
+
abort("must have opts[:params] set!") unless opts[:params]
|
503
|
+
set_from_bioworks_xml(bioworks_file, opts[:params], opts)
|
504
|
+
elsif spec_id.is_a? SRFGroup
|
505
|
+
spec_id.srfs.map do |srf|
|
506
|
+
new_from_srf(srf, opts)
|
507
|
+
end
|
508
|
+
else
|
509
|
+
abort "invalid object"
|
510
|
+
end
|
511
|
+
|
512
|
+
if opts[:print]
|
513
|
+
pepxml_objs.each do |obj|
|
514
|
+
obj.to_pepxml(obj.base_name + ".xml")
|
515
|
+
end
|
516
|
+
end
|
517
|
+
pepxml_objs
|
518
|
+
end
|
519
|
+
|
520
|
+
|
521
|
+
# Takes bioworks 3.2/3.3 xml output (with no filters)
|
522
|
+
# Returns a list of PepXML objects
|
523
|
+
# params = sequest.params file
|
524
|
+
# bioworks = bioworks.xml exported multi-consensus view file
|
525
|
+
# pepxml_version = 0 for tpp 1.2.3
|
526
|
+
# pepxml_version = 18 for tpp 2.8.2, 2.8.3, 2.9.2
|
527
|
+
def self.set_from_bioworks_xml(bioworks, params, opts={})
|
528
|
+
opts = Default_Options.merge(opts)
|
529
|
+
pepxml_version, ms_manufacturer, ms_model, ms_ionization, ms_mass_analyzer, ms_detector, raw_data_type, raw_data, out_data_type, out_data, ms_data, out_path = opts.values_at(:pepxml_version, :ms_manufacturer, :ms_model, :ms_ionization, :ms_mass_analyzer, :ms_detector, :raw_data_type, :raw_data, :out_data_type, :out_data, :ms_data, :out_path)
|
530
|
+
|
531
|
+
|
532
|
+
|
533
|
+
unless out_path
|
534
|
+
out_path = '.'
|
535
|
+
end
|
536
|
+
|
537
|
+
supported_versions = [18]
|
538
|
+
|
539
|
+
unless supported_versions.include?(opts[:pepxml_version])
|
540
|
+
abort "pepxml_version: #{pepxml_version} not currently supported. Current support is for versions #{supported_versions.join(', ')}"
|
541
|
+
end
|
542
|
+
|
543
|
+
## Turn params and bioworks_obj into objects if necessary:
|
544
|
+
# Params:
|
545
|
+
if params.class == Sequest::Params # OK!
|
546
|
+
elsif params.class == String ; params = Sequest::Params.new(params)
|
547
|
+
else ; abort "Don't recognize #{params} as object or string!"
|
548
|
+
end
|
549
|
+
# Bioworks:
|
550
|
+
if bioworks.class == Bioworks # OK!
|
551
|
+
elsif bioworks.class == String ; bioworks = SpecID.new(bioworks)
|
552
|
+
else ; abort "Don't recognize #{bioworks} as object or string!"
|
553
|
+
end
|
554
|
+
|
555
|
+
sample_enzyme_obj =
|
556
|
+
if opts[:sample_enzyme]
|
557
|
+
opts[:sample_enzyme]
|
558
|
+
else
|
559
|
+
params.sample_enzyme
|
560
|
+
end
|
561
|
+
|
562
|
+
#puts "bioworks.peps.size: #{bioworks.peps.size}"; #puts "bioworks.prots.size: #{bioworks.prots.size}"; #puts "Bioworks.version: #{bioworks.version}"
|
563
|
+
|
564
|
+
## TURN THIS ON IF YOU THINK YOU MIGHT NOT BE GETTING PEPTIDES from
|
565
|
+
## bioworks
|
566
|
+
#bioworks.peps.each { |pep| if pep.class != Bioworks::Pep ; puts "trying to pass as pep: "; p pep; abort "NOT a pep!" end }
|
567
|
+
|
568
|
+
## check to see if we need backup_db
|
569
|
+
|
570
|
+
backup_db_path = opts.delete(:backup_db_path)
|
571
|
+
if !File.exist?(params.database) && backup_db_path
|
572
|
+
params.database_path = backup_db_path
|
573
|
+
end
|
574
|
+
|
575
|
+
## Start
|
576
|
+
split_bio_objs = []
|
577
|
+
|
578
|
+
## (num_prots_by_pep, prot_by_pep) =
|
579
|
+
#num_prots_by_pep.each do |k,v| puts "k: #{k} v: #{v}\n"; break end ; prot_by_pep.each do |k,v| puts "k: #{k} v: #{v}" ; break end ; abort "HERE"
|
580
|
+
|
581
|
+
modifications_string = bioworks.modifications
|
582
|
+
|
583
|
+
## Create a hash of spectrum_query arrays by filename (this very big block):
|
584
|
+
spectrum_queries_by_base_name = {}
|
585
|
+
# Hash by the filenames to split into filenames:
|
586
|
+
pepxml_objects = bioworks.peps.hash_by(:base_name).map do |base_name, pep_arr|
|
587
|
+
|
588
|
+
search_summary = Sequest::PepXML::SearchSummary.new(params, modifications_string, {:search_database => Sequest::PepXML::SearchDatabase.new(params), :out_data_type => out_data_type, :out_data => out_data})
|
589
|
+
modifications_obj = search_summary.modifications
|
590
|
+
|
591
|
+
pepxml_obj = Sequest::PepXML.new(pepxml_version, params)
|
592
|
+
full_base_name_no_ext = self.make_base_name( File.expand_path(out_path), base_name)
|
593
|
+
|
594
|
+
case pepxml_version
|
595
|
+
when 18
|
596
|
+
pipeline = Sequest::PepXML::MSMSPipelineAnalysis.new({:date=>nil,:summary_xml=>base_name+'.xml'})
|
597
|
+
msms_run_summary = Sequest::PepXML::MSMSRunSummary.new({
|
598
|
+
:base_name => full_base_name_no_ext,
|
599
|
+
:ms_manufacturer => ms_manufacturer,
|
600
|
+
:ms_model => ms_model,
|
601
|
+
:ms_ionization => ms_ionization,
|
602
|
+
:ms_mass_analyzer => ms_mass_analyzer,
|
603
|
+
:ms_detector => ms_detector,
|
604
|
+
:raw_data_type => raw_data_type,
|
605
|
+
:raw_data => raw_data,
|
606
|
+
:sample_enzyme => sample_enzyme_obj, # usually, params.sample_enzyme,
|
607
|
+
:search_summary => search_summary,
|
608
|
+
})
|
609
|
+
pipeline.msms_run_summary = msms_run_summary
|
610
|
+
pepxml_obj.msms_pipeline_analysis = pipeline
|
611
|
+
pepxml_obj.msms_pipeline_analysis.msms_run_summary.search_summary.base_name = full_base_name_no_ext
|
612
|
+
pepxml_obj.base_name = full_base_name_no_ext
|
613
|
+
pepxml_obj
|
614
|
+
end
|
615
|
+
|
616
|
+
# Create a hash by pep object containing num_tot_proteins
|
617
|
+
# This is only valid if all hits are present (no previous thresholding)
|
618
|
+
# Since out2summary only acts on one folder at a time,
|
619
|
+
# we should only do it for one folder at a time! (that's why we do this
|
620
|
+
# here instead of globally)
|
621
|
+
self._prot_num_and_first_prot_by_pep(pep_arr)
|
622
|
+
prec_mz_arr = nil
|
623
|
+
case x = bioworks.version
|
624
|
+
when /3.2/
|
625
|
+
calc_prec_by = :prec_mz_arr
|
626
|
+
# get the precursor_mz array for this filename
|
627
|
+
mzxml_file = MS::Converter::MzXML.file_to_mzxml(File.join(ms_data, base_name))
|
628
|
+
prec_mz_arr = MS::MSRun.precursor_mz_by_scan_num(mzxml_file)
|
629
|
+
when /3.3/
|
630
|
+
calc_prec_by = :deltamass
|
631
|
+
else
|
632
|
+
abort "invalid BioworksBrowser version: #{x}"
|
633
|
+
end
|
634
|
+
|
635
|
+
if opts[:copy_mzxml]
|
636
|
+
to_copy = MS::Converter::MzXML.file_to_mzxml(File.join(ms_data, base_name))
|
637
|
+
if to_copy
|
638
|
+
FileUtils.cp to_copy, out_path
|
639
|
+
end
|
640
|
+
end
|
641
|
+
|
642
|
+
|
643
|
+
spectrum_queries_ar = pep_arr.hash_by(:first_scan, :last_scan, :charge).map do |key,arr|
|
644
|
+
|
645
|
+
|
646
|
+
# Sort_by_rank and take the top hit (to mimick out2summary):
|
647
|
+
|
648
|
+
arr = arr.sort_by {|pep| pep.xcorr.to_f } # ascending
|
649
|
+
top_pep = arr.pop
|
650
|
+
second_hit = arr.last # needed for deltacnstar
|
651
|
+
|
652
|
+
|
653
|
+
case calc_prec_by
|
654
|
+
when :prec_mz_arr
|
655
|
+
precursor_neutral_mass = Sequest::PepXML::SpectrumQuery.calc_precursor_neutral_mass(calc_prec_by, top_pep.first_scan.to_i, top_pep.last_scan.to_i, prec_mz_arr, top_pep.charge, pepxml_obj.avg_parent)
|
656
|
+
when :deltamass
|
657
|
+
precursor_neutral_mass = Sequest::PepXML::SpectrumQuery.calc_precursor_neutral_mass(calc_prec_by, top_pep.mass.to_f, top_pep.deltamass.to_f, pepxml_obj.avg_parent)
|
658
|
+
end
|
659
|
+
|
660
|
+
calc_neutral_pep_mass = (top_pep.mass.to_f - pepxml_obj.h_plus)
|
661
|
+
|
662
|
+
# deltacn & star:
|
663
|
+
# (NOTE: OLD?? out2summary wants the deltacn of the 2nd best hit.)
|
664
|
+
if second_hit
|
665
|
+
#top_pep.deltacn = second_hit.deltacn
|
666
|
+
deltacnstar = '0'
|
667
|
+
else
|
668
|
+
top_pep.deltacn = '1.0'
|
669
|
+
deltacnstar = '1'
|
670
|
+
end
|
671
|
+
# Create the nested structure of queries{results{hits}}
|
672
|
+
# (Ruby's blocks work beautifully for things like this)
|
673
|
+
spec_query = Sequest::PepXML::SpectrumQuery.new({
|
674
|
+
:spectrum => [top_pep.base_name, top_pep.first_scan, top_pep.last_scan, top_pep.charge].join("."),
|
675
|
+
:start_scan => top_pep.first_scan,
|
676
|
+
:end_scan => top_pep.last_scan,
|
677
|
+
:precursor_neutral_mass => precursor_neutral_mass,
|
678
|
+
:assumed_charge => top_pep.charge,
|
679
|
+
:pepxml_version => pepxml_version,
|
680
|
+
})
|
681
|
+
|
682
|
+
|
683
|
+
search_result = Sequest::PepXML::SearchResult.new
|
684
|
+
#puts "set MASSDIFF: "
|
685
|
+
#p precursor_neutral_mass - calc_neutral_pep_mass
|
686
|
+
## Calculate some interdependent values;
|
687
|
+
# NOTE: the bioworks mass is reallyf M+H if two or more scans went
|
688
|
+
# into the search_hit; calc_neutral_pep_mass is simply the avg of
|
689
|
+
# precursor masses adjusted to be neutral
|
690
|
+
(prevaa, pepseq, nextaa) = SpecID::Pep.prepare_sequence(top_pep.sequence)
|
691
|
+
(num_matched_ions, tot_num_ions) = Sequest::PepXML::SearchHit.split_ions(top_pep.ions)
|
692
|
+
search_hit = Sequest::PepXML::SearchHit.new({
|
693
|
+
:hit_rank => 1,
|
694
|
+
:peptide => pepseq,
|
695
|
+
:peptide_prev_aa => prevaa,
|
696
|
+
:peptide_next_aa => nextaa,
|
697
|
+
:protein => top_pep._first_prot.reference.split(" ").first,
|
698
|
+
:num_tot_proteins => top_pep._num_prots,
|
699
|
+
:num_matched_ions => num_matched_ions,
|
700
|
+
:tot_num_ions => tot_num_ions,
|
701
|
+
:calc_neutral_pep_mass => calc_neutral_pep_mass,
|
702
|
+
:massdiff => precursor_neutral_mass - calc_neutral_pep_mass,
|
703
|
+
:num_tol_term => sample_enzyme_obj.num_tol_term(top_pep.sequence),
|
704
|
+
:num_missed_cleavages => sample_enzyme_obj.num_missed_cleavages(pepseq),
|
705
|
+
:is_rejected => 0,
|
706
|
+
# These are search score attributes:
|
707
|
+
:xcorr => top_pep.xcorr,
|
708
|
+
:deltacn => top_pep.deltacn,
|
709
|
+
:deltacnstar => deltacnstar,
|
710
|
+
:spscore => top_pep.sp,
|
711
|
+
:sprank => top_pep.rsp,
|
712
|
+
:modification_info => modifications_obj.modification_info(SpecID::Pep.split_sequence(top_pep.sequence)[1]),
|
713
|
+
:spectrum_query => spec_query,
|
714
|
+
})
|
715
|
+
search_result.search_hits = [search_hit] # there can be multiple search hits
|
716
|
+
spec_query.search_results = [search_result] # can be multiple search_results
|
717
|
+
spec_query
|
718
|
+
end
|
719
|
+
|
720
|
+
# create an index by spectrum as results end up typically in out2summary
|
721
|
+
# (I really dislike this order, however)
|
722
|
+
spectrum_queries_ar = spectrum_queries_ar.sort_by {|pep| pep.spectrum }
|
723
|
+
spectrum_queries_ar.each_with_index {|res,index| res.index = "#{index + 1}" }
|
724
|
+
pipeline.msms_run_summary.spectrum_queries = spectrum_queries_ar
|
725
|
+
pepxml_obj
|
726
|
+
end ## collects pepxml_objs
|
727
|
+
# summary_xml is the short basename of the pepxml file (e.g., "020.xml")
|
728
|
+
pepxml_objects.sort_by {|obj| obj.summary_xml }
|
729
|
+
end
|
730
|
+
|
731
|
+
def summary_xml
|
732
|
+
base_name + ".xml"
|
733
|
+
end
|
734
|
+
|
735
|
+
def precursor_mass_type
|
736
|
+
@params.precursor_mass_type
|
737
|
+
end
|
738
|
+
|
739
|
+
def fragment_mass_type
|
740
|
+
@params.fragment_mass_type
|
741
|
+
end
|
742
|
+
|
743
|
+
# combines filename in a manner consistent with the path
|
744
|
+
def self.make_base_name(path, filename)
|
745
|
+
sep = '/'
|
746
|
+
if path.split('/').size < path.split("\\").size
|
747
|
+
sep = "\\"
|
748
|
+
end
|
749
|
+
if path.split('').last == sep
|
750
|
+
path + File.basename(filename)
|
751
|
+
else
|
752
|
+
path + sep + File.basename(filename)
|
753
|
+
end
|
754
|
+
end
|
755
|
+
|
756
|
+
# outputs pepxml, (to file if given)
|
757
|
+
def to_pepxml(file=nil)
|
758
|
+
string = header
|
759
|
+
string << @msms_pipeline_analysis.to_pepxml
|
760
|
+
|
761
|
+
if file
|
762
|
+
File.open(file, "w") do |fh| fh.print string end
|
763
|
+
end
|
764
|
+
string
|
765
|
+
end
|
766
|
+
|
767
|
+
# given any kind of filename (from windows or whatever)
|
768
|
+
# returns the base of the filename with no file extension
|
769
|
+
def self.base_name_noext(file)
|
770
|
+
file.gsub!("\\", '/')
|
771
|
+
File.basename(file).sub(/\.[\w^\.]+$/, '')
|
772
|
+
end
|
773
|
+
|
774
|
+
|
775
|
+
end # PepXML
|
776
|
+
|
777
|
+
|
778
|
+
class Sequest::PepXML::SearchResult
|
779
|
+
include SpecIDXML
|
780
|
+
# an array of search_hits
|
781
|
+
attr_accessor :search_hits
|
782
|
+
|
783
|
+
# if block given, then search_hits set to return value
|
784
|
+
def initialize(search_hits = [])
|
785
|
+
@search_hits = search_hits
|
786
|
+
end
|
787
|
+
|
788
|
+
def to_pepxml
|
789
|
+
element_xml_no_atts(:search_result) do
|
790
|
+
@search_hits.map {|sh| sh.to_pepxml }.join
|
791
|
+
end
|
792
|
+
end
|
793
|
+
|
794
|
+
end
|
795
|
+
|
796
|
+
class Sequest::PepXML::SearchSummary
|
797
|
+
include SpecIDXML
|
798
|
+
attr_accessor :params
|
799
|
+
attr_accessor :base_name
|
800
|
+
attr_accessor :out_data_type
|
801
|
+
attr_accessor :out_data
|
802
|
+
# by default, "1"
|
803
|
+
attr_accessor :search_id
|
804
|
+
attr_accessor :modifications
|
805
|
+
# A SearchDatabase object (responds to :local_path and :type)
|
806
|
+
attr_accessor :search_database
|
807
|
+
# if given a sequest params object, then will set the following attributes:
|
808
|
+
# args is a hash of parameters
|
809
|
+
# modifications_string -> See Modifications
|
810
|
+
def initialize(prms=nil, modifications_string='', args=nil)
|
811
|
+
@search_id = "1"
|
812
|
+
if prms
|
813
|
+
@params = prms
|
814
|
+
@modifications = Sequest::PepXML::Modifications.new(prms, modifications_string)
|
815
|
+
end
|
816
|
+
if args ; set_from_hash(args) end
|
817
|
+
end
|
818
|
+
|
819
|
+
def method_missing(symbol, *args)
|
820
|
+
if @params ; @params.send(symbol, *args) end
|
821
|
+
end
|
822
|
+
|
823
|
+
def to_pepxml
|
824
|
+
element_xml(:search_summary, [:base_name, :search_engine, :precursor_mass_type, :fragment_mass_type, :out_data_type, :out_data, :search_id]) do
|
825
|
+
search_database.to_pepxml +
|
826
|
+
if @params.enzyme =~ /^No_Enzyme/
|
827
|
+
''
|
828
|
+
else
|
829
|
+
short_element_xml(:enzymatic_search_constraint, [:enzyme, :max_num_internal_cleavages, :min_number_termini])
|
830
|
+
end +
|
831
|
+
@modifications.to_pepxml +
|
832
|
+
Sequest::PepXML::Parameters.new(@params).to_pepxml
|
833
|
+
end
|
834
|
+
end
|
835
|
+
|
836
|
+
def self.from_pepxml_node(node)
|
837
|
+
self.new.from_pepxml_node(node)
|
838
|
+
end
|
839
|
+
|
840
|
+
def from_pepxml_node(node)
|
841
|
+
raise NotImplementedError, "right now we just have the xml node at your disposal"
|
842
|
+
end
|
843
|
+
|
844
|
+
end
|
845
|
+
|
846
|
+
class Sequest::PepXML::Parameters
|
847
|
+
include SpecIDXML
|
848
|
+
|
849
|
+
attr_accessor :params
|
850
|
+
|
851
|
+
def initialize(obj=nil)
|
852
|
+
@params = obj
|
853
|
+
end
|
854
|
+
# (used to be called pepxml_parameters)
|
855
|
+
# Returns xml in the form <parameter name="#{method_name}"
|
856
|
+
# value="#{method_value}"/> for list of symbols
|
857
|
+
def to_pepxml
|
858
|
+
keys_as_symbols = @params.opts.sort.map do |k,v| k.to_s end
|
859
|
+
params_xml(@params, *keys_as_symbols)
|
860
|
+
# (:peptide_mass_tol, :peptide_mass_units, :fragment_ion_tol, :ion_series, :max_num_differential_AA_per_mod, :nucleotide_reading_frame, :num_output_lines, :remove_precursor_peak, :ion_cutoff_percentage, :match_peak_count, :match_peak_allowed_error, :match_peak_tolerance, :protein_mass_filter, :sequence_header_filter)
|
861
|
+
end
|
862
|
+
end
|
863
|
+
|
864
|
+
class Sequest::PepXML::Modifications
|
865
|
+
include SpecIDXML
|
866
|
+
|
867
|
+
# sequest params object
|
868
|
+
attr_accessor :params
|
869
|
+
# array holding AAModifications
|
870
|
+
attr_accessor :aa_mods
|
871
|
+
# array holding TerminalModifications
|
872
|
+
attr_accessor :term_mods
|
873
|
+
# a hash of all differential modifications present by aa_one_letter_symbol
|
874
|
+
# and special_symbol. This is NOT the mass difference but the total mass {
|
875
|
+
# 'M*' => 155.5, 'S@' => 190.3 }. NOTE: Since the termini are dependent on
|
876
|
+
# the amino acid sequence, they are give the *differential* mass. The
|
877
|
+
# termini are given the special symbol as in sequest e.g. '[' => 12.22, #
|
878
|
+
# cterminus ']' => 14.55 # nterminus
|
879
|
+
attr_accessor :masses_by_diff_mod_hash
|
880
|
+
# a hash, key is [AA_one_letter_symbol.to_sym, difference.to_f]
|
881
|
+
# values are the special_symbols
|
882
|
+
attr_accessor :mod_symbols_hash
|
883
|
+
|
884
|
+
# The modification symbols string looks like this:
|
885
|
+
# (M* +15.90000) (M# +29.00000) (S@ +80.00000) (C^ +12.00000) (ct[ +12.33000) (nt] +14.20000)
|
886
|
+
# ct is cterminal peptide (differential)
|
887
|
+
# nt is nterminal peptide (differential)
|
888
|
+
# the C is just cysteine
|
889
|
+
# will set_modifications and masses_by_diff_mod hash
|
890
|
+
def initialize(params=nil, modification_symbols_string='')
|
891
|
+
@params = params
|
892
|
+
if @params
|
893
|
+
set_modifications(params, modification_symbols_string)
|
894
|
+
end
|
895
|
+
end
|
896
|
+
|
897
|
+
# set the masses_by_diff_mod and mod_symbols_hash from
|
898
|
+
def set_hashes(modification_symbols_string)
|
899
|
+
|
900
|
+
@mod_symbols_hash = {}
|
901
|
+
@masses_by_diff_mod = {}
|
902
|
+
if (modification_symbols_string == nil || modification_symbols_string == '')
|
903
|
+
return nil
|
904
|
+
end
|
905
|
+
table = @params.mass_table
|
906
|
+
modification_symbols_string.split(/\)\s+\(/).each do |mod|
|
907
|
+
if mod =~ /\(?(\w+)(.) (.[\d\.]+)\)?/
|
908
|
+
if $1 == 'ct' || $1 == 'nt'
|
909
|
+
mass_diff = $3.to_f
|
910
|
+
@masses_by_diff_mod[$2] = mass_diff
|
911
|
+
@mod_symbols_hash[[$1.to_sym, mass_diff]] = $2.dup
|
912
|
+
# changed from below to match tests, is this right?
|
913
|
+
# @mod_symbols_hash[[$1, mass_diff]] = $2.dup
|
914
|
+
else
|
915
|
+
symbol_string = $2.dup
|
916
|
+
mass_diff = $3.to_f
|
917
|
+
$1.split('').each do |aa|
|
918
|
+
aa_as_sym = aa.to_sym
|
919
|
+
@masses_by_diff_mod[aa+symbol_string] = mass_diff + table[aa_as_sym]
|
920
|
+
@mod_symbols_hash[[aa_as_sym, mass_diff]] = symbol_string
|
921
|
+
end
|
922
|
+
end
|
923
|
+
end
|
924
|
+
end
|
925
|
+
end
|
926
|
+
|
927
|
+
# given a bare peptide (no end pieces) returns a ModificationInfo object
|
928
|
+
# e.g. given "]PEPT*IDE", NOT 'K.PEPTIDE.R'
|
929
|
+
# if there are no modifications, returns nil
|
930
|
+
def modification_info(peptide)
|
931
|
+
if @masses_by_diff_mod.size == 0
|
932
|
+
return nil
|
933
|
+
end
|
934
|
+
hash = {}
|
935
|
+
hash[:modified_peptide] = peptide.dup
|
936
|
+
hsh = @masses_by_diff_mod
|
937
|
+
table = @params.mass_table
|
938
|
+
h = table[:h] # this? or h_plus ??
|
939
|
+
oh = table[:o] + h
|
940
|
+
## only the termini can match a single char
|
941
|
+
if hsh.key? peptide[0,1]
|
942
|
+
# AA + H + differential_mod
|
943
|
+
hash[:mod_nterm_mass] = table[peptide[1,1].to_sym] + h + hsh[peptide[0,1]]
|
944
|
+
peptide = peptide[1...(peptide.size)]
|
945
|
+
end
|
946
|
+
if hsh.key? peptide[(peptide.size-1),1]
|
947
|
+
# AA + OH + differential_mod
|
948
|
+
hash[:mod_cterm_mass] = table[peptide[(peptide.size-2),1].to_sym] + oh + hsh[peptide[-1,1]]
|
949
|
+
peptide.slice!( 0..-2 )
|
950
|
+
peptide = peptide[0...(peptide.size-1)]
|
951
|
+
end
|
952
|
+
mod_array = []
|
953
|
+
(0...peptide.size).each do |i|
|
954
|
+
if hsh.key? peptide[i,2]
|
955
|
+
mod_array << Sequest::PepXML::SearchHit::ModificationInfo::ModAminoacidMass.new([ i+1 , hsh[peptide[i,2]] ])
|
956
|
+
end
|
957
|
+
end
|
958
|
+
if mod_array.size > 0
|
959
|
+
hash[:mod_aminoacid_masses] = mod_array
|
960
|
+
end
|
961
|
+
if hash.size > 1 # if there is more than just the modified peptide there
|
962
|
+
Sequest::PepXML::SearchHit::ModificationInfo.new(hash)
|
963
|
+
#Sequest::PepXML::SearchHit::ModificationInfo.new(hash.values_at(:modified_peptide, :mod_aminoacid_masses, :mod_nterm_mass, :mod_cterm_mass)
|
964
|
+
else
|
965
|
+
nil
|
966
|
+
end
|
967
|
+
end
|
968
|
+
|
969
|
+
# returns an array of static mod objects and static terminal mod objects
|
970
|
+
def create_static_mods(params)
|
971
|
+
|
972
|
+
####################################
|
973
|
+
## static mods
|
974
|
+
####################################
|
975
|
+
|
976
|
+
static_mods = [] # [[one_letter_amino_acid.to_sym, add_amount.to_f], ...]
|
977
|
+
static_terminal_mods = [] # e.g. [add_Cterm_peptide, amount.to_f]
|
978
|
+
|
979
|
+
params.mods.each do |k,v|
|
980
|
+
v_to_f = v.to_f
|
981
|
+
if v_to_f != 0.0
|
982
|
+
if k =~ /add_(\w)_/
|
983
|
+
static_mods << [$1.to_sym, v_to_f]
|
984
|
+
else
|
985
|
+
static_terminal_mods << [k, v_to_f]
|
986
|
+
end
|
987
|
+
end
|
988
|
+
end
|
989
|
+
aa_hash = params.mass_table
|
990
|
+
|
991
|
+
## Create the static_mods objects
|
992
|
+
static_mods.map! do |mod|
|
993
|
+
hash = {
|
994
|
+
:aminoacid => mod[0].to_s,
|
995
|
+
:massdiff => mod[1],
|
996
|
+
:mass => aa_hash[mod[0]] + mod[1],
|
997
|
+
:variable => 'N',
|
998
|
+
:binary => 'Y',
|
999
|
+
}
|
1000
|
+
Sequest::PepXML::AAModification.new(hash)
|
1001
|
+
end
|
1002
|
+
|
1003
|
+
## Create the static_terminal_mods objects
|
1004
|
+
static_terminal_mods.map! do |mod|
|
1005
|
+
terminus = if mod[0] =~ /Cterm/ ; 'c'
|
1006
|
+
else ; 'n' # only two possible termini
|
1007
|
+
end
|
1008
|
+
protein_terminus = case mod[0]
|
1009
|
+
when /Nterm_protein/ ; 'n'
|
1010
|
+
when /Cterm_protein/ ; 'c'
|
1011
|
+
else nil
|
1012
|
+
end
|
1013
|
+
|
1014
|
+
# create the hash
|
1015
|
+
hash = {
|
1016
|
+
:terminus => terminus,
|
1017
|
+
:massdiff => mod[1],
|
1018
|
+
:variable => 'N',
|
1019
|
+
:description => mod[0],
|
1020
|
+
}
|
1021
|
+
hash[:protein_terminus] = protein_terminus if protein_terminus
|
1022
|
+
Sequest::PepXML::TerminalModification.new(hash)
|
1023
|
+
end
|
1024
|
+
[static_mods, static_terminal_mods]
|
1025
|
+
end
|
1026
|
+
|
1027
|
+
# 1. sets aa_mods and term_mods from a sequest params object
|
1028
|
+
# 2. sets @params
|
1029
|
+
# 3. sets @masses_by_diff_mod
|
1030
|
+
def set_modifications(params, modification_symbols_string)
|
1031
|
+
@params = params
|
1032
|
+
|
1033
|
+
set_hashes(modification_symbols_string)
|
1034
|
+
(static_mods, static_terminal_mods) = create_static_mods(params)
|
1035
|
+
|
1036
|
+
aa_hash = params.mass_table
|
1037
|
+
#################################
|
1038
|
+
# Variable Mods:
|
1039
|
+
#################################
|
1040
|
+
arr = params.diff_search_options.rstrip.split(/\s+/)
|
1041
|
+
# [aa.to_sym, diff.to_f]
|
1042
|
+
variable_mods = []
|
1043
|
+
(0...arr.size).step(2) do |i|
|
1044
|
+
if arr[i].to_f != 0.0
|
1045
|
+
variable_mods << [arr[i+1], arr[i].to_f]
|
1046
|
+
end
|
1047
|
+
end
|
1048
|
+
mod_objects = []
|
1049
|
+
variable_mods.each do |mod|
|
1050
|
+
mod[0].split('').each do |aa|
|
1051
|
+
hash = {
|
1052
|
+
|
1053
|
+
:aminoacid => aa,
|
1054
|
+
:massdiff => mod[1],
|
1055
|
+
:mass => aa_hash[aa.to_sym] + mod[1],
|
1056
|
+
:variable => 'Y',
|
1057
|
+
:binary => 'N',
|
1058
|
+
:symbol => @mod_symbols_hash[[aa.to_sym, mod[1]]],
|
1059
|
+
}
|
1060
|
+
mod_objects << Sequest::PepXML::AAModification.new(hash)
|
1061
|
+
end
|
1062
|
+
end
|
1063
|
+
variable_mods = mod_objects
|
1064
|
+
#################################
|
1065
|
+
# TERMINAL Variable Mods:
|
1066
|
+
#################################
|
1067
|
+
# These are always peptide, not protein termini (for sequest)
|
1068
|
+
(nterm_diff, cterm_diff) = params.term_diff_search_options.rstrip.split(/\s+/).map{|v| v.to_f }
|
1069
|
+
|
1070
|
+
to_add = []
|
1071
|
+
if nterm_diff != 0.0
|
1072
|
+
to_add << ['n',nterm_diff.to_plus_minus_string, @mod_symbols_hash[:nt, nterm_diff]]
|
1073
|
+
end
|
1074
|
+
if cterm_diff != 0.0
|
1075
|
+
to_add << ['c', cterm_diff.to_plus_minus_string, @mod_symbols_hash[:ct, cterm_diff]]
|
1076
|
+
end
|
1077
|
+
|
1078
|
+
variable_terminal_mods = to_add.map do |term, mssdiff, symb|
|
1079
|
+
hash = {
|
1080
|
+
:terminus => term,
|
1081
|
+
:massdiff => mssdiff,
|
1082
|
+
:variable => 'Y',
|
1083
|
+
:symbol => symb,
|
1084
|
+
}
|
1085
|
+
Sequest::PepXML::TerminalModification.new(hash)
|
1086
|
+
end
|
1087
|
+
|
1088
|
+
#########################
|
1089
|
+
# COLLECT THEM
|
1090
|
+
#########################
|
1091
|
+
@aa_mods = static_mods + variable_mods
|
1092
|
+
@term_mods = static_terminal_mods + variable_terminal_mods
|
1093
|
+
end
|
1094
|
+
|
1095
|
+
## Generates the pepxml for static and differential amino acid mods based on
|
1096
|
+
## sequest object
|
1097
|
+
def to_pepxml
|
1098
|
+
st = ''
|
1099
|
+
if @aa_mods
|
1100
|
+
st << @aa_mods.map {|v| v.to_pepxml }.join
|
1101
|
+
end
|
1102
|
+
if @term_mods
|
1103
|
+
st << @term_mods.map {|v| v.to_pepxml }.join
|
1104
|
+
end
|
1105
|
+
st
|
1106
|
+
end
|
1107
|
+
|
1108
|
+
end
|
1109
|
+
|
1110
|
+
# Modified aminoacid, static or variable
|
1111
|
+
# unless otherwise stated, all attributes can be anything
|
1112
|
+
class Sequest::PepXML::AAModification
|
1113
|
+
include SpecIDXML
|
1114
|
+
|
1115
|
+
# The amino acid (one letter code)
|
1116
|
+
attr_accessor :aminoacid
|
1117
|
+
# Must be a string!!!!
|
1118
|
+
# Mass difference with respect to unmodified aminoacid, must begin with
|
1119
|
+
# either + (nonnegative) or - [e.g. +1.05446 or -2.3342]
|
1120
|
+
# consider Numeric#to_plus_minus_string at top
|
1121
|
+
attr_accessor :massdiff
|
1122
|
+
# Mass of modified aminoacid
|
1123
|
+
attr_accessor :mass
|
1124
|
+
# Y if both modified and unmodified aminoacid could be present in the
|
1125
|
+
# dataset, N if only modified aminoacid can be present
|
1126
|
+
attr_accessor :variable
|
1127
|
+
# whether modification can reside only at protein terminus (specified 'n',
|
1128
|
+
# 'c', or 'nc')
|
1129
|
+
attr_accessor :peptide_terminus
|
1130
|
+
# MSial symbol used by search engine to designate this modification
|
1131
|
+
attr_accessor :symbol
|
1132
|
+
# Y if each peptide must have only modified or unmodified aminoacid, N if a
|
1133
|
+
# peptide may contain both modified and unmodified aminoacid
|
1134
|
+
attr_accessor :binary
|
1135
|
+
|
1136
|
+
def initialize(hash=nil)
|
1137
|
+
instance_var_set_from_hash(hash) if hash # can use unless there are weird methods
|
1138
|
+
end
|
1139
|
+
|
1140
|
+
def to_pepxml
|
1141
|
+
# note massdiff
|
1142
|
+
short_element_xml_and_att_string("aminoacid_modification", "aminoacid=\"#{aminoacid}\" massdiff=\"#{massdiff.to_plus_minus_string}\" mass=\"#{mass}\" variable=\"#{variable}\" peptide_terminus=\"#{peptide_terminus}\" symbol=\"#{symbol}\" binary=\"#{binary}\"")
|
1143
|
+
end
|
1144
|
+
|
1145
|
+
end
|
1146
|
+
|
1147
|
+
# Modified aminoacid, static or variable
|
1148
|
+
class Sequest::PepXML::TerminalModification
|
1149
|
+
include SpecIDXML
|
1150
|
+
|
1151
|
+
# n for N-terminus, c for C-terminus
|
1152
|
+
attr_accessor :terminus
|
1153
|
+
# Mass difference with respect to unmodified terminus
|
1154
|
+
attr_accessor :massdiff
|
1155
|
+
# Mass of modified terminus
|
1156
|
+
attr_accessor :mass
|
1157
|
+
# Y if both modified and unmodified terminus could be present in the
|
1158
|
+
# dataset, N if only modified terminus can be present
|
1159
|
+
attr_accessor :variable
|
1160
|
+
# MSial symbol used by search engine to designate this modification
|
1161
|
+
attr_accessor :symbol
|
1162
|
+
# whether modification can reside only at protein terminus (specified n or
|
1163
|
+
# c)
|
1164
|
+
attr_accessor :protein_terminus
|
1165
|
+
attr_accessor :description
|
1166
|
+
|
1167
|
+
def initialize(hash=nil)
|
1168
|
+
instance_var_set_from_hash(hash) if hash # can use unless there are weird methods
|
1169
|
+
end
|
1170
|
+
|
1171
|
+
def to_pepxml
|
1172
|
+
#short_element_xml_from_instance_vars("terminal_modification")
|
1173
|
+
short_element_xml_and_att_string("terminal_modification", "terminus=\"#{terminus}\" massdiff=\"#{massdiff.to_plus_minus_string}\" mass=\"#{mass}\" variable=\"#{variable}\" symbol=\"#{symbol}\" protein_terminus=\"#{protein_terminus}\" description=\"#{description}\"")
|
1174
|
+
end
|
1175
|
+
end
|
1176
|
+
|
1177
|
+
|
1178
|
+
class Sequest::PepXML::SearchDatabase
|
1179
|
+
include SpecIDXML
|
1180
|
+
attr_accessor :local_path
|
1181
|
+
attr_writer :seq_type
|
1182
|
+
# Takes a SequestParams object
|
1183
|
+
# Sets :local_path from the params object attr :database
|
1184
|
+
def initialize(params=nil, args=nil)
|
1185
|
+
@seq_type = nil
|
1186
|
+
if params
|
1187
|
+
@local_path = params.database
|
1188
|
+
end
|
1189
|
+
if args ; set_from_hash(args) end
|
1190
|
+
end
|
1191
|
+
|
1192
|
+
def seq_type
|
1193
|
+
if @seq_type ; @seq_type
|
1194
|
+
else
|
1195
|
+
if @local_path =~ /\.fasta/
|
1196
|
+
'AA'
|
1197
|
+
else
|
1198
|
+
abort "Don't recognize type from your database local path: #{@local_path}"
|
1199
|
+
end
|
1200
|
+
end
|
1201
|
+
end
|
1202
|
+
|
1203
|
+
def to_pepxml
|
1204
|
+
short_element_xml_and_att_string(:search_database, "local_path=\"#{local_path}\" type=\"#{seq_type}\"")
|
1205
|
+
end
|
1206
|
+
|
1207
|
+
end
|
1208
|
+
|
1209
|
+
Sequest::PepXML::SpectrumQuery = Arrayclass.new(%w(spectrum start_scan end_scan precursor_neutral_mass index assumed_charge search_results pepxml_version))
|
1210
|
+
|
1211
|
+
class Sequest::PepXML::SpectrumQuery
|
1212
|
+
include SpecIDXML
|
1213
|
+
|
1214
|
+
############################################################
|
1215
|
+
# FOR PEPXML:
|
1216
|
+
############################################################
|
1217
|
+
def to_pepxml
|
1218
|
+
case Sequest::PepXML.pepxml_version
|
1219
|
+
when 18
|
1220
|
+
element_xml("spectrum_query", [:spectrum, :start_scan, :end_scan, :precursor_neutral_mass, :assumed_charge, :index]) do
|
1221
|
+
search_results.collect { |sr| sr.to_pepxml }.join
|
1222
|
+
end
|
1223
|
+
end
|
1224
|
+
end
|
1225
|
+
|
1226
|
+
def self.from_pepxml_node(node)
|
1227
|
+
self.new.from_pepxml_node(node)
|
1228
|
+
end
|
1229
|
+
|
1230
|
+
def from_pepxml_node(node)
|
1231
|
+
self[0] = node['spectrum']
|
1232
|
+
self[1] = node['start_scan'].to_i
|
1233
|
+
self[2] = node['end_scan'].to_i
|
1234
|
+
self[3] = node['precursor_neutral_mass'].to_f
|
1235
|
+
self[4] = node['index'].to_i
|
1236
|
+
self[5] = node['assumed_charge'].to_i
|
1237
|
+
self
|
1238
|
+
end
|
1239
|
+
|
1240
|
+
# Returns the precursor_neutral based on the scans and an array indexed by
|
1241
|
+
# scan numbers. first and last scan and charge should be integers.
|
1242
|
+
# This is the precursor_mz - h_plus!
|
1243
|
+
# by=:prec_mz_arr|:deltamass
|
1244
|
+
# if prec_mz_arr then the following arguments must be supplied:
|
1245
|
+
# :first_scan = int, :last_scan = int, :prec_mz_arr = array with the precursor
|
1246
|
+
# m/z for each product scan, :charge = int
|
1247
|
+
# if deltamass then the following arguments must be supplied:
|
1248
|
+
# m_plus_h = float, deltamass = float
|
1249
|
+
# For both flavors, a final additional argument 'average_weights'
|
1250
|
+
# can be used. If true (default), average weights will be used, if false,
|
1251
|
+
# monoisotopic weights (currently this is simply the mass of the proton)
|
1252
|
+
def self.calc_precursor_neutral_mass(by, *args)
|
1253
|
+
average_weights = true
|
1254
|
+
case by
|
1255
|
+
when :prec_mz_arr
|
1256
|
+
(first_scan, last_scan, prec_mz_arr, charge, average_weights) = args
|
1257
|
+
when :deltamass
|
1258
|
+
(m_plus_h, deltamass, average_weights) = args
|
1259
|
+
end
|
1260
|
+
|
1261
|
+
if average_weights
|
1262
|
+
mass_h_plus = SpecID::AVG[:h_plus]
|
1263
|
+
else
|
1264
|
+
mass_h_plus = SpecID::MONO[:h_plus]
|
1265
|
+
end
|
1266
|
+
|
1267
|
+
case by
|
1268
|
+
when :prec_mz_arr
|
1269
|
+
mz = nil
|
1270
|
+
if first_scan != last_scan
|
1271
|
+
sum = 0.0
|
1272
|
+
tot_num = 0
|
1273
|
+
(first_scan..last_scan).each do |scan|
|
1274
|
+
val = prec_mz_arr[scan]
|
1275
|
+
if val # if the scan is not an mslevel 2
|
1276
|
+
sum += val
|
1277
|
+
tot_num += 1
|
1278
|
+
end
|
1279
|
+
end
|
1280
|
+
mz = sum/tot_num
|
1281
|
+
else
|
1282
|
+
mz = prec_mz_arr[first_scan]
|
1283
|
+
end
|
1284
|
+
charge * (mz - mass_h_plus)
|
1285
|
+
when :deltamass
|
1286
|
+
m_plus_h - mass_h_plus + deltamass
|
1287
|
+
else
|
1288
|
+
abort "don't recognize 'by' in calc_precursor_neutral_mass: #{by}"
|
1289
|
+
end
|
1290
|
+
end
|
1291
|
+
|
1292
|
+
end
|
1293
|
+
|
1294
|
+
|
1295
|
+
Sequest::PepXML::SearchHit = Arrayclass.new( %w( hit_rank peptide peptide_prev_aa peptide_next_aa protein num_tot_proteins num_matched_ions tot_num_ions calc_neutral_pep_mass massdiff num_tol_term num_missed_cleavages is_rejected deltacnstar xcorr deltacn spscore sprank modification_info spectrum_query) )
|
1296
|
+
|
1297
|
+
# 0=hit_rank 1=peptide 2=peptide_prev_aa 3=peptide_next_aa 4=protein 5=num_tot_proteins 6=num_matched_ions 7=tot_num_ions 8=calc_neutral_pep_mass 9=massdiff 10=num_tol_term 11=num_missed_cleavages 12=is_rejected 13=deltacnstar 14=xcorr 15=deltacn 16=spscore 17=sprank 18=modification_info 19=spectrum_query
|
1298
|
+
|
1299
|
+
class Sequest::PepXML::SearchHit
|
1300
|
+
include SpecID::Pep
|
1301
|
+
include SpecIDXML
|
1302
|
+
|
1303
|
+
Non_standard_amino_acid_char_re = /[^A-Z\.\-]/
|
1304
|
+
|
1305
|
+
def aaseq ; self[1] end
|
1306
|
+
def aaseq=(arg) ; self[1] = arg end
|
1307
|
+
|
1308
|
+
# These are all search_score elements:
|
1309
|
+
|
1310
|
+
# 1 if there is no second ranked hit, 0 otherwise
|
1311
|
+
|
1312
|
+
tmp_verb = $VERBOSE
|
1313
|
+
$VERBOSE = nil
|
1314
|
+
def initialize(hash=nil)
|
1315
|
+
super(self.class.size)
|
1316
|
+
if hash
|
1317
|
+
self[0,20] = [hash[:hit_rank], hash[:peptide], hash[:peptide_prev_aa], hash[:peptide_next_aa], hash[:protein], hash[:num_tot_proteins], hash[:num_matched_ions], hash[:tot_num_ions], hash[:calc_neutral_pep_mass], hash[:massdiff], hash[:num_tol_term], hash[:num_missed_cleavages], hash[:is_rejected], hash[:deltacnstar], hash[:xcorr], hash[:deltacn], hash[:spscore], hash[:sprank], hash[:modification_info], hash[:spectrum_query]]
|
1318
|
+
end
|
1319
|
+
self
|
1320
|
+
end
|
1321
|
+
$VERBOSE = tmp_verb
|
1322
|
+
|
1323
|
+
undef_method :inspect
|
1324
|
+
def inspect
|
1325
|
+
var = @@attributes.map do |m| "#{m}:#{self.send(m)}" end.join(" ")
|
1326
|
+
"#<SearchHit #{var}>"
|
1327
|
+
end
|
1328
|
+
|
1329
|
+
# Takes ions in the form XX/YY and returns [XX.to_i, YY.to_i]
|
1330
|
+
def self.split_ions(ions)
|
1331
|
+
ions.split("/").map {|ion| ion.to_i }
|
1332
|
+
end
|
1333
|
+
|
1334
|
+
def search_score_xml(symbol)
|
1335
|
+
"#{tabs}<search_score name=\"#{symbol}\" value=\"#{send(symbol)}\"/>"
|
1336
|
+
end
|
1337
|
+
|
1338
|
+
def search_scores_xml(*symbol_list)
|
1339
|
+
symbol_list.collect do |sy|
|
1340
|
+
search_score_xml(sy)
|
1341
|
+
end.join("\n") + "\n"
|
1342
|
+
end
|
1343
|
+
|
1344
|
+
def to_pepxml
|
1345
|
+
mod_pepxml =
|
1346
|
+
if self[18]
|
1347
|
+
self[18].to_pepxml
|
1348
|
+
else
|
1349
|
+
''
|
1350
|
+
end
|
1351
|
+
|
1352
|
+
#string = element_xml_and_att_string("search_hit", [:hit_rank, :peptide, :peptide_prev_aa, :peptide_next_aa, :protein, :num_tot_proteins, :num_matched_ions, :tot_num_ions, :calc_neutral_pep_mass, :massdiff_as_string, :num_tol_term, :num_missed_cleavages, :is_rejected]) do
|
1353
|
+
# note the to_plus_minus_string
|
1354
|
+
#puts "MASSDIFF:"
|
1355
|
+
#p massdiff
|
1356
|
+
element_xml_and_att_string("search_hit", "hit_rank=\"#{hit_rank}\" peptide=\"#{peptide}\" peptide_prev_aa=\"#{peptide_prev_aa}\" peptide_next_aa=\"#{peptide_next_aa}\" protein=\"#{protein}\" num_tot_proteins=\"#{num_tot_proteins}\" num_matched_ions=\"#{num_matched_ions}\" tot_num_ions=\"#{tot_num_ions}\" calc_neutral_pep_mass=\"#{calc_neutral_pep_mass}\" massdiff=\"#{massdiff.to_plus_minus_string}\" num_tol_term=\"#{num_tol_term}\" num_missed_cleavages=\"#{num_missed_cleavages}\" is_rejected=\"#{is_rejected}\"") do
|
1357
|
+
mod_pepxml +
|
1358
|
+
search_scores_xml(:xcorr, :deltacn, :deltacnstar, :spscore, :sprank)
|
1359
|
+
end
|
1360
|
+
end
|
1361
|
+
|
1362
|
+
def from_pepxml_node(node)
|
1363
|
+
self[0] = node['hit_rank'].to_i
|
1364
|
+
self[1] = node['peptide']
|
1365
|
+
self[2] = node['peptide_prev_aa']
|
1366
|
+
self[3] = node['peptide_next_aa']
|
1367
|
+
self[4] = node['protein'] ## will this be the string?? (yes, for now)
|
1368
|
+
self[5] = node['num_tot_proteins'].to_i
|
1369
|
+
self[6] = node['num_matched_ions'].to_i
|
1370
|
+
self[7] = node['tot_num_ions'].to_i
|
1371
|
+
self[8] = node['calc_neutral_pep_mass'].to_f
|
1372
|
+
self[9] = node['massdiff'].to_f
|
1373
|
+
self[10] = node['num_tol_term'].to_i
|
1374
|
+
self[11] = node['num_missed_cleavages'].to_i
|
1375
|
+
self[12] = node['is_rejected'].to_i
|
1376
|
+
self
|
1377
|
+
end
|
1378
|
+
|
1379
|
+
end
|
1380
|
+
|
1381
|
+
|
1382
|
+
Sequest::PepXML::SearchHit::ModificationInfo = Arrayclass.new(%w(modified_peptide mod_aminoacid_masses mod_nterm_mass mod_cterm_mass))
|
1383
|
+
|
1384
|
+
# Positions and masses of modifications
|
1385
|
+
class Sequest::PepXML::SearchHit::ModificationInfo
|
1386
|
+
include SpecIDXML
|
1387
|
+
|
1388
|
+
## Should be something like this:
|
1389
|
+
# <modification_info mod_nterm_mass=" " mod_nterm_mass=" " modified_peptide=" ">
|
1390
|
+
# <mod_aminoacid_mass position=" " mass=" "/>
|
1391
|
+
# </modification_info>
|
1392
|
+
|
1393
|
+
alias_method :masses, :mod_aminoacid_masses
|
1394
|
+
alias_method :masses=, :mod_aminoacid_masses=
|
1395
|
+
|
1396
|
+
# Mass of modified N terminus<
|
1397
|
+
#attr_accessor :mod_nterm_mass
|
1398
|
+
# Mass of modified C terminus<
|
1399
|
+
#attr_accessor :mod_cterm_mass
|
1400
|
+
# Peptide sequence (with indicated modifications) I'm assuming that the
|
1401
|
+
# native sequest indicators are OK here
|
1402
|
+
#attr_accessor :modified_peptide
|
1403
|
+
|
1404
|
+
# These are objects of type: ...ModAminoacidMass
|
1405
|
+
# position ranges from 1 to peptide length
|
1406
|
+
#attr_accessor :mod_aminoacid_masses
|
1407
|
+
|
1408
|
+
# Will escape any xml special chars in modified_peptide
|
1409
|
+
def to_pepxml
|
1410
|
+
## Collect the modifications:
|
1411
|
+
mod_strings = []
|
1412
|
+
if masses and masses.size > 0
|
1413
|
+
mod_strings = masses.map do |ar|
|
1414
|
+
"position=\"#{ar[0]}\" mass=\"#{ar[1]}\""
|
1415
|
+
end
|
1416
|
+
end
|
1417
|
+
## Create the attribute string:
|
1418
|
+
att_parts = []
|
1419
|
+
if mod_nterm_mass
|
1420
|
+
att_parts << "mod_nterm_mass=\"#{mod_nterm_mass}\""
|
1421
|
+
end
|
1422
|
+
if mod_cterm_mass
|
1423
|
+
att_parts << "mod_cterm_mass=\"#{mod_cterm_mass}\""
|
1424
|
+
end
|
1425
|
+
if modified_peptide
|
1426
|
+
att_parts << "modified_peptide=\"#{escape_special_chars(modified_peptide)}\""
|
1427
|
+
end
|
1428
|
+
element_xml_and_att_string('modification_info', att_parts.join(" ")) do
|
1429
|
+
mod_strings.map {|st| short_element_xml_and_att_string('mod_aminoacid_mass', st) }.join
|
1430
|
+
end
|
1431
|
+
end
|
1432
|
+
|
1433
|
+
def self.from_pepxml_node(node)
|
1434
|
+
self.new.from_pepxml_node(node)
|
1435
|
+
end
|
1436
|
+
|
1437
|
+
# returns self
|
1438
|
+
def from_pepxml_node(node)
|
1439
|
+
self[0] = node['modified_peptide']
|
1440
|
+
self[2] = node['mod_nterm_mass']
|
1441
|
+
self[3] = node['mod_cterm_mass']
|
1442
|
+
masses = []
|
1443
|
+
node.children do |mass_n|
|
1444
|
+
masses << Sequest::PepXML::SearchHit::ModificationInfo::ModAminoacidMass.new([mass_n['position'].to_i, mass_n['mass'].to_f])
|
1445
|
+
end
|
1446
|
+
self[1] = masses
|
1447
|
+
self
|
1448
|
+
end
|
1449
|
+
|
1450
|
+
##
|
1451
|
+
|
1452
|
+
# <modification_info modified_peptide="GC[546]M[147]PSKEVLSAGAHR">
|
1453
|
+
# <mod_aminoacid_mass position="2" mass="545.7160"/>
|
1454
|
+
# <mod_aminoacid_mass position="3" mass="147.1926"/>
|
1455
|
+
# </modification_info>
|
1456
|
+
end
|
1457
|
+
|
1458
|
+
Sequest::PepXML::SearchHit::ModificationInfo::ModAminoacidMass = Arrayclass.new(%w(position mass))
|