mspire 0.2.4 → 0.3.0
Sign up to get free protection for your applications and to get access to all the features.
- data/INSTALL +1 -0
- data/README +25 -0
- data/Rakefile +129 -40
- data/bin/{find_aa_freq.rb → aafreqs.rb} +2 -2
- data/bin/bioworks_to_pepxml.rb +1 -0
- data/bin/fasta_shaker.rb +1 -96
- data/bin/filter_and_validate.rb +5 -0
- data/bin/{mzxml_to_lmat.rb → ms_to_lmat.rb} +8 -7
- data/bin/prob_validate.rb +6 -0
- data/bin/raw_to_mzXML.rb +2 -2
- data/bin/srf_group.rb +1 -0
- data/bin/srf_to_sqt.rb +40 -0
- data/changelog.txt +68 -0
- data/lib/align/chams.rb +6 -6
- data/lib/align.rb +4 -3
- data/lib/bsearch.rb +120 -0
- data/lib/fasta.rb +318 -86
- data/lib/group_by.rb +10 -0
- data/lib/index_by.rb +11 -0
- data/lib/merge_deep.rb +21 -0
- data/lib/{spec → ms/converter}/mzxml.rb +77 -109
- data/lib/ms/gradient_program.rb +171 -0
- data/lib/ms/msrun.rb +209 -0
- data/lib/{spec/msrun.rb → ms/msrun_index.rb} +7 -40
- data/lib/ms/parser/mzdata/axml.rb +12 -0
- data/lib/ms/parser/mzdata/dom.rb +160 -0
- data/lib/ms/parser/mzdata/libxml.rb +7 -0
- data/lib/ms/parser/mzdata.rb +25 -0
- data/lib/ms/parser/mzxml/axml.rb +11 -0
- data/lib/ms/parser/mzxml/dom.rb +159 -0
- data/lib/ms/parser/mzxml/hpricot.rb +253 -0
- data/lib/ms/parser/mzxml/libxml.rb +15 -0
- data/lib/ms/parser/mzxml/regexp.rb +122 -0
- data/lib/ms/parser/mzxml/rexml.rb +72 -0
- data/lib/ms/parser/mzxml/xmlparser.rb +248 -0
- data/lib/ms/parser/mzxml.rb +175 -0
- data/lib/ms/parser.rb +108 -0
- data/lib/ms/precursor.rb +10 -0
- data/lib/ms/scan.rb +81 -0
- data/lib/ms/spectrum.rb +193 -0
- data/lib/ms.rb +10 -0
- data/lib/mspire.rb +4 -0
- data/lib/roc.rb +61 -1
- data/lib/sample_enzyme.rb +31 -8
- data/lib/scan_i.rb +21 -0
- data/lib/spec_id/aa_freqs.rb +7 -3
- data/lib/spec_id/bioworks.rb +20 -14
- data/lib/spec_id/digestor.rb +139 -0
- data/lib/spec_id/mass.rb +116 -0
- data/lib/spec_id/parser/proph.rb +236 -0
- data/lib/spec_id/precision/filter/cmdline.rb +209 -0
- data/lib/spec_id/precision/filter/interactive.rb +134 -0
- data/lib/spec_id/precision/filter/output.rb +147 -0
- data/lib/spec_id/precision/filter.rb +623 -0
- data/lib/spec_id/precision/output.rb +60 -0
- data/lib/spec_id/precision/prob/cmdline.rb +139 -0
- data/lib/spec_id/precision/prob/output.rb +88 -0
- data/lib/spec_id/precision/prob.rb +171 -0
- data/lib/spec_id/proph/pep_summary.rb +92 -0
- data/lib/spec_id/proph/prot_summary.rb +484 -0
- data/lib/spec_id/proph.rb +2 -466
- data/lib/spec_id/protein_summary.rb +2 -2
- data/lib/spec_id/sequest/params.rb +316 -0
- data/lib/spec_id/sequest/pepxml.rb +1513 -0
- data/lib/spec_id/sequest.rb +2 -1672
- data/lib/spec_id/srf.rb +445 -177
- data/lib/spec_id.rb +183 -95
- data/lib/spec_id_xml.rb +8 -10
- data/lib/transmem/phobius.rb +147 -0
- data/lib/transmem/toppred.rb +368 -0
- data/lib/transmem.rb +157 -0
- data/lib/validator/aa.rb +135 -0
- data/lib/validator/background.rb +73 -0
- data/lib/validator/bias.rb +95 -0
- data/lib/validator/cmdline.rb +260 -0
- data/lib/validator/decoy.rb +94 -0
- data/lib/validator/digestion_based.rb +69 -0
- data/lib/validator/probability.rb +48 -0
- data/lib/validator/prot_from_pep.rb +234 -0
- data/lib/validator/transmem.rb +272 -0
- data/lib/validator/true_pos.rb +46 -0
- data/lib/validator.rb +214 -0
- data/lib/xml.rb +38 -0
- data/lib/xml_style_parser.rb +105 -0
- data/lib/xmlparser_wrapper.rb +19 -0
- data/script/compile_and_plot_smriti_final.rb +97 -0
- data/script/extract_gradient_programs.rb +56 -0
- data/script/get_apex_values_rexml.rb +44 -0
- data/script/mzXML2timeIndex.rb +1 -1
- data/script/smriti_final_analysis.rb +103 -0
- data/script/toppred_to_yaml.rb +47 -0
- data/script/tpp_installer.rb +1 -1
- data/{test/tc_align.rb → specs/align_spec.rb} +21 -27
- data/{test/tc_bioworks_to_pepxml.rb → specs/bin/bioworks_to_pepxml_spec.rb} +25 -41
- data/specs/bin/fasta_shaker_spec.rb +259 -0
- data/specs/bin/filter_and_validate__multiple_vals_helper.yaml +202 -0
- data/specs/bin/filter_and_validate_spec.rb +124 -0
- data/specs/bin/ms_to_lmat_spec.rb +34 -0
- data/specs/bin/prob_validate_spec.rb +62 -0
- data/specs/bin/protein_summary_spec.rb +10 -0
- data/{test/tc_fasta.rb → specs/fasta_spec.rb} +354 -310
- data/specs/gi_spec.rb +22 -0
- data/specs/load_bin_path.rb +7 -0
- data/specs/merge_deep_spec.rb +13 -0
- data/specs/ms/gradient_program_spec.rb +77 -0
- data/specs/ms/msrun_spec.rb +455 -0
- data/specs/ms/parser_spec.rb +92 -0
- data/specs/ms/spectrum_spec.rb +89 -0
- data/specs/roc_spec.rb +251 -0
- data/specs/rspec_autotest.rb +149 -0
- data/specs/sample_enzyme_spec.rb +41 -0
- data/specs/spec_helper.rb +133 -0
- data/specs/spec_id/aa_freqs_spec.rb +52 -0
- data/{test/tc_bioworks.rb → specs/spec_id/bioworks_spec.rb} +56 -71
- data/specs/spec_id/digestor_spec.rb +75 -0
- data/specs/spec_id/precision/filter/cmdline_spec.rb +20 -0
- data/specs/spec_id/precision/filter/output_spec.rb +31 -0
- data/specs/spec_id/precision/filter_spec.rb +243 -0
- data/specs/spec_id/precision/prob_spec.rb +111 -0
- data/specs/spec_id/precision/prob_spec_helper.rb +0 -0
- data/specs/spec_id/proph/pep_summary_spec.rb +143 -0
- data/{test/tc_proph.rb → specs/spec_id/proph/prot_summary_spec.rb} +52 -32
- data/{test/tc_protein_summary.rb → specs/spec_id/protein_summary_spec.rb} +85 -0
- data/specs/spec_id/sequest/params_spec.rb +68 -0
- data/specs/spec_id/sequest/pepxml_spec.rb +452 -0
- data/specs/spec_id/sqt_spec.rb +138 -0
- data/specs/spec_id/srf_spec.rb +209 -0
- data/specs/spec_id/srf_spec_helper.rb +302 -0
- data/specs/spec_id_helper.rb +33 -0
- data/specs/spec_id_spec.rb +361 -0
- data/specs/spec_id_xml_spec.rb +33 -0
- data/specs/transmem/phobius_spec.rb +423 -0
- data/specs/transmem/toppred_spec.rb +297 -0
- data/specs/transmem_spec.rb +60 -0
- data/specs/transmem_spec_shared.rb +64 -0
- data/specs/validator/aa_spec.rb +107 -0
- data/specs/validator/background_spec.rb +51 -0
- data/specs/validator/bias_spec.rb +146 -0
- data/specs/validator/decoy_spec.rb +51 -0
- data/specs/validator/fasta_helper.rb +26 -0
- data/specs/validator/prot_from_pep_spec.rb +141 -0
- data/specs/validator/transmem_spec.rb +145 -0
- data/specs/validator/true_pos_spec.rb +58 -0
- data/specs/validator_helper.rb +33 -0
- data/specs/xml_spec.rb +12 -0
- data/test_files/000_pepxml18_small.xml +206 -0
- data/test_files/020a.mzXML.timeIndex +4710 -0
- data/test_files/4-03-03_mzXML/000.mzXML.timeIndex +3973 -0
- data/test_files/4-03-03_mzXML/020.mzXML.timeIndex +3872 -0
- data/test_files/4-03-03_small-prot.xml +321 -0
- data/test_files/4-03-03_small.xml +3876 -0
- data/test_files/7MIX_STD_110802_1.sequest_params_fragment.srf +0 -0
- data/test_files/bioworks-3.3_10prots.xml +5999 -0
- data/test_files/bioworks31.params +77 -0
- data/test_files/bioworks32.params +62 -0
- data/test_files/bioworks33.params +63 -0
- data/test_files/bioworks_single_run_small.xml +7237 -0
- data/test_files/bioworks_small.fasta +212 -0
- data/test_files/bioworks_small.params +63 -0
- data/test_files/bioworks_small.phobius +109 -0
- data/test_files/bioworks_small.toppred.out +2847 -0
- data/test_files/bioworks_small.xml +5610 -0
- data/test_files/bioworks_with_INV_small.xml +3753 -0
- data/test_files/bioworks_with_SHUFF_small.xml +2503 -0
- data/test_files/corrupted_900.srf +0 -0
- data/test_files/head_of_7MIX.srf +0 -0
- data/test_files/interact-opd1_mods_small-prot.xml +304 -0
- data/test_files/messups.fasta +297 -0
- data/test_files/opd1/000.my_answer.100lines.xml +101 -0
- data/test_files/opd1/000.tpp_1.2.3.first10.xml +115 -0
- data/test_files/opd1/000.tpp_2.9.2.first10.xml +126 -0
- data/test_files/opd1/000.v2.1.mzXML.timeIndex +3748 -0
- data/test_files/opd1/000_020-prot.png +0 -0
- data/test_files/opd1/000_020_3prots-prot.mod_initprob.xml +62 -0
- data/test_files/opd1/000_020_3prots-prot.xml +62 -0
- data/test_files/opd1/opd1_cat_inv_small-prot.xml +139 -0
- data/test_files/opd1/sequest.3.1.params +77 -0
- data/test_files/opd1/sequest.3.2.params +62 -0
- data/test_files/opd1/twenty_scans.mzXML +418 -0
- data/test_files/opd1/twenty_scans.v2.1.mzXML +382 -0
- data/test_files/opd1/twenty_scans_answ.lmat +0 -0
- data/test_files/opd1/twenty_scans_answ.lmata +9 -0
- data/test_files/opd1_020_beginning.RAW +0 -0
- data/test_files/opd1_2runs_2mods/interact-opd1_mods__small.xml +753 -0
- data/test_files/orbitrap_mzData/000_cut.xml +1920 -0
- data/test_files/pepproph_small.xml +4691 -0
- data/test_files/phobius.small.noheader.txt +50 -0
- data/test_files/phobius.small.small.txt +53 -0
- data/test_files/s01_anC1_ld020mM.key.txt +25 -0
- data/test_files/s01_anC1_ld020mM.meth +0 -0
- data/test_files/small.fasta +297 -0
- data/test_files/smallraw.RAW +0 -0
- data/test_files/tf_bioworks2excel.bioXML +14340 -0
- data/test_files/tf_bioworks2excel.txt.actual +1035 -0
- data/test_files/toppred.small.out +416 -0
- data/test_files/toppred.xml.out +318 -0
- data/test_files/validator_hits_separate/bias_bioworks_small_HS.fasta +7 -0
- data/test_files/validator_hits_separate/bioworks_small_HS.xml +5651 -0
- data/test_files/yeast_gly_small-prot.xml +265 -0
- data/test_files/yeast_gly_small.1.0_1.0_1.0.parentTimes +6 -0
- data/test_files/yeast_gly_small.xml +3807 -0
- data/test_files/yeast_gly_small2.parentTimes +6 -0
- metadata +273 -57
- data/bin/filter.rb +0 -6
- data/bin/precision.rb +0 -5
- data/lib/spec/mzdata/parser.rb +0 -108
- data/lib/spec/mzdata.rb +0 -48
- data/lib/spec/mzxml/parser.rb +0 -449
- data/lib/spec/scan.rb +0 -55
- data/lib/spec_id/filter.rb +0 -797
- data/lib/spec_id/precision.rb +0 -421
- data/lib/toppred.rb +0 -18
- data/script/filter-peps.rb +0 -164
- data/test/tc_aa_freqs.rb +0 -59
- data/test/tc_fasta_shaker.rb +0 -149
- data/test/tc_filter.rb +0 -203
- data/test/tc_filter_peps.rb +0 -46
- data/test/tc_gi.rb +0 -17
- data/test/tc_id_class_anal.rb +0 -70
- data/test/tc_id_precision.rb +0 -89
- data/test/tc_msrun.rb +0 -88
- data/test/tc_mzxml.rb +0 -88
- data/test/tc_mzxml_to_lmat.rb +0 -36
- data/test/tc_peptide_parent_times.rb +0 -27
- data/test/tc_precision.rb +0 -60
- data/test/tc_roc.rb +0 -166
- data/test/tc_sample_enzyme.rb +0 -32
- data/test/tc_scan.rb +0 -26
- data/test/tc_sequest.rb +0 -336
- data/test/tc_spec.rb +0 -78
- data/test/tc_spec_id.rb +0 -201
- data/test/tc_spec_id_xml.rb +0 -36
- data/test/tc_srf.rb +0 -262
data/lib/spec_id/proph.rb
CHANGED
@@ -1,468 +1,4 @@
|
|
1
1
|
|
2
|
-
require '
|
3
|
-
require '
|
4
|
-
require 'instance_var_set_from_hash'
|
5
|
-
require 'axml'
|
6
|
-
require 'spec_id'
|
2
|
+
#require 'spec_id/proph/prot_summary'
|
3
|
+
#require 'spec_id/proph/pep_summary'
|
7
4
|
|
8
|
-
|
9
|
-
module SpecID ; end
|
10
|
-
module SpecID::Prot ; end
|
11
|
-
module SpecID::Pep ; end
|
12
|
-
|
13
|
-
class Proph
|
14
|
-
|
15
|
-
|
16
|
-
################ --BEGIN
|
17
|
-
|
18
|
-
|
19
|
-
class Parser
|
20
|
-
def root_el(file)
|
21
|
-
AXML.parse_file(file)
|
22
|
-
end
|
23
|
-
end
|
24
|
-
|
25
|
-
|
26
|
-
class ProtSummary
|
27
|
-
include SpecID
|
28
|
-
|
29
|
-
attr_writer :prots
|
30
|
-
attr_accessor :prot_groups
|
31
|
-
|
32
|
-
def hi_prob_best ; true end
|
33
|
-
|
34
|
-
def initialize(file=nil)
|
35
|
-
@prots = nil
|
36
|
-
if file
|
37
|
-
@prot_groups = ProtSummary::Parser.new.parse_file(file)
|
38
|
-
end
|
39
|
-
end
|
40
|
-
|
41
|
-
def prots
|
42
|
-
if @prots ; @prots
|
43
|
-
else
|
44
|
-
@prots = unique_prots(@prot_groups)
|
45
|
-
@prots
|
46
|
-
end
|
47
|
-
end
|
48
|
-
|
49
|
-
# returns a set of unique proteins
|
50
|
-
def unique_prots(prot_groups)
|
51
|
-
all_prots = []
|
52
|
-
prot_groups.each do |pg|
|
53
|
-
pg.prots.each do |prt|
|
54
|
-
all_prots << prt
|
55
|
-
end
|
56
|
-
end
|
57
|
-
all_prots.hash_by(:protein_name).map{|name,prot_arr| prot_arr.first }
|
58
|
-
end
|
59
|
-
|
60
|
-
end
|
61
|
-
|
62
|
-
class ProtSummary::Parser < Parser
|
63
|
-
attr_accessor :prot_groups
|
64
|
-
def initialize(file=nil, with_peps=false, tp='axml')
|
65
|
-
if file
|
66
|
-
@prot_groups = parse_file(file, with_peps, tp)
|
67
|
-
end
|
68
|
-
end
|
69
|
-
|
70
|
-
# returns an array of protein_groups
|
71
|
-
def parse_file(file, with_peps=false, tp='axml')
|
72
|
-
File.open(file) do |fh|
|
73
|
-
@prot_groups = _parse_for_prot_groups(fh, with_peps, tp)
|
74
|
-
end
|
75
|
-
@prot_groups
|
76
|
-
end
|
77
|
-
|
78
|
-
# returns an array of ProtGroup objects
|
79
|
-
def _parse_for_prot_groups(stream, with_peps=false, tp='axml')
|
80
|
-
prtgrps = []
|
81
|
-
case tp
|
82
|
-
when 'axml'
|
83
|
-
root = AXML.parse(stream)
|
84
|
-
root.protein_group.each do |protein_group|
|
85
|
-
pg = ProtGroup.new(protein_group.attrs) do
|
86
|
-
protein_group.map do |protein|
|
87
|
-
Prot.new(protein.attrs)
|
88
|
-
end
|
89
|
-
end
|
90
|
-
prtgrps << pg
|
91
|
-
end
|
92
|
-
end
|
93
|
-
prtgrps
|
94
|
-
end
|
95
|
-
end # ProtSummary::Parser
|
96
|
-
|
97
|
-
|
98
|
-
class ProtGroup
|
99
|
-
attr_accessor :group_number, :probability, :prots
|
100
|
-
def initialize(args=nil)
|
101
|
-
@prots = []
|
102
|
-
if args
|
103
|
-
instance_var_set_from_hash(args)
|
104
|
-
end
|
105
|
-
if block_given?
|
106
|
-
@prots = yield
|
107
|
-
end
|
108
|
-
end
|
109
|
-
end
|
110
|
-
|
111
|
-
class Prot
|
112
|
-
include SpecID::Prot
|
113
|
-
|
114
|
-
## probability and reference accessors are inherited
|
115
|
-
attr_accessor :peps, :protein_name, :cutoff, :group_sibling_id, :n_indistinguishable_proteins, :percent_coverage, :unique_stripped_peptides, :total_number_peptides, :pct_spectrum_ids, :description
|
116
|
-
|
117
|
-
# returns protein_name
|
118
|
-
def name ; @protein_name end
|
119
|
-
def reference ; @protein_name end
|
120
|
-
|
121
|
-
def initialize(args)
|
122
|
-
self.instance_var_set_from_hash(args)
|
123
|
-
if @probability ; @probability = @probability.to_f end
|
124
|
-
end
|
125
|
-
|
126
|
-
# def self.uniq_prots_with_prob_and_reference(file)
|
127
|
-
# root = Parser.root_el(file)
|
128
|
-
# prots = []
|
129
|
-
# root.protein_group.each do |group|
|
130
|
-
# group.protein.each do |prt|
|
131
|
-
# #prots << prt
|
132
|
-
# prots <<
|
133
|
-
# end
|
134
|
-
# end
|
135
|
-
#
|
136
|
-
# un_prots = prots.hash_by(:_protein_name).map{|name,prot_arr| prot_arr.first }
|
137
|
-
#
|
138
|
-
# end
|
139
|
-
|
140
|
-
def to_s
|
141
|
-
'<Prot: protein_name=' + @protein_name + ' ' + 'probability=' + @probability.to_s + '>'
|
142
|
-
end
|
143
|
-
|
144
|
-
end # class Prot
|
145
|
-
|
146
|
-
class Pep
|
147
|
-
include SpecID::Pep
|
148
|
-
|
149
|
-
attr_accessor :sequence, :probability, :filenames, :charge, :precursor_neutral_mass, :nsp_cutoff, :scans
|
150
|
-
attr_writer :arithmetic_avg_scan_by_parent_time
|
151
|
-
|
152
|
-
def initialize(args=nil)
|
153
|
-
if args
|
154
|
-
@sequence = args[:sequence]
|
155
|
-
@probability = args[:probability] ## nsp prob
|
156
|
-
@filenames = args[:filenames]
|
157
|
-
@charge = args[:charge]
|
158
|
-
@nsp_cutoff = args[:nsp_cutoff]
|
159
|
-
if args.key?(:scans)
|
160
|
-
@scans = args[:scans]
|
161
|
-
else
|
162
|
-
@scans = [] ## this is set later if needed
|
163
|
-
end
|
164
|
-
else
|
165
|
-
@scans = []
|
166
|
-
end
|
167
|
-
end
|
168
|
-
|
169
|
-
# filter peptides based on the number of scans
|
170
|
-
# if a peptide has more than max_dups scans, the peptide is tossed
|
171
|
-
# note that multiple scans that were used as a single dtafile scan
|
172
|
-
# will be counted as a single scan for these purposes!
|
173
|
-
# (easy, since they are stored as a single item in the array of scans)
|
174
|
-
def self.filter_by_max_dup_scans(max_dups=nil, peps=nil)
|
175
|
-
if max_dups
|
176
|
-
new_peps = []
|
177
|
-
peps.each do |pep|
|
178
|
-
unless pep.scans.size > max_dups
|
179
|
-
new_peps << pep
|
180
|
-
end
|
181
|
-
end
|
182
|
-
new_peps
|
183
|
-
else
|
184
|
-
peps.dup
|
185
|
-
end
|
186
|
-
end
|
187
|
-
|
188
|
-
## from the list of scans, creates a scan object whose time is the
|
189
|
-
## arithmetic mean of the parent scans (based on prec_inten) and whose
|
190
|
-
## prec_mz is the avg of all prec_mz's. num is nil, charge is the first
|
191
|
-
def arithmetic_avg_scan_by_parent_time
|
192
|
-
unless @arithmetic_avg_scan_by_parent_time
|
193
|
-
flat_scans = @scans.flatten
|
194
|
-
|
195
|
-
# new_prec_mz
|
196
|
-
prec_mz_sum = 0.0
|
197
|
-
prec_inten_sum = 0.0
|
198
|
-
times = []
|
199
|
-
intens = []
|
200
|
-
tot_inten = 0.0
|
201
|
-
flat_scans.each do |c|
|
202
|
-
prec_inten = c.prec_inten
|
203
|
-
prec_inten_sum += prec_inten
|
204
|
-
prec_mz_sum += c.prec_mz
|
205
|
-
tot_inten += prec_inten
|
206
|
-
times << c.parent.time
|
207
|
-
intens << prec_inten
|
208
|
-
end
|
209
|
-
new_prec_mz = prec_mz_sum / flat_scans.size
|
210
|
-
new_prec_inten = prec_inten_sum / flat_scans.size
|
211
|
-
|
212
|
-
fraction_inten = []
|
213
|
-
intens.each do |inten|
|
214
|
-
fraction_inten.push( inten/tot_inten )
|
215
|
-
end
|
216
|
-
|
217
|
-
new_time = 0.0
|
218
|
-
(0...times.size).each do |i|
|
219
|
-
new_time += times[i] * fraction_inten[i]
|
220
|
-
end
|
221
|
-
|
222
|
-
@arithmetic_avg_scan_by_parent_time = Spec::Scan.new( nil, @scans.first.ms_level, new_time, new_prec_mz, new_prec_inten )
|
223
|
-
|
224
|
-
end
|
225
|
-
@arithmetic_avg_scan_by_parent_time
|
226
|
-
end
|
227
|
-
|
228
|
-
def to_s
|
229
|
-
'<Pep seq=' + @sequence + ' ' + 'prob=' + @probability.to_s + ' charge=' + @charge + '>'
|
230
|
-
end
|
231
|
-
|
232
|
-
def has_dta?(dta_filename)
|
233
|
-
if @filenames
|
234
|
-
@filenames.each do |fn|
|
235
|
-
if dta_filename == fn
|
236
|
-
return true
|
237
|
-
end
|
238
|
-
end
|
239
|
-
end
|
240
|
-
return false
|
241
|
-
end
|
242
|
-
|
243
|
-
# Given a list of peptides, returns only those unique based on
|
244
|
-
# sequence/charge
|
245
|
-
def self.uniq_by_seqcharge(peptides)
|
246
|
-
# @TODO: this could be done with one fewer traversals, but it is beautiful
|
247
|
-
peptides.hash_by(:sequence, :charge).collect do |k,v|
|
248
|
-
v.first
|
249
|
-
end
|
250
|
-
end
|
251
|
-
|
252
|
-
end # class Pep
|
253
|
-
|
254
|
-
|
255
|
-
# Class for parsing the peptide prophet output files in various ways
|
256
|
-
class Pep::Parser < Parser
|
257
|
-
|
258
|
-
# parse_type = "rexml" | "regex"
|
259
|
-
# regex's are about 50 times faster but are not guaranteed to work
|
260
|
-
# seq charge hash is keyed on an array -> [sequence,charge]
|
261
|
-
# @TODO: implement parsing on this with xmlparser
|
262
|
-
def dta_filenames_by_seq_charge(pep_xml_file, parse_type="rexml")
|
263
|
-
seq_charge_hash = Hash.new {|hash,key| hash[key] = [] }
|
264
|
-
case parse_type
|
265
|
-
when "rexml"
|
266
|
-
#puts "READING: " + pep_xml_file + " ..."
|
267
|
-
doc = REXML::Document.new File.new(pep_xml_file)
|
268
|
-
|
269
|
-
## Create a hash of peptides based on sequence_charge (takes an array)
|
270
|
-
doc.elements.each("msms_pipeline_analysis/msms_run_summary/search_result") do |result|
|
271
|
-
pep_charge = result.attributes['assumed_charge']
|
272
|
-
filename = result.attributes['spectrum']
|
273
|
-
result.elements.to_a('search_hit').each do |hit|
|
274
|
-
pep_seq = hit.attributes['peptide']
|
275
|
-
seq_charge = [pep_seq, pep_charge]
|
276
|
-
seq_charge_hash[seq_charge] << filename
|
277
|
-
end
|
278
|
-
end
|
279
|
-
seq_charge_hash
|
280
|
-
when "regex"
|
281
|
-
#puts "READING: " + pep_xml_file + " ..."
|
282
|
-
## Create a hash of peptides based on sequence_charge (takes an array)
|
283
|
-
|
284
|
-
## file from peptideAtlas:
|
285
|
-
search_result_regex1 = /<spectrum_query spectrum="(.*\.\d+\.\d+\.\d)".* assumed_charge="(\d)"/o
|
286
|
-
search_result_regex2 = /<search_result sxpectrum="(.*\.\d+\.\d+\.\d)".* assumed_charge="(\d)"/o
|
287
|
-
search_hit_regex = /<search_hit .*peptide="(\w+)" /o
|
288
|
-
|
289
|
-
peptide_h = {}
|
290
|
-
filename = nil
|
291
|
-
pep_charge = nil
|
292
|
-
File.open(pep_xml_file).each do |line|
|
293
|
-
if line =~ search_result_regex1
|
294
|
-
filename = $1.dup
|
295
|
-
pep_charge = $2.dup
|
296
|
-
elsif line =~ search_result_regex2
|
297
|
-
filename = $1.dup
|
298
|
-
pep_charge = $2.dup
|
299
|
-
end
|
300
|
-
if line =~ search_hit_regex
|
301
|
-
pep_seq = $1.dup
|
302
|
-
seq_charge = [pep_seq, pep_charge]
|
303
|
-
seq_charge_hash[seq_charge] << filename
|
304
|
-
end
|
305
|
-
end
|
306
|
-
end
|
307
|
-
seq_charge_hash
|
308
|
-
end
|
309
|
-
|
310
|
-
# drops all search_hits that have peptideprophet probability < min_val
|
311
|
-
# and drops any search_results that end up with 0 search_hits
|
312
|
-
def filter_by_min_pep_prob(file, outfile, min_val)
|
313
|
-
root = root_el(file)
|
314
|
-
|
315
|
-
d_search_hit = nil
|
316
|
-
d_search_result = nil
|
317
|
-
root.children.each do |child1|
|
318
|
-
if child1.name == 'msms_run_summary'
|
319
|
-
d_search_result = []
|
320
|
-
child1.children.each do |child2|
|
321
|
-
if child2.name == 'search_result'
|
322
|
-
#puts "size before: " + child2.size.to_s
|
323
|
-
d_search_hit = []
|
324
|
-
child2.children.each do |child3|
|
325
|
-
if child3.name == 'search_hit'
|
326
|
-
child3.children.each do |child4|
|
327
|
-
if child4.name == 'peptideprophet_result'
|
328
|
-
if child4.attrs["probability"].to_f < min_val
|
329
|
-
#puts "dropping probability: #{child4.attrs["probability"]}"
|
330
|
-
d_search_hit << child3
|
331
|
-
else
|
332
|
-
#puts "keeping probability: #{child4.attrs["probability"]}"
|
333
|
-
end
|
334
|
-
end
|
335
|
-
end
|
336
|
-
end
|
337
|
-
end
|
338
|
-
d_search_hit.each do |to_drop|
|
339
|
-
to_drop.drop
|
340
|
-
end
|
341
|
-
#puts "size after: " + child2.size.to_s
|
342
|
-
if child2.size == 0
|
343
|
-
d_search_result << child2
|
344
|
-
end
|
345
|
-
end
|
346
|
-
end
|
347
|
-
d_search_result.each do |to_drop|
|
348
|
-
to_drop.drop
|
349
|
-
end
|
350
|
-
end
|
351
|
-
end
|
352
|
-
|
353
|
-
File.open(outfile, "w") do |fh|
|
354
|
-
fh.print root.to_s
|
355
|
-
end
|
356
|
-
end
|
357
|
-
end # Pep::Parser
|
358
|
-
|
359
|
-
|
360
|
-
# Class for parsing the '*-prot.xml' files in different ways
|
361
|
-
class Prot::Parser < Parser
|
362
|
-
|
363
|
-
attr_accessor :prots
|
364
|
-
attr_writer :peps
|
365
|
-
|
366
|
-
def initialize
|
367
|
-
@prots = []
|
368
|
-
end
|
369
|
-
|
370
|
-
# returns all the peptides from prots
|
371
|
-
def peps
|
372
|
-
unless @peps
|
373
|
-
@peps = []
|
374
|
-
@prots.each do |prot|
|
375
|
-
@peps.push(*(prot.peps))
|
376
|
-
end
|
377
|
-
end
|
378
|
-
@peps
|
379
|
-
end
|
380
|
-
|
381
|
-
|
382
|
-
# sets and returns an array of Prot objects
|
383
|
-
# parse_type = "rexml" | "regex"
|
384
|
-
def get_prots_and_peps(protxmlfile, prot_prob_cutoff=1.0, pep_init_prob_cutoff=1.0, pep_nsp_prob_cutoff=1.0, parse_type="rexml")
|
385
|
-
## ensure these are all floats
|
386
|
-
(prot_prob_cutoff, pep_init_prob_cutoff, pep_nsp_prob_cutoff) = [prot_prob_cutoff, pep_init_prob_cutoff, pep_nsp_prob_cutoff].collect do |cutoff|
|
387
|
-
cutoff.to_f
|
388
|
-
end
|
389
|
-
|
390
|
-
case parse_type
|
391
|
-
when "rexml"
|
392
|
-
doc = REXML::Document.new File.new(protxmlfile)
|
393
|
-
doc.elements.each("protein_summary/protein_group/protein") do |elem|
|
394
|
-
if elem.attributes['probability'].to_f >= prot_prob_cutoff
|
395
|
-
prob = elem.attributes['probability'].to_f
|
396
|
-
name= elem.attributes['protein_name']
|
397
|
-
curr_prot = Prot.new({:probability => prob, :protein_name => name, :cutoff => prot_prob_cutoff})
|
398
|
-
peptides = []
|
399
|
-
elem.elements.to_a('peptide').each do |pep|
|
400
|
-
if pep.attributes['nsp_adjusted_probability'].to_f >= pep_nsp_prob_cutoff && pep.attributes['initial_probability'].to_f >= pep_init_prob_cutoff
|
401
|
-
nsp_prob = pep.attributes['nsp_adjusted_probability'].to_f
|
402
|
-
sequence = pep.attributes['peptide_sequence']
|
403
|
-
charge = pep.attributes['charge']
|
404
|
-
pnm = pep.attributes['precursor_neutral_mass']
|
405
|
-
peptides.push(Pep.new(:probability => nsp_prob, :sequence => sequence, :charge => charge, :precursor_neutral_mass => pnm, :nsp_cutoff => pep_nsp_prob_cutoff))
|
406
|
-
end
|
407
|
-
## Only take proteins with peptides!
|
408
|
-
if peptides.size > 0
|
409
|
-
curr_prot.peps = peptides
|
410
|
-
@prots << curr_prot
|
411
|
-
end
|
412
|
-
end
|
413
|
-
end
|
414
|
-
end
|
415
|
-
when "regex"
|
416
|
-
prot_regex = /<protein protein_name="(.*)?" n_indistinguishable_proteins(.*)/o
|
417
|
-
prot_prob_regex = /probability="([\d\.]+)"/o
|
418
|
-
pep_regex = /<peptide peptide_sequence="(\w+)?"(.*)/o
|
419
|
-
pep_else_regex = /charge="(\d)" initial_probability="([\d\.]+)" nsp_adjusted_probability="([\d\.]+)"/o
|
420
|
-
|
421
|
-
curr_prot = nil
|
422
|
-
peptides = []
|
423
|
-
File.open(protxmlfile).each do |line|
|
424
|
-
if line =~ prot_regex
|
425
|
-
prob = nil
|
426
|
-
name = $1.dup
|
427
|
-
rest = $2
|
428
|
-
if rest =~ prot_prob_regex
|
429
|
-
prob = $1.dup
|
430
|
-
end
|
431
|
-
if curr_prot
|
432
|
-
if curr_prot.probability.to_f >= prot_prob_cutoff
|
433
|
-
if peptides.size > 0
|
434
|
-
curr_prot.peps = peptides
|
435
|
-
@prots.push(curr_prot)
|
436
|
-
end
|
437
|
-
end
|
438
|
-
end
|
439
|
-
curr_prot = Prot.new({:probability => prob, :protein_name => name, :cutoff => prot_prob_cutoff})
|
440
|
-
peptides = []
|
441
|
-
end
|
442
|
-
if line =~ pep_regex
|
443
|
-
sequence = $1.dup
|
444
|
-
rest = $2
|
445
|
-
if rest =~ pep_else_regex
|
446
|
-
charge = $1
|
447
|
-
init_prob = $2
|
448
|
-
nsp_prob = $3
|
449
|
-
if nsp_prob.to_f >= pep_nsp_prob_cutoff && init_prob.to_f >= pep_init_prob_cutoff
|
450
|
-
peptides.push(Pep.new(:probability => nsp_prob, :sequence => sequence, :charge => charge, :nsp_cutoff => pep_nsp_prob_cutoff))
|
451
|
-
end
|
452
|
-
end
|
453
|
-
end
|
454
|
-
# get the last one:
|
455
|
-
if curr_prot && curr_prot.probability.to_f > prot_prob_cutoff && peptides.size > 0
|
456
|
-
curr_prot.peps = peptides
|
457
|
-
@prots.push(curr_prot)
|
458
|
-
end
|
459
|
-
end
|
460
|
-
end
|
461
|
-
@prots
|
462
|
-
end
|
463
|
-
|
464
|
-
end # Prot::Parser
|
465
|
-
|
466
|
-
################ --END
|
467
|
-
|
468
|
-
end # Proph
|
@@ -5,7 +5,7 @@ require 'hash_by'
|
|
5
5
|
require 'optparse'
|
6
6
|
require 'ostruct'
|
7
7
|
require 'spec_id'
|
8
|
-
require 'spec_id/precision'
|
8
|
+
#require 'spec_id/precision' # gone now
|
9
9
|
require 'gi'
|
10
10
|
|
11
11
|
#############################################################
|
@@ -428,7 +428,7 @@ class ProteinSummary
|
|
428
428
|
op.on("--#{PRECISION_PROGRAM_BASE}", "include output of #{PRECISION_PROGRAM_BASE}.rb,") {|v| opt.precision = v}
|
429
429
|
op.separator(" type '#{PRECISION_PROGRAM_BASE}.rb' for details")
|
430
430
|
op.separator ""
|
431
|
-
op.separator "
|
431
|
+
op.separator "MSific to ProteinProphet (with no concatenated DB):"
|
432
432
|
op.on("-c", "--cutoff percent", "false positive predictive rate (FPPR)% for given cutoff") {|v| opt.c = v }
|
433
433
|
op.on("--cut_at percent", "only reports proteins within FPPR %") {|v| opt.cut_at = v }
|
434
434
|
op.on("--get_annotation", "retrieves annotation by gi code") {|v| opt.get_annotation = v}
|