mspire 0.1.5 → 0.1.7
Sign up to get free protection for your applications and to get access to all the features.
- data/Rakefile +5 -2
- data/bin/bioworks_to_pepxml.rb +84 -40
- data/bin/fasta_shaker.rb +100 -0
- data/bin/filter_spec_id.rb +185 -23
- data/bin/gi2annot.rb +2 -110
- data/bin/id_class_anal.rb +31 -21
- data/bin/id_precision.rb +12 -8
- data/bin/{false_positive_rate.rb → precision.rb} +1 -1
- data/bin/protein_summary.rb +55 -62
- data/changelog.txt +34 -0
- data/lib/align.rb +0 -1
- data/lib/fasta.rb +88 -24
- data/lib/gi.rb +114 -0
- data/lib/roc.rb +64 -58
- data/lib/spec_id/aa_freqs.rb +166 -0
- data/lib/spec_id/bioworks.rb +5 -1
- data/lib/spec_id/precision.rb +427 -0
- data/lib/spec_id/proph.rb +2 -2
- data/lib/spec_id/sequest.rb +810 -113
- data/lib/spec_id/srf.rb +486 -0
- data/lib/spec_id.rb +107 -23
- data/release_notes.txt +11 -0
- data/script/estimate_fpr_by_cysteine.rb +226 -0
- data/script/filter-peps.rb +3 -3
- data/script/find_cysteine_background.rb +137 -0
- data/script/gen_database_searching.rb +11 -7
- data/script/genuine_tps_and_probs.rb +136 -0
- data/script/top_hit_per_scan.rb +5 -2
- data/test/tc_aa_freqs.rb +59 -0
- data/test/tc_bioworks.rb +6 -1
- data/test/tc_bioworks_to_pepxml.rb +25 -18
- data/test/tc_fasta.rb +81 -3
- data/test/tc_fasta_shaker.rb +147 -0
- data/test/tc_gi.rb +20 -0
- data/test/tc_id_class_anal.rb +9 -12
- data/test/tc_id_precision.rb +12 -11
- data/test/{tc_false_positive_rate.rb → tc_precision.rb} +13 -22
- data/test/tc_protein_summary.rb +31 -22
- data/test/tc_roc.rb +95 -50
- data/test/tc_sequest.rb +212 -145
- data/test/tc_spec.rb +10 -5
- data/test/tc_spec_id.rb +0 -2
- data/test/tc_spec_id_xml.rb +36 -0
- data/test/tc_srf.rb +216 -0
- metadata +35 -21
- data/lib/spec_id/false_positive_rate.rb +0 -476
- data/test/tc_gi2annot.rb +0 -12
data/lib/spec_id/sequest.rb
CHANGED
@@ -6,6 +6,74 @@ require 'set_from_hash'
|
|
6
6
|
require 'spec_id/bioworks'
|
7
7
|
require 'instance_var_set_from_hash'
|
8
8
|
require 'spec/msrun'
|
9
|
+
require 'spec_id/srf'
|
10
|
+
|
11
|
+
class Numeric
|
12
|
+
# returns a string with a + or - on the front
|
13
|
+
def to_plus_minus_string
|
14
|
+
if self >= 0
|
15
|
+
'+' << self.to_s
|
16
|
+
else
|
17
|
+
'-' << self.to_s
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
21
|
+
|
22
|
+
##########################################
|
23
|
+
# NEED TO ADD MODIFICATIONS and generally verify pepxml creation!!! :
|
24
|
+
# HERE's an excerpt from an example file from tpp 2.9.2 that I'm going to follow:
|
25
|
+
=begin
|
26
|
+
<search_summary base_name="/regis/data3/search/akeller/LCQ/COMET/LIGHT/haloICAT2_41" search_engine="COMET" precursor_mass_type="average" fragment_mass_type="average">
|
27
|
+
<sequence_search_constraint sequence="C"/>
|
28
|
+
<aminoacid_modification aminoacid="C" massdiff="8.049" mass="553.765" variable="Y" binary="N"/>
|
29
|
+
<aminoacid_modification aminoacid="C" massdiff="442.5772" mass="545.7160" variable="N"/>
|
30
|
+
<aminoacid_modification aminoacid="M" massdiff="16.0000" mass="147.1926" variable="Y" binary="N" symbol="1"/>
|
31
|
+
<parameter name="peptide_mass_tol" value="3.0000"/>
|
32
|
+
<parameter name="peptide_mass_tol_units" value="DA"/>
|
33
|
+
<parameter name="num_output_lines" value="10"/>
|
34
|
+
<parameter name="remove_precursor_peak" value="0"/>
|
35
|
+
<parameter name="num_dup_headers" value="1"/>
|
36
|
+
<parameter name="email_address" value=""/>
|
37
|
+
<parameter name="ion_series" value="010000010"/>
|
38
|
+
<parameter name="max_num_var_mod_residues" value="3"/>
|
39
|
+
<parameter name="md5_check_sum" value="2547286a77a35abe2af3f2e9825ab814"/>
|
40
|
+
</search_summary>
|
41
|
+
=end
|
42
|
+
|
43
|
+
# and a guy with modifications:
|
44
|
+
=begin
|
45
|
+
<search_result spectrum="haloICAT2_41.1110.1110.2" start_scan="1110" end_scan="1110" precursor_neutral_mass="2000.6641" assumed_charge="2" index="28">
|
46
|
+
<search_hit hit_rank="1" peptide="GCMPSKEVLSAGAHR" peptide_prev_aa="R" peptide_next_aa="Y" protein="Chr_ORF0132" num_tot_proteins="1" num_matched_ions="19" tot_num_ions="30" calc_neutral_pep_mass="2001.3685" massdiff="-0.704" num_tol_term="2" num_missed_cleavages="1" is_rejected="0">
|
47
|
+
<modification_info modified_peptide="GC[546]M[147]PSKEVLSAGAHR">
|
48
|
+
<mod_aminoacid_mass position="2" mass="545.7160"/>
|
49
|
+
<mod_aminoacid_mass position="3" mass="147.1926"/>
|
50
|
+
</modification_info>
|
51
|
+
<search_score name="dotproduct" value="359"/>
|
52
|
+
<search_score name="delta" value="0.296"/>
|
53
|
+
<search_score name="deltastar" value="0"/>
|
54
|
+
<search_score name="zscore" value="5.290"/>
|
55
|
+
<search_score name="expect" value="0.000E+00"/>
|
56
|
+
<peptideprophet_result probability="0.9994" all_ntt_prob="(0.3713,0.4360,0.9994)">
|
57
|
+
<search_score_summary>
|
58
|
+
<parameter name="fval" value="3.4002"/>
|
59
|
+
<parameter name="ntt" value="2"/>
|
60
|
+
<parameter name="nmc" value="1"/>
|
61
|
+
<parameter name="massd" value="-0.704"/>
|
62
|
+
</search_score_summary>
|
63
|
+
</peptideprophet_result>
|
64
|
+
=end
|
65
|
+
|
66
|
+
# sequest.params option:
|
67
|
+
# diff_search_options = 15.994910 M 0.000000 C 0.000000 M 0.000000 X 0.000000 T 0.000000 Y
|
68
|
+
# permanent mods are at the bottom: ...
|
69
|
+
# add_A_Alanine = 0.0000 ; added to A
|
70
|
+
# add_S_Serine = 0.0000 ; added to S
|
71
|
+
# add_P_Proline = 0.0000 ; added to P
|
72
|
+
# add_V_Valine = 0.0000 ; added to V
|
73
|
+
# add_T_Threonine = 0.0000 ; added to T
|
74
|
+
# ...
|
75
|
+
|
76
|
+
|
9
77
|
|
10
78
|
module SpecID::Sequest; end
|
11
79
|
class SpecID::Sequest::PepXML; end
|
@@ -26,8 +94,12 @@ class SpecID::Sequest::PepXML::MSMSPipelineAnalysis
|
|
26
94
|
@xmlns = nil
|
27
95
|
@xmlns_xsi = nil
|
28
96
|
@xsi_schema_location = nil
|
29
|
-
|
30
|
-
|
97
|
+
if hash
|
98
|
+
self.set_from_hash(hash)
|
99
|
+
end
|
100
|
+
if block_given?
|
101
|
+
@msms_run_summary = yield
|
102
|
+
end
|
31
103
|
end
|
32
104
|
|
33
105
|
# if no date string given, then it will set to Time.now
|
@@ -80,7 +152,8 @@ class SpecID::Sequest::PepXML::MSMSRunSummary
|
|
80
152
|
include SpecIDXML
|
81
153
|
|
82
154
|
# the version of TPP you are using (determines xml output)
|
83
|
-
# The name of the pep xml file (without extension)
|
155
|
+
# The name of the pep xml file (without extension) (but this is a long
|
156
|
+
# filename!!!)
|
84
157
|
attr_accessor :base_name
|
85
158
|
# The name of the mass spec manufacturer
|
86
159
|
attr_accessor :ms_manufacturer
|
@@ -104,7 +177,9 @@ class SpecID::Sequest::PepXML::MSMSRunSummary
|
|
104
177
|
# set to the return value of the block
|
105
178
|
def initialize(hash=nil)
|
106
179
|
@spectrum_queries = []
|
107
|
-
|
180
|
+
if hash
|
181
|
+
instance_var_set_from_hash(hash)
|
182
|
+
end
|
108
183
|
if block_given? ; @spectrum_queries = yield end
|
109
184
|
end
|
110
185
|
|
@@ -137,6 +212,8 @@ end
|
|
137
212
|
|
138
213
|
class SpecID::Sequest::PepXML
|
139
214
|
include SpecIDXML
|
215
|
+
|
216
|
+
## CREATE a default version for the entire class
|
140
217
|
class << self
|
141
218
|
attr_accessor :pepxml_version
|
142
219
|
end
|
@@ -144,7 +221,11 @@ class SpecID::Sequest::PepXML
|
|
144
221
|
self.pepxml_version = DEF_VERSION # default version
|
145
222
|
|
146
223
|
attr_accessor :pepxml_version, :msms_pipeline_analysis
|
224
|
+
## the full path name (no extension)
|
147
225
|
attr_accessor :base_name
|
226
|
+
attr_accessor :h_plus
|
227
|
+
attr_accessor :avg_parent
|
228
|
+
|
148
229
|
#attr_accessor :spectrum_queries, :params, :base_name, :search_engine, :database, :raw_data_type, :raw_data, :out_data_type, :out_data, :sample_enzyme, :pepxml_version
|
149
230
|
|
150
231
|
# returns an array of spectrum queries
|
@@ -153,10 +234,29 @@ class SpecID::Sequest::PepXML
|
|
153
234
|
end
|
154
235
|
|
155
236
|
# msms_pipeline_analysis is set to the result of the yielded block
|
156
|
-
|
237
|
+
# and set_mono_or_avg is called with params if given
|
238
|
+
def initialize(pepxml_version=DEF_VERSION, sequest_params_obj=nil)
|
157
239
|
self.class.pepxml_version = pepxml_version
|
158
|
-
|
159
|
-
|
240
|
+
if sequest_params_obj
|
241
|
+
set_mono_or_avg(sequest_params_obj)
|
242
|
+
end
|
243
|
+
if block_given?
|
244
|
+
@msms_pipeline_analysis = yield
|
245
|
+
@base_name = @msms_pipeline_analysis.msms_run_summary.base_name
|
246
|
+
end
|
247
|
+
end
|
248
|
+
|
249
|
+
# sets @h_plus and @avg_parent from the sequest params object
|
250
|
+
def set_mono_or_avg(sequest_params_obj)
|
251
|
+
case sequest_params_obj.precursor_mass_type
|
252
|
+
when "monoisotopic" ; @avg_parent = false
|
253
|
+
else ; @avg_parent = true
|
254
|
+
end
|
255
|
+
|
256
|
+
case @avg_parent
|
257
|
+
when true ; @h_plus = SpecID::AVG[:h_plus]
|
258
|
+
when false ; @h_plus = SpecID::MONO[:h_plus]
|
259
|
+
end
|
160
260
|
end
|
161
261
|
|
162
262
|
def date
|
@@ -203,6 +303,190 @@ class SpecID::Sequest::PepXML
|
|
203
303
|
end
|
204
304
|
end
|
205
305
|
|
306
|
+
|
307
|
+
Default_Options = {
|
308
|
+
:out_path => nil,
|
309
|
+
:backup_db_path => '/project/marcotte/marcotte/ms/database',
|
310
|
+
# a PepXML option
|
311
|
+
:pepxml_version => DEF_VERSION,
|
312
|
+
## MSMSRunSummary options:
|
313
|
+
# string must be recognized in sample_enzyme.rb
|
314
|
+
# or create your own SampleEnzyme object
|
315
|
+
:sample_enzyme => 'trypsin',
|
316
|
+
:ms_manufacturer => 'ThermoFinnigan',
|
317
|
+
:ms_model => 'LCQ Deca XP',
|
318
|
+
:ms_ionization => 'ESI',
|
319
|
+
:ms_mass_analyzer => 'Ion Trap',
|
320
|
+
:ms_detector => 'UNKNOWN',
|
321
|
+
:raw_data_type => "raw",
|
322
|
+
:raw_data => ".mzXML", ## even if you don't have it?
|
323
|
+
## SearchSummary options:
|
324
|
+
:out_data_type => "out", ## may be srf?? don't think pepxml recognizes this yet
|
325
|
+
:out_data => ".tgz" ## may be srf??
|
326
|
+
}
|
327
|
+
|
328
|
+
# will dynamically set :ms_model and :ms_mass_analyzer from srf info
|
329
|
+
# (ignoring defaults or anything passed in) for LTQ Orbitrap
|
330
|
+
# and LCQ Deca XP
|
331
|
+
# See SRF::Sequest::PepXML::Default_Options hash for defaults
|
332
|
+
# unless given, the out_path will be given as the path of the srf_file
|
333
|
+
def self.new_from_srf(srf_file, opts={})
|
334
|
+
opts = Default_Options.merge(opts)
|
335
|
+
|
336
|
+
## set the outpath
|
337
|
+
out_path = opts.delete(:out_path)
|
338
|
+
unless out_path
|
339
|
+
out_path = File.dirname(srf_file)
|
340
|
+
end
|
341
|
+
|
342
|
+
## read the srf file
|
343
|
+
srf = SRF.new(srf_file)
|
344
|
+
|
345
|
+
params = srf.params
|
346
|
+
|
347
|
+
## check to see if we need backup_db
|
348
|
+
backup_db_path = opts.delete(:backup_db_path)
|
349
|
+
unless File.exist? params.database
|
350
|
+
params.database_path = backup_db_path
|
351
|
+
end
|
352
|
+
|
353
|
+
#######################################################################
|
354
|
+
# PREPARE THE OPTIONS:
|
355
|
+
#######################################################################
|
356
|
+
## remove items from the options hash that don't belong to
|
357
|
+
ppxml_version = opts.delete(:pepxml_version)
|
358
|
+
out_data_type = opts.delete(:out_data_type)
|
359
|
+
out_data = opts.delete(:out_data)
|
360
|
+
|
361
|
+
## Extract meta info from srf
|
362
|
+
bn_noext = base_name_noext(srf.header.raw_filename)
|
363
|
+
opts[:ms_model] = srf.header.model
|
364
|
+
case opts[:ms_model]
|
365
|
+
when /Orbitrap/
|
366
|
+
opts[:ms_mass_analyzer] = 'Orbitrap'
|
367
|
+
when /LCQ Deca XP/
|
368
|
+
opts[:ms_mass_analyzer] = 'Ion Trap'
|
369
|
+
end
|
370
|
+
|
371
|
+
## Create the base name
|
372
|
+
full_base_name_no_ext = make_base_name( File.expand_path(out_path), bn_noext)
|
373
|
+
opts[:base_name] = full_base_name_no_ext
|
374
|
+
|
375
|
+
## Create the search summary:
|
376
|
+
search_summary_options = {
|
377
|
+
:search_database => SpecID::Sequest::PepXML::SearchDatabase.new(params),
|
378
|
+
:base_name => full_base_name_no_ext,
|
379
|
+
:out_data_type => out_data_type,
|
380
|
+
:out_data => out_data
|
381
|
+
}
|
382
|
+
opts[:search_summary] = SpecID::Sequest::PepXML::SearchSummary.new( params, search_summary_options)
|
383
|
+
|
384
|
+
## Create the SampleEnzyme object if necessary
|
385
|
+
unless opts[:sample_enzyme].is_a? SampleEnzyme
|
386
|
+
opts[:sample_enzyme] = SampleEnzyme.new(opts[:sample_enzyme])
|
387
|
+
end
|
388
|
+
|
389
|
+
## Create the pepxml obj
|
390
|
+
pepxml_obj = SpecID::Sequest::PepXML.new(ppxml_version, params)
|
391
|
+
## name some common variables we'll need
|
392
|
+
h_plus = pepxml_obj.h_plus
|
393
|
+
avg_parent = pepxml_obj.avg_parent
|
394
|
+
|
395
|
+
#######################################################################
|
396
|
+
# CREATE the spectrum_queries_ar
|
397
|
+
#######################################################################
|
398
|
+
srf_index = srf.index
|
399
|
+
out_files = srf.out_files
|
400
|
+
spectrum_queries_arr = Array.new(srf.dta_files.size)
|
401
|
+
files_with_hits_index = 0 ## will end up being 1 indexed
|
402
|
+
srf.dta_files.each_with_index do |dta_file,i|
|
403
|
+
next if out_files[i].num_hits == 0
|
404
|
+
files_with_hits_index += 1
|
405
|
+
|
406
|
+
# Sort the hits
|
407
|
+
hits = out_files[i].hits
|
408
|
+
arr = hits.sort_by{|v| v.xcorr }
|
409
|
+
|
410
|
+
# Get proper deltacn and deltacnstar
|
411
|
+
# Prophet deltacn is not the same as the native Sequest deltacn
|
412
|
+
# It is the deltacn of the second best hit!
|
413
|
+
top_hit = arr.pop
|
414
|
+
second_hit = arr.last
|
415
|
+
if second_hit
|
416
|
+
top_hit[1] = second_hit[1]
|
417
|
+
deltacnstar = '0'
|
418
|
+
else
|
419
|
+
top_hit[1] = '1.0'
|
420
|
+
deltacnstar = '1'
|
421
|
+
end
|
422
|
+
|
423
|
+
## mass calculations:
|
424
|
+
precursor_neutral_mass = dta_file.mh - h_plus
|
425
|
+
calc_neutral_pep_mass = top_hit[0] - h_plus
|
426
|
+
massdiff = precursor_neutral_mass - calc_neutral_pep_mass
|
427
|
+
if massdiff >= 0 ; massdiff = "+" + massdiff.to_s
|
428
|
+
else ; massdiff = massdiff.to_s end
|
429
|
+
|
430
|
+
(start_scan, end_scan, charge) = srf_index[i]
|
431
|
+
sq_hash = {
|
432
|
+
:spectrum => [bn_noext, start_scan, end_scan, charge].join('.'),
|
433
|
+
:start_scan => start_scan,
|
434
|
+
:end_scan => end_scan,
|
435
|
+
:precursor_neutral_mass => precursor_neutral_mass,
|
436
|
+
:assumed_charge => charge,
|
437
|
+
:pepxml_version => ppxml_version,
|
438
|
+
:index => files_with_hits_index,
|
439
|
+
}
|
440
|
+
|
441
|
+
# NEED TO MODIFY SPLIT SEQUENCE TO DO MODS!
|
442
|
+
## THIS IS ALL INNER LOOP, so we make every effort at speed here:
|
443
|
+
(prevaa, pepseq, nextaa) = SpecID::Sequest::PepXML::SearchHit.prepare_sequence(top_hit[8])
|
444
|
+
# ind_keys = {:mh => 0, :deltacn => 1, :sp => 2, :xcorr => 3, :id => 4, :rsp => 5, :ions_matched => 6, :ions_total => 7, :peptide => 8, :reference => 9 }
|
445
|
+
|
446
|
+
sh_hash = {
|
447
|
+
:hit_rank => "1",
|
448
|
+
:peptide => pepseq,
|
449
|
+
:peptide_prev_aa => prevaa,
|
450
|
+
:peptide_next_aa => nextaa,
|
451
|
+
:protein => top_hit[9].split(" ").first,
|
452
|
+
:num_tot_proteins => top_hit[10],
|
453
|
+
:num_matched_ions => top_hit[6],
|
454
|
+
:tot_num_ions => top_hit[7],
|
455
|
+
:calc_neutral_pep_mass => calc_neutral_pep_mass,
|
456
|
+
:massdiff => massdiff,
|
457
|
+
:num_tol_term => SpecID::Sequest::PepXML::SearchHit.calc_num_tol_term(params, top_hit[8]),
|
458
|
+
:num_missed_cleavages => SpecID::Sequest::PepXML::SearchHit.calc_num_missed_cleavages(params, top_hit[8]),
|
459
|
+
:is_rejected => '0',
|
460
|
+
# These are search score attributes:
|
461
|
+
:xcorr => top_hit[3],
|
462
|
+
:deltacn => top_hit[1],
|
463
|
+
:deltacnstar => deltacnstar,
|
464
|
+
:spscore => top_hit[2],
|
465
|
+
:sprank => top_hit[5],
|
466
|
+
}
|
467
|
+
|
468
|
+
spectrum_queries_arr[files_with_hits_index] = SpecID::Sequest::PepXML::SpectrumQuery.new(sq_hash) do
|
469
|
+
search_result = SpecID::Sequest::PepXML::SearchResult.new do
|
470
|
+
[ SpecID::Sequest::PepXML::SearchHit.new(sh_hash) ] # there can be multiple hits
|
471
|
+
end # SearchResult
|
472
|
+
[search_result] # can be multiple
|
473
|
+
end
|
474
|
+
end
|
475
|
+
spectrum_queries_arr.compact!
|
476
|
+
|
477
|
+
#######################################################################
|
478
|
+
# ADD the pipeline analysis
|
479
|
+
#######################################################################
|
480
|
+
|
481
|
+
pipeline = SpecID::Sequest::PepXML::MSMSPipelineAnalysis.new({:date=>nil,:summary_xml=> bn_noext +'.xml'}) do
|
482
|
+
SpecID::Sequest::PepXML::MSMSRunSummary.new(opts) { spectrum_queries_arr }
|
483
|
+
end
|
484
|
+
pepxml_obj.msms_pipeline_analysis = pipeline
|
485
|
+
pepxml_obj.base_name = pipeline.msms_run_summary.base_name
|
486
|
+
pepxml_obj
|
487
|
+
end
|
488
|
+
|
489
|
+
# Takes bioworks 3.2/3.3 xml output (with no filters)
|
206
490
|
# Returns a list of PepXML objects
|
207
491
|
# msdata = path to mzXML files (or .timeIndex files) (or @TODO: path to sqt file(s))
|
208
492
|
# params = sequest.params file
|
@@ -246,6 +530,7 @@ class SpecID::Sequest::PepXML
|
|
246
530
|
|
247
531
|
## Create a hash of spectrum_query arrays by filename (this very big block):
|
248
532
|
spectrum_queries_by_base_name = {}
|
533
|
+
pepxml_objs_by_base_name = {}
|
249
534
|
# Hash by the filenames to split into filenames:
|
250
535
|
bioworks.peps.hash_by(:base_name).each do |base_name, pep_arr|
|
251
536
|
|
@@ -262,7 +547,10 @@ class SpecID::Sequest::PepXML
|
|
262
547
|
abort "invalid BioworksBrowser version: #{x}"
|
263
548
|
end
|
264
549
|
|
265
|
-
|
550
|
+
pepxml_obj = SpecID::Sequest::PepXML.new(pepxml_version, params)
|
551
|
+
pepxml_objs_by_base_name[base_name] = pepxml_obj
|
552
|
+
|
553
|
+
spectrum_queries_ar = pep_arr.hash_by(:first_scan, :last_scan, :charge).collect do |key,arr|
|
266
554
|
|
267
555
|
|
268
556
|
# Sort_by_rank and take the top hit (to mimick out2summary):
|
@@ -270,28 +558,18 @@ class SpecID::Sequest::PepXML
|
|
270
558
|
top_pep = arr.pop
|
271
559
|
second_hit = arr.last # needed for deltacnstar
|
272
560
|
|
273
|
-
case params.precursor_mass_type
|
274
|
-
when "monoisotopic" ; avg_parent = false
|
275
|
-
else ; avg_parent = true
|
276
|
-
end
|
277
|
-
|
278
|
-
case avg_parent
|
279
|
-
when true ; h_plus = SpecID::AVG[:h_plus]
|
280
|
-
when false ; h_plus = SpecID::MONO[:h_plus]
|
281
|
-
end
|
282
561
|
|
283
|
-
|
284
562
|
case calc_prec_by
|
285
563
|
when :prec_mz_arr
|
286
|
-
precursor_neutral_mass = SpecID::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.to_i, avg_parent)
|
564
|
+
precursor_neutral_mass = SpecID::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.to_i, pepxml_obj.avg_parent)
|
287
565
|
when :deltamass
|
288
|
-
precursor_neutral_mass = SpecID::Sequest::PepXML::SpectrumQuery.calc_precursor_neutral_mass(calc_prec_by, top_pep.mass.to_f, top_pep.deltamass.to_f, avg_parent)
|
566
|
+
precursor_neutral_mass = SpecID::Sequest::PepXML::SpectrumQuery.calc_precursor_neutral_mass(calc_prec_by, top_pep.mass.to_f, top_pep.deltamass.to_f, pepxml_obj.avg_parent)
|
289
567
|
end
|
290
568
|
|
291
|
-
calc_neutral_pep_mass = (top_pep.mass.to_f - h_plus)
|
569
|
+
calc_neutral_pep_mass = (top_pep.mass.to_f - pepxml_obj.h_plus)
|
292
570
|
massdiff = precursor_neutral_mass - calc_neutral_pep_mass
|
293
571
|
if massdiff >= 0 ; massdiff = "+" + massdiff.to_s
|
294
|
-
else ; massdiff = massdiff.to_s end
|
572
|
+
else ; massdiff = massdiff.to_s end #already has a -
|
295
573
|
# deltacn & star:
|
296
574
|
# (NOTE: OLD?? out2summary wants the deltacn of the 2nd best hit.)
|
297
575
|
if second_hit
|
@@ -317,7 +595,7 @@ class SpecID::Sequest::PepXML
|
|
317
595
|
# NOTE: the bioworks mass is really M+H if two or more scans went
|
318
596
|
# into the search_hit; calc_neutral_pep_mass is simply the avg of
|
319
597
|
# precursor masses adjusted to be neutral
|
320
|
-
(prevaa, pepseq, nextaa) = SpecID::Sequest::PepXML::SearchHit.
|
598
|
+
(prevaa, pepseq, nextaa) = SpecID::Sequest::PepXML::SearchHit.prepare_sequence(top_pep.sequence)
|
321
599
|
(num_matched_ions, tot_num_ions) = SpecID::Sequest::PepXML::SearchHit.split_ions(top_pep.ions)
|
322
600
|
search_hit = SpecID::Sequest::PepXML::SearchHit.new({
|
323
601
|
:hit_rank => "1",
|
@@ -348,32 +626,36 @@ class SpecID::Sequest::PepXML
|
|
348
626
|
|
349
627
|
# create an index by spectrum as results end up typically in out2summary
|
350
628
|
# (I really dislike this order, however)
|
351
|
-
|
352
|
-
|
629
|
+
spectrum_queries_ar = spectrum_queries_ar.sort_by {|pep| pep.spectrum }
|
630
|
+
spectrum_queries_ar.each_with_index {|res,index| res.index = "#{index + 1}" }
|
353
631
|
|
354
|
-
spectrum_queries_by_base_name[base_name] =
|
632
|
+
spectrum_queries_by_base_name[base_name] = spectrum_queries_ar
|
355
633
|
end
|
356
634
|
|
357
|
-
|
635
|
+
modifications_string = bioworks.modifications
|
636
|
+
|
637
|
+
spectrum_queries_by_base_name.collect do |base_name, spectrum_queries_ar|
|
358
638
|
case pepxml_version
|
359
639
|
when 18
|
360
|
-
SpecID::Sequest::PepXML.new(
|
361
|
-
|
362
|
-
|
363
|
-
|
364
|
-
|
365
|
-
|
366
|
-
|
367
|
-
|
368
|
-
|
369
|
-
|
370
|
-
|
371
|
-
|
372
|
-
|
373
|
-
|
374
|
-
}) do spectrum_queries end
|
375
|
-
end
|
640
|
+
pipeline = SpecID::Sequest::PepXML::MSMSPipelineAnalysis.new({:date=>nil,:summary_xml=>base_name+'.xml'}) do
|
641
|
+
full_base_name_no_ext = self.make_base_name( File.expand_path(out_path), base_name)
|
642
|
+
SpecID::Sequest::PepXML::MSMSRunSummary.new({
|
643
|
+
:base_name => full_base_name_no_ext,
|
644
|
+
:ms_manufacturer => ms_manufacturer,
|
645
|
+
:ms_model => ms_model,
|
646
|
+
:ms_ionization => ms_ionization,
|
647
|
+
:ms_mass_analyzer => ms_mass_analyzer,
|
648
|
+
:ms_detector => ms_detector,
|
649
|
+
:raw_data_type => raw_data_type,
|
650
|
+
:raw_data => raw_data,
|
651
|
+
:sample_enzyme => SampleEnzyme.new(sample_enzyme),
|
652
|
+
:search_summary => SpecID::Sequest::PepXML::SearchSummary.new(params, modifications_string, {:search_database => SpecID::Sequest::PepXML::SearchDatabase.new(params), :base_name => full_base_name_no_ext, :out_data_type => out_data_type, :out_data => out_data}),
|
653
|
+
}) { spectrum_queries_ar }
|
376
654
|
end
|
655
|
+
pepxml_obj = pepxml_objs_by_base_name[base_name]
|
656
|
+
pepxml_obj.msms_pipeline_analysis = pipeline
|
657
|
+
pepxml_obj.base_name = pipeline.msms_run_summary.base_name
|
658
|
+
pepxml_obj
|
377
659
|
when 0
|
378
660
|
## @TODO: NEED TO REVAMP THIS:
|
379
661
|
# SpecID::Sequest::PepXML.new(pepxml_version).set_from_hash({
|
@@ -429,6 +711,14 @@ class SpecID::Sequest::PepXML
|
|
429
711
|
string
|
430
712
|
end
|
431
713
|
|
714
|
+
# given any kind of filename (from windows or whatever)
|
715
|
+
# returns the base of the filename with no file extension
|
716
|
+
def self.base_name_noext(file)
|
717
|
+
file.gsub!("\\", '/')
|
718
|
+
File.basename(file).sub(/\.[\w^\.]+$/, '')
|
719
|
+
end
|
720
|
+
|
721
|
+
|
432
722
|
end # PepXML
|
433
723
|
|
434
724
|
##
|
@@ -461,6 +751,15 @@ class SpecID::Sequest::Params
|
|
461
751
|
one,two = line.split @@param_re
|
462
752
|
two,comment = two.split @@param_two_split
|
463
753
|
hash[one] = two.rstrip
|
754
|
+
# it is necessary to add this break so that params files inside srf
|
755
|
+
# files can be read. This will terminate the reading at the end of
|
756
|
+
# the file even though there are more lines
|
757
|
+
if line =~ /added to U/ || line =~ /digest_mass_range/## Will only work on bioworks 3.2 & 3.3 (bioworks 3.1 last line => Elastase/Tryp...)
|
758
|
+
break
|
759
|
+
end
|
760
|
+
if line =~ /digest_mass_range/ # there is no space in the srf params files
|
761
|
+
break
|
762
|
+
end
|
464
763
|
else
|
465
764
|
break
|
466
765
|
end
|
@@ -468,17 +767,26 @@ class SpecID::Sequest::Params
|
|
468
767
|
hash
|
469
768
|
end
|
470
769
|
|
770
|
+
# returns self
|
771
|
+
def parse_handle(fh)
|
772
|
+
sequest_line = fh.gets #[SEQUEST]
|
773
|
+
@opts = grab_params(fh)
|
774
|
+
@opts["search_engine"] = "SEQUEST"
|
775
|
+
@mods = grab_params(fh)
|
776
|
+
|
777
|
+
## this gets rid of the .hdr postfix on indexed databases
|
778
|
+
@opts["first_database_name"] = @opts["first_database_name"].sub(/\.hdr$/, '')
|
779
|
+
self
|
780
|
+
end
|
781
|
+
|
471
782
|
## parses file
|
472
783
|
## and drops the .hdr behind indexed fasta files
|
784
|
+
## returns self
|
473
785
|
def parse(file)
|
474
786
|
File.open(file) do |fh|
|
475
|
-
|
476
|
-
@opts = grab_params(fh)
|
477
|
-
@opts["search_engine"] = "SEQUEST"
|
478
|
-
@mods = grab_params(fh)
|
787
|
+
parse_handle(fh)
|
479
788
|
end
|
480
|
-
|
481
|
-
@opts["first_database_name"] = @opts["first_database_name"].sub(/\.hdr$/, '')
|
789
|
+
self
|
482
790
|
end
|
483
791
|
|
484
792
|
# returns( split_after, except_before)
|
@@ -569,6 +877,17 @@ class SpecID::Sequest::Params
|
|
569
877
|
@opts["first_database_name"]
|
570
878
|
end
|
571
879
|
|
880
|
+
# returns the appropriate aminoacid mass lookup table (in spec_id.rb SpecID::MONO or
|
881
|
+
# SpecID::AVG based on precursor_mass_type
|
882
|
+
def mass_table
|
883
|
+
case precursor_mass_type
|
884
|
+
when 'average'
|
885
|
+
SpecID::AVG
|
886
|
+
when 'monoisotopic'
|
887
|
+
SpecID::MONO
|
888
|
+
end
|
889
|
+
end
|
890
|
+
|
572
891
|
# at least in Bioworks 3.2, the First number after the enzyme
|
573
892
|
# is the indication of the enzymatic end stringency (required):
|
574
893
|
# 1 = Fully enzymatic
|
@@ -628,7 +947,7 @@ class SpecID::Sequest::PepXML::SearchResult
|
|
628
947
|
attr_accessor :search_hits
|
629
948
|
|
630
949
|
# if block given, then search_hits set to return value
|
631
|
-
def initialize
|
950
|
+
def initialize
|
632
951
|
if block_given? ; @search_hits = yield
|
633
952
|
else ; @search_hits = [] end
|
634
953
|
end
|
@@ -646,13 +965,16 @@ class SpecID::Sequest::PepXML::SearchSummary
|
|
646
965
|
attr_accessor :base_name
|
647
966
|
attr_accessor :out_data_type
|
648
967
|
attr_accessor :out_data
|
968
|
+
attr_accessor :modifications
|
649
969
|
# A SearchDatabase object (responds to :local_path and :type)
|
650
970
|
attr_accessor :search_database
|
651
971
|
# if given a sequest params object, then will set the following attributes:
|
652
972
|
# args is a hash of parameters
|
653
|
-
|
973
|
+
# modifications_string -> See Modifications
|
974
|
+
def initialize(params, modifications_string='', args=nil)
|
654
975
|
@search_id = nil
|
655
976
|
@params = params
|
977
|
+
@modifications = SpecID::Sequest::PepXML::Modifications.new(params, modifications_string)
|
656
978
|
if args ; set_from_hash(args) end
|
657
979
|
end
|
658
980
|
|
@@ -665,16 +987,304 @@ class SpecID::Sequest::PepXML::SearchSummary
|
|
665
987
|
else ; '1' end
|
666
988
|
end
|
667
989
|
|
990
|
+
|
668
991
|
def to_pepxml
|
669
992
|
element_xml(:search_summary, [:base_name, :search_engine, :precursor_mass_type, :fragment_mass_type, :out_data_type, :out_data, :search_id]) do
|
670
993
|
search_database.to_pepxml +
|
671
994
|
short_element_xml(:enzymatic_search_constraint, [:enzyme, :max_num_internal_cleavages, :min_number_termini]) +
|
995
|
+
@modifications.to_pepxml +
|
672
996
|
@params.pepxml_parameters
|
673
997
|
end
|
674
998
|
end
|
675
999
|
|
676
1000
|
end
|
677
1001
|
|
1002
|
+
class SpecID::Sequest::PepXML::Modifications
|
1003
|
+
include SpecIDXML
|
1004
|
+
|
1005
|
+
# sequest params object
|
1006
|
+
attr_accessor :params
|
1007
|
+
# array holding AAModifications
|
1008
|
+
attr_accessor :aa_mods
|
1009
|
+
# array holding TerminalModifications
|
1010
|
+
attr_accessor :term_mods
|
1011
|
+
# a hash of all differential modifications present by aa_one_letter_symbol
|
1012
|
+
# and special_symbol. This is NOT the mass difference but the total mass {
|
1013
|
+
# 'M*' => 155.5, 'S@' => 190.3 }. NOTE: Since the termini are dependent on
|
1014
|
+
# the amino acid sequence, they are give the *differential* mass. The
|
1015
|
+
# termini are given the special symbol as in sequest e.g. '[' => 12.22, #
|
1016
|
+
# cterminus ']' => 14.55 # nterminus
|
1017
|
+
attr_accessor :masses_by_diff_mod_hash
|
1018
|
+
# a hash, key is [AA_one_letter_symbol.to_sym, difference.to_f]
|
1019
|
+
# values are the special_symbols
|
1020
|
+
attr_accessor :mod_symbols_hash
|
1021
|
+
|
1022
|
+
# The modification symbols string looks like this:
|
1023
|
+
# (M* +15.90000) (M# +29.00000) (S@ +80.00000) (C^ +12.00000) (ct[ +12.33000) (nt] +14.20000)
|
1024
|
+
# ct is cterminal peptide (differential)
|
1025
|
+
# nt is nterminal peptide (differential)
|
1026
|
+
# the C is just cysteine
|
1027
|
+
# will set_modifications and masses_by_diff_mod hash
|
1028
|
+
def initialize(params, modification_symbols_string='')
|
1029
|
+
@params = params
|
1030
|
+
set_modifications(params, modification_symbols_string)
|
1031
|
+
end
|
1032
|
+
|
1033
|
+
# set the masses_by_diff_mod and mod_symbols_hash from
|
1034
|
+
def set_hashes(modification_symbols_string)
|
1035
|
+
@mod_symbols_hash = {}
|
1036
|
+
@masses_by_diff_mod = {}
|
1037
|
+
if modification_symbols_string == nil || modification_symbols_string == ''
|
1038
|
+
return nil
|
1039
|
+
end
|
1040
|
+
table = @params.mass_table
|
1041
|
+
modification_symbols_string.split(/\)\s+\(/).each do |mod|
|
1042
|
+
if mod =~ /\(?(\w{1,2})(.) (.[\d\.]+)\)?/
|
1043
|
+
aa_as_sym = $1.to_sym,
|
1044
|
+
@mod_symbols_hash[[aa_as_sym, $3.to_f]] = $2.dup
|
1045
|
+
if $1 == 'ct' || $1 == 'nt'
|
1046
|
+
@masses_by_diff_mod[$2] = $3.to_f
|
1047
|
+
else
|
1048
|
+
@masses_by_diff_mod[$1+$2] = $3.to_f + table[aa_as_sym]
|
1049
|
+
end
|
1050
|
+
end
|
1051
|
+
end
|
1052
|
+
end
|
1053
|
+
|
1054
|
+
# given a bare peptide (no end pieces) returns a ModificationInfo object
|
1055
|
+
# e.g. given "]PEPT*IDE", NOT 'K.PEPTIDE.R'
|
1056
|
+
# if there are no modifications, returns nil
|
1057
|
+
def modification_info(peptide)
|
1058
|
+
if @masses_by_diff_mod.size == 0
|
1059
|
+
return nil
|
1060
|
+
end
|
1061
|
+
hash[:modified_peptide] = peptide.dup
|
1062
|
+
hash = {}
|
1063
|
+
hsh = @masses_by_diff_mod
|
1064
|
+
table = @params.mass_table
|
1065
|
+
h = table[:h] # this? or h_plus ??
|
1066
|
+
oh = table[:o] + h
|
1067
|
+
## only the termini can match a single char
|
1068
|
+
if hsh.key? peptide[0,1]
|
1069
|
+
# AA + H + differential_mod
|
1070
|
+
hash[:mod_nterm_mass] = table[peptide[1,1].to_sym] + h + hsh[peptide[0,1]]
|
1071
|
+
peptide.slice!( 1..-1 )
|
1072
|
+
end
|
1073
|
+
if hsh.key? peptide[-1,1]
|
1074
|
+
# AA + OH + differential_mod
|
1075
|
+
hash[:mod_cterm_mass] = table[peptide[-2,1].to_sym] + oh + hsh[peptide[-1,1]]
|
1076
|
+
peptide.slice!( 0..-2 )
|
1077
|
+
end
|
1078
|
+
mod_array = []
|
1079
|
+
(0...peptide.size).each do |i|
|
1080
|
+
if hsh.key? peptide[i,2]
|
1081
|
+
mod_array << [ i+1 , hsh[peptide[i,2]] ]
|
1082
|
+
end
|
1083
|
+
end
|
1084
|
+
if mod_array.size > 0
|
1085
|
+
hash[:mod_aminoacid_mass_array] = mod_array
|
1086
|
+
end
|
1087
|
+
if hash.size > 0
|
1088
|
+
SpecID::Sequest::PepXML::SearchHit::ModificationInfo.new(hash)
|
1089
|
+
else
|
1090
|
+
nil
|
1091
|
+
end
|
1092
|
+
end
|
1093
|
+
|
1094
|
+
# 1. sets aa_mods and term_mods from a sequest params object
|
1095
|
+
# 2. sets @params
|
1096
|
+
# 3. sets @masses_by_diff_mod
|
1097
|
+
def set_modifications(params, modification_symbols_string)
|
1098
|
+
@params = params
|
1099
|
+
|
1100
|
+
set_hashes(modification_symbols_string)
|
1101
|
+
|
1102
|
+
####################################
|
1103
|
+
## static mods
|
1104
|
+
####################################
|
1105
|
+
|
1106
|
+
static_mods = [] # [[one_letter_amino_acid.to_sym, add_amount.to_f], ...]
|
1107
|
+
static_terminal_mods = [] # e.g. [add_Cterm_peptide, amount.to_f]
|
1108
|
+
|
1109
|
+
params.mods.each do |k,v|
|
1110
|
+
v_to_f = v.to_f
|
1111
|
+
if v_to_f != 0.0
|
1112
|
+
if k =~ /add_(\w)_/
|
1113
|
+
static_mods << [$1.to_sym, v_to_f]
|
1114
|
+
else
|
1115
|
+
static_terminal_mods << [k, v_to_f]
|
1116
|
+
end
|
1117
|
+
end
|
1118
|
+
end
|
1119
|
+
aa_hash = params.mass_table
|
1120
|
+
|
1121
|
+
## Create the static_mods objects
|
1122
|
+
static_mods.map! do |mod|
|
1123
|
+
hash = {
|
1124
|
+
:aminoacid => mod[0].to_s,
|
1125
|
+
:massdiff => mod[1].to_plus_minus_string,
|
1126
|
+
:mass => aa_hash[mod[0]] + mod[1],
|
1127
|
+
:variable => 'N',
|
1128
|
+
:binary => 'Y',
|
1129
|
+
}
|
1130
|
+
SpecID::Sequest::PepXML::AAModification.new(hash)
|
1131
|
+
end
|
1132
|
+
|
1133
|
+
## Create the static_terminal_mods objects
|
1134
|
+
static_terminal_mods.map! do |mod|
|
1135
|
+
terminus = if mod[0] =~ /Cterm/ ; 'c'
|
1136
|
+
else ; 'n' # only two possible termini
|
1137
|
+
end
|
1138
|
+
protein_terminus = case mod[0]
|
1139
|
+
when /Nterm_protein/ ; 'n'
|
1140
|
+
when /Cterm_protein/ ; 'c'
|
1141
|
+
else nil
|
1142
|
+
end
|
1143
|
+
|
1144
|
+
# create the hash
|
1145
|
+
hash = {
|
1146
|
+
:terminus => terminus,
|
1147
|
+
:massdiff => mod[1].to_plus_minus_string,
|
1148
|
+
:variable => 'N',
|
1149
|
+
:description => mod[0],
|
1150
|
+
}
|
1151
|
+
hash[:protein_terminus] = protein_terminus if protein_terminus
|
1152
|
+
SpecID::Sequest::PepXML::TerminalModification.new(hash)
|
1153
|
+
end
|
1154
|
+
#################################
|
1155
|
+
# Variable Mods:
|
1156
|
+
#################################
|
1157
|
+
arr = params.diff_search_options.rstrip.split(/\s+/)
|
1158
|
+
# [aa.to_sym, diff.to_f]
|
1159
|
+
variable_mods = []
|
1160
|
+
(0...arr.size).step(2) do |i|
|
1161
|
+
if arr[i].to_f != 0.0
|
1162
|
+
variable_mods << [arr[i+1].to_sym, arr[i].to_f]
|
1163
|
+
end
|
1164
|
+
end
|
1165
|
+
variable_mods.map! do |mod|
|
1166
|
+
hash = {
|
1167
|
+
:aminoacid => mod[0].to_s,
|
1168
|
+
:massdiff => mod[1].to_plus_minus_string,
|
1169
|
+
:mass => aa_hash[mod[0]] + mod[1],
|
1170
|
+
:variable => 'Y',
|
1171
|
+
:binary => 'N',
|
1172
|
+
:symbol => @mod_symbols_hash[mod],
|
1173
|
+
}
|
1174
|
+
SpecID::Sequest::PepXML::AAModification.new(hash)
|
1175
|
+
end
|
1176
|
+
#################################
|
1177
|
+
# TERMINAL Variable Mods:
|
1178
|
+
#################################
|
1179
|
+
# These are always peptide, not protein termini (for sequest)
|
1180
|
+
(nterm_diff, cterm_diff) = params.term_diff_search_options.rstrip.split(/\s+/).map{|v| v.to_f }
|
1181
|
+
|
1182
|
+
to_add = []
|
1183
|
+
if nterm_diff != 0.0
|
1184
|
+
to_add << ['n',nterm_diff.to_plus_minus_string, @mod_symbols_hash[:nt, nterm_diff]]
|
1185
|
+
end
|
1186
|
+
if cterm_diff != 0.0
|
1187
|
+
to_add << ['c', cterm_diff.to_plus_minus_string, @mod_symbols_hash[:ct, cterm_diff]]
|
1188
|
+
end
|
1189
|
+
|
1190
|
+
variable_terminal_mods = to_add.map do |term, mssdiff, symb|
|
1191
|
+
hash = {
|
1192
|
+
:terminus => term,
|
1193
|
+
:massdiff => mssdiff,
|
1194
|
+
:variable => 'Y',
|
1195
|
+
:symbol => symb,
|
1196
|
+
}
|
1197
|
+
SpecID::Sequest::PepXML::TerminalModification.new(hash)
|
1198
|
+
end
|
1199
|
+
|
1200
|
+
#########################
|
1201
|
+
# COLLECT THEM
|
1202
|
+
#########################
|
1203
|
+
@aa_mods = static_mods + variable_mods
|
1204
|
+
@term_mods = static_terminal_mods + variable_terminal_mods
|
1205
|
+
end
|
1206
|
+
|
1207
|
+
## Generates the pepxml for static and differential amino acid mods based on
|
1208
|
+
## sequest object
|
1209
|
+
def to_pepxml
|
1210
|
+
st = ''
|
1211
|
+
if @aa_mods
|
1212
|
+
st << @aa_mods.map {|v| v.to_pepxml }.join
|
1213
|
+
end
|
1214
|
+
if @term_mods
|
1215
|
+
st << @term_mods.map {|v| v.to_pepxml }.join
|
1216
|
+
end
|
1217
|
+
st
|
1218
|
+
end
|
1219
|
+
|
1220
|
+
end
|
1221
|
+
|
1222
|
+
# Modified aminoacid, static or variable
|
1223
|
+
# unless otherwise stated, all attributes can be anything
|
1224
|
+
class SpecID::Sequest::PepXML::AAModification
|
1225
|
+
include SpecIDXML
|
1226
|
+
|
1227
|
+
# The amino acid (one letter code)
|
1228
|
+
attr_accessor :aminoacid
|
1229
|
+
# Must be a string!!!!
|
1230
|
+
# Mass difference with respect to unmodified aminoacid, must begin with
|
1231
|
+
# either + (nonnegative) or - [e.g. +1.05446 or -2.3342]
|
1232
|
+
# consider Numeric#to_plus_minus_string at top
|
1233
|
+
attr_accessor :massdiff
|
1234
|
+
# Mass of modified aminoacid
|
1235
|
+
attr_accessor :mass
|
1236
|
+
# Y if both modified and unmodified aminoacid could be present in the
|
1237
|
+
# dataset, N if only modified aminoacid can be present
|
1238
|
+
attr_accessor :variable
|
1239
|
+
# whether modification can reside only at protein terminus (specified 'n',
|
1240
|
+
# 'c', or 'nc')
|
1241
|
+
attr_accessor :peptide_terminus
|
1242
|
+
# Special symbol used by search engine to designate this modification
|
1243
|
+
attr_accessor :symbol
|
1244
|
+
# Y if each peptide must have only modified or unmodified aminoacid, N if a
|
1245
|
+
# peptide may contain both modified and unmodified aminoacid
|
1246
|
+
attr_accessor :binary
|
1247
|
+
|
1248
|
+
def initialize(hash=nil)
|
1249
|
+
instance_var_set_from_hash(hash) if hash # can use unless there are weird methods
|
1250
|
+
end
|
1251
|
+
|
1252
|
+
def to_pepxml
|
1253
|
+
short_element_xml_from_instance_vars("aminoacid_modification")
|
1254
|
+
end
|
1255
|
+
|
1256
|
+
end
|
1257
|
+
|
1258
|
+
# Modified aminoacid, static or variable
|
1259
|
+
class SpecID::Sequest::PepXML::TerminalModification
|
1260
|
+
include SpecIDXML
|
1261
|
+
|
1262
|
+
# n for N-terminus, c for C-terminus
|
1263
|
+
attr_accessor :terminus
|
1264
|
+
# Mass difference with respect to unmodified terminus
|
1265
|
+
attr_accessor :massdiff
|
1266
|
+
# Mass of modified terminus
|
1267
|
+
attr_accessor :mass
|
1268
|
+
# Y if both modified and unmodified terminus could be present in the
|
1269
|
+
# dataset, N if only modified terminus can be present
|
1270
|
+
attr_accessor :variable
|
1271
|
+
# Special symbol used by search engine to designate this modification
|
1272
|
+
attr_accessor :symbol
|
1273
|
+
# whether modification can reside only at protein terminus (specified n or
|
1274
|
+
# c)
|
1275
|
+
attr_accessor :protein_terminus
|
1276
|
+
attr_accessor :description
|
1277
|
+
|
1278
|
+
def initialize(hash=nil)
|
1279
|
+
instance_var_set_from_hash(hash) if hash # can use unless there are weird methods
|
1280
|
+
end
|
1281
|
+
|
1282
|
+
def to_pepxml
|
1283
|
+
short_element_xml_from_instance_vars("terminal_modification")
|
1284
|
+
end
|
1285
|
+
end
|
1286
|
+
|
1287
|
+
|
678
1288
|
class SpecID::Sequest::PepXML::SearchDatabase
|
679
1289
|
include SpecIDXML
|
680
1290
|
attr_accessor :local_path
|
@@ -708,7 +1318,15 @@ end
|
|
708
1318
|
|
709
1319
|
class SpecID::Sequest::PepXML::SpectrumQuery
|
710
1320
|
include SpecIDXML
|
711
|
-
|
1321
|
+
|
1322
|
+
# basename_noext.first_scan.last_scan.charge
|
1323
|
+
attr_accessor :spectrum
|
1324
|
+
attr_accessor :start_scan
|
1325
|
+
attr_accessor :end_scan
|
1326
|
+
attr_accessor :precursor_neutral_mass
|
1327
|
+
attr_accessor :index
|
1328
|
+
attr_accessor :search_results
|
1329
|
+
|
712
1330
|
# this is a string
|
713
1331
|
attr_accessor :assumed_charge
|
714
1332
|
attr_accessor :pepxml_version
|
@@ -803,6 +1421,10 @@ end
|
|
803
1421
|
# this responds to flatten (so that it won't flatten).
|
804
1422
|
class SpecID::Sequest::PepXML::SearchHit < Array
|
805
1423
|
include SpecIDXML
|
1424
|
+
|
1425
|
+
Non_standard_amino_acid_char_re = /[^A-Z\.\-]/
|
1426
|
+
|
1427
|
+
# num_tot_proteins = "Number of unique proteins in search database containing peptide"
|
806
1428
|
#attr_accessor 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
|
807
1429
|
#attr_accessor 13:deltacnstar
|
808
1430
|
#attr_accessor 14:xcorr, 15:deltacn, 16:spscore, 17:sprank
|
@@ -811,69 +1433,82 @@ class SpecID::Sequest::PepXML::SearchHit < Array
|
|
811
1433
|
ind_keys = {:hit_rank => 0, :peptide => 1, :peptide_prev_aa => 2, :peptide_next_aa => 3, :protein => 4, :num_tot_proteins => 5, :num_matched_ions => 6, :tot_num_ions => 7, :calc_neutral_pep_mass => 8, :massdiff => 9, :num_tol_term => 10, :num_missed_cleavages => 11, :is_rejected => 12, :deltacnstar => 13, :xcorr => 14, :deltacn => 15, :spscore => 16, :sprank => 17}
|
812
1434
|
@@methods = ind_keys.keys
|
813
1435
|
def hit_rank ; self[0] end ; def hit_rank=(oth) ; self[0] = oth end
|
814
|
-
def peptide ; self[1] end ; def peptide=(oth) ; self[1] = oth end
|
815
|
-
def peptide_prev_aa ; self[2] end ; def peptide_prev_aa=(oth) ; self[2] = oth end
|
816
|
-
def peptide_next_aa ; self[3] end ; def peptide_next_aa=(oth) ; self[3] = oth end
|
817
|
-
def protein ; self[4] end ; def protein=(oth) ; self[4] = oth end
|
818
|
-
def num_tot_proteins ; self[5] end ; def num_tot_proteins=(oth) ; self[5] = oth end
|
819
|
-
def num_matched_ions ; self[6] end ; def num_matched_ions=(oth) ; self[6] = oth end
|
820
|
-
def tot_num_ions ; self[7] end ; def tot_num_ions=(oth) ; self[7] = oth end
|
821
|
-
def calc_neutral_pep_mass ; self[8] end ; def calc_neutral_pep_mass=(oth) ; self[8] = oth end
|
822
|
-
def massdiff ; self[9] end ; def massdiff=(oth) ; self[9] = oth end
|
823
|
-
def num_tol_term ; self[10] end ; def num_tol_term=(oth) ; self[10] = oth end
|
824
|
-
def num_missed_cleavages ; self[11] end ; def num_missed_cleavages=(oth) ; self[11] = oth end
|
825
|
-
def is_rejected ; self[12] end ; def is_rejected=(oth) ; self[12] = oth end
|
826
|
-
def deltacnstar ; self[13] end ; def deltacnstar=(oth) ; self[13] = oth end
|
827
|
-
def xcorr ; self[14] end ; def xcorr=(oth) ; self[14] = oth end
|
828
|
-
def deltacn ; self[15] end ; def deltacn=(oth) ; self[15] = oth end
|
829
|
-
def spscore ; self[16] end ; def spscore=(oth) ; self[16] = oth end
|
830
|
-
def sprank ; self[17] end ; def sprank=(oth) ; self[17] = oth end
|
831
|
-
|
832
|
-
@@arr_size = ind_keys.size
|
833
|
-
ind_keys.each {|k,v| ind_keys_w_eq["#{k}=".to_sym] = v }
|
834
|
-
ind_keys.merge!(ind_keys_w_eq)
|
835
|
-
ind_keys.each {|k,v| @@ind[k] = v ; @@ind["#{k}"] = v}
|
836
|
-
|
837
|
-
# These are all search_score elements:
|
838
|
-
|
839
|
-
# 1 if there is no second ranked hit, 0 otherwise
|
840
|
-
|
841
|
-
def initialize(hash=nil)
|
842
|
-
super(@@arr_size)
|
843
|
-
self[0,18] = [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]]
|
844
|
-
self
|
845
|
-
#if hash ; set_from_hash(hash) end
|
846
|
-
end
|
1436
|
+
def peptide ; self[1] end ; def peptide=(oth) ; self[1] = oth end
|
1437
|
+
def peptide_prev_aa ; self[2] end ; def peptide_prev_aa=(oth) ; self[2] = oth end
|
1438
|
+
def peptide_next_aa ; self[3] end ; def peptide_next_aa=(oth) ; self[3] = oth end
|
1439
|
+
def protein ; self[4] end ; def protein=(oth) ; self[4] = oth end
|
1440
|
+
def num_tot_proteins ; self[5] end ; def num_tot_proteins=(oth) ; self[5] = oth end
|
1441
|
+
def num_matched_ions ; self[6] end ; def num_matched_ions=(oth) ; self[6] = oth end
|
1442
|
+
def tot_num_ions ; self[7] end ; def tot_num_ions=(oth) ; self[7] = oth end
|
1443
|
+
def calc_neutral_pep_mass ; self[8] end ; def calc_neutral_pep_mass=(oth) ; self[8] = oth end
|
1444
|
+
def massdiff ; self[9] end ; def massdiff=(oth) ; self[9] = oth end
|
1445
|
+
def num_tol_term ; self[10] end ; def num_tol_term=(oth) ; self[10] = oth end
|
1446
|
+
def num_missed_cleavages ; self[11] end ; def num_missed_cleavages=(oth) ; self[11] = oth end
|
1447
|
+
def is_rejected ; self[12] end ; def is_rejected=(oth) ; self[12] = oth end
|
1448
|
+
def deltacnstar ; self[13] end ; def deltacnstar=(oth) ; self[13] = oth end
|
1449
|
+
def xcorr ; self[14] end ; def xcorr=(oth) ; self[14] = oth end
|
1450
|
+
def deltacn ; self[15] end ; def deltacn=(oth) ; self[15] = oth end
|
1451
|
+
def spscore ; self[16] end ; def spscore=(oth) ; self[16] = oth end
|
1452
|
+
def sprank ; self[17] end ; def sprank=(oth) ; self[17] = oth end
|
1453
|
+
|
1454
|
+
@@arr_size = ind_keys.size
|
1455
|
+
ind_keys.each {|k,v| ind_keys_w_eq["#{k}=".to_sym] = v }
|
1456
|
+
ind_keys.merge!(ind_keys_w_eq)
|
1457
|
+
ind_keys.each {|k,v| @@ind[k] = v ; @@ind["#{k}"] = v}
|
1458
|
+
|
1459
|
+
# These are all search_score elements:
|
1460
|
+
|
1461
|
+
# 1 if there is no second ranked hit, 0 otherwise
|
847
1462
|
|
848
|
-
|
849
|
-
|
850
|
-
|
851
|
-
|
852
|
-
|
853
|
-
|
854
|
-
|
855
|
-
|
856
|
-
|
857
|
-
|
858
|
-
|
859
|
-
|
860
|
-
peptide_prev_aa, peptide, peptide_next_aa = *pieces
|
861
|
-
when 2
|
862
|
-
if pieces[0].size > 1 ## N termini
|
863
|
-
peptide_prev_aa, peptide, peptide_next_aa = '-', pieces[0], pieces[1]
|
864
|
-
else ## C termini
|
865
|
-
peptide_prev_aa, peptide, peptide_next_aa = pieces[0], pieces[1], '-'
|
866
|
-
end
|
867
|
-
when 1 ## this must be a parse error!
|
868
|
-
peptide_prev_aa, peptide, peptide_next_aa = nil,nil,nil
|
869
|
-
when 0
|
870
|
-
peptide_prev_aa, peptide, peptide_next_aa = nil,nil,nil
|
871
|
-
end
|
872
|
-
return peptide_prev_aa, peptide, peptide_next_aa
|
873
|
-
end
|
1463
|
+
def initialize(hash=nil)
|
1464
|
+
super(@@arr_size)
|
1465
|
+
self[0,18] = [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]]
|
1466
|
+
self
|
1467
|
+
#if hash ; set_from_hash(hash) end
|
1468
|
+
end
|
1469
|
+
|
1470
|
+
# remove_non_amino_acids && split_sequence
|
1471
|
+
def self.prepare_sequence(val)
|
1472
|
+
nv = remove_non_amino_acids(val)
|
1473
|
+
split_sequence(nv)
|
1474
|
+
end
|
874
1475
|
|
875
|
-
|
876
|
-
|
1476
|
+
# Returns prev, peptide, next from sequence. Parse errors return
|
1477
|
+
# nil,nil,nil
|
1478
|
+
# R.PEPTIDE.A # -> R, PEPTIDE, A
|
1479
|
+
# R.PEPTIDE.- # -> R, PEPTIDE, -
|
1480
|
+
# PEPTIDE.A # -> -, PEPTIDE, A
|
1481
|
+
# A.PEPTIDE # -> A, PEPTIDE, -
|
1482
|
+
# PEPTIDE # -> nil,nil,nil
|
1483
|
+
def self.split_sequence(val)
|
1484
|
+
peptide_prev_aa = ""; peptide = ""; peptide_next_aa = ""
|
1485
|
+
pieces = val.split('.')
|
1486
|
+
case pieces.size
|
1487
|
+
when 3
|
1488
|
+
peptide_prev_aa, peptide, peptide_next_aa = *pieces
|
1489
|
+
when 2
|
1490
|
+
if pieces[0].size > 1 ## N termini
|
1491
|
+
peptide_prev_aa, peptide, peptide_next_aa = '-', pieces[0], pieces[1]
|
1492
|
+
else ## C termini
|
1493
|
+
peptide_prev_aa, peptide, peptide_next_aa = pieces[0], pieces[1], '-'
|
1494
|
+
end
|
1495
|
+
when 1 ## this must be a parse error!
|
1496
|
+
peptide_prev_aa, peptide, peptide_next_aa = nil,nil,nil
|
1497
|
+
when 0
|
1498
|
+
peptide_prev_aa, peptide, peptide_next_aa = nil,nil,nil
|
1499
|
+
end
|
1500
|
+
return peptide_prev_aa, peptide, peptide_next_aa
|
1501
|
+
end
|
1502
|
+
|
1503
|
+
# removes nonstandard chars with Non_standard_amino_acid_char_re
|
1504
|
+
# preserves A-Z and '.
|
1505
|
+
def self.remove_non_amino_acids(sequence)
|
1506
|
+
sequence.gsub(Non_standard_amino_acid_char_re, '')
|
1507
|
+
end
|
1508
|
+
|
1509
|
+
def inspect
|
1510
|
+
var = @@methods.map do |m| "#{m}:#{self.send(m)}" end.join(" ")
|
1511
|
+
"#<SearchHit #{var}>"
|
877
1512
|
end
|
878
1513
|
|
879
1514
|
# requires Params object and full sequence (with heads and tails)
|
@@ -924,3 +1559,65 @@ def inspect
|
|
924
1559
|
|
925
1560
|
end
|
926
1561
|
|
1562
|
+
# Positions and masses of modifications
|
1563
|
+
class SpecID::Sequest::PepXML::SearchHit::ModificationInfo
|
1564
|
+
include SpecIDXML
|
1565
|
+
|
1566
|
+
## Should be something like this:
|
1567
|
+
# <modification_info mod_nterm_mass=" " mod_nterm_mass=" " modified_peptide=" ">
|
1568
|
+
# <mod_aminoacid_mass position=" " mass=" "/>
|
1569
|
+
# </modification_info>
|
1570
|
+
|
1571
|
+
|
1572
|
+
# Mass of modified N terminus<
|
1573
|
+
attr_accessor :mod_nterm_mass
|
1574
|
+
# Mass of modified C terminus<
|
1575
|
+
attr_accessor :mod_cterm_mass
|
1576
|
+
# Peptide sequence (with indicated modifications) I'm assuming that the
|
1577
|
+
# native sequest indicators are OK here
|
1578
|
+
attr_accessor :modified_peptide
|
1579
|
+
## A few main types:
|
1580
|
+
|
1581
|
+
# this should be an array of arrays: [[position, modified_mass], ...]
|
1582
|
+
# position ranges from 1 to peptide length
|
1583
|
+
attr_accessor :mod_aminoacid_mass_array
|
1584
|
+
|
1585
|
+
def initialize(hash=nil)
|
1586
|
+
instance_var_set_from_hash(hash)
|
1587
|
+
end
|
1588
|
+
|
1589
|
+
# Will escape any xml special chars in modified_peptide
|
1590
|
+
def to_pepxml
|
1591
|
+
## Collect the modifications:
|
1592
|
+
mod_strings = []
|
1593
|
+
if @mod_aminoacid_mass_array
|
1594
|
+
mod_strings = @mod_aminoacid_mass_array.map do |ar|
|
1595
|
+
"position=\"#{ar[0]}\" mass=\"#{ar[1]}\""
|
1596
|
+
end
|
1597
|
+
end
|
1598
|
+
## Create the attribute string:
|
1599
|
+
att_parts = []
|
1600
|
+
if @mod_nterm_mass
|
1601
|
+
att_parts << "mod_nterm_mass=\"#{@mod_nterm_mass}\""
|
1602
|
+
end
|
1603
|
+
if @mod_cterm_mass
|
1604
|
+
att_parts << "mod_cterm_mass=\"#{@mod_cterm_mass}\""
|
1605
|
+
end
|
1606
|
+
if @modified_peptide
|
1607
|
+
att_parts << "modified_peptide=\"#{escape_special_chars(@modified_peptide)}\""
|
1608
|
+
end
|
1609
|
+
element_xml_and_att_string('modification_info', att_parts.join(" ")) do
|
1610
|
+
mod_strings.map {|st| short_element_xml_and_att_string('mod_aminoacid_mass', st) }.join
|
1611
|
+
end
|
1612
|
+
end
|
1613
|
+
|
1614
|
+
##
|
1615
|
+
|
1616
|
+
# <modification_info modified_peptide="GC[546]M[147]PSKEVLSAGAHR">
|
1617
|
+
# <mod_aminoacid_mass position="2" mass="545.7160"/>
|
1618
|
+
# <mod_aminoacid_mass position="3" mass="147.1926"/>
|
1619
|
+
# </modification_info>
|
1620
|
+
|
1621
|
+
|
1622
|
+
end
|
1623
|
+
|