ms-sequest 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- data/History +8 -0
- data/MIT-LICENSE +20 -0
- data/README +23 -0
- data/lib/ms/sequest.rb +6 -0
- data/lib/ms/sequest/params.rb +343 -0
- data/lib/ms/sequest/sqt.rb +363 -0
- data/lib/ms/sequest/srf.rb +707 -0
- data/lib/ms/sequest/srf/sqt.rb +169 -0
- metadata +88 -0
data/History
ADDED
data/MIT-LICENSE
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2006 University of Texas at Austin, Regents of the University of
|
2
|
+
Colorado, and Howard Hughes Medical Institute.
|
3
|
+
|
4
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
5
|
+
of this software and associated documentation files (the "Software"), to deal
|
6
|
+
in the Software without restriction, including without limitation the rights
|
7
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
8
|
+
copies of the Software, and to permit persons to whom the Software is
|
9
|
+
furnished to do so, subject to the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be included in all
|
12
|
+
copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
15
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
16
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
17
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
18
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
19
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
20
|
+
SOFTWARE.
|
data/README
ADDED
@@ -0,0 +1,23 @@
|
|
1
|
+
= {Ms-Sequest}[http://mspire.rubyforge.org/projects/ms-sequest]
|
2
|
+
|
3
|
+
An {Mspire}[http://mspire.rubyforge.org] library supporting SEQUEST, Bioworks, SQT and associated formats.
|
4
|
+
|
5
|
+
== Description
|
6
|
+
|
7
|
+
* Lighthouse[http://bahuvrihi.lighthouseapp.com/projects/16692-mspire/tickets]
|
8
|
+
* Github[http://github.com/jtprince/ms-sequest/tree/master]
|
9
|
+
* {Google Group}[http://groups.google.com/group/mspire-forum]
|
10
|
+
|
11
|
+
== Installation
|
12
|
+
|
13
|
+
Ms-Sequest is available as a gem on RubyForge[http://rubyforge.org/projects/mspire]. Use:
|
14
|
+
|
15
|
+
% gem install ms-sequest
|
16
|
+
|
17
|
+
== Info
|
18
|
+
|
19
|
+
Copyright (c) 2006 University of Texas at Austin
|
20
|
+
Copyright (c) Regents of the University of Colorado and Howard Hughes Medical Institute.
|
21
|
+
Developer:: {John Prince}, {Edward Marcotte Lab}[http://polaris.icmb.utexas.edu/home.html], {Natalie Ahn Lab}[http://www.colorado.edu/chem/people/ahnn.html], {Howard Hughes Medical Institute}[http://www.hhmi.org/], {BYU Dept. of Chemistry and Biochemistry}[http://www.chem.byu.edu/]
|
22
|
+
Support::
|
23
|
+
Licence:: {MIT-Style}[link:files/MIT-LICENSE.html]
|
data/lib/ms/sequest.rb
ADDED
@@ -0,0 +1,343 @@
|
|
1
|
+
require 'ms/mass/aa'
|
2
|
+
|
3
|
+
# In the future, this guy should accept any version of bioworks params file
|
4
|
+
# and spit out any param queried.
|
5
|
+
|
6
|
+
module Ms ; end
|
7
|
+
module Ms::Sequest ; end
|
8
|
+
|
9
|
+
# 1) provides a reader and simple parameter lookup for SEQUEST params files
|
10
|
+
# supporting Bioworks 3.1-3.3.1.
|
11
|
+
# params = Ms::Sequest::Params.new("sequest.params") # filename by default
|
12
|
+
# params = Ms::Sequest::Params.new.parse_io(some_io_object)
|
13
|
+
#
|
14
|
+
# params.some_parameter # => any parameter defined has a method
|
15
|
+
# params.nonexistent_parameter # => nil
|
16
|
+
#
|
17
|
+
# Provides consistent behavior between different versions important info:
|
18
|
+
#
|
19
|
+
# # some basic methods shared by all versions:
|
20
|
+
# params.version # => '3.1' | '3.2' | '3.3'
|
21
|
+
# params.enzyme # => enzyme name with no parentheses
|
22
|
+
# params.min_number_termini
|
23
|
+
# params.database # => first_database_name
|
24
|
+
# params.enzyme_specificity # => [offset, cleave_at, expect_if_after]
|
25
|
+
# params.precursor_mass_type # => "average" | "monoisotopic"
|
26
|
+
# params.fragment_mass_type # => "average" | "monoisotopic"
|
27
|
+
#
|
28
|
+
# # some backwards/forwards compatibility methods:
|
29
|
+
# params.max_num_internal_cleavages # == max_num_internal_cleavage_sites
|
30
|
+
# params.fragment_ion_tol # => fragment_ion_tolerance
|
31
|
+
#
|
32
|
+
class Ms::Sequest::Params
|
33
|
+
|
34
|
+
Bioworks31_Enzyme_Info_Array = [
|
35
|
+
['No_Enzyme', 0, '-', '-'], # 0
|
36
|
+
['Trypsin', 1, 'KR', '-'], # 1
|
37
|
+
['Trypsin(KRLNH)', 1, 'KRLNH', '-'], # 2
|
38
|
+
['Chymotrypsin', 1, 'FWYL', '-'], # 3
|
39
|
+
['Chymotrypsin(FWY)', 1, 'FWY', 'P'], # 4
|
40
|
+
['Clostripain', 1, 'R', '-'], # 5
|
41
|
+
['Cyanogen_Bromide', 1, 'M', '-'], # 6
|
42
|
+
['IodosoBenzoate', 1, 'W', '-'], # 7
|
43
|
+
['Proline_Endopept', 1, 'P', '-'], # 8
|
44
|
+
['Staph_Protease', 1, 'E', '-'], # 9
|
45
|
+
['Trypsin_K', 1, 'K', 'P'], # 10
|
46
|
+
['Trypsin_R', 1, 'R', 'P'], # 11
|
47
|
+
['GluC', 1, 'ED', '-'], # 12
|
48
|
+
['LysC', 1, 'K', '-'], # 13
|
49
|
+
['AspN', 0, 'D', '-'], # 14
|
50
|
+
['Elastase', 1, 'ALIV', 'P'], # 15
|
51
|
+
['Elastase/Tryp/Chymo', 1, 'ALIVKRWFY', 'P'], # 16
|
52
|
+
]
|
53
|
+
|
54
|
+
# current attributes supported are:
|
55
|
+
# bioworks 3.2:
|
56
|
+
@@param_re = / = ?/o
|
57
|
+
@@param_two_split = ';'
|
58
|
+
@@sequest_line = /\[SEQUEST\]/o
|
59
|
+
|
60
|
+
# the general options
|
61
|
+
attr_accessor :opts
|
62
|
+
# the static weights added to amino acids
|
63
|
+
attr_accessor :mods
|
64
|
+
|
65
|
+
# all keys and values stored as strings!
|
66
|
+
# will accept a sequest.params file or .srf file
|
67
|
+
def initialize(file=nil)
|
68
|
+
if file
|
69
|
+
parse_file(file)
|
70
|
+
end
|
71
|
+
end
|
72
|
+
|
73
|
+
# returns hash of params up until add_U_user_amino_acid
|
74
|
+
def grab_params(fh)
|
75
|
+
hash = {}
|
76
|
+
in_add_amino_acid_section = false
|
77
|
+
add_section_re = /^\s*add_/
|
78
|
+
prev_pos = nil
|
79
|
+
while line = fh.gets
|
80
|
+
if line =~ add_section_re
|
81
|
+
in_add_amino_acid_section = true
|
82
|
+
end
|
83
|
+
if (in_add_amino_acid_section and !(line =~ add_section_re))
|
84
|
+
fh.pos = prev_pos
|
85
|
+
break
|
86
|
+
end
|
87
|
+
prev_pos = fh.pos
|
88
|
+
if line =~ /\w+/
|
89
|
+
one,two = line.split @@param_re
|
90
|
+
two,comment = two.split @@param_two_split
|
91
|
+
hash[one] = two.rstrip
|
92
|
+
end
|
93
|
+
end
|
94
|
+
hash
|
95
|
+
end
|
96
|
+
|
97
|
+
# returns self
|
98
|
+
def parse_io(fh)
|
99
|
+
# seek to the SEQUEST file
|
100
|
+
loop do
|
101
|
+
if fh.gets =~ @@sequest_line
|
102
|
+
# double check that we are in a sequest params file:
|
103
|
+
pos = fh.pos
|
104
|
+
if fh.gets =~ /^first_database_name/
|
105
|
+
fh.pos = pos
|
106
|
+
break
|
107
|
+
end
|
108
|
+
end
|
109
|
+
end
|
110
|
+
@opts = grab_params(fh)
|
111
|
+
@opts["search_engine"] = "SEQUEST"
|
112
|
+
# extract out the mods
|
113
|
+
@mods = {}
|
114
|
+
@opts.each do |k,v|
|
115
|
+
if k =~ /^add_/
|
116
|
+
@mods[k] = @opts.delete(k)
|
117
|
+
end
|
118
|
+
end
|
119
|
+
|
120
|
+
## this gets rid of the .hdr postfix on indexed databases
|
121
|
+
@opts["first_database_name"] = @opts["first_database_name"].sub(/\.hdr$/, '')
|
122
|
+
self
|
123
|
+
end
|
124
|
+
|
125
|
+
## parses file
|
126
|
+
## and drops the .hdr behind indexed fasta files
|
127
|
+
## returns self
|
128
|
+
## can read sequest.params file or .srf file handle
|
129
|
+
def parse_file(file)
|
130
|
+
File.open(file) do |fh|
|
131
|
+
parse_io(fh)
|
132
|
+
end
|
133
|
+
self
|
134
|
+
end
|
135
|
+
|
136
|
+
# returns( offset, cleave_at, except_if_after )
|
137
|
+
# offset is an Integer specifying how far after an amino acid to cut
|
138
|
+
# cleave_at is a string of all amino acids that should be cut at
|
139
|
+
# except_if_after for not cutting after those
|
140
|
+
# normal tryptic behavior would be: [1, 'KR', 'P']
|
141
|
+
# NOTE: a '-' in a params file is returned as an '' (empty string)
|
142
|
+
# AspN is [0,'D','']
|
143
|
+
def enzyme_specificity
|
144
|
+
enzyme_ar =
|
145
|
+
if version == '3.1'
|
146
|
+
Bioworks31_Enzyme_Info_Array[@opts['enzyme_number'].to_i][1,3]
|
147
|
+
elsif version >= '3.2'
|
148
|
+
arr = enzyme_info.split(/\s+/)[2,3]
|
149
|
+
arr[0] = arr[0].to_i
|
150
|
+
arr
|
151
|
+
else
|
152
|
+
raise ArgumentError, "don't recognize anything but Bioworks 3.1--3.3"
|
153
|
+
end
|
154
|
+
enzyme_ar.map! do |str|
|
155
|
+
if str == '-' ; ''
|
156
|
+
else ; str
|
157
|
+
end
|
158
|
+
end
|
159
|
+
enzyme_ar
|
160
|
+
end
|
161
|
+
|
162
|
+
# Returns the version of the sequest.params file
|
163
|
+
# Returns String "3.3" if contains "fragment_ion_units"
|
164
|
+
# Returns String "3.2" if contains "enyzme_info"
|
165
|
+
# Returns String "3.1" if contains "enzyme_number"
|
166
|
+
def version
|
167
|
+
if @opts['fragment_ion_units'] ; return '3.3'
|
168
|
+
elsif @opts['enzyme_info'] ; return '3.2'
|
169
|
+
elsif @opts['enzyme_number'] ; return '3.1'
|
170
|
+
end
|
171
|
+
end
|
172
|
+
|
173
|
+
####################################################
|
174
|
+
# TO PEPXML
|
175
|
+
####################################################
|
176
|
+
# In some ways, this is merely translating to the older Bioworks
|
177
|
+
# sequest.params files
|
178
|
+
|
179
|
+
# I'm not sure if this is the right mapping for sequence_search_constraint?
|
180
|
+
def sequence
|
181
|
+
pseq = @opts['partial_sequence']
|
182
|
+
if !pseq || pseq == "" ; pseq = "0" end
|
183
|
+
pseq
|
184
|
+
end
|
185
|
+
|
186
|
+
def precursor_mass_type
|
187
|
+
case @opts['mass_type_parent']
|
188
|
+
when '0' ; "average"
|
189
|
+
when '1' ; "monoisotopic"
|
190
|
+
else ; abort "error in mass_type_parent in sequest!"
|
191
|
+
end
|
192
|
+
end
|
193
|
+
|
194
|
+
def fragment_mass_type
|
195
|
+
fmtype =
|
196
|
+
case @opts['mass_type_fragment']
|
197
|
+
when '0' ; "average"
|
198
|
+
when '1' ; "monoisotopic"
|
199
|
+
else ; abort "error in mass_type_fragment in sequest!"
|
200
|
+
end
|
201
|
+
end
|
202
|
+
|
203
|
+
def method_missing(name, *args)
|
204
|
+
string = name.to_s
|
205
|
+
if @opts.key?(string) ; return @opts[string]
|
206
|
+
elsif @mods.key?(string) ; return @mods[string]
|
207
|
+
else ; return nil
|
208
|
+
end
|
209
|
+
end
|
210
|
+
|
211
|
+
## We only need to define values if they are different than sequest.params
|
212
|
+
## The method_missing will look them up in the hash!
|
213
|
+
|
214
|
+
# Returns a system independent basename
|
215
|
+
# Splits on "\" or "/"
|
216
|
+
def _sys_ind_basename(file)
|
217
|
+
return file.split(/[\\\/]/)[-1]
|
218
|
+
end
|
219
|
+
|
220
|
+
# changes the path of the database
|
221
|
+
def database_path=(newpath)
|
222
|
+
db = @opts["first_database_name"]
|
223
|
+
newpath = File.join(newpath, _sys_ind_basename(db))
|
224
|
+
@opts["first_database_name"] = newpath
|
225
|
+
end
|
226
|
+
|
227
|
+
def database
|
228
|
+
@opts["first_database_name"]
|
229
|
+
end
|
230
|
+
|
231
|
+
# returns the appropriate aminoacid mass lookup table from Ms::Mass::AA
|
232
|
+
# based_on may be :precursor or :fragment
|
233
|
+
def mass_index(based_on=:precursor)
|
234
|
+
reply = case based_on
|
235
|
+
when :precursor : precursor_mass_type
|
236
|
+
when :fragment : fragment_mass_type
|
237
|
+
end
|
238
|
+
case reply
|
239
|
+
when 'average'
|
240
|
+
Ms::Mass::AA::AVG
|
241
|
+
when 'monoisotopic'
|
242
|
+
Ms::Mass::AA::MONO
|
243
|
+
end
|
244
|
+
end
|
245
|
+
|
246
|
+
# at least in Bioworks 3.2, the First number after the enzyme
|
247
|
+
# is the indication of the enzymatic end stringency (required):
|
248
|
+
# 1 = Fully enzymatic
|
249
|
+
# 2 = Either end
|
250
|
+
# 3 = N terminal only
|
251
|
+
# 4 = C terminal only
|
252
|
+
# So, to get min_number_termini we map like this:
|
253
|
+
# 1 => 2
|
254
|
+
# 2 => 1
|
255
|
+
def min_number_termini
|
256
|
+
if e_info = @opts["enzyme_info"]
|
257
|
+
case e_info.split(" ")[1]
|
258
|
+
when "1": return "2"
|
259
|
+
when "2": return "1"
|
260
|
+
end
|
261
|
+
end
|
262
|
+
warn "No Enzyme termini info, using min_number_termini = '1'"
|
263
|
+
return "1"
|
264
|
+
end
|
265
|
+
|
266
|
+
## returns a SampleEnzyme object
|
267
|
+
#def sample_enzyme
|
268
|
+
# (offset, cleave_at, except_if_after) = enzyme_specificity.map do |v|
|
269
|
+
# if v == '' ; nil ; else v end
|
270
|
+
# end
|
271
|
+
# SampleEnzyme.new do |se|
|
272
|
+
# se.name = self.enzyme
|
273
|
+
# se.cut = cleave_at
|
274
|
+
# se.no_cut = except_if_after
|
275
|
+
# se.sense =
|
276
|
+
# if se.name == "No_Enzyme"
|
277
|
+
# nil
|
278
|
+
# elsif offset == 1
|
279
|
+
# 'C'
|
280
|
+
# elsif offset == 0
|
281
|
+
# 'N'
|
282
|
+
# end
|
283
|
+
# end
|
284
|
+
#end
|
285
|
+
|
286
|
+
# returns the enzyme name (but no parentheses connected with the name).
|
287
|
+
# this will likely be capitalized.
|
288
|
+
def enzyme
|
289
|
+
v = self.version
|
290
|
+
basic_name =
|
291
|
+
if v == '3.1'
|
292
|
+
Bioworks31_Enzyme_Info_Array[ @opts['enzyme_number'].to_i ][0]
|
293
|
+
elsif v >= '3.2'
|
294
|
+
@opts["enzyme_info"]
|
295
|
+
end
|
296
|
+
basic_name.split('(')[0]
|
297
|
+
end
|
298
|
+
|
299
|
+
def max_num_internal_cleavages
|
300
|
+
@opts["max_num_internal_cleavage_sites"]
|
301
|
+
end
|
302
|
+
|
303
|
+
# my take on peptide_mass_units:
|
304
|
+
# (see http://www.ionsource.com/tutorial/isotopes/slide2.htm)
|
305
|
+
# amu = atomic mass units = (mass_real - mass_measured).abs (??abs??)
|
306
|
+
# mmu = milli mass units (amu / 1000)
|
307
|
+
# ppm = parts per million = 10^6 * ∆m_accuracy / mass_measured [ where ∆m_accuracy = mass_real – mass_measured ]
|
308
|
+
|
309
|
+
def peptide_mass_tol
|
310
|
+
if @opts["peptide_mass_units"] != "0"
|
311
|
+
puts "WARNING: peptide_mass_tol units need to be adjusted!"
|
312
|
+
end
|
313
|
+
@opts["peptide_mass_tolerance"]
|
314
|
+
end
|
315
|
+
|
316
|
+
def fragment_ion_tol
|
317
|
+
@opts["fragment_ion_tolerance"]
|
318
|
+
end
|
319
|
+
|
320
|
+
def max_num_differential_AA_per_mod
|
321
|
+
@opts["max_num_differential_AA_per_mod"] || @opts["max_num_differential_per_peptide"]
|
322
|
+
end
|
323
|
+
|
324
|
+
# returns a hash by add_<whatever> of any static mods != 0
|
325
|
+
# the values are still as strings
|
326
|
+
def static_mods
|
327
|
+
hash = {}
|
328
|
+
@mods.each do |k,v|
|
329
|
+
if v.to_f != 0.0
|
330
|
+
hash[k] = v
|
331
|
+
end
|
332
|
+
end
|
333
|
+
hash
|
334
|
+
end
|
335
|
+
|
336
|
+
## @TODO: We could add some of the parameters not currently being asked for to be more complete
|
337
|
+
## @TODO: We could always add the Bioworks 3.2 specific params as params
|
338
|
+
|
339
|
+
####################################################
|
340
|
+
####################################################
|
341
|
+
|
342
|
+
end
|
343
|
+
|
@@ -0,0 +1,363 @@
|
|
1
|
+
|
2
|
+
require 'ms/fasta'
|
3
|
+
require 'arrayclass'
|
4
|
+
require 'set'
|
5
|
+
|
6
|
+
require 'ms/id/peptide'
|
7
|
+
require 'ms/id/search'
|
8
|
+
|
9
|
+
module Ms
|
10
|
+
module Sequest
|
11
|
+
class SqtGroup
|
12
|
+
include Ms::Id::SearchGroup
|
13
|
+
|
14
|
+
#attr_accessor :sqts, :filenames
|
15
|
+
|
16
|
+
def search_class
|
17
|
+
Ms::Sequest::Sqt
|
18
|
+
end
|
19
|
+
|
20
|
+
def extension() 'sqg' end
|
21
|
+
|
22
|
+
def initialize(arg, opts={}, &block)
|
23
|
+
orig_opts = opts.dup
|
24
|
+
indiv_opts = { :link_protein_hits => false }
|
25
|
+
super(arg, opts.merge(indiv_opts)) do
|
26
|
+
unless orig_opts[:link_protein_hits] == false
|
27
|
+
puts "MERGING GROUP!"
|
28
|
+
(@peps, @prots) = merge!(@searches.map {|v| v.peps }, &Ms::Sequest::Sqt::NEW_PROT)
|
29
|
+
end
|
30
|
+
end
|
31
|
+
block.call(self) if block_given?
|
32
|
+
end
|
33
|
+
|
34
|
+
|
35
|
+
# # NOTE THAT this is copy/paste from srf.rb, should be refactored...
|
36
|
+
## returns the filename used
|
37
|
+
## if the file exists, the name will be expanded to full path, otherwise just
|
38
|
+
## what is given
|
39
|
+
#def to_sqg(sqg_filename='bioworks.sqg')
|
40
|
+
#File.open(sqg_filename, 'w') do |v|
|
41
|
+
#@filenames.each do |sqt_file|
|
42
|
+
#if File.exist? sqt_file
|
43
|
+
#v.puts File.expand_path(sqt_file)
|
44
|
+
#else
|
45
|
+
#v.puts sqt_file
|
46
|
+
#end
|
47
|
+
#end
|
48
|
+
#end
|
49
|
+
#sqg_filename
|
50
|
+
#end
|
51
|
+
|
52
|
+
end # SqtGroup
|
53
|
+
|
54
|
+
|
55
|
+
class Sqt
|
56
|
+
include Ms::Id::Search
|
57
|
+
PercolatorHeaderMatch = /^Percolator v/
|
58
|
+
Delimiter = "\t"
|
59
|
+
attr_accessor :header
|
60
|
+
attr_accessor :spectra
|
61
|
+
attr_accessor :base_name
|
62
|
+
# boolean
|
63
|
+
attr_accessor :percolator_results
|
64
|
+
|
65
|
+
# assumes the file exists and is readable
|
66
|
+
# returns [DBSeqLength, DBLocusCount, DBMD5Sum] or nil if no file
|
67
|
+
def self.get_db_info(dbfile)
|
68
|
+
Ms::Fasta.open(dbfile) do |fasta|
|
69
|
+
[fasta.total_sequence_length, fasta.size, fasta.md5_sum]
|
70
|
+
end
|
71
|
+
end
|
72
|
+
|
73
|
+
def protein_class
|
74
|
+
Ms::Sequest::Sqt::Locus
|
75
|
+
end
|
76
|
+
|
77
|
+
# opts =
|
78
|
+
# :percolator_results => false | true (default false)
|
79
|
+
# :link_protein_hits => true | false (default true)
|
80
|
+
def initialize(filename=nil, opts={})
|
81
|
+
@peps = []
|
82
|
+
@prots = []
|
83
|
+
if filename
|
84
|
+
from_file(filename, opts)
|
85
|
+
end
|
86
|
+
end
|
87
|
+
|
88
|
+
NEW_PROT = lambda do |_prot, _peps|
|
89
|
+
Ms::Sequest::Sqt::Locus.new([_prot.locus, _prot.description, _peps])
|
90
|
+
end
|
91
|
+
|
92
|
+
# if the file contains the header key '/$Percolator v/' then the results
|
93
|
+
# will be interpreted as percolator results regardless of the value
|
94
|
+
# passed in.
|
95
|
+
def from_file(filename, opts={})
|
96
|
+
opts = {:percolator_results=>false, :link_protein_hits => true}.merge(opts)
|
97
|
+
@percolator_results = opts[:percolator_results]
|
98
|
+
@base_name = File.basename( filename.gsub('\\','/') ).sub(/\.\w+$/, '')
|
99
|
+
File.open(filename) do |fh|
|
100
|
+
@header = Ms::Sequest::Sqt::Header.new.from_handle(fh)
|
101
|
+
if @header.keys.any? {|v| v =~ PercolatorHeaderMatch }
|
102
|
+
@percolator_results = true
|
103
|
+
end
|
104
|
+
(@spectra, @peps) = Ms::Sequest::Sqt::Spectrum.spectra_from_handle(fh, @base_name, @percolator_results)
|
105
|
+
end
|
106
|
+
if opts[:link_protein_hits]
|
107
|
+
(@peps, @prots) = merge!([@peps], &NEW_PROT)
|
108
|
+
end
|
109
|
+
end
|
110
|
+
|
111
|
+
|
112
|
+
# Inherits from hash, so all header stuff can be accessed by key. Multiline
|
113
|
+
# values will be pushed into an array.
|
114
|
+
# All header values are stored as (newline-removed) strings!
|
115
|
+
class Header < Hash
|
116
|
+
Leader = 'H'
|
117
|
+
|
118
|
+
# These will be in arrays no matter what: StaticMod, DynamicMod, Comment
|
119
|
+
# Any other keys repeated will be shoved into an array; otherwise a string
|
120
|
+
Arrayed = %w(DyanmicMod StaticMod Comment).to_set
|
121
|
+
|
122
|
+
HeaderKeys = {
|
123
|
+
:sqt_generator => 'SQTGenerator',
|
124
|
+
:sqt_generator_version => 'SQTGeneratorVersion',
|
125
|
+
:database => 'Database',
|
126
|
+
:fragment_masses => 'FragmentMasses',
|
127
|
+
:precursor_masses => 'PrecursorMasses',
|
128
|
+
:start_time => 'StartTime',
|
129
|
+
:db_seq_length => 'DBSeqLength',
|
130
|
+
:db_locus_count => 'DBLocusCount',
|
131
|
+
:db_md5sum => 'DBMD5Sum',
|
132
|
+
:peptide_mass_tolerance => 'Alg-PreMassTol',
|
133
|
+
:fragment_ion_tolerance => 'Alg-FragMassTol',
|
134
|
+
# nonstandard (mine)
|
135
|
+
:peptide_mass_units => 'Alg-PreMassUnits',
|
136
|
+
:ion_series => 'Alg-IonSeries',
|
137
|
+
:enzyme => 'Alg-Enzyme',
|
138
|
+
# nonstandard (mine)
|
139
|
+
:ms_model => 'Alg-MSModel',
|
140
|
+
:static_mods => 'StaticMod',
|
141
|
+
:dynamic_mods => 'DynamicMod',
|
142
|
+
:comments => 'Comment'
|
143
|
+
}
|
144
|
+
|
145
|
+
|
146
|
+
KeysToAtts = HeaderKeys.invert
|
147
|
+
|
148
|
+
HeaderKeys.keys.each do |ky|
|
149
|
+
attr_accessor ky
|
150
|
+
end
|
151
|
+
|
152
|
+
def from_handle(fh)
|
153
|
+
Arrayed.each do |ky|
|
154
|
+
self[ky] = []
|
155
|
+
end
|
156
|
+
pos = fh.pos
|
157
|
+
lines = []
|
158
|
+
loop do
|
159
|
+
line = fh.gets
|
160
|
+
if line && (line[0,1] == Ms::Sequest::Sqt::Header::Leader )
|
161
|
+
lines << line
|
162
|
+
else # reset the fh.pos and we're done
|
163
|
+
fh.pos = pos
|
164
|
+
break
|
165
|
+
end
|
166
|
+
pos = fh.pos
|
167
|
+
end
|
168
|
+
from_lines(lines)
|
169
|
+
end
|
170
|
+
|
171
|
+
def from_lines(array_of_header_lines)
|
172
|
+
array_of_header_lines.each do |line|
|
173
|
+
line.chomp!
|
174
|
+
(ky, *rest) = line.split(Ms::Sequest::Sqt::Delimiter)[1..-1]
|
175
|
+
# just in case they have any tabs in their field
|
176
|
+
value = rest.join(Ms::Sequest::Sqt::Delimiter)
|
177
|
+
if Arrayed.include?(ky)
|
178
|
+
self[ky] << value
|
179
|
+
elsif self.key? ky # already exists
|
180
|
+
if self[ky].is_a? Array
|
181
|
+
self[ky] << value
|
182
|
+
else
|
183
|
+
self[ky] = [self[ky], value]
|
184
|
+
end
|
185
|
+
else # normal
|
186
|
+
self[ky] = value
|
187
|
+
end
|
188
|
+
end
|
189
|
+
KeysToAtts.each do |ky,methd|
|
190
|
+
self.send("#{methd}=".to_sym, self[ky])
|
191
|
+
end
|
192
|
+
self
|
193
|
+
end
|
194
|
+
|
195
|
+
end
|
196
|
+
end
|
197
|
+
end
|
198
|
+
end
|
199
|
+
|
200
|
+
# all are cast as expected (total_intensity is a float)
|
201
|
+
# mh = observed mh
|
202
|
+
Ms::Sequest::Sqt::Spectrum = Arrayclass.new(%w[first_scan last_scan charge time_to_process node mh total_intensity lowest_sp num_matched_peptides matches])
|
203
|
+
|
204
|
+
# 0=first_scan 1=last_scan 2=charge 3=time_to_process 4=node 5=mh 6=total_intensity 7=lowest_sp 8=num_matched_peptides 9=matches
|
205
|
+
|
206
|
+
class Ms::Sequest::Sqt::Spectrum
|
207
|
+
Leader = 'S'
|
208
|
+
|
209
|
+
# assumes the first line starts with an 'S'
|
210
|
+
def self.spectra_from_handle(fh, base_name, percolator_results=false)
|
211
|
+
peps = []
|
212
|
+
spectra = []
|
213
|
+
|
214
|
+
while line = fh.gets
|
215
|
+
case line[0,1]
|
216
|
+
when Ms::Sequest::Sqt::Spectrum::Leader
|
217
|
+
spectrum = Ms::Sequest::Sqt::Spectrum.new.from_line( line )
|
218
|
+
spectra << spectrum
|
219
|
+
matches = []
|
220
|
+
spectrum.matches = matches
|
221
|
+
when Ms::Sequest::Sqt::Match::Leader
|
222
|
+
match_klass = if percolator_results
|
223
|
+
Ms::Sequest::Sqt::Match::Percolator
|
224
|
+
else
|
225
|
+
Ms::Sequest::Sqt::Match
|
226
|
+
end
|
227
|
+
match = match_klass.new.from_line( line )
|
228
|
+
match[10,3] = spectrum[0,3]
|
229
|
+
match[15] = base_name
|
230
|
+
matches << match
|
231
|
+
peps << match
|
232
|
+
loci = []
|
233
|
+
match.loci = loci
|
234
|
+
matches << match
|
235
|
+
when Ms::Sequest::Sqt::Locus::Leader
|
236
|
+
line.chomp!
|
237
|
+
key = line.split(Ms::Sequest::Sqt::Delimiter)[1]
|
238
|
+
locus = Ms::Sequest::Sqt::Locus.new.from_line( line )
|
239
|
+
loci << locus
|
240
|
+
end
|
241
|
+
end
|
242
|
+
# set the deltacn:
|
243
|
+
set_deltacn(spectra)
|
244
|
+
[spectra, peps]
|
245
|
+
end
|
246
|
+
|
247
|
+
def self.set_deltacn(spectra)
|
248
|
+
spectra.each do |spec|
|
249
|
+
matches = spec.matches
|
250
|
+
if matches.size > 0
|
251
|
+
|
252
|
+
(0...(matches.size-1)).each do |i|
|
253
|
+
matches[i].deltacn = matches[i+1].deltacn_orig
|
254
|
+
end
|
255
|
+
matches[-1].deltacn = 1.1
|
256
|
+
end
|
257
|
+
end
|
258
|
+
spectra
|
259
|
+
end
|
260
|
+
|
261
|
+
|
262
|
+
# returns an array -> [the next spectra line (or nil if eof), spectrum]
|
263
|
+
def from_line(line)
|
264
|
+
line.chomp!
|
265
|
+
ar = line.split(Ms::Sequest::Sqt::Delimiter)
|
266
|
+
self[0] = ar[1].to_i
|
267
|
+
self[1] = ar[2].to_i
|
268
|
+
self[2] = ar[3].to_i
|
269
|
+
self[3] = ar[4].to_f
|
270
|
+
self[4] = ar[5]
|
271
|
+
self[5] = ar[6].to_f
|
272
|
+
self[6] = ar[7].to_f
|
273
|
+
self[7] = ar[8].to_f
|
274
|
+
self[8] = ar[9].to_i
|
275
|
+
self[9] = []
|
276
|
+
self
|
277
|
+
end
|
278
|
+
end
|
279
|
+
|
280
|
+
# Sqt format uses only indices 0 - 9
|
281
|
+
Ms::Sequest::Sqt::Match = Arrayclass.new(%w[rxcorr rsp mh deltacn_orig xcorr sp ions_matched ions_total sequence manual_validation_status first_scan last_scan charge deltacn aaseq base_name loci])
|
282
|
+
|
283
|
+
# 0=rxcorr 1=rsp 2=mh 3=deltacn_orig 4=xcorr 5=sp 6=ions_matched 7=ions_total 8=sequence 9=manual_validation_status 10=first_scan 11=last_scan 12=charge 13=deltacn 14=aaseq 15=base_name 16=loci
|
284
|
+
|
285
|
+
# rxcorr = rank by xcorr
|
286
|
+
# rsp = rank by sp
|
287
|
+
# NOTE:
|
288
|
+
# deltacn_orig
|
289
|
+
# deltacn is the adjusted deltacn (like Bioworks - shift all scores up and
|
290
|
+
# give the last one 1.1)
|
291
|
+
class Ms::Sequest::Sqt::Match
|
292
|
+
Leader = 'M'
|
293
|
+
|
294
|
+
# same as 'loci'
|
295
|
+
def prots
|
296
|
+
self[16]
|
297
|
+
end
|
298
|
+
|
299
|
+
def from_line(line)
|
300
|
+
line.chomp!
|
301
|
+
ar = line.split(Ms::Sequest::Sqt::Delimiter)
|
302
|
+
self[0] = ar[1].to_i
|
303
|
+
self[1] = ar[2].to_i
|
304
|
+
self[2] = ar[3].to_f
|
305
|
+
self[3] = ar[4].to_f
|
306
|
+
self[4] = ar[5].to_f
|
307
|
+
self[5] = ar[6].to_f
|
308
|
+
self[6] = ar[7].to_i
|
309
|
+
self[7] = ar[8].to_i
|
310
|
+
self[8] = ar[9]
|
311
|
+
self[9] = ar[10]
|
312
|
+
self[14] = Ms::Id::Peptide.sequence_to_aaseq(self[8])
|
313
|
+
self
|
314
|
+
end
|
315
|
+
end
|
316
|
+
|
317
|
+
|
318
|
+
class Ms::Sequest::Sqt::Match::Percolator < Ms::Sequest::Sqt::Match
|
319
|
+
# we will keep access to these old terms since we can then access routines
|
320
|
+
# that sort on xcorr...
|
321
|
+
#undef_method :xcorr
|
322
|
+
#undef_method :xcorr=
|
323
|
+
#undef_method :sp
|
324
|
+
#undef_method :sp=
|
325
|
+
|
326
|
+
def percolator_score
|
327
|
+
self[4]
|
328
|
+
end
|
329
|
+
def percolator_score=(score)
|
330
|
+
self[4] = score
|
331
|
+
end
|
332
|
+
def negative_q_value
|
333
|
+
self[5]
|
334
|
+
end
|
335
|
+
def negative_q_value=(arg)
|
336
|
+
self[5] = arg
|
337
|
+
end
|
338
|
+
def q_value
|
339
|
+
-self[5]
|
340
|
+
end
|
341
|
+
# for compatibility with scripts that want this guy
|
342
|
+
def probability
|
343
|
+
-self[5]
|
344
|
+
end
|
345
|
+
end
|
346
|
+
|
347
|
+
Ms::Sequest::Sqt::Locus = Arrayclass.new(%w[locus description peps])
|
348
|
+
|
349
|
+
class Ms::Sequest::Sqt::Locus
|
350
|
+
Leader = 'L'
|
351
|
+
|
352
|
+
def first_entry ; self[0] end
|
353
|
+
def reference ; self[0] end
|
354
|
+
|
355
|
+
def from_line(line)
|
356
|
+
line.chomp!
|
357
|
+
ar = line.split(Ms::Sequest::Sqt::Delimiter)
|
358
|
+
self[0] = ar[1]
|
359
|
+
self[1] = ar[2]
|
360
|
+
self
|
361
|
+
end
|
362
|
+
|
363
|
+
end
|