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
@@ -0,0 +1,484 @@
|
|
1
|
+
require 'rexml/document'
|
2
|
+
require 'hash_by'
|
3
|
+
require 'instance_var_set_from_hash'
|
4
|
+
require 'axml'
|
5
|
+
require 'spec_id'
|
6
|
+
require 'array_class'
|
7
|
+
|
8
|
+
require 'spec_id/parser/proph'
|
9
|
+
|
10
|
+
|
11
|
+
module SpecID ; end
|
12
|
+
module SpecID::Prot ; end
|
13
|
+
module SpecID::Pep ; end
|
14
|
+
|
15
|
+
module Proph
|
16
|
+
|
17
|
+
class ProtSummary
|
18
|
+
include SpecID
|
19
|
+
|
20
|
+
# if you get this match it's a protein prophet file and the version is the
|
21
|
+
# first match!
|
22
|
+
Filetype_and_version_re_old = /ProteinProphet_v([\.\d]+)\.dtd/ # gives 1.9 or what else?
|
23
|
+
Filetype_and_version_re_new = /protXML_v([\.\d]+)\.xsd/ # gives 4 right now
|
24
|
+
# inherits prots and peps
|
25
|
+
|
26
|
+
# the protein groups
|
27
|
+
attr_accessor :prot_groups
|
28
|
+
attr_accessor :version
|
29
|
+
|
30
|
+
def hi_prob_best ; true end
|
31
|
+
|
32
|
+
def get_version(file)
|
33
|
+
answer = nil
|
34
|
+
File.open(file) do |fh|
|
35
|
+
5.times do
|
36
|
+
line = fh.gets
|
37
|
+
answer =
|
38
|
+
if line =~ Filetype_and_version_re_new
|
39
|
+
$1.dup
|
40
|
+
elsif line =~ Filetype_and_version_re_old
|
41
|
+
$1.dup
|
42
|
+
end
|
43
|
+
break if answer
|
44
|
+
end
|
45
|
+
end
|
46
|
+
raise(ArgumentError, "couldn't detect version in #{file}") unless answer
|
47
|
+
answer
|
48
|
+
end
|
49
|
+
|
50
|
+
def initialize(file=nil)
|
51
|
+
@prots = nil
|
52
|
+
if file
|
53
|
+
@version = get_version(file)
|
54
|
+
#@prot_groups = ProtSummary::Parser.new.parse_file(file)
|
55
|
+
SpecID::Parser::ProtProph.new(:spec_id).parse(file, :spec_id => self)
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
# returns a set of unique proteins
|
60
|
+
def unique_prots(prot_groups)
|
61
|
+
all_prots = []
|
62
|
+
prot_groups.each do |pg|
|
63
|
+
pg.prots.each do |prt|
|
64
|
+
all_prots << prt
|
65
|
+
end
|
66
|
+
end
|
67
|
+
all_prots.hash_by(:protein_name).map{|name,prot_arr| prot_arr.first }
|
68
|
+
end
|
69
|
+
|
70
|
+
end
|
71
|
+
|
72
|
+
class ProtSummary::Parser
|
73
|
+
attr_accessor :prot_groups
|
74
|
+
def initialize(file=nil, with_peps=false, tp='axml')
|
75
|
+
if file
|
76
|
+
@prot_groups = parse_file(file, with_peps, tp)
|
77
|
+
end
|
78
|
+
end
|
79
|
+
|
80
|
+
# returns an array of protein_groups
|
81
|
+
def parse_file(file, with_peps=false, tp='axml')
|
82
|
+
File.open(file) do |fh|
|
83
|
+
@prot_groups = _parse_for_prot_groups(fh, with_peps, tp)
|
84
|
+
end
|
85
|
+
@prot_groups
|
86
|
+
end
|
87
|
+
|
88
|
+
# returns an array of ProtGroup objects
|
89
|
+
def _parse_for_prot_groups(stream, with_peps=false, tp='axml')
|
90
|
+
prtgrps = []
|
91
|
+
case tp
|
92
|
+
when 'axml'
|
93
|
+
root = AXML.parse(stream)
|
94
|
+
root.protein_group.each do |protein_group|
|
95
|
+
pg = ProtGroup.new(protein_group.attrs) do
|
96
|
+
protein_group.map do |protein|
|
97
|
+
Prot.new(protein.attrs)
|
98
|
+
end
|
99
|
+
end
|
100
|
+
prtgrps << pg
|
101
|
+
end
|
102
|
+
end
|
103
|
+
prtgrps
|
104
|
+
end
|
105
|
+
end # ProtSummary::Parser
|
106
|
+
|
107
|
+
|
108
|
+
class ProtGroup
|
109
|
+
attr_accessor :group_number, :probability, :prots
|
110
|
+
def initialize(args=nil)
|
111
|
+
@prots = []
|
112
|
+
if args
|
113
|
+
instance_var_set_from_hash(args)
|
114
|
+
end
|
115
|
+
if block_given?
|
116
|
+
@prots = yield
|
117
|
+
end
|
118
|
+
end
|
119
|
+
end
|
120
|
+
|
121
|
+
end # Proph
|
122
|
+
|
123
|
+
|
124
|
+
|
125
|
+
Proph::Prot = ArrayClass.new(%w(protein_name probability n_indistinguishable_proteins percent_coverage unique_stripped_peptides group_sibling_id total_number_peptides pct_spectrum_ids description peps))
|
126
|
+
|
127
|
+
# note that 'description' is found in the element 'annotation', attribute 'protein_description'
|
128
|
+
# NOTE!: unique_stripped peptides is an array rather than + joined string
|
129
|
+
class Proph::Prot
|
130
|
+
include SpecID::Prot
|
131
|
+
|
132
|
+
# returns protein_name
|
133
|
+
def name ; self[0] end
|
134
|
+
def reference ; self[0] end
|
135
|
+
def first_entry ; self[0] end # the name is also the first_entry
|
136
|
+
|
137
|
+
end
|
138
|
+
|
139
|
+
#def to_s
|
140
|
+
# '<Prot: protein_name=' + @protein_name + ' ' + 'probability=' + @probability.to_s + '>'
|
141
|
+
#end
|
142
|
+
|
143
|
+
# this is a pep from a -prot.xml file
|
144
|
+
|
145
|
+
Proph::Prot::Pep = ArrayClass.new(%w(peptide_sequence charge initial_probability nsp_adjusted_probability weight is_nondegenerate_evidence n_enzymatic_termini n_sibling_peptides n_sibling_peptides_bin n_instances is_contributing_evidence calc_neutral_pep_mass modification_info prots))
|
146
|
+
|
147
|
+
class Proph::Prot::Pep
|
148
|
+
include SpecID::Pep
|
149
|
+
|
150
|
+
alias_method :mod_info, :modification_info
|
151
|
+
alias_method :mod_info=, :modification_info=
|
152
|
+
|
153
|
+
def aaseq ; self[0] end
|
154
|
+
def probability ; self[3] end
|
155
|
+
|
156
|
+
end # class Pep
|
157
|
+
|
158
|
+
=begin
|
159
|
+
#attr_accessor :sequence, :probability, :filenames, :charge, :precursor_neutral_mass, :nsp_cutoff, :scans
|
160
|
+
#attr_writer :arithmetic_avg_scan_by_parent_time
|
161
|
+
|
162
|
+
#def initialize(args=nil)
|
163
|
+
# if args
|
164
|
+
# @sequence = args[:sequence]
|
165
|
+
# @probability = args[:probability] ## nsp prob
|
166
|
+
# @filenames = args[:filenames]
|
167
|
+
# @charge = args[:charge]
|
168
|
+
# @nsp_cutoff = args[:nsp_cutoff]
|
169
|
+
# if args.key?(:scans)
|
170
|
+
# @scans = args[:scans]
|
171
|
+
# else
|
172
|
+
# @scans = [] ## this is set later if needed
|
173
|
+
# end
|
174
|
+
# else
|
175
|
+
# @scans = []
|
176
|
+
# end
|
177
|
+
#end
|
178
|
+
|
179
|
+
# filter peptides based on the number of scans
|
180
|
+
# if a peptide has more than max_dups scans, the peptide is tossed
|
181
|
+
# note that multiple scans that were used as a single dtafile scan
|
182
|
+
# will be counted as a single scan for these purposes!
|
183
|
+
# (easy, since they are stored as a single item in the array of scans)
|
184
|
+
def self.filter_by_max_dup_scans(max_dups=nil, peps=nil)
|
185
|
+
if max_dups
|
186
|
+
new_peps = []
|
187
|
+
peps.each do |pep|
|
188
|
+
unless pep.scans.size > max_dups
|
189
|
+
new_peps << pep
|
190
|
+
end
|
191
|
+
end
|
192
|
+
new_peps
|
193
|
+
else
|
194
|
+
peps.dup
|
195
|
+
end
|
196
|
+
end
|
197
|
+
|
198
|
+
|
199
|
+
## from the list of scans, creates a scan object whose time is the
|
200
|
+
## arithmetic mean of the parent scans (based on prec_inten) and whose
|
201
|
+
## prec_mz is the avg of all prec_mz's. num is nil, charge is the first
|
202
|
+
def arithmetic_avg_scan_by_parent_time
|
203
|
+
unless @arithmetic_avg_scan_by_parent_time
|
204
|
+
flat_scans = @scans.flatten
|
205
|
+
|
206
|
+
# new_prec_mz
|
207
|
+
prec_mz_sum = 0.0
|
208
|
+
prec_inten_sum = 0.0
|
209
|
+
times = []
|
210
|
+
intens = []
|
211
|
+
tot_inten = 0.0
|
212
|
+
flat_scans.each do |c|
|
213
|
+
prec_inten = c.prec_inten
|
214
|
+
prec_inten_sum += prec_inten
|
215
|
+
prec_mz_sum += c.prec_mz
|
216
|
+
tot_inten += prec_inten
|
217
|
+
times << c.parent.time
|
218
|
+
intens << prec_inten
|
219
|
+
end
|
220
|
+
new_prec_mz = prec_mz_sum / flat_scans.size
|
221
|
+
new_prec_inten = prec_inten_sum / flat_scans.size
|
222
|
+
|
223
|
+
fraction_inten = []
|
224
|
+
intens.each do |inten|
|
225
|
+
fraction_inten.push( inten/tot_inten )
|
226
|
+
end
|
227
|
+
|
228
|
+
new_time = 0.0
|
229
|
+
(0...times.size).each do |i|
|
230
|
+
new_time += times[i] * fraction_inten[i]
|
231
|
+
end
|
232
|
+
|
233
|
+
@arithmetic_avg_scan_by_parent_time = MS::Scan.new( nil, @scans.first.ms_level, new_time, new_prec_mz, new_prec_inten )
|
234
|
+
|
235
|
+
end
|
236
|
+
@arithmetic_avg_scan_by_parent_time
|
237
|
+
end
|
238
|
+
|
239
|
+
def to_s
|
240
|
+
'<Pep seq=' + @sequence + ' ' + 'prob=' + @probability.to_s + ' charge=' + @charge + '>'
|
241
|
+
end
|
242
|
+
|
243
|
+
def has_dta?(dta_filename)
|
244
|
+
if @filenames
|
245
|
+
@filenames.each do |fn|
|
246
|
+
if dta_filename == fn
|
247
|
+
return true
|
248
|
+
end
|
249
|
+
end
|
250
|
+
end
|
251
|
+
return false
|
252
|
+
end
|
253
|
+
|
254
|
+
|
255
|
+
# Given a list of peptides, returns only those unique based on
|
256
|
+
# sequence/charge
|
257
|
+
def self.uniq_by_seqcharge(peptides)
|
258
|
+
# @TODO: this could be done with one fewer traversals, but it is beautiful
|
259
|
+
peptides.hash_by(:sequence, :charge).collect do |k,v|
|
260
|
+
v.first
|
261
|
+
end
|
262
|
+
end
|
263
|
+
=end
|
264
|
+
|
265
|
+
|
266
|
+
|
267
|
+
|
268
|
+
|
269
|
+
=begin
|
270
|
+
|
271
|
+
# Class for parsing the peptide prophet output files in various ways
|
272
|
+
class Proph::Pep::Parser < Parser
|
273
|
+
|
274
|
+
# parse_type = "rexml" | "regex"
|
275
|
+
# regex's are about 50 times faster but are not guaranteed to work
|
276
|
+
# seq charge hash is keyed on an array -> [sequence,charge]
|
277
|
+
# @TODO: implement parsing on this with xmlparser
|
278
|
+
def dta_filenames_by_seq_charge(pep_xml_file, parse_type="rexml")
|
279
|
+
seq_charge_hash = Hash.new {|hash,key| hash[key] = [] }
|
280
|
+
case parse_type
|
281
|
+
when "rexml"
|
282
|
+
#puts "READING: " + pep_xml_file + " ..."
|
283
|
+
doc = REXML::Document.new File.new(pep_xml_file)
|
284
|
+
|
285
|
+
## Create a hash of peptides based on sequence_charge (takes an array)
|
286
|
+
doc.elements.each("msms_pipeline_analysis/msms_run_summary/search_result") do |result|
|
287
|
+
pep_charge = result.attributes['assumed_charge']
|
288
|
+
filename = result.attributes['spectrum']
|
289
|
+
result.elements.to_a('search_hit').each do |hit|
|
290
|
+
pep_seq = hit.attributes['peptide']
|
291
|
+
seq_charge = [pep_seq, pep_charge]
|
292
|
+
seq_charge_hash[seq_charge] << filename
|
293
|
+
end
|
294
|
+
end
|
295
|
+
seq_charge_hash
|
296
|
+
when "regex"
|
297
|
+
#puts "READING: " + pep_xml_file + " ..."
|
298
|
+
## Create a hash of peptides based on sequence_charge (takes an array)
|
299
|
+
|
300
|
+
## file from peptideAtlas:
|
301
|
+
search_result_regex1 = /<spectrum_query spectrum="(.*\.\d+\.\d+\.\d)".* assumed_charge="(\d)"/o
|
302
|
+
search_result_regex2 = /<search_result sxpectrum="(.*\.\d+\.\d+\.\d)".* assumed_charge="(\d)"/o
|
303
|
+
search_hit_regex = /<search_hit .*peptide="(\w+)" /o
|
304
|
+
|
305
|
+
peptide_h = {}
|
306
|
+
filename = nil
|
307
|
+
pep_charge = nil
|
308
|
+
File.open(pep_xml_file).each do |line|
|
309
|
+
if line =~ search_result_regex1
|
310
|
+
filename = $1.dup
|
311
|
+
pep_charge = $2.dup
|
312
|
+
elsif line =~ search_result_regex2
|
313
|
+
filename = $1.dup
|
314
|
+
pep_charge = $2.dup
|
315
|
+
end
|
316
|
+
if line =~ search_hit_regex
|
317
|
+
pep_seq = $1.dup
|
318
|
+
seq_charge = [pep_seq, pep_charge]
|
319
|
+
seq_charge_hash[seq_charge] << filename
|
320
|
+
end
|
321
|
+
end
|
322
|
+
end
|
323
|
+
seq_charge_hash
|
324
|
+
end
|
325
|
+
|
326
|
+
# drops all search_hits that have peptideprophet probability < min_val
|
327
|
+
# and drops any search_results that end up with 0 search_hits
|
328
|
+
def filter_by_min_pep_prob(file, outfile, min_val)
|
329
|
+
root = root_el(file)
|
330
|
+
|
331
|
+
d_search_hit = nil
|
332
|
+
d_search_result = nil
|
333
|
+
root.children.each do |child1|
|
334
|
+
if child1.name == 'msms_run_summary'
|
335
|
+
d_search_result = []
|
336
|
+
child1.children.each do |child2|
|
337
|
+
if child2.name == 'search_result'
|
338
|
+
#puts "size before: " + child2.size.to_s
|
339
|
+
d_search_hit = []
|
340
|
+
child2.children.each do |child3|
|
341
|
+
if child3.name == 'search_hit'
|
342
|
+
child3.children.each do |child4|
|
343
|
+
if child4.name == 'peptideprophet_result'
|
344
|
+
if child4.attrs["probability"].to_f < min_val
|
345
|
+
#puts "dropping probability: #{child4.attrs["probability"]}"
|
346
|
+
d_search_hit << child3
|
347
|
+
else
|
348
|
+
#puts "keeping probability: #{child4.attrs["probability"]}"
|
349
|
+
end
|
350
|
+
end
|
351
|
+
end
|
352
|
+
end
|
353
|
+
end
|
354
|
+
d_search_hit.each do |to_drop|
|
355
|
+
to_drop.drop
|
356
|
+
end
|
357
|
+
#puts "size after: " + child2.size.to_s
|
358
|
+
if child2.size == 0
|
359
|
+
d_search_result << child2
|
360
|
+
end
|
361
|
+
end
|
362
|
+
end
|
363
|
+
d_search_result.each do |to_drop|
|
364
|
+
to_drop.drop
|
365
|
+
end
|
366
|
+
end
|
367
|
+
end
|
368
|
+
|
369
|
+
File.open(outfile, "w") do |fh|
|
370
|
+
fh.print root.to_s
|
371
|
+
end
|
372
|
+
end
|
373
|
+
end # Pep::Parser
|
374
|
+
|
375
|
+
|
376
|
+
# Class for parsing the '*-prot.xml' files in different ways
|
377
|
+
class Proph::Prot::Parser < Parser
|
378
|
+
|
379
|
+
attr_accessor :prots
|
380
|
+
attr_writer :peps
|
381
|
+
|
382
|
+
def initialize
|
383
|
+
@prots = []
|
384
|
+
end
|
385
|
+
|
386
|
+
# returns all the peptides from prots
|
387
|
+
def peps
|
388
|
+
unless @peps
|
389
|
+
@peps = []
|
390
|
+
@prots.each do |prot|
|
391
|
+
@peps.push(*(prot.peps))
|
392
|
+
end
|
393
|
+
end
|
394
|
+
@peps
|
395
|
+
end
|
396
|
+
|
397
|
+
|
398
|
+
# sets and returns an array of Prot objects
|
399
|
+
# parse_type = "rexml" | "regex"
|
400
|
+
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")
|
401
|
+
## ensure these are all floats
|
402
|
+
(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|
|
403
|
+
cutoff.to_f
|
404
|
+
end
|
405
|
+
|
406
|
+
case parse_type
|
407
|
+
when "rexml"
|
408
|
+
doc = REXML::Document.new File.new(protxmlfile)
|
409
|
+
doc.elements.each("protein_summary/protein_group/protein") do |elem|
|
410
|
+
if elem.attributes['probability'].to_f >= prot_prob_cutoff
|
411
|
+
prob = elem.attributes['probability'].to_f
|
412
|
+
name= elem.attributes['protein_name']
|
413
|
+
curr_prot = Prot.new({:probability => prob, :protein_name => name, :cutoff => prot_prob_cutoff})
|
414
|
+
peptides = []
|
415
|
+
elem.elements.to_a('peptide').each do |pep|
|
416
|
+
if pep.attributes['nsp_adjusted_probability'].to_f >= pep_nsp_prob_cutoff && pep.attributes['initial_probability'].to_f >= pep_init_prob_cutoff
|
417
|
+
nsp_prob = pep.attributes['nsp_adjusted_probability'].to_f
|
418
|
+
sequence = pep.attributes['peptide_sequence']
|
419
|
+
charge = pep.attributes['charge']
|
420
|
+
pnm = pep.attributes['precursor_neutral_mass']
|
421
|
+
peptides.push(Pep.new(:probability => nsp_prob, :sequence => sequence, :charge => charge, :precursor_neutral_mass => pnm, :nsp_cutoff => pep_nsp_prob_cutoff))
|
422
|
+
end
|
423
|
+
## Only take proteins with peptides!
|
424
|
+
if peptides.size > 0
|
425
|
+
curr_prot.peps = peptides
|
426
|
+
@prots << curr_prot
|
427
|
+
end
|
428
|
+
end
|
429
|
+
end
|
430
|
+
end
|
431
|
+
when "regex"
|
432
|
+
prot_regex = /<protein protein_name="(.*)?" n_indistinguishable_proteins(.*)/o
|
433
|
+
prot_prob_regex = /probability="([\d\.]+)"/o
|
434
|
+
pep_regex = /<peptide peptide_sequence="(\w+)?"(.*)/o
|
435
|
+
pep_else_regex = /charge="(\d)" initial_probability="([\d\.]+)" nsp_adjusted_probability="([\d\.]+)"/o
|
436
|
+
|
437
|
+
curr_prot = nil
|
438
|
+
peptides = []
|
439
|
+
File.open(protxmlfile).each do |line|
|
440
|
+
if line =~ prot_regex
|
441
|
+
prob = nil
|
442
|
+
name = $1.dup
|
443
|
+
rest = $2
|
444
|
+
if rest =~ prot_prob_regex
|
445
|
+
prob = $1.dup
|
446
|
+
end
|
447
|
+
if curr_prot
|
448
|
+
if curr_prot.probability.to_f >= prot_prob_cutoff
|
449
|
+
if peptides.size > 0
|
450
|
+
curr_prot.peps = peptides
|
451
|
+
@prots.push(curr_prot)
|
452
|
+
end
|
453
|
+
end
|
454
|
+
end
|
455
|
+
curr_prot = Prot.new({:probability => prob, :protein_name => name, :cutoff => prot_prob_cutoff})
|
456
|
+
peptides = []
|
457
|
+
end
|
458
|
+
if line =~ pep_regex
|
459
|
+
sequence = $1.dup
|
460
|
+
rest = $2
|
461
|
+
if rest =~ pep_else_regex
|
462
|
+
charge = $1
|
463
|
+
init_prob = $2
|
464
|
+
nsp_prob = $3
|
465
|
+
if nsp_prob.to_f >= pep_nsp_prob_cutoff && init_prob.to_f >= pep_init_prob_cutoff
|
466
|
+
peptides.push(Pep.new(:probability => nsp_prob, :sequence => sequence, :charge => charge, :nsp_cutoff => pep_nsp_prob_cutoff))
|
467
|
+
end
|
468
|
+
end
|
469
|
+
end
|
470
|
+
# get the last one:
|
471
|
+
if curr_prot && curr_prot.probability.to_f > prot_prob_cutoff && peptides.size > 0
|
472
|
+
curr_prot.peps = peptides
|
473
|
+
@prots.push(curr_prot)
|
474
|
+
end
|
475
|
+
end
|
476
|
+
end
|
477
|
+
@prots
|
478
|
+
end
|
479
|
+
|
480
|
+
end # Prot::Parser
|
481
|
+
|
482
|
+
################ --END
|
483
|
+
|
484
|
+
=end
|