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/srf.rb
CHANGED
@@ -1,7 +1,12 @@
|
|
1
|
+
require 'spec_id'
|
1
2
|
require 'spec_id/sequest'
|
3
|
+
require 'fasta'
|
4
|
+
require 'mspire'
|
5
|
+
require 'set'
|
6
|
+
require 'fasta'
|
2
7
|
|
3
8
|
module BinaryReader
|
4
|
-
Null_char = "\0"[0] ## change for ruby 1.9 or 2.0
|
9
|
+
Null_char = "\0"[0] ## TODO: change for ruby 1.9 or 2.0
|
5
10
|
# extracts a string with all empty chars at the end stripped
|
6
11
|
# expects the filehandle to be at the proper location
|
7
12
|
def get_null_padded_string(fh,bytes)
|
@@ -16,62 +21,6 @@ module BinaryReader
|
|
16
21
|
end
|
17
22
|
|
18
23
|
# class to extract information from <file>_dta.log files
|
19
|
-
class DTALog
|
20
|
-
# returns an array indexed by the dta file number (starting at 0)
|
21
|
-
# each entry is an array [first_scan, last_scan, dta_filename_noext]
|
22
|
-
# this is now obsolete since I found the scan # index at the end of the srf
|
23
|
-
# files
|
24
|
-
def self.dta_and_scans_by_dta_index(file)
|
25
|
-
dta_index = nil
|
26
|
-
final_scan = nil
|
27
|
-
dta_cnt = 0
|
28
|
-
re = /^ m/o
|
29
|
-
scan_line_re = /scan: (\d+) - (\d+), Datafile: (.*?) (.*)/o
|
30
|
-
other_dta_re = /Datafile: (.*?) /o
|
31
|
-
File.open(file) do |fh|
|
32
|
-
10.times { fh.readline }
|
33
|
-
scan_range_line = fh.readline
|
34
|
-
if scan_range_line =~ /scan range\s+= \d+ - (\d+)/
|
35
|
-
# this is an overestimate (since MS scans have no dta, but that's OK)
|
36
|
-
dta_index = Array.new($1.to_i)
|
37
|
-
else
|
38
|
-
dta_index = []
|
39
|
-
end
|
40
|
-
3.times { fh.readline }
|
41
|
-
fh.each do |line|
|
42
|
-
if line =~ re
|
43
|
-
if line =~ scan_line_re
|
44
|
-
first_scan = $1.to_i
|
45
|
-
last_scan = $2.to_i
|
46
|
-
the_rest = $4.dup
|
47
|
-
dta_index[dta_cnt] = [first_scan, last_scan, $3.sub(/\.dta/,'')]
|
48
|
-
dta_cnt += 1
|
49
|
-
if the_rest =~ other_dta_re
|
50
|
-
dta_index[dta_cnt] = [first_scan, last_scan, $1.sub(/\.dta/,'')]
|
51
|
-
dta_cnt += 1
|
52
|
-
end
|
53
|
-
end
|
54
|
-
break
|
55
|
-
end
|
56
|
-
end
|
57
|
-
fh.each do |line|
|
58
|
-
if line =~ scan_line_re
|
59
|
-
first_scan = $1.to_i
|
60
|
-
last_scan = $2.to_i
|
61
|
-
the_rest = $4.dup
|
62
|
-
dta_index[dta_cnt] = [first_scan, last_scan, $3.sub(/\.dta/,'')]
|
63
|
-
dta_cnt += 1
|
64
|
-
if the_rest =~ other_dta_re
|
65
|
-
dta_index[dta_cnt] = [first_scan, last_scan, $1.sub(/\.dta/,'')]
|
66
|
-
dta_cnt += 1
|
67
|
-
end
|
68
|
-
end
|
69
|
-
end
|
70
|
-
end
|
71
|
-
dta_index.compact! # remove those trailing nils
|
72
|
-
dta_index
|
73
|
-
end
|
74
|
-
end
|
75
24
|
|
76
25
|
class SRFGroup
|
77
26
|
include SpecID
|
@@ -83,12 +32,15 @@ class SRFGroup
|
|
83
32
|
# takes an array of filenames
|
84
33
|
# or a single .srg filename
|
85
34
|
# see from_srg to load a single .srg file
|
86
|
-
|
35
|
+
# by default, the hits will be returned filtered by sequest params values.
|
36
|
+
# [The raw SRF data is unfiltered!]
|
37
|
+
def initialize(filenames=nil, filter_hits_by_params=true)
|
87
38
|
@filenames = filenames
|
88
39
|
@peps = []
|
89
40
|
@prots = []
|
90
|
-
@global_ref_hash = {}
|
91
41
|
@srfs = []
|
42
|
+
|
43
|
+
global_ref_hash = {}
|
92
44
|
if filenames
|
93
45
|
if filenames.is_a?(String) && filenames =~ /\.srg$/
|
94
46
|
srg_filename = filenames.dup
|
@@ -103,16 +55,99 @@ class SRFGroup
|
|
103
55
|
end
|
104
56
|
end
|
105
57
|
filenames.each do |file|
|
106
|
-
@srfs << SRF.new(file, @peps,
|
58
|
+
@srfs << SRF.new(file, @peps, global_ref_hash)
|
59
|
+
end
|
60
|
+
@prots = global_ref_hash.values
|
61
|
+
if filter_hits_by_params
|
62
|
+
filter_by_peptide_mass_tolerance
|
63
|
+
end
|
64
|
+
end
|
65
|
+
end
|
66
|
+
|
67
|
+
# if srfs were read in separately, then the proteins will need to be merged
|
68
|
+
# by their reference
|
69
|
+
def merge_different_sets(srfs)
|
70
|
+
raise NotImplementedError, "need to implement?"
|
71
|
+
end
|
72
|
+
|
73
|
+
# 1. sets @prots and returns it: a new list of proteins based on which
|
74
|
+
# peptides passed.
|
75
|
+
# 2. updates the out_file's list of hits based on passing peptides (but not
|
76
|
+
# the original hit id; rank is implicit in array ordering)
|
77
|
+
# 3. updates each protein to only include peptides passing thresholds.
|
78
|
+
# [Note, this process is how .out files are generated!]
|
79
|
+
# 4. recalculates deltacn values completely if number of hits changed (does
|
80
|
+
# not touch deltacn orig)
|
81
|
+
# ASSUMES:
|
82
|
+
# A. all srfs have identical params objects and each has a
|
83
|
+
# peptide_mass_tolerance filter attribute.
|
84
|
+
# B. proteins are already unique (peptides referencing the same protein
|
85
|
+
# reference the same object already) In practice, this means all srfs were
|
86
|
+
# read in together.
|
87
|
+
def filter_by_peptide_mass_tolerance
|
88
|
+
prots_in_set = Set.new
|
89
|
+
params = @srfs.first.params
|
90
|
+
pmt = params.peptide_mass_tolerance.to_f
|
91
|
+
methd = nil # the method to
|
92
|
+
|
93
|
+
case params.peptide_mass_units
|
94
|
+
when '0'
|
95
|
+
amu_based = true
|
96
|
+
milli_amu = false
|
97
|
+
when '1'
|
98
|
+
amu_based = true
|
99
|
+
milli_amu = true
|
100
|
+
when '2'
|
101
|
+
amu_based = false
|
102
|
+
end
|
103
|
+
|
104
|
+
@srfs.each do |srf|
|
105
|
+
srf.out_files.each do |out_file|
|
106
|
+
hits = out_file.hits
|
107
|
+
before = hits.size
|
108
|
+
hits.reject! do |pep|
|
109
|
+
do_not_keep =
|
110
|
+
if amu_based
|
111
|
+
if milli_amu
|
112
|
+
(pep.deltamass.abs > (pmt/1000))
|
113
|
+
else
|
114
|
+
(pep.deltamass.abs > pmt)
|
115
|
+
end
|
116
|
+
else
|
117
|
+
(pep.ppm.abs > pmt)
|
118
|
+
end
|
119
|
+
unless do_not_keep
|
120
|
+
pep.prots.each do |prot|
|
121
|
+
if prots_in_set.include?(prot)
|
122
|
+
prot.peps << pep
|
123
|
+
else
|
124
|
+
prots_in_set.add(prot)
|
125
|
+
prot.peps = [pep]
|
126
|
+
end
|
127
|
+
end
|
128
|
+
end
|
129
|
+
do_not_keep
|
130
|
+
end
|
131
|
+
if hits.size != before
|
132
|
+
SRF::OUT::Pep.set_deltacn_from_xcorr(hits)
|
133
|
+
end
|
107
134
|
end
|
108
135
|
end
|
136
|
+
@prots = prots_in_set.to_a
|
137
|
+
|
109
138
|
end
|
110
139
|
|
111
140
|
# returns the filename used
|
141
|
+
# if the file exists, the name will be expanded to full path, otherwise just
|
142
|
+
# what is given
|
112
143
|
def to_srg(srg_filename='bioworks.srg')
|
113
144
|
File.open(srg_filename, 'w') do |v|
|
114
145
|
@filenames.each do |srf_file|
|
115
|
-
|
146
|
+
if File.exist? srf_file
|
147
|
+
v.puts File.expand_path(srf_file)
|
148
|
+
else
|
149
|
+
v.puts srf_file
|
150
|
+
end
|
116
151
|
end
|
117
152
|
end
|
118
153
|
srg_filename
|
@@ -132,15 +167,25 @@ class SRF
|
|
132
167
|
# [first_scan, last_scan, charge]
|
133
168
|
attr_accessor :index
|
134
169
|
attr_accessor :base_name
|
170
|
+
# this is the global peptides array
|
171
|
+
attr_accessor :peps
|
172
|
+
# the global reference hash that allows...
|
173
|
+
attr_accessor :global_ref_hash
|
135
174
|
|
136
175
|
def dta_start_byte
|
137
176
|
case @version
|
138
177
|
when '3.2' ; 3260
|
139
178
|
when '3.3' ; 3644
|
179
|
+
when '3.5' ; 3644
|
140
180
|
end
|
141
181
|
end
|
142
182
|
|
143
|
-
# peps and
|
183
|
+
# peps and global_ref_hash are created as the srf files is read. If the
|
184
|
+
# file is read as part of a group, then these should be passed in.
|
185
|
+
# NOTE: if you want the hits filtered by precursor tolerance (the way they
|
186
|
+
# might be displayed in .out files) you should probably use SRFGroup (which
|
187
|
+
# does this by default)
|
188
|
+
# SRF is meant to be a low level read of the file.
|
144
189
|
def initialize(filename=nil, peps=[], global_ref_hash={})
|
145
190
|
@dta_files = []
|
146
191
|
@out_files = []
|
@@ -149,17 +194,203 @@ class SRF
|
|
149
194
|
end
|
150
195
|
end
|
151
196
|
|
197
|
+
def round(float, decimal_places)
|
198
|
+
sprintf("%.#{decimal_places}f", float)
|
199
|
+
end
|
200
|
+
|
201
|
+
# the out_filename will be the base_name + .sqt unless 'out_filename' is
|
202
|
+
# defined
|
203
|
+
# :round => round floating point numbers
|
204
|
+
# etc...
|
205
|
+
def to_sqt(out_filename=nil, opts={})
|
206
|
+
tic_dp = 2
|
207
|
+
mh_dp = 7
|
208
|
+
xcorr_dp = 5
|
209
|
+
sp_dp = 2
|
210
|
+
dcn_dp = 5
|
211
|
+
|
212
|
+
defaults = {:db_info=>false, :new_db_path=>nil, :update_db_path=>false, :round=>false}
|
213
|
+
opt = defaults.merge(opts)
|
214
|
+
|
215
|
+
outfile =
|
216
|
+
if out_filename
|
217
|
+
out_filename
|
218
|
+
else
|
219
|
+
base_name + '.sqt'
|
220
|
+
end
|
221
|
+
invariant_ordering = %w(SQTGenerator SQTGeneratorVersion Database FragmentMasses PrecursorMasses StartTime) # just for readability and consistency
|
222
|
+
fmt =
|
223
|
+
if params.fragment_mass_type == 'average' ; 'AVG'
|
224
|
+
else ; 'MONO'
|
225
|
+
end
|
226
|
+
pmt =
|
227
|
+
if params.precursor_mass_type == 'average' ; 'AVG'
|
228
|
+
else ; 'MONO'
|
229
|
+
end
|
230
|
+
|
231
|
+
mass_table = params.mass_table
|
232
|
+
static_mods = params.static_mods.map do |k,v|
|
233
|
+
key = k.split(/_/)[1]
|
234
|
+
if key.size == 1
|
235
|
+
key + '=' + (mass_table[key.to_sym] + v.to_f).to_s
|
236
|
+
else
|
237
|
+
key + '=' + v
|
238
|
+
end
|
239
|
+
end
|
240
|
+
|
241
|
+
dynamic_mods = []
|
242
|
+
header.modifications.scan(/\((.*?)\)/) do |match|
|
243
|
+
dynamic_mods << match.first.sub(/ /,'=')
|
244
|
+
end
|
245
|
+
plural = {
|
246
|
+
'StaticMod' => static_mods,
|
247
|
+
'DynamicMod' => dynamic_mods, # example as diff mod
|
248
|
+
'Comment' => ['Created from Bioworks .srf file']
|
249
|
+
}
|
250
|
+
|
251
|
+
|
252
|
+
db_filename = header.db_filename
|
253
|
+
db_filename_in_sqt = db_filename
|
254
|
+
if opt[:new_db_path]
|
255
|
+
db_filename = File.join(opt[:new_db_path], File.basename(db_filename.gsub('\\', '/')))
|
256
|
+
if opt[:update_db_path]
|
257
|
+
db_filename_in_sqt = File.expand_path(db_filename)
|
258
|
+
warn "writing Database #{db_filename} to sqt, but it does not exist on this file system" unless File.exist?(db_filename)
|
259
|
+
end
|
260
|
+
end
|
261
|
+
|
262
|
+
apmu =
|
263
|
+
case params.peptide_mass_units
|
264
|
+
when '0' : 'amu'
|
265
|
+
when '1' : 'mmu'
|
266
|
+
when '2' : 'ppm'
|
267
|
+
end
|
268
|
+
|
269
|
+
hh = {
|
270
|
+
'SQTGenerator' => 'mspire',
|
271
|
+
'SQTGeneratorVersion' => Mspire::Version,
|
272
|
+
'Database' => db_filename_in_sqt,
|
273
|
+
'FragmentMasses' => fmt,
|
274
|
+
'PrecursorMasses' => pmt,
|
275
|
+
'StartTime' => '', # Bioworks 3.2 also leaves this blank...
|
276
|
+
'Alg-PreMassTol' => params.peptide_mass_tolerance,
|
277
|
+
'Alg-FragMassTol' => params.fragment_ion_tolerance,
|
278
|
+
'Alg-PreMassUnits' => apmu, ## mine
|
279
|
+
'Alg-IonSeries' => header.ion_series.split(':').last.lstrip,
|
280
|
+
'Alg-Enzyme' => header.enzyme.split(':').last,
|
281
|
+
'Alg-MSModel' => header.model,
|
282
|
+
}
|
283
|
+
|
284
|
+
if opt[:db_info]
|
285
|
+
if File.exist?(db_filename)
|
286
|
+
reply = get_db_info_for_sqt(db_filename)
|
287
|
+
%w(DBSeqLength DBLocusCount DBMD5Sum).zip(reply) do |label,val|
|
288
|
+
hh[label] = val
|
289
|
+
end
|
290
|
+
else
|
291
|
+
warn "file #{db_filename} does not exist, no extra db info in header!"
|
292
|
+
end
|
293
|
+
end
|
294
|
+
|
295
|
+
has_hits = (self.out_files.size > 0)
|
296
|
+
if has_hits
|
297
|
+
# somewhat redundant with above, but we can get this without a db present!
|
298
|
+
hh['DBLocusCount'] = self.out_files.first.db_locus_count
|
299
|
+
end
|
300
|
+
|
301
|
+
File.open(outfile, 'w') do |out|
|
302
|
+
# print the header:
|
303
|
+
invariant_ordering.each do |iv|
|
304
|
+
out.puts ['H', iv, hh.delete(iv)].join("\t")
|
305
|
+
end
|
306
|
+
hh.each do |k,v|
|
307
|
+
out.puts ['H', k, v].join("\t")
|
308
|
+
end
|
309
|
+
plural.each do |k,vals|
|
310
|
+
vals.each do |val|
|
311
|
+
out.puts ['H', k, val].join("\t")
|
312
|
+
end
|
313
|
+
end
|
314
|
+
|
315
|
+
##### SPECTRA
|
316
|
+
time_to_process = '0.0'
|
317
|
+
#########################################
|
318
|
+
# NEED TO FIGURE OUT: (in spectra guy)
|
319
|
+
# * Lowest Sp value for top 500 spectra
|
320
|
+
# * Number of sequences matching this precursor ion
|
321
|
+
#########################################
|
322
|
+
|
323
|
+
|
324
|
+
manual_validation_status = 'U'
|
325
|
+
self.out_files.zip(dta_files) do |out_file, dta_file|
|
326
|
+
# don't have the time to process (using 0.0 like bioworks 3.2)
|
327
|
+
dta_file_mh = dta_file.mh
|
328
|
+
out_file_total_inten = out_file.total_inten
|
329
|
+
out_file_lowest_sp = out_file.lowest_sp
|
330
|
+
if opt[:round]
|
331
|
+
dta_file_mh = round(dta_file_mh, mh_dp)
|
332
|
+
out_file_total_inten = round(out_file_total_inten, tic_dp)
|
333
|
+
out_file_lowest_sp = round(out_file_lowest_sp, sp_dp)
|
334
|
+
end
|
335
|
+
|
336
|
+
out.puts ['S', out_file.first_scan, out_file.last_scan, out_file.charge, time_to_process, out_file.computer, dta_file_mh, out_file_total_inten, out_file_lowest_sp, out_file.num_matched_peptides].join("\t")
|
337
|
+
out_file.hits.each_with_index do |hit,index|
|
338
|
+
hit_mh = hit.mh
|
339
|
+
hit_deltacn_orig = hit.deltacn_orig
|
340
|
+
hit_xcorr = hit.xcorr
|
341
|
+
hit_sp = hit.sp
|
342
|
+
if opt[:round]
|
343
|
+
hit_mh = round(hit_mh, mh_dp)
|
344
|
+
hit_deltacn_orig = round(hit_deltacn_orig, dcn_dp)
|
345
|
+
hit_xcorr = round(hit_xcorr, xcorr_dp)
|
346
|
+
hit_sp = round(hit_sp, sp_dp)
|
347
|
+
end
|
348
|
+
# note that the rank is determined by the order..
|
349
|
+
out.puts ['M', index+1, hit.rsp, hit_mh, hit_deltacn_orig, hit_xcorr, hit_sp, hit.ions_matched, hit.ions_total, hit.sequence, manual_validation_status].join("\t")
|
350
|
+
hit.prots.each do |prot|
|
351
|
+
out.puts ['L', prot.first_entry].join("\t")
|
352
|
+
end
|
353
|
+
end
|
354
|
+
end
|
355
|
+
end # close the filehandle
|
356
|
+
|
357
|
+
end
|
358
|
+
|
359
|
+
# assumes the file exists and is readable
|
360
|
+
# returns [DBSeqLength, DBLocusCount, DBMD5Sum] or nil if no file
|
361
|
+
def get_db_info_for_sqt(dbfile)
|
362
|
+
fasta = Fasta.new(dbfile)
|
363
|
+
[fasta.aa_seq_length, fasta.size, fasta.md5_sum]
|
364
|
+
end
|
365
|
+
|
366
|
+
|
152
367
|
# returns self
|
153
368
|
def from_file(filename, peps, global_ref_hash)
|
154
369
|
|
155
370
|
File.open(filename, "rb") do |fh|
|
156
371
|
@header = SRF::Header.new.from_handle(fh)
|
157
372
|
@version = @header.version
|
158
|
-
|
159
|
-
|
160
|
-
|
161
|
-
|
162
|
-
|
373
|
+
unpack_35 = case @version
|
374
|
+
when '3.2'
|
375
|
+
false
|
376
|
+
when '3.3'
|
377
|
+
false
|
378
|
+
when '3.5'
|
379
|
+
true
|
380
|
+
end
|
381
|
+
@dta_files, measured_mhs = read_dta_files(fh,@header.num_dta_files, unpack_35)
|
382
|
+
|
383
|
+
@out_files = read_out_files(fh,@header.num_dta_files, global_ref_hash, measured_mhs, unpack_35)
|
384
|
+
if fh.eof?
|
385
|
+
warn "FILE: '#{filename}' appears to be an abortive run (no params in srf file)\nstill continuing..."
|
386
|
+
@params = nil
|
387
|
+
@index = []
|
388
|
+
else
|
389
|
+
@params = Sequest::Params.new.parse_handle(fh)
|
390
|
+
# This is very sensitive to the grab_params method in sequest params
|
391
|
+
fh.read(12) ## gap between last params entry and index
|
392
|
+
@index = read_scan_index(fh,@header.num_dta_files)
|
393
|
+
end
|
163
394
|
end
|
164
395
|
|
165
396
|
### UPDATE SOME THINGS ON SINGLE PASS:
|
@@ -168,14 +399,15 @@ class SRF
|
|
168
399
|
@index.each_with_index do |ind,i|
|
169
400
|
mass_measured = @dta_files[i][0]
|
170
401
|
#puts @out_files[i].join(", ")
|
171
|
-
|
402
|
+
@out_files[i][0,3] = *ind
|
403
|
+
pep_hits = @out_files[i][6]
|
172
404
|
peps.push( *pep_hits )
|
173
405
|
pep_hits.each do |pep_hit|
|
174
|
-
pep_hit[
|
406
|
+
pep_hit[14,4] = @base_name, *ind
|
175
407
|
# add the deltamass
|
176
|
-
pep_hit[
|
177
|
-
pep_hit[
|
178
|
-
pep_hit[
|
408
|
+
pep_hit[11] = pep_hit[0] - mass_measured # real - measured (deltamass)
|
409
|
+
pep_hit[12] = 1.0e6 * pep_hit[11].abs / mass_measured ## ppm
|
410
|
+
pep_hit[18] = self ## link with the srf object
|
179
411
|
end
|
180
412
|
end
|
181
413
|
self
|
@@ -195,27 +427,17 @@ class SRF
|
|
195
427
|
index
|
196
428
|
end
|
197
429
|
|
198
|
-
# given a zero indexed list where each entry is [first_scan, last_scan,
|
199
|
-
# dta_filename] updates the out info
|
200
|
-
# returns self
|
201
|
-
def update_out_scan_info_from_dta_log(dta_log)
|
202
|
-
index = DTALog.dta_and_scans_by_dta_index(dta_log)
|
203
|
-
@out_files.each_with_index do |ot,i|
|
204
|
-
ot[4,3] = index[i] #contingent on implementation of ot
|
205
|
-
end
|
206
|
-
self
|
207
|
-
end
|
208
|
-
|
209
430
|
# returns an array of dta_files
|
210
|
-
def read_dta_files(fh, num_files)
|
431
|
+
def read_dta_files(fh, num_files, unpack_35)
|
211
432
|
measured_mhs = Array.new(num_files) ## A parallel array to capture the actual mh
|
212
433
|
dta_files = Array.new(num_files)
|
213
434
|
start = dta_start_byte
|
214
435
|
unless fh.pos == start
|
215
436
|
fh.pos = start
|
216
437
|
end
|
438
|
+
|
217
439
|
header.num_dta_files.times do |i|
|
218
|
-
dta_file = SRF::DTA.new.from_handle(fh)
|
440
|
+
dta_file = SRF::DTA.new.from_handle(fh, unpack_35)
|
219
441
|
measured_mhs[i] = dta_file[0]
|
220
442
|
dta_files[i] = dta_file
|
221
443
|
end
|
@@ -224,10 +446,10 @@ class SRF
|
|
224
446
|
|
225
447
|
# filehandle (fh) must be at the start of the outfiles. 'read_dta_files'
|
226
448
|
# will put the fh there.
|
227
|
-
def read_out_files(fh,number_files, global_ref_hash, measured_mhs)
|
449
|
+
def read_out_files(fh,number_files, global_ref_hash, measured_mhs, unpack_35)
|
228
450
|
out_files = Array.new(number_files)
|
229
451
|
header.num_dta_files.times do |i|
|
230
|
-
out_files[i] = SRF::OUT.new.from_handle(fh, global_ref_hash)
|
452
|
+
out_files[i] = SRF::OUT.new.from_handle(fh, global_ref_hash, unpack_35)
|
231
453
|
end
|
232
454
|
out_files
|
233
455
|
end
|
@@ -326,31 +548,44 @@ class SRF::DTAGen
|
|
326
548
|
end
|
327
549
|
end
|
328
550
|
|
551
|
+
# total_num_possible_charge_states is not correct under 3.5 (Bioworks 3.3.1)
|
552
|
+
# unknown is, well unknown...
|
329
553
|
SRF::DTA = ArrayClass.new(%w(mh dta_tic num_peaks charge ms_level unknown total_num_possible_charge_states peaks))
|
330
554
|
|
331
555
|
class SRF::DTA
|
332
|
-
|
333
|
-
|
334
|
-
|
335
|
-
|
556
|
+
# original
|
557
|
+
# Unpack = "EeIvvvv"
|
558
|
+
Unpack_32 = "EeIvvvv"
|
559
|
+
Unpack_35 = "Ex8eVx2vvvv"
|
336
560
|
|
337
561
|
# note on peaks (self[7])
|
338
562
|
# this is a byte array of floats, you can get the peaks out with
|
339
563
|
# unpack("e*")
|
340
564
|
|
565
|
+
undef_method :inspect
|
341
566
|
def inspect
|
342
567
|
peaks_st = 'nil'
|
343
568
|
if self[7] ; peaks_st = "[#{self[7].size} bytes]" end
|
344
569
|
"<SRF::DTA @mh=#{mh} @dta_tic=#{dta_tic} @num_peaks=#{num_peaks} @charge=#{charge} @ms_level=#{ms_level} @total_num_possible_charge_states=#{total_num_possible_charge_states} @peaks=#{peaks_st} >"
|
345
570
|
end
|
346
571
|
|
347
|
-
def from_handle(fh)
|
348
|
-
|
572
|
+
def from_handle(fh, unpack_35)
|
573
|
+
if unpack_35
|
574
|
+
@unpack = Unpack_35
|
575
|
+
@read_header = 34
|
576
|
+
@read_spacer = 22
|
577
|
+
else
|
578
|
+
@unpack = Unpack_32
|
579
|
+
@read_header = 24
|
580
|
+
@read_spacer = 24
|
581
|
+
end
|
582
|
+
|
583
|
+
st = fh.read(@read_header)
|
349
584
|
# get the bulk of the data in single unpack
|
350
|
-
self[0,7] = st.unpack(
|
585
|
+
self[0,7] = st.unpack(@unpack)
|
351
586
|
|
352
|
-
# Scan numbers
|
353
|
-
st2 = fh.read(
|
587
|
+
# Scan numbers are given at the end in an index!
|
588
|
+
st2 = fh.read(@read_spacer)
|
354
589
|
|
355
590
|
num_bytes_to_read = num_peaks * 8
|
356
591
|
st3 = fh.read(num_bytes_to_read)
|
@@ -360,135 +595,176 @@ class SRF::DTA
|
|
360
595
|
|
361
596
|
end
|
362
597
|
|
363
|
-
SRF::OUT =
|
364
|
-
# 0=
|
598
|
+
SRF::OUT = ArrayClass.new( %w(first_scan last_scan charge num_hits computer date_time hits total_inten lowest_sp num_matched_peptides db_locus_count) )
|
599
|
+
# 0=first_scan, 1=last_scan, 2=charge, 3=num_hits, 4=computer, 5=date_time, 6=hits, 7=total_inten, 8=lowest_sp, 9=num_matched_peptides, 10=db_locus_count
|
365
600
|
|
366
601
|
class SRF::OUT
|
367
|
-
|
602
|
+
Unpack_32 = '@36vx2Z*@60Z*'
|
603
|
+
Unpack_35 = '@36vx4Z*@62Z*'
|
368
604
|
|
605
|
+
undef_method :inspect
|
369
606
|
def inspect
|
370
|
-
|
371
|
-
|
372
|
-
|
373
|
-
|
607
|
+
hits_s =
|
608
|
+
if self[6]
|
609
|
+
", @hits(#)=#{hits.size}"
|
610
|
+
else
|
611
|
+
''
|
612
|
+
end
|
613
|
+
"<SRF::OUT first_scan=#{first_scan}, last_scan=#{last_scan}, charge=#{charge}, num_hits=#{num_hits}, computer=#{computer}, date_time=#{date_time}#{hits_s}>"
|
374
614
|
end
|
375
615
|
|
376
|
-
def from_handle(fh, global_ref_hash)
|
616
|
+
def from_handle(fh, global_ref_hash, unpack_35)
|
377
617
|
## EMPTY out file is 96 bytes
|
378
618
|
## each hit is 320 bytes
|
379
619
|
## num_hits and charge:
|
380
620
|
st = fh.read(96)
|
381
|
-
|
382
|
-
|
621
|
+
|
622
|
+
self[3,3] = st.unpack( (unpack_35 ? Unpack_35 : Unpack_32) )
|
623
|
+
self[7,4] = st.unpack('@8eex4Ix4I')
|
624
|
+
num_hits = self[3]
|
383
625
|
|
384
626
|
ar = Array.new(num_hits)
|
385
627
|
if ar.size > 0
|
628
|
+
num_extra_references = 0
|
386
629
|
num_hits.times do |i|
|
387
|
-
ar[i] = SRF::OUT::Pep.new.from_handle(fh, global_ref_hash)
|
630
|
+
ar[i] = SRF::OUT::Pep.new.from_handle(fh, global_ref_hash, unpack_35)
|
631
|
+
num_extra_references += ar[i].num_other_loci
|
388
632
|
end
|
633
|
+
SRF::OUT::Pep.read_extra_references(fh, num_extra_references, ar, global_ref_hash)
|
389
634
|
## The xcorrs are already ordered by best to worst hit
|
390
635
|
## ADJUST the deltacn's to be meaningful for the top hit:
|
391
636
|
## (the same as bioworks and prophet)
|
392
|
-
(
|
393
|
-
ar.
|
637
|
+
SRF::OUT::Pep.set_deltacn_from_deltacn_orig(ar)
|
638
|
+
#puts ar.map {|a| a.deltacn }.join(", ")
|
394
639
|
end
|
395
|
-
self[
|
396
|
-
|
640
|
+
self[6] = ar
|
397
641
|
self
|
398
642
|
end
|
399
643
|
|
644
|
+
|
645
|
+
|
400
646
|
end
|
401
647
|
|
648
|
+
|
402
649
|
# deltacn is modified to be that of the next best hit (by xcorr).
|
650
|
+
# deltacn_orig is the one that sequest originally reports
|
403
651
|
# if there is no next best hit, then it will be 1.1 (like bioworks)
|
404
652
|
# mh is the theoretical mass + h
|
405
653
|
# prots are created as SRF prot objects with a reference and linked to their
|
406
654
|
# peptides (from global hash by reference)
|
407
655
|
# ppm = 10^6 * ∆m_accuracy / mass_measured [ where ∆m_accuracy = mass_real – mass_measured ]
|
408
656
|
# This is calculated for the M+H mass!
|
657
|
+
# num_other_loci is the number of other loci that the peptide matches beyond
|
658
|
+
# the first one listed
|
409
659
|
# srf = the srf object this scan came from
|
410
|
-
SRF::OUT::Pep = ArrayClass.new(%w( mh deltacn sp xcorr id rsp ions_matched ions_total sequence prots deltamass ppm aaseq base_name first_scan last_scan charge srf) )
|
411
660
|
|
412
|
-
|
661
|
+
SRF::OUT::Pep = ArrayClass.new(%w( mh deltacn_orig sp xcorr id num_other_loci rsp ions_matched ions_total sequence prots deltamass ppm aaseq base_name first_scan last_scan charge srf deltacn) )
|
662
|
+
|
663
|
+
# 0=mh 1=deltacn 2=sp 3=xcorr 4=id 5=num_other_loci 6=rsp 7=ions_matched 8=ions_total 9=sequence 10=prots 11=deltamass 12=ppm 13=aaseq 14=base_name 15=first_scan 16=last_scan 17=charge 18=srf 19=deltacn
|
413
664
|
|
414
665
|
class SRF::OUT::Pep
|
415
666
|
include SpecID::Pep
|
416
667
|
|
417
|
-
|
668
|
+
# creates the deltacn that is meaningful for the top hit (the deltacn_orig
|
669
|
+
# or the second best hit and so on).
|
670
|
+
# assumes sorted
|
671
|
+
def self.set_deltacn_from_deltacn_orig(ar)
|
672
|
+
(1...ar.size).each {|i| ar[i-1].deltacn = ar[i].deltacn_orig }
|
673
|
+
ar[-1].deltacn = 1.1
|
674
|
+
end
|
675
|
+
|
676
|
+
# same as set_deltacn_from_deltacn_orig except calculates with xcorr.
|
677
|
+
# assumes sorted
|
678
|
+
def self.set_deltacn_from_xcorr(ar)
|
679
|
+
if ar.size > 0
|
680
|
+
top_score = ar.first[3]
|
681
|
+
other_scores = (1...(ar.size)).to_a.map do |i|
|
682
|
+
(top_score - ar[i][3])/top_score
|
683
|
+
end
|
684
|
+
(0...(ar.size-1)).each do |i|
|
685
|
+
ar[i][19] = other_scores[i]
|
686
|
+
end
|
687
|
+
ar.last[19] = 1.1
|
688
|
+
end
|
689
|
+
end
|
690
|
+
|
691
|
+
def self.read_extra_references(fh, num_extra_references, pep_hits, global_ref_hash)
|
692
|
+
num_extra_references.times do
|
693
|
+
# 80 bytes total (with index number)
|
694
|
+
pep = pep_hits[fh.read(8).unpack('x4I').first - 1]
|
695
|
+
|
696
|
+
ref = fh.read(80).unpack('A*').first
|
697
|
+
pep[10] << pep.new_protein(ref[0,38], pep, global_ref_hash)
|
698
|
+
end
|
699
|
+
# fh.read(6) if unpack_35
|
700
|
+
end
|
701
|
+
|
702
|
+
# x2=???
|
703
|
+
#Unpack_35 = '@64Ex8ex12eeIx22vx2vvx8Z*@246Z*'
|
704
|
+
### NOTE:
|
705
|
+
# I need to verify that this is correct (I mean the 'I' after x18)
|
706
|
+
Unpack_35 = '@64Ex8ex12eeIx18Ivx2vvx8Z*@246Z*'
|
707
|
+
# translation: @64=(64 bytes in to the record), E=mH, x8=8unknown bytes, e=deltacn,
|
708
|
+
# x12=12unknown bytes, e=sp, e=xcorr, I=ID#, x18=18 unknown bytes, v=rsp,
|
709
|
+
# v=ions_matched, v=ions_total, x8=8unknown bytes, Z*=sequence, 240Z*=at
|
710
|
+
# byte 240 grab the string (which is proteins).
|
711
|
+
#Unpack_32 = '@64Ex8ex12eeIx18vvvx8Z*@240Z*'
|
712
|
+
Unpack_32 = '@64Ex8ex12eeIx14Ivvvx8Z*@240Z*'
|
418
713
|
Unpack_four_null_bytes = 'a*'
|
419
714
|
Unpack_Zstar = 'Z*'
|
715
|
+
Read_35 = 426
|
716
|
+
Read_32 = 320
|
420
717
|
|
421
718
|
FourNullBytes_as_string = "\0\0\0\0"
|
422
719
|
#NewRecordStart = "\0\0" + 0x3a.chr + 0x1a.chr + "\0\0"
|
423
720
|
NewRecordStart = 0x01.chr + 0x00.chr
|
424
721
|
Sequest_record_start = "[SEQUEST]"
|
425
722
|
|
426
|
-
|
427
|
-
def prots() self[9] end
|
428
|
-
$VERBOSE = tmp
|
429
|
-
|
723
|
+
undef_method :inspect
|
430
724
|
def inspect
|
431
|
-
st = %w(aaseq sequence mh
|
432
|
-
if v
|
725
|
+
st = %w(aaseq sequence mh deltacn_orig sp xcorr id rsp ions_matched ions_total prots deltamass ppm base_name first_scan last_scan charge deltacn).map do |v|
|
726
|
+
if v == 'prots'
|
727
|
+
"#{v}(#)=#{send(v.to_sym).size}"
|
728
|
+
elsif v.is_a? Array
|
433
729
|
"##{v}=#{send(v.to_sym).size}"
|
434
730
|
else
|
435
|
-
"
|
731
|
+
"#{v}=#{send(v.to_sym).inspect}"
|
436
732
|
end
|
437
733
|
end
|
438
734
|
st.unshift("<#{self.class}")
|
439
735
|
if srf
|
440
|
-
st.push("
|
736
|
+
st.push("srf(base_name)=#{srf.base_name.inspect}")
|
441
737
|
end
|
442
738
|
st.push('>')
|
443
739
|
st.join(' ')
|
444
740
|
#"<SRF::OUT::Pep @mh=#{mh}, @deltacn=#{deltacn}, @sp=#{sp}, @xcorr=#{xcorr}, @id=#{id}, @rsp=#{rsp}, @ions_matched=#{ions_matched}, @ions_total=#{ions_total}, @sequence=#{sequence}, @prots(count)=#{prots.size}, @deltamass=#{deltamass}, @ppm=#{ppm} @aaseq=#{aaseq}, @base_name=#{base_name}, @first_scan=#{first_scan}, @last_scan=#{last_scan}, @charge=#{charge}, @srf(base_name)=#{srf.base_name}>"
|
445
741
|
end
|
742
|
+
# extra_references_array is an array that grows with peptides as extra
|
743
|
+
# references are discovered.
|
744
|
+
def from_handle(fh, global_ref_hash, unpack_35)
|
745
|
+
unpack =
|
746
|
+
if unpack_35 ; Unpack_35
|
747
|
+
else ; Unpack_32
|
748
|
+
end
|
446
749
|
|
447
|
-
|
448
|
-
|
449
|
-
## so that we are in register for the next reading
|
450
|
-
def read_extra_references(fh, global_ref_hash)
|
451
|
-
$SRF_OUT_HIT_FH_POS = fh.pos
|
452
|
-
st = fh.read(4)
|
453
|
-
#puts "HHH: " + st.unpack("H*").first
|
454
|
-
## if we see 0000 0000 we are done
|
455
|
-
if st.unpack(Unpack_four_null_bytes).first == FourNullBytes_as_string
|
456
|
-
fh.pos = $SRF_OUT_HIT_FH_POS
|
457
|
-
return nil
|
458
|
-
end
|
459
|
-
# read in context of 4 bytes read above:
|
460
|
-
|
461
|
-
## NOTE: in context of 4 bytes read above!
|
462
|
-
st = fh.read(36)
|
463
|
-
if st[34,2] == NewRecordStart
|
464
|
-
fh.pos = $SRF_OUT_HIT_FH_POS
|
465
|
-
return nil
|
466
|
-
end
|
750
|
+
## get the first part of the info
|
751
|
+
st = fh.read(( unpack_35 ? Read_35 : Read_32) ) ## read all the hit data
|
467
752
|
|
468
|
-
|
469
|
-
## BACK to beginning of this section
|
470
|
-
fh.pos = $SRF_OUT_HIT_FH_POS
|
471
|
-
if fh.read(9) == Sequest_record_start
|
472
|
-
fh.pos = $SRF_OUT_HIT_FH_POS
|
473
|
-
return
|
474
|
-
end
|
753
|
+
self[0,10] = st.unpack(unpack)
|
475
754
|
|
476
|
-
|
477
|
-
|
478
|
-
|
479
|
-
self[9].push( new_protein(fh.read(80).unpack(Unpack_Zstar).first, self, global_ref_hash ) )
|
755
|
+
# we are slicing the reference to 38 chars to be the same length as
|
756
|
+
# duplicate references
|
757
|
+
self[10] = [new_protein(self[10][0,38], self, global_ref_hash)]
|
480
758
|
|
481
|
-
|
482
|
-
|
483
|
-
|
484
|
-
|
485
|
-
|
486
|
-
# abort
|
487
|
-
#end
|
488
|
-
|
489
|
-
read_extra_references(fh,global_ref_hash)
|
759
|
+
self[13] = SpecID::Pep.sequence_to_aaseq(self[9])
|
760
|
+
|
761
|
+
fh.read(6) if unpack_35
|
762
|
+
|
763
|
+
self
|
490
764
|
end
|
491
765
|
|
766
|
+
|
767
|
+
|
492
768
|
def new_protein(reference, peptide, global_ref_hash)
|
493
769
|
if global_ref_hash.key? reference
|
494
770
|
global_ref_hash[reference].peps << peptide
|
@@ -498,29 +774,20 @@ class SRF::OUT::Pep
|
|
498
774
|
global_ref_hash[reference]
|
499
775
|
end
|
500
776
|
|
501
|
-
|
502
|
-
## get the first part of the info
|
503
|
-
st = fh.read(320) ## read all the hit data
|
504
|
-
self[0,10] = st.unpack(Unpack)
|
505
|
-
# we are slicing the reference to 38 chars to be the same length as
|
506
|
-
# duplicate references
|
507
|
-
self[9] = [new_protein(self[9][0,38], self, global_ref_hash)]
|
508
|
-
self[12] = SpecID::Pep.sequence_to_aaseq(self[8])
|
509
|
-
read_extra_references(fh, global_ref_hash)
|
510
|
-
|
511
|
-
self
|
512
|
-
end
|
513
|
-
|
514
|
-
end
|
777
|
+
end
|
515
778
|
|
516
779
|
SRF::OUT::Prot = ArrayClass.new( %w(reference peps) )
|
517
780
|
|
518
781
|
class SRF::OUT::Prot
|
519
782
|
include SpecID::Prot
|
783
|
+
# we shouldn't have to do this because this is inlcuded in SpecID::Prot, but
|
784
|
+
# under some circumstances it won't work without explicitly calling it.
|
785
|
+
include ProteinReferenceable
|
520
786
|
|
521
787
|
tmp = $VERBOSE ; $VERBOSE = nil
|
522
788
|
def initialize(reference=nil, peps=[])
|
523
|
-
super(@@arr_size)
|
789
|
+
#super(@@arr_size)
|
790
|
+
super(size)
|
524
791
|
#@reference = reference
|
525
792
|
#@peps = peps
|
526
793
|
self[0,2] = reference, peps
|
@@ -529,6 +796,7 @@ class SRF::OUT::Prot
|
|
529
796
|
|
530
797
|
# "<SRF::OUT::Prot reference=\"#{@reference}\">"
|
531
798
|
|
799
|
+
undef_method :inspect
|
532
800
|
def inspect
|
533
801
|
"<SRF::OUT::Prot @reference=#{reference}, @peps(#)=#{peps.size}>"
|
534
802
|
end
|