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/sequest.rb
CHANGED
@@ -1,1675 +1,5 @@
|
|
1
|
+
require 'spec_id/sequest/params'
|
1
2
|
|
2
|
-
|
3
|
-
require 'spec/mzxml/parser'
|
4
|
-
require 'hash_by'
|
5
|
-
require 'set_from_hash'
|
6
|
-
require 'spec_id/bioworks'
|
7
|
-
require 'instance_var_set_from_hash'
|
8
|
-
require 'spec/msrun'
|
9
|
-
require 'spec_id/srf'
|
10
|
-
require 'fileutils'
|
11
|
-
|
12
|
-
class Numeric
|
13
|
-
# returns a string with a + or - on the front
|
14
|
-
def to_plus_minus_string
|
15
|
-
if self >= 0
|
16
|
-
'+' << self.to_s
|
17
|
-
else
|
18
|
-
'-' << self.to_s
|
19
|
-
end
|
20
|
-
end
|
21
|
-
end
|
22
|
-
|
23
|
-
##########################################
|
24
|
-
# NEED TO ADD MODIFICATIONS and generally verify pepxml creation!!! :
|
25
|
-
# HERE's an excerpt from an example file from tpp 2.9.2 that I'm going to follow:
|
26
|
-
=begin
|
27
|
-
<search_summary base_name="/regis/data3/search/akeller/LCQ/COMET/LIGHT/haloICAT2_41" search_engine="COMET" precursor_mass_type="average" fragment_mass_type="average">
|
28
|
-
<sequence_search_constraint sequence="C"/>
|
29
|
-
<aminoacid_modification aminoacid="C" massdiff="8.049" mass="553.765" variable="Y" binary="N"/>
|
30
|
-
<aminoacid_modification aminoacid="C" massdiff="442.5772" mass="545.7160" variable="N"/>
|
31
|
-
<aminoacid_modification aminoacid="M" massdiff="16.0000" mass="147.1926" variable="Y" binary="N" symbol="1"/>
|
32
|
-
<parameter name="peptide_mass_tol" value="3.0000"/>
|
33
|
-
<parameter name="peptide_mass_tol_units" value="DA"/>
|
34
|
-
<parameter name="num_output_lines" value="10"/>
|
35
|
-
<parameter name="remove_precursor_peak" value="0"/>
|
36
|
-
<parameter name="num_dup_headers" value="1"/>
|
37
|
-
<parameter name="email_address" value=""/>
|
38
|
-
<parameter name="ion_series" value="010000010"/>
|
39
|
-
<parameter name="max_num_var_mod_residues" value="3"/>
|
40
|
-
<parameter name="md5_check_sum" value="2547286a77a35abe2af3f2e9825ab814"/>
|
41
|
-
</search_summary>
|
42
|
-
=end
|
43
|
-
|
44
|
-
# and a guy with modifications:
|
45
|
-
=begin
|
46
|
-
<search_result spectrum="haloICAT2_41.1110.1110.2" start_scan="1110" end_scan="1110" precursor_neutral_mass="2000.6641" assumed_charge="2" index="28">
|
47
|
-
<search_hit hit_rank="1" peptide="GCMPSKEVLSAGAHR" peptide_prev_aa="R" peptide_next_aa="Y" protein="Chr_ORF0132" num_tot_proteins="1" num_matched_ions="19" tot_num_ions="30" calc_neutral_pep_mass="2001.3685" massdiff="-0.704" num_tol_term="2" num_missed_cleavages="1" is_rejected="0">
|
48
|
-
<modification_info modified_peptide="GC[546]M[147]PSKEVLSAGAHR">
|
49
|
-
<mod_aminoacid_mass position="2" mass="545.7160"/>
|
50
|
-
<mod_aminoacid_mass position="3" mass="147.1926"/>
|
51
|
-
</modification_info>
|
52
|
-
<search_score name="dotproduct" value="359"/>
|
53
|
-
<search_score name="delta" value="0.296"/>
|
54
|
-
<search_score name="deltastar" value="0"/>
|
55
|
-
<search_score name="zscore" value="5.290"/>
|
56
|
-
<search_score name="expect" value="0.000E+00"/>
|
57
|
-
<peptideprophet_result probability="0.9994" all_ntt_prob="(0.3713,0.4360,0.9994)">
|
58
|
-
<search_score_summary>
|
59
|
-
<parameter name="fval" value="3.4002"/>
|
60
|
-
<parameter name="ntt" value="2"/>
|
61
|
-
<parameter name="nmc" value="1"/>
|
62
|
-
<parameter name="massd" value="-0.704"/>
|
63
|
-
</search_score_summary>
|
64
|
-
</peptideprophet_result>
|
65
|
-
=end
|
66
|
-
|
67
|
-
# sequest.params option:
|
68
|
-
# diff_search_options = 15.994910 M 0.000000 C 0.000000 M 0.000000 X 0.000000 T 0.000000 Y
|
69
|
-
# permanent mods are at the bottom: ...
|
70
|
-
# add_A_Alanine = 0.0000 ; added to A
|
71
|
-
# add_S_Serine = 0.0000 ; added to S
|
72
|
-
# add_P_Proline = 0.0000 ; added to P
|
73
|
-
# add_V_Valine = 0.0000 ; added to V
|
74
|
-
# add_T_Threonine = 0.0000 ; added to T
|
75
|
-
# ...
|
76
|
-
|
77
|
-
|
78
|
-
|
79
|
-
module Sequest; end
|
80
|
-
class Sequest::PepXML; end
|
81
|
-
|
82
|
-
class Sequest::PepXML::MSMSPipelineAnalysis
|
83
|
-
include SpecIDXML
|
84
|
-
# Version 1.2.3
|
85
|
-
attr_writer :date
|
86
|
-
attr_writer :xmlns, :xmlns_xsi, :xsi_schemaLocation
|
87
|
-
attr_accessor :summary_xml
|
88
|
-
# Version 2.3.4
|
89
|
-
attr_writer :xmlns, :xmlns_xsi, :xsi_schema_location
|
90
|
-
attr_accessor :pepxml_version
|
91
|
-
attr_accessor :msms_run_summary
|
92
|
-
|
93
|
-
# if block given, sets msms_run_summary to block
|
94
|
-
def initialize(hash=nil)
|
95
|
-
@xmlns = nil
|
96
|
-
@xmlns_xsi = nil
|
97
|
-
@xsi_schema_location = nil
|
98
|
-
if hash
|
99
|
-
self.set_from_hash(hash)
|
100
|
-
end
|
101
|
-
if block_given?
|
102
|
-
@msms_run_summary = yield
|
103
|
-
end
|
104
|
-
end
|
105
|
-
|
106
|
-
# if no date string given, then it will set to Time.now
|
107
|
-
def date
|
108
|
-
if @date ; @date
|
109
|
-
else
|
110
|
-
case Sequest::PepXML.pepxml_version
|
111
|
-
when 18 ; tarr = Time.now.to_a ; tarr[3..5].reverse.join('-') + "T#{tarr[0..2].reverse.join(':')}"
|
112
|
-
when 0 ; Time.new.to_s
|
113
|
-
end
|
114
|
-
end
|
115
|
-
end
|
116
|
-
|
117
|
-
def xmlns
|
118
|
-
if @xmlns ; @xmlns
|
119
|
-
else ; "http://regis-web.systemsbiology.net/pepXML"
|
120
|
-
end
|
121
|
-
end
|
122
|
-
|
123
|
-
def xmlns_xsi
|
124
|
-
if @xmlns_xsi ; @xmlns_xsi
|
125
|
-
else ; "http://www.w3.org/2001/XMLSchema-instance"
|
126
|
-
end
|
127
|
-
end
|
128
|
-
|
129
|
-
def xsi_schema_location
|
130
|
-
if @xsi_schema_location ; @xsi_schema_location
|
131
|
-
else ; "http://regis-web.systemsbiology.net/pepXML /tools/bin/TPP/tpp/schema/pepXML_v18.xsd"
|
132
|
-
end
|
133
|
-
end
|
134
|
-
|
135
|
-
def to_pepxml
|
136
|
-
case Sequest::PepXML.pepxml_version
|
137
|
-
when 0
|
138
|
-
element_xml(:msms_pipeline_analysis, [:date, :summary_xml]) do
|
139
|
-
@msms_run_summary.to_pepxml
|
140
|
-
end
|
141
|
-
when 18
|
142
|
-
element_xml_and_att_string(:msms_pipeline_analysis, "date=\"#{date}\" xmlns=\"#{xmlns}\" xmlns:xsi=\"#{xmlns_xsi}\" xsi:schemaLocation=\"#{xsi_schema_location}\" summary_xml=\"#{summary_xml}\"") do
|
143
|
-
@msms_run_summary.to_pepxml
|
144
|
-
end
|
145
|
-
else
|
146
|
-
abort "Don't know how to deal with version: #{Sequest::PepXML.pepxml_version}"
|
147
|
-
end
|
148
|
-
end
|
149
|
-
|
150
|
-
end
|
151
|
-
|
152
|
-
class Sequest::PepXML::MSMSRunSummary
|
153
|
-
include SpecIDXML
|
154
|
-
|
155
|
-
# the version of TPP you are using (determines xml output)
|
156
|
-
# The name of the pep xml file (without extension) (but this is a long
|
157
|
-
# filename!!!)
|
158
|
-
attr_accessor :base_name
|
159
|
-
# The name of the mass spec manufacturer
|
160
|
-
attr_accessor :ms_manufacturer
|
161
|
-
attr_accessor :ms_model
|
162
|
-
attr_accessor :ms_mass_analyzer
|
163
|
-
attr_accessor :ms_detector
|
164
|
-
attr_accessor :raw_data_type
|
165
|
-
attr_accessor :raw_data
|
166
|
-
attr_accessor :ms_ionization
|
167
|
-
attr_accessor :pepxml_version
|
168
|
-
|
169
|
-
# A SampleEnzyme object (responds to: name, cut, no_cut, sense)
|
170
|
-
attr_accessor :sample_enzyme
|
171
|
-
# A SearchSummary object
|
172
|
-
attr_accessor :search_summary
|
173
|
-
# An array of spectrum_queries
|
174
|
-
attr_accessor :spectrum_queries
|
175
|
-
|
176
|
-
# takes a hash of name, value pairs
|
177
|
-
# if block given, spectrum_queries (should be array of spectrum queries) is
|
178
|
-
# set to the return value of the block
|
179
|
-
def initialize(hash=nil)
|
180
|
-
@spectrum_queries = []
|
181
|
-
if hash
|
182
|
-
instance_var_set_from_hash(hash)
|
183
|
-
end
|
184
|
-
if block_given? ; @spectrum_queries = yield end
|
185
|
-
end
|
186
|
-
|
187
|
-
def to_pepxml
|
188
|
-
case Sequest::PepXML.pepxml_version
|
189
|
-
when 18
|
190
|
-
element_xml_and_att_string(:msms_run_summary, "base_name=\"#{base_name}\" msManufacturer=\"#{ms_manufacturer}\" msModel=\"#{ms_model}\" msIonization=\"#{ms_ionization}\" msMassAnalyzer=\"#{ms_mass_analyzer}\" msDetector=\"#{ms_detector}\" raw_data_type=\"#{raw_data_type}\" raw_data=\"#{raw_data}\"") do
|
191
|
-
sample_enzyme.to_pepxml +
|
192
|
-
search_summary.to_pepxml +
|
193
|
-
spectrum_queries.map {|sq| sq.to_pepxml }.join
|
194
|
-
end
|
195
|
-
when 0
|
196
|
-
# element_xml(:msms_run_summary, [:base_name, :search_engine, :database, :raw_data_type, :raw_data, :out_data_type, :out_data, :sample_enzyme]) do
|
197
|
-
# element_xml(:search_summary, [:base_name, :search_engine, :precursor_mass_type, :fragment_mass_type]) do
|
198
|
-
# [
|
199
|
-
# @params.short_element_xml(:enzymatic_search_constraint, [:enzyme, :max_num_internal_cleavages, :min_number_termini]),
|
200
|
-
# @params.short_element_xml(:sequence_search_constraint, [:sequence]),
|
201
|
-
# @params.short_element_xml(:sequence_search_constraint, [:sequence]),
|
202
|
-
# @params.pepxml_parameters(:peptide_mass_tol, :fragment_ion_tol, :ion_series, :max_num_differential_AA_per_mod, :nucleotide_reading_frame, :num_output_lines, :remove_precursor_peak, :ion_cutoff_percentage, :match_peak_count, :match_peak_allowed_error, :match_peak_tolerance, :protein_mass_filter, :sequence_header_filter)
|
203
|
-
# ].join("\n")
|
204
|
-
# end + "\n" +
|
205
|
-
# @spectrum_queries.collect {|result| result.to_pepxml }.join("\n")
|
206
|
-
# end
|
207
|
-
end
|
208
|
-
end
|
209
|
-
|
210
|
-
end
|
211
|
-
|
212
|
-
|
213
|
-
|
214
|
-
class Sequest::PepXML
|
215
|
-
include SpecIDXML
|
216
|
-
|
217
|
-
## CREATE a default version for the entire class
|
218
|
-
class << self
|
219
|
-
attr_accessor :pepxml_version
|
220
|
-
end
|
221
|
-
DEF_VERSION = 18
|
222
|
-
self.pepxml_version = DEF_VERSION # default version
|
223
|
-
|
224
|
-
attr_accessor :pepxml_version, :msms_pipeline_analysis
|
225
|
-
## the full path name (no extension)
|
226
|
-
attr_accessor :base_name
|
227
|
-
attr_accessor :h_plus
|
228
|
-
attr_accessor :avg_parent
|
229
|
-
|
230
|
-
#attr_accessor :spectrum_queries, :params, :base_name, :search_engine, :database, :raw_data_type, :raw_data, :out_data_type, :out_data, :sample_enzyme, :pepxml_version
|
231
|
-
|
232
|
-
# returns an array of spectrum queries
|
233
|
-
def spectrum_queries
|
234
|
-
msms_pipeline_analysis.msms_run_summary.spectrum_queries
|
235
|
-
end
|
236
|
-
|
237
|
-
# msms_pipeline_analysis is set to the result of the yielded block
|
238
|
-
# and set_mono_or_avg is called with params if given
|
239
|
-
def initialize(pepxml_version=DEF_VERSION, sequest_params_obj=nil)
|
240
|
-
self.class.pepxml_version = pepxml_version
|
241
|
-
if sequest_params_obj
|
242
|
-
set_mono_or_avg(sequest_params_obj)
|
243
|
-
end
|
244
|
-
if block_given?
|
245
|
-
@msms_pipeline_analysis = yield
|
246
|
-
@base_name = @msms_pipeline_analysis.msms_run_summary.base_name
|
247
|
-
end
|
248
|
-
end
|
249
|
-
|
250
|
-
# sets @h_plus and @avg_parent from the sequest params object
|
251
|
-
def set_mono_or_avg(sequest_params_obj)
|
252
|
-
case sequest_params_obj.precursor_mass_type
|
253
|
-
when "monoisotopic" ; @avg_parent = false
|
254
|
-
else ; @avg_parent = true
|
255
|
-
end
|
256
|
-
|
257
|
-
case @avg_parent
|
258
|
-
when true ; @h_plus = SpecID::AVG[:h_plus]
|
259
|
-
when false ; @h_plus = SpecID::MONO[:h_plus]
|
260
|
-
end
|
261
|
-
end
|
262
|
-
|
263
|
-
def date
|
264
|
-
Time.new.to_s
|
265
|
-
end
|
266
|
-
|
267
|
-
def xml_version
|
268
|
-
'<?xml version="1.0" encoding="UTF-8"?>' + "\n"
|
269
|
-
end
|
270
|
-
|
271
|
-
# for pepxml_version == 0
|
272
|
-
def doctype
|
273
|
-
'<!DOCTYPE msms_pipeline_analysis SYSTEM "/usr/bin/msms_analysis3.dtd">' + "\n"
|
274
|
-
end
|
275
|
-
|
276
|
-
def style_sheet
|
277
|
-
case self.class.pepxml_version
|
278
|
-
when 0
|
279
|
-
'<?xml-stylesheet type="text/xsl" href="/isb/std_xsl/pepXML_std.xsl"?>' + "\n"
|
280
|
-
when 18
|
281
|
-
'<?xml-stylesheet type="text/xsl" href="/tools/bin/TPP/tpp/schema/pepXML_std.xsl"?>'
|
282
|
-
end
|
283
|
-
end
|
284
|
-
|
285
|
-
def header
|
286
|
-
case self.class.pepxml_version
|
287
|
-
when 0 ; xml_version + doctype + style_sheet
|
288
|
-
when 18 ; xml_version + style_sheet
|
289
|
-
end
|
290
|
-
end
|
291
|
-
|
292
|
-
# updates the private attrs _num_prots and _first_prot on bioworks pep
|
293
|
-
# objects. Ideally, we'd like these attributes to reside elsewhere, but for
|
294
|
-
# memory concerns, this is best for now.
|
295
|
-
def self._prot_num_and_first_prot_by_pep(pep_array)
|
296
|
-
pep_array.hash_by(:aaseq).each do |aasq, pep_arr|
|
297
|
-
prts = []
|
298
|
-
pep_arr.each { |pep| prts.push( *(pep.prots) ) }
|
299
|
-
prts.uniq!
|
300
|
-
_size = prts.size
|
301
|
-
pep_arr.each do |pep|
|
302
|
-
pep._num_prots = _size.to_s
|
303
|
-
pep._first_prot = prts.first
|
304
|
-
end
|
305
|
-
end
|
306
|
-
end
|
307
|
-
|
308
|
-
|
309
|
-
Default_Options = {
|
310
|
-
:out_path => '.',
|
311
|
-
#:backup_db_path => '.',
|
312
|
-
# a PepXML option
|
313
|
-
:pepxml_version => DEF_VERSION,
|
314
|
-
## MSMSRunSummary options:
|
315
|
-
# string must be recognized in sample_enzyme.rb
|
316
|
-
# or create your own SampleEnzyme object
|
317
|
-
:sample_enzyme => 'trypsin',
|
318
|
-
:ms_manufacturer => 'ThermoFinnigan',
|
319
|
-
:ms_model => 'LCQ Deca XP Plus',
|
320
|
-
:ms_ionization => 'ESI',
|
321
|
-
:ms_mass_analyzer => 'Ion Trap',
|
322
|
-
:ms_detector => 'UNKNOWN',
|
323
|
-
:ms_data => '.', # path to ms data files (raw or mzxml)
|
324
|
-
:raw_data_type => "raw",
|
325
|
-
:raw_data => ".mzXML", ## even if you don't have it?
|
326
|
-
## SearchSummary options:
|
327
|
-
:out_data_type => "out", ## may be srf?? don't think pepxml recognizes this yet
|
328
|
-
:out_data => ".tgz", ## may be srf??
|
329
|
-
:copy_mzxml => false, # copy the mzxml file to the out_path (create it if necessary)
|
330
|
-
:print => false, # print the objects to file
|
331
|
-
}
|
332
|
-
|
333
|
-
# will dynamically set :ms_model and :ms_mass_analyzer from srf info
|
334
|
-
# (ignoring defaults or anything passed in) for LTQ Orbitrap
|
335
|
-
# and LCQ Deca XP
|
336
|
-
# See SRF::Sequest::PepXML::Default_Options hash for defaults
|
337
|
-
# unless given, the out_path will be given as the path of the srf_file
|
338
|
-
# srf may be an object or a filename
|
339
|
-
def self.new_from_srf(srf, opts={})
|
340
|
-
opts = Default_Options.merge(opts)
|
341
|
-
|
342
|
-
## read the srf file
|
343
|
-
if srf.is_a? String
|
344
|
-
srf = SRF.new(srf)
|
345
|
-
end
|
346
|
-
|
347
|
-
## set the outpath
|
348
|
-
out_path = opts.delete(:out_path)
|
349
|
-
|
350
|
-
params = srf.params
|
351
|
-
|
352
|
-
## check to see if we need backup_db
|
353
|
-
backup_db_path = opts.delete(:backup_db_path)
|
354
|
-
if !File.exist?(params.database) && backup_db_path
|
355
|
-
params.database_path = backup_db_path
|
356
|
-
end
|
357
|
-
|
358
|
-
#######################################################################
|
359
|
-
# PREPARE THE OPTIONS:
|
360
|
-
#######################################################################
|
361
|
-
## remove items from the options hash that don't belong to
|
362
|
-
ppxml_version = opts.delete(:pepxml_version)
|
363
|
-
out_data_type = opts.delete(:out_data_type)
|
364
|
-
out_data = opts.delete(:out_data)
|
365
|
-
|
366
|
-
## Extract meta info from srf
|
367
|
-
bn_noext = base_name_noext(srf.header.raw_filename)
|
368
|
-
opts[:ms_model] = srf.header.model
|
369
|
-
case opts[:ms_model]
|
370
|
-
when /Orbitrap/
|
371
|
-
opts[:ms_mass_analyzer] = 'Orbitrap'
|
372
|
-
when /LCQ Deca XP/
|
373
|
-
opts[:ms_mass_analyzer] = 'Ion Trap'
|
374
|
-
end
|
375
|
-
|
376
|
-
## Create the base name
|
377
|
-
full_base_name_no_ext = make_base_name( File.expand_path(out_path), bn_noext)
|
378
|
-
opts[:base_name] = full_base_name_no_ext
|
379
|
-
|
380
|
-
## Create the search summary:
|
381
|
-
search_summary_options = {
|
382
|
-
:search_database => Sequest::PepXML::SearchDatabase.new(params),
|
383
|
-
:base_name => full_base_name_no_ext,
|
384
|
-
:out_data_type => out_data_type,
|
385
|
-
:out_data => out_data
|
386
|
-
}
|
387
|
-
modifications_string = srf.header.modifications
|
388
|
-
search_summary = Sequest::PepXML::SearchSummary.new( params, modifications_string, search_summary_options)
|
389
|
-
|
390
|
-
## Create the SampleEnzyme object if necessary
|
391
|
-
unless opts[:sample_enzyme].is_a? SampleEnzyme
|
392
|
-
opts[:sample_enzyme] = SampleEnzyme.new(opts[:sample_enzyme])
|
393
|
-
end
|
394
|
-
|
395
|
-
## Create the pepxml obj and top level objects
|
396
|
-
pepxml_obj = Sequest::PepXML.new(ppxml_version, params)
|
397
|
-
pipeline = Sequest::PepXML::MSMSPipelineAnalysis.new({:date=>nil,:summary_xml=> bn_noext +'.xml'})
|
398
|
-
pepxml_obj.msms_pipeline_analysis = pipeline
|
399
|
-
pipeline.msms_run_summary = Sequest::PepXML::MSMSRunSummary.new(opts)
|
400
|
-
pipeline.msms_run_summary.search_summary = search_summary
|
401
|
-
modifications_obj = search_summary.modifications
|
402
|
-
|
403
|
-
## name some common variables we'll need
|
404
|
-
h_plus = pepxml_obj.h_plus
|
405
|
-
avg_parent = pepxml_obj.avg_parent
|
406
|
-
|
407
|
-
|
408
|
-
## COPY MZXML FILES IF NECESSARY
|
409
|
-
if opts[:copy_mzxml]
|
410
|
-
mzxml_pathname_noext = File.join(opts[:ms_data], bn_noext)
|
411
|
-
to_copy = Spec::MzXML.file_to_mzxml(mzxml_pathname_noext)
|
412
|
-
if to_copy
|
413
|
-
FileUtils.cp to_copy, out_path
|
414
|
-
else
|
415
|
-
puts "Couldn't file mzXML file with base: #{mzxml_pathname_noext}"
|
416
|
-
puts "Perhaps you need to specifiy the location of the raw data"
|
417
|
-
puts "or need an mzXML converter (readw.exe or t2x)"
|
418
|
-
exit
|
419
|
-
end
|
420
|
-
end
|
421
|
-
|
422
|
-
|
423
|
-
#######################################################################
|
424
|
-
# CREATE the spectrum_queries_ar
|
425
|
-
#######################################################################
|
426
|
-
srf_index = srf.index
|
427
|
-
out_files = srf.out_files
|
428
|
-
spectrum_queries_arr = Array.new(srf.dta_files.size)
|
429
|
-
files_with_hits_index = 0 ## will end up being 1 indexed
|
430
|
-
srf.dta_files.each_with_index do |dta_file,i|
|
431
|
-
next if out_files[i].num_hits == 0
|
432
|
-
files_with_hits_index += 1
|
433
|
-
|
434
|
-
# Sort the hits
|
435
|
-
hits = out_files[i].hits
|
436
|
-
arr = hits.sort_by{|v| v.xcorr }
|
437
|
-
|
438
|
-
# Get proper deltacn and deltacnstar
|
439
|
-
# Prophet deltacn is not the same as the native Sequest deltacn
|
440
|
-
# It is the deltacn of the second best hit!
|
441
|
-
top_hit = arr.pop
|
442
|
-
second_hit = arr.last
|
443
|
-
if second_hit
|
444
|
-
top_hit[1] = second_hit[1]
|
445
|
-
deltacnstar = '0'
|
446
|
-
else
|
447
|
-
top_hit[1] = '1.0'
|
448
|
-
deltacnstar = '1'
|
449
|
-
end
|
450
|
-
|
451
|
-
|
452
|
-
|
453
|
-
## mass calculations:
|
454
|
-
precursor_neutral_mass = dta_file.mh - h_plus
|
455
|
-
calc_neutral_pep_mass = top_hit[0] - h_plus
|
456
|
-
massdiff = precursor_neutral_mass - calc_neutral_pep_mass
|
457
|
-
if massdiff >= 0 ; massdiff = "+" + massdiff.to_s
|
458
|
-
else ; massdiff = massdiff.to_s end
|
459
|
-
|
460
|
-
(start_scan, end_scan, charge) = srf_index[i]
|
461
|
-
|
462
|
-
|
463
|
-
|
464
|
-
sq_hash = {
|
465
|
-
:spectrum => [bn_noext, start_scan, end_scan, charge].join('.'),
|
466
|
-
:start_scan => start_scan,
|
467
|
-
:end_scan => end_scan,
|
468
|
-
:precursor_neutral_mass => precursor_neutral_mass,
|
469
|
-
:assumed_charge => charge,
|
470
|
-
:pepxml_version => ppxml_version,
|
471
|
-
:index => files_with_hits_index,
|
472
|
-
}
|
473
|
-
|
474
|
-
spectrum_query = Sequest::PepXML::SpectrumQuery.new(sq_hash)
|
475
|
-
|
476
|
-
sequence = top_hit[8]
|
477
|
-
|
478
|
-
# NEED TO MODIFY SPLIT SEQUENCE TO DO MODS!
|
479
|
-
## THIS IS ALL INNER LOOP, so we make every effort at speed here:
|
480
|
-
(prevaa, pepseq, nextaa) = SpecID::Pep.prepare_sequence(sequence)
|
481
|
-
# ind_keys = {:mh => 0, :deltacn => 1, :sp => 2, :xcorr => 3, :id => 4, :rsp => 5, :ions_matched => 6, :ions_total => 7, :peptide => 8, :reference => 9 }
|
482
|
-
|
483
|
-
sh_hash = {
|
484
|
-
:hit_rank => "1",
|
485
|
-
:peptide => pepseq,
|
486
|
-
:peptide_prev_aa => prevaa,
|
487
|
-
:peptide_next_aa => nextaa,
|
488
|
-
:protein => top_hit[9].first.reference.split(" ").first,
|
489
|
-
:num_tot_proteins => top_hit[9].size,
|
490
|
-
:num_matched_ions => top_hit[6],
|
491
|
-
:tot_num_ions => top_hit[7],
|
492
|
-
:calc_neutral_pep_mass => calc_neutral_pep_mass,
|
493
|
-
:massdiff => massdiff,
|
494
|
-
:num_tol_term => Sequest::PepXML::SearchHit.calc_num_tol_term(params, sequence),
|
495
|
-
:num_missed_cleavages => Sequest::PepXML::SearchHit.calc_num_missed_cleavages(params, sequence),
|
496
|
-
:is_rejected => '0',
|
497
|
-
# These are search score attributes:
|
498
|
-
:xcorr => top_hit[3],
|
499
|
-
:deltacn => top_hit[1],
|
500
|
-
:deltacnstar => deltacnstar,
|
501
|
-
:spscore => top_hit[2],
|
502
|
-
:sprank => top_hit[5],
|
503
|
-
:modification_info => modifications_obj.modification_info(SpecID::Pep.split_sequence(sequence)[1]),
|
504
|
-
}
|
505
|
-
search_hit = Sequest::PepXML::SearchHit.new(sh_hash) # there can be multiple hits
|
506
|
-
|
507
|
-
search_result = Sequest::PepXML::SearchResult.new
|
508
|
-
search_result.search_hits = [search_hit]
|
509
|
-
spectrum_query.search_results = [search_result]
|
510
|
-
spectrum_queries_arr[files_with_hits_index] = spectrum_query
|
511
|
-
end
|
512
|
-
spectrum_queries_arr.compact!
|
513
|
-
|
514
|
-
pipeline.msms_run_summary.spectrum_queries = spectrum_queries_arr
|
515
|
-
pepxml_obj.base_name = pipeline.msms_run_summary.base_name
|
516
|
-
pipeline.msms_run_summary.spectrum_queries = spectrum_queries_arr
|
517
|
-
|
518
|
-
pepxml_obj
|
519
|
-
end
|
520
|
-
|
521
|
-
# takes an .srg or bioworks.xml file
|
522
|
-
# if possible, ensures that an mzXML file is present for each pepxml file
|
523
|
-
# :print => true, will print files
|
524
|
-
def self.set_from_bioworks(bioworks_file, opts={})
|
525
|
-
opts = Default_Options.merge(opts)
|
526
|
-
## Create the out_path directory if necessary
|
527
|
-
|
528
|
-
unless File.exist? opts[:out_path]
|
529
|
-
FileUtils.mkpath(opts[:out_path])
|
530
|
-
end
|
531
|
-
unless File.directory? opts[:out_path]
|
532
|
-
abort "#{opts[:out_path]} must be a directory!"
|
533
|
-
end
|
534
|
-
|
535
|
-
spec_id = SpecID.new(bioworks_file)
|
536
|
-
pepxml_objs =
|
537
|
-
if spec_id.is_a? Bioworks
|
538
|
-
abort("must have opts[:params] set!") unless opts[:params]
|
539
|
-
set_from_bioworks_xml(bioworks_file, opts[:params], opts)
|
540
|
-
elsif spec_id.is_a? SRFGroup
|
541
|
-
spec_id.srfs.map do |srf|
|
542
|
-
new_from_srf(srf, opts)
|
543
|
-
end
|
544
|
-
else
|
545
|
-
abort "invalid object"
|
546
|
-
end
|
547
|
-
|
548
|
-
if opts[:print]
|
549
|
-
pepxml_objs.each do |obj|
|
550
|
-
obj.to_pepxml(obj.base_name + ".xml")
|
551
|
-
end
|
552
|
-
end
|
553
|
-
pepxml_objs
|
554
|
-
end
|
555
|
-
|
556
|
-
|
557
|
-
# Takes bioworks 3.2/3.3 xml output (with no filters)
|
558
|
-
# Returns a list of PepXML objects
|
559
|
-
# params = sequest.params file
|
560
|
-
# bioworks = bioworks.xml exported multi-consensus view file
|
561
|
-
# pepxml_version = 0 for tpp 1.2.3
|
562
|
-
# pepxml_version = 18 for tpp 2.8.2, 2.8.3, 2.9.2
|
563
|
-
def self.set_from_bioworks_xml(bioworks, params, opts={})
|
564
|
-
opts = Default_Options.merge(opts)
|
565
|
-
pepxml_version, sample_enzyme, ms_manufacturer, ms_model, ms_ionization, ms_mass_analyzer, ms_detector, raw_data_type, raw_data, out_data_type, out_data, ms_data, out_path = opts.values_at(:pepxml_version, :sample_enzyme, :ms_manufacturer, :ms_model, :ms_ionization, :ms_mass_analyzer, :ms_detector, :raw_data_type, :raw_data, :out_data_type, :out_data, :ms_data, :out_path)
|
566
|
-
|
567
|
-
unless out_path
|
568
|
-
out_path = '.'
|
569
|
-
end
|
570
|
-
|
571
|
-
supported_versions = [0,18]
|
572
|
-
|
573
|
-
unless supported_versions.include?(opts[:pepxml_version])
|
574
|
-
abort "pepxml_version: #{pepxml_version} not currently supported. Current support is for versions #{supported_versions.join(', ')}"
|
575
|
-
end
|
576
|
-
|
577
|
-
## Turn params and bioworks_obj into objects if necessary:
|
578
|
-
# Params:
|
579
|
-
if params.class == Sequest::Params # OK!
|
580
|
-
elsif params.class == String ; params = Sequest::Params.new(params)
|
581
|
-
else ; abort "Don't recognize #{params} as object or string!"
|
582
|
-
end
|
583
|
-
# Bioworks:
|
584
|
-
if bioworks.class == Bioworks # OK!
|
585
|
-
elsif bioworks.class == String ; bioworks = SpecID.new(bioworks)
|
586
|
-
else ; abort "Don't recognize #{bioworks} as object or string!"
|
587
|
-
end
|
588
|
-
|
589
|
-
#puts "bioworks.peps.size: #{bioworks.peps.size}"; #puts "bioworks.prots.size: #{bioworks.prots.size}"; #puts "Bioworks.version: #{bioworks.version}"
|
590
|
-
|
591
|
-
## TURN THIS ON IF YOU THINK YOU MIGHT NOT BE GETTING PEPTIDES from
|
592
|
-
## bioworks
|
593
|
-
#bioworks.peps.each { |pep| if pep.class != Bioworks::Pep ; puts "trying to pass as pep: "; p pep; abort "NOT a pep!" end }
|
594
|
-
|
595
|
-
## check to see if we need backup_db
|
596
|
-
|
597
|
-
backup_db_path = opts.delete(:backup_db_path)
|
598
|
-
if !File.exist?(params.database) && backup_db_path
|
599
|
-
params.database_path = backup_db_path
|
600
|
-
end
|
601
|
-
|
602
|
-
## Start
|
603
|
-
split_bio_objs = []
|
604
|
-
|
605
|
-
## (num_prots_by_pep, prot_by_pep) =
|
606
|
-
#num_prots_by_pep.each do |k,v| puts "k: #{k} v: #{v}\n"; break end ; prot_by_pep.each do |k,v| puts "k: #{k} v: #{v}" ; break end ; abort "HERE"
|
607
|
-
|
608
|
-
modifications_string = bioworks.modifications
|
609
|
-
search_summary = Sequest::PepXML::SearchSummary.new(params, modifications_string, {:search_database => Sequest::PepXML::SearchDatabase.new(params), :out_data_type => out_data_type, :out_data => out_data})
|
610
|
-
modifications_obj = search_summary.modifications
|
611
|
-
|
612
|
-
## Create a hash of spectrum_query arrays by filename (this very big block):
|
613
|
-
spectrum_queries_by_base_name = {}
|
614
|
-
# Hash by the filenames to split into filenames:
|
615
|
-
bioworks.peps.hash_by(:base_name).map do |base_name, pep_arr|
|
616
|
-
|
617
|
-
pepxml_obj = Sequest::PepXML.new(pepxml_version, params)
|
618
|
-
full_base_name_no_ext = self.make_base_name( File.expand_path(out_path), base_name)
|
619
|
-
|
620
|
-
case pepxml_version
|
621
|
-
when 18
|
622
|
-
pipeline = Sequest::PepXML::MSMSPipelineAnalysis.new({:date=>nil,:summary_xml=>base_name+'.xml'})
|
623
|
-
msms_run_summary = Sequest::PepXML::MSMSRunSummary.new({
|
624
|
-
:base_name => full_base_name_no_ext,
|
625
|
-
:ms_manufacturer => ms_manufacturer,
|
626
|
-
:ms_model => ms_model,
|
627
|
-
:ms_ionization => ms_ionization,
|
628
|
-
:ms_mass_analyzer => ms_mass_analyzer,
|
629
|
-
:ms_detector => ms_detector,
|
630
|
-
:raw_data_type => raw_data_type,
|
631
|
-
:raw_data => raw_data,
|
632
|
-
:sample_enzyme => SampleEnzyme.new(sample_enzyme),
|
633
|
-
:search_summary => search_summary,
|
634
|
-
})
|
635
|
-
pipeline.msms_run_summary = msms_run_summary
|
636
|
-
pepxml_obj.msms_pipeline_analysis = pipeline
|
637
|
-
pepxml_obj.msms_pipeline_analysis.msms_run_summary.search_summary.base_name = full_base_name_no_ext
|
638
|
-
pepxml_obj.base_name = full_base_name_no_ext
|
639
|
-
pepxml_obj
|
640
|
-
when 0
|
641
|
-
## @TODO: NEED TO REVAMP THIS:
|
642
|
-
# Sequest::PepXML.new(pepxml_version).set_from_hash({
|
643
|
-
# :params => params,
|
644
|
-
# :search_results => spectrum_queries_arr,
|
645
|
-
# :base_name => self.make_base_name( File.expand_path(out_path), base_name),
|
646
|
-
# :search_engine => params.search_engine,
|
647
|
-
# :database => params.database,
|
648
|
-
# :raw_data_type => "mzXML",
|
649
|
-
# :raw_data => ".mzXML",
|
650
|
-
# :out_data_type => "out",
|
651
|
-
# :out_data => ".tgz",
|
652
|
-
# :sample_enzyme => params.enzyme,
|
653
|
-
# })
|
654
|
-
end
|
655
|
-
|
656
|
-
|
657
|
-
|
658
|
-
|
659
|
-
|
660
|
-
# Create a hash by pep object containing num_tot_proteins
|
661
|
-
# This is only valid if all hits are present (no previous thresholding)
|
662
|
-
# Since out2summary only acts on one folder at a time,
|
663
|
-
# we should only do it for one folder at a time! (that's why we do this
|
664
|
-
# here instead of globally)
|
665
|
-
self._prot_num_and_first_prot_by_pep(pep_arr)
|
666
|
-
prec_mz_arr = nil
|
667
|
-
case x = bioworks.version
|
668
|
-
when /3.2/
|
669
|
-
calc_prec_by = :prec_mz_arr
|
670
|
-
# get the precursor_mz array for this filename
|
671
|
-
prec_mz_arr = Spec::MSRun.precursor_mz_by_scan(File.join(ms_data, base_name))
|
672
|
-
when /3.3/
|
673
|
-
calc_prec_by = :deltamass
|
674
|
-
else
|
675
|
-
abort "invalid BioworksBrowser version: #{x}"
|
676
|
-
end
|
677
|
-
|
678
|
-
if opts[:copy_mzxml]
|
679
|
-
to_copy = Spec::MzXML.file_to_mzxml(File.join(ms_data, base_name))
|
680
|
-
if to_copy
|
681
|
-
FileUtils.cp to_copy, out_path
|
682
|
-
end
|
683
|
-
end
|
684
|
-
|
685
|
-
|
686
|
-
spectrum_queries_ar = pep_arr.hash_by(:first_scan, :last_scan, :charge).collect do |key,arr|
|
687
|
-
|
688
|
-
|
689
|
-
# Sort_by_rank and take the top hit (to mimick out2summary):
|
690
|
-
arr = arr.sort_by {|pep| pep.xcorr.to_f } # ascending
|
691
|
-
top_pep = arr.pop
|
692
|
-
second_hit = arr.last # needed for deltacnstar
|
693
|
-
|
694
|
-
|
695
|
-
case calc_prec_by
|
696
|
-
when :prec_mz_arr
|
697
|
-
precursor_neutral_mass = Sequest::PepXML::SpectrumQuery.calc_precursor_neutral_mass(calc_prec_by, top_pep.first_scan.to_i, top_pep.last_scan.to_i, prec_mz_arr, top_pep.charge.to_i, pepxml_obj.avg_parent)
|
698
|
-
when :deltamass
|
699
|
-
precursor_neutral_mass = Sequest::PepXML::SpectrumQuery.calc_precursor_neutral_mass(calc_prec_by, top_pep.mass.to_f, top_pep.deltamass.to_f, pepxml_obj.avg_parent)
|
700
|
-
end
|
701
|
-
|
702
|
-
calc_neutral_pep_mass = (top_pep.mass.to_f - pepxml_obj.h_plus)
|
703
|
-
massdiff = precursor_neutral_mass - calc_neutral_pep_mass
|
704
|
-
if massdiff >= 0 ; massdiff = "+" + massdiff.to_s
|
705
|
-
else ; massdiff = massdiff.to_s end #already has a -
|
706
|
-
# deltacn & star:
|
707
|
-
# (NOTE: OLD?? out2summary wants the deltacn of the 2nd best hit.)
|
708
|
-
if second_hit
|
709
|
-
#top_pep.deltacn = second_hit.deltacn
|
710
|
-
deltacnstar = '0'
|
711
|
-
else
|
712
|
-
top_pep.deltacn = '1.0'
|
713
|
-
deltacnstar = '1'
|
714
|
-
end
|
715
|
-
# Create the nested structure of queries{results{hits}}
|
716
|
-
# (Ruby's blocks work beautifully for things like this)
|
717
|
-
spec_query = Sequest::PepXML::SpectrumQuery.new({
|
718
|
-
:spectrum => [top_pep.base_name, top_pep.first_scan, top_pep.last_scan, top_pep.charge].join("."),
|
719
|
-
:start_scan => top_pep.first_scan,
|
720
|
-
:end_scan => top_pep.last_scan,
|
721
|
-
:precursor_neutral_mass => precursor_neutral_mass.to_s,
|
722
|
-
:assumed_charge => top_pep.charge,
|
723
|
-
:pepxml_version => pepxml_version,
|
724
|
-
})
|
725
|
-
|
726
|
-
|
727
|
-
search_result = Sequest::PepXML::SearchResult.new
|
728
|
-
|
729
|
-
## Calculate some interdependent values;
|
730
|
-
# NOTE: the bioworks mass is reallyf M+H if two or more scans went
|
731
|
-
# into the search_hit; calc_neutral_pep_mass is simply the avg of
|
732
|
-
# precursor masses adjusted to be neutral
|
733
|
-
(prevaa, pepseq, nextaa) = SpecID::Pep.prepare_sequence(top_pep.sequence)
|
734
|
-
(num_matched_ions, tot_num_ions) = Sequest::PepXML::SearchHit.split_ions(top_pep.ions)
|
735
|
-
search_hit = Sequest::PepXML::SearchHit.new({
|
736
|
-
:hit_rank => "1",
|
737
|
-
:peptide => pepseq,
|
738
|
-
:peptide_prev_aa => prevaa,
|
739
|
-
:peptide_next_aa => nextaa,
|
740
|
-
:protein => top_pep._first_prot.reference.split(" ").first,
|
741
|
-
:num_tot_proteins => top_pep._num_prots,
|
742
|
-
:num_matched_ions => num_matched_ions,
|
743
|
-
:tot_num_ions => tot_num_ions,
|
744
|
-
:calc_neutral_pep_mass => calc_neutral_pep_mass.to_s,
|
745
|
-
:massdiff => massdiff,
|
746
|
-
:num_tol_term => Sequest::PepXML::SearchHit.calc_num_tol_term(params, top_pep.sequence).to_s,
|
747
|
-
:num_missed_cleavages => Sequest::PepXML::SearchHit.calc_num_missed_cleavages(params, top_pep.sequence).to_s,
|
748
|
-
:is_rejected => "0",
|
749
|
-
# These are search score attributes:
|
750
|
-
:xcorr => top_pep.xcorr,
|
751
|
-
:deltacn => top_pep.deltacn,
|
752
|
-
:deltacnstar => deltacnstar,
|
753
|
-
:spscore => top_pep.sp,
|
754
|
-
:sprank => top_pep.rsp,
|
755
|
-
:modification_info => modifications_obj.modification_info(SpecID::Pep.split_sequence(top_pep.sequence)[1]),
|
756
|
-
})
|
757
|
-
search_result.search_hits = [search_hit] # there can be multiple search hits
|
758
|
-
spec_query.search_results = [search_result] # can be multiple search_results
|
759
|
-
spec_query
|
760
|
-
end
|
761
|
-
|
762
|
-
# create an index by spectrum as results end up typically in out2summary
|
763
|
-
# (I really dislike this order, however)
|
764
|
-
spectrum_queries_ar = spectrum_queries_ar.sort_by {|pep| pep.spectrum }
|
765
|
-
spectrum_queries_ar.each_with_index {|res,index| res.index = "#{index + 1}" }
|
766
|
-
pipeline.msms_run_summary.spectrum_queries = spectrum_queries_ar
|
767
|
-
pepxml_obj
|
768
|
-
end ## collects pepxml_objs
|
769
|
-
end
|
770
|
-
|
771
|
-
def summary_xml
|
772
|
-
base_name + ".xml"
|
773
|
-
end
|
774
|
-
|
775
|
-
def precursor_mass_type
|
776
|
-
@params.precursor_mass_type
|
777
|
-
end
|
778
|
-
|
779
|
-
def fragment_mass_type
|
780
|
-
@params.fragment_mass_type
|
781
|
-
end
|
782
|
-
|
783
|
-
# combines filename in a manner consistent with the path
|
784
|
-
def self.make_base_name(path, filename)
|
785
|
-
sep = "/"
|
786
|
-
if path.split("/").size < path.split("\\").size
|
787
|
-
sep = "\\"
|
788
|
-
end
|
789
|
-
if path.split("").last == sep
|
790
|
-
return path + File.basename(filename)
|
791
|
-
else
|
792
|
-
return path + sep + File.basename(filename)
|
793
|
-
end
|
794
|
-
end
|
795
|
-
|
796
|
-
# outputs pepxml, (to file if given)
|
797
|
-
def to_pepxml(file=nil)
|
798
|
-
string = header
|
799
|
-
string << @msms_pipeline_analysis.to_pepxml
|
800
|
-
|
801
|
-
if file
|
802
|
-
File.open(file, "w") do |fh| fh.print string end
|
803
|
-
end
|
804
|
-
string
|
805
|
-
end
|
806
|
-
|
807
|
-
# given any kind of filename (from windows or whatever)
|
808
|
-
# returns the base of the filename with no file extension
|
809
|
-
def self.base_name_noext(file)
|
810
|
-
file.gsub!("\\", '/')
|
811
|
-
File.basename(file).sub(/\.[\w^\.]+$/, '')
|
812
|
-
end
|
813
|
-
|
814
|
-
|
815
|
-
end # PepXML
|
816
|
-
|
817
|
-
##
|
818
|
-
# In the future, this guy should accept any version of bioworks params file
|
819
|
-
# and spit out any param queried.
|
820
|
-
class Sequest::Params
|
821
|
-
include SpecIDXML
|
822
|
-
|
823
|
-
# current attributes supported are:
|
824
|
-
# bioworks 3.2:
|
825
|
-
@@param_re = / = ?/o
|
826
|
-
@@param_two_split = ';'
|
827
|
-
|
828
|
-
# opts are the general options
|
829
|
-
# mods are the weights added to amino acids
|
830
|
-
attr_accessor :opts, :mods
|
831
|
-
|
832
|
-
# all keys and values stored as strings!
|
833
|
-
def initialize(file=nil)
|
834
|
-
if file
|
835
|
-
parse(file)
|
836
|
-
end
|
837
|
-
end
|
838
|
-
|
839
|
-
# returns hash of params for continuous lines of non-whitespace
|
840
|
-
def grab_params(fh)
|
841
|
-
hash = {}
|
842
|
-
while line = fh.gets
|
843
|
-
if line =~ /[^\s]/
|
844
|
-
one,two = line.split @@param_re
|
845
|
-
two,comment = two.split @@param_two_split
|
846
|
-
hash[one] = two.rstrip
|
847
|
-
# it is necessary to add this break so that params files inside srf
|
848
|
-
# files can be read. This will terminate the reading at the end of
|
849
|
-
# the file even though there are more lines
|
850
|
-
if line =~ /added to U/ || line =~ /digest_mass_range/## Will only work on bioworks 3.2 & 3.3 (bioworks 3.1 last line => Elastase/Tryp...)
|
851
|
-
break
|
852
|
-
end
|
853
|
-
if line =~ /digest_mass_range/ # there is no space in the srf params files
|
854
|
-
break
|
855
|
-
end
|
856
|
-
else
|
857
|
-
break
|
858
|
-
end
|
859
|
-
end
|
860
|
-
hash
|
861
|
-
end
|
862
|
-
|
863
|
-
# returns self
|
864
|
-
def parse_handle(fh)
|
865
|
-
sequest_line = fh.gets #[SEQUEST]
|
866
|
-
@opts = grab_params(fh)
|
867
|
-
@opts["search_engine"] = "SEQUEST"
|
868
|
-
@mods = grab_params(fh)
|
869
|
-
|
870
|
-
## this gets rid of the .hdr postfix on indexed databases
|
871
|
-
@opts["first_database_name"] = @opts["first_database_name"].sub(/\.hdr$/, '')
|
872
|
-
self
|
873
|
-
end
|
874
|
-
|
875
|
-
## parses file
|
876
|
-
## and drops the .hdr behind indexed fasta files
|
877
|
-
## returns self
|
878
|
-
def parse(file)
|
879
|
-
File.open(file) do |fh|
|
880
|
-
parse_handle(fh)
|
881
|
-
end
|
882
|
-
self
|
883
|
-
end
|
884
|
-
|
885
|
-
# returns( split_after, except_before)
|
886
|
-
def enzyme_specificity
|
887
|
-
if version == "3.2"
|
888
|
-
arr = enzyme_info.split(/\s+/)[3,2]
|
889
|
-
arr.collect! do |str|
|
890
|
-
if str && str.class == String ; str
|
891
|
-
else ; ""
|
892
|
-
end
|
893
|
-
end
|
894
|
-
return *arr
|
895
|
-
end
|
896
|
-
end
|
897
|
-
|
898
|
-
# Returns the version of the sequest.params file
|
899
|
-
# Returns String "3.2" if contains "enyzme_info"
|
900
|
-
# Returns String "3.1" if contains "enzyme_number"
|
901
|
-
def version
|
902
|
-
if @opts["enzyme_info"] ; return "3.2"
|
903
|
-
elsif @opts["enzyme_number"] ; return "3.1"
|
904
|
-
end
|
905
|
-
end
|
906
|
-
|
907
|
-
####################################################
|
908
|
-
# TO PEPXML
|
909
|
-
####################################################
|
910
|
-
# In some ways, this is merely translating to the older Bioworks
|
911
|
-
# sequest.params files
|
912
|
-
|
913
|
-
# I'm not sure if this is the right mapping for sequence_search_constraint?
|
914
|
-
def sequence
|
915
|
-
pseq = @opts['partial_sequence']
|
916
|
-
if !pseq || pseq == "" ; pseq = "0" end
|
917
|
-
pseq
|
918
|
-
end
|
919
|
-
|
920
|
-
# Returns xml in the form <parameter name="#{method_name}"
|
921
|
-
# value="#{method_value}"/> for list of symbols
|
922
|
-
def pepxml_parameters
|
923
|
-
keys_as_symbols = @opts.sort.map do |k,v| k.to_s end
|
924
|
-
params_xml(*keys_as_symbols)
|
925
|
-
# (:peptide_mass_tol, :peptide_mass_units, :fragment_ion_tol, :ion_series, :max_num_differential_AA_per_mod, :nucleotide_reading_frame, :num_output_lines, :remove_precursor_peak, :ion_cutoff_percentage, :match_peak_count, :match_peak_allowed_error, :match_peak_tolerance, :protein_mass_filter, :sequence_header_filter)
|
926
|
-
end
|
927
|
-
|
928
|
-
def precursor_mass_type
|
929
|
-
case @opts['mass_type_parent']
|
930
|
-
when '0' ; "average"
|
931
|
-
when '1' ; "monoisotopic"
|
932
|
-
else ; abort "error in mass_type_parent in sequest!"
|
933
|
-
end
|
934
|
-
end
|
935
|
-
|
936
|
-
def fragment_mass_type
|
937
|
-
fmtype =
|
938
|
-
case @opts['mass_type_fragment']
|
939
|
-
when '0' ; "average"
|
940
|
-
when '1' ; "monoisotopic"
|
941
|
-
else ; abort "error in mass_type_fragment in sequest!"
|
942
|
-
end
|
943
|
-
end
|
944
|
-
|
945
|
-
def method_missing(name, *args)
|
946
|
-
string = name.to_s
|
947
|
-
if @opts.key?(string) ; return @opts[string]
|
948
|
-
elsif @mods.key?(string) ; return @mods[string]
|
949
|
-
else ; return nil
|
950
|
-
end
|
951
|
-
end
|
952
|
-
|
953
|
-
## We only need to define values if they are different than sequest.params
|
954
|
-
## The method_missing will look them up in the hash!
|
955
|
-
|
956
|
-
# Returns a system independent basename
|
957
|
-
# Splits on "\" or "/"
|
958
|
-
def _sys_ind_basename(file)
|
959
|
-
return file.split(/[\\\/]/)[-1]
|
960
|
-
end
|
961
|
-
|
962
|
-
# changes the path of the database
|
963
|
-
def database_path=(newpath)
|
964
|
-
db = @opts["first_database_name"]
|
965
|
-
newpath = File.join(newpath, _sys_ind_basename(db))
|
966
|
-
@opts["first_database_name"] = newpath
|
967
|
-
end
|
968
|
-
|
969
|
-
def database
|
970
|
-
@opts["first_database_name"]
|
971
|
-
end
|
972
|
-
|
973
|
-
# returns the appropriate aminoacid mass lookup table (in spec_id.rb SpecID::MONO or
|
974
|
-
# SpecID::AVG based on precursor_mass_type
|
975
|
-
def mass_table
|
976
|
-
case precursor_mass_type
|
977
|
-
when 'average'
|
978
|
-
SpecID::AVG
|
979
|
-
when 'monoisotopic'
|
980
|
-
SpecID::MONO
|
981
|
-
end
|
982
|
-
end
|
983
|
-
|
984
|
-
# at least in Bioworks 3.2, the First number after the enzyme
|
985
|
-
# is the indication of the enzymatic end stringency (required):
|
986
|
-
# 1 = Fully enzymatic
|
987
|
-
# 2 = Either end
|
988
|
-
# 3 = N terminal only
|
989
|
-
# 4 = C terminal only
|
990
|
-
# So, to get min_number_termini we map like this:
|
991
|
-
# 1 => 2
|
992
|
-
# 2 => 1
|
993
|
-
def min_number_termini
|
994
|
-
termini_number = @opts["enzyme_info"].split(" ")[1]
|
995
|
-
if termini_number == "1"
|
996
|
-
return "2"
|
997
|
-
elsif termini_number == "2"
|
998
|
-
return "1"
|
999
|
-
else
|
1000
|
-
puts "WARNING: Enzyme termini info might be imprecise!"
|
1001
|
-
return "1"
|
1002
|
-
end
|
1003
|
-
end
|
1004
|
-
|
1005
|
-
def enzyme
|
1006
|
-
#if @opts["enzyme_info"] =~ /Trypsin/ ; return "tryptic"
|
1007
|
-
#else ; return @opts["enzyme_info"].split('(')[0] end
|
1008
|
-
return @opts["enzyme_info"].split('(')[0]
|
1009
|
-
end
|
1010
|
-
|
1011
|
-
def max_num_internal_cleavages
|
1012
|
-
@opts["max_num_internal_cleavage_sites"]
|
1013
|
-
end
|
1014
|
-
|
1015
|
-
def peptide_mass_tol
|
1016
|
-
if @opts["peptide_mass_units"] != "0"
|
1017
|
-
puts "WARNING: peptide_mass_tol units need to be adjusted!"
|
1018
|
-
end
|
1019
|
-
@opts["peptide_mass_tolerance"]
|
1020
|
-
end
|
1021
|
-
|
1022
|
-
def fragment_ion_tol
|
1023
|
-
@opts["fragment_ion_tolerance"]
|
1024
|
-
end
|
1025
|
-
def max_num_differential_AA_per_mod
|
1026
|
-
@opts["max_num_differential_per_peptide"]
|
1027
|
-
end
|
1028
|
-
|
1029
|
-
## @TODO: We could add some of the parameters not currently being asked for to be more complete
|
1030
|
-
## @TODO: We could always add the Bioworks 3.2 specific params as params
|
1031
|
-
|
1032
|
-
####################################################
|
1033
|
-
####################################################
|
1034
|
-
|
1035
|
-
end
|
1036
|
-
|
1037
|
-
class Sequest::PepXML::SearchResult
|
1038
|
-
include SpecIDXML
|
1039
|
-
# an array of search_hits
|
1040
|
-
attr_accessor :search_hits
|
1041
|
-
|
1042
|
-
# if block given, then search_hits set to return value
|
1043
|
-
def initialize
|
1044
|
-
if block_given? ; @search_hits = yield
|
1045
|
-
else ; @search_hits = [] end
|
1046
|
-
end
|
1047
|
-
|
1048
|
-
def to_pepxml
|
1049
|
-
element_xml_no_atts(:search_result) do
|
1050
|
-
@search_hits.map {|sh| sh.to_pepxml }.join
|
1051
|
-
end
|
1052
|
-
end
|
1053
|
-
end
|
1054
|
-
|
1055
|
-
class Sequest::PepXML::SearchSummary
|
1056
|
-
include SpecIDXML
|
1057
|
-
attr_accessor :params
|
1058
|
-
attr_accessor :base_name
|
1059
|
-
attr_accessor :out_data_type
|
1060
|
-
attr_accessor :out_data
|
1061
|
-
attr_accessor :modifications
|
1062
|
-
# A SearchDatabase object (responds to :local_path and :type)
|
1063
|
-
attr_accessor :search_database
|
1064
|
-
# if given a sequest params object, then will set the following attributes:
|
1065
|
-
# args is a hash of parameters
|
1066
|
-
# modifications_string -> See Modifications
|
1067
|
-
def initialize(params, modifications_string='', args=nil)
|
1068
|
-
@search_id = nil
|
1069
|
-
@params = params
|
1070
|
-
@modifications = Sequest::PepXML::Modifications.new(params, modifications_string)
|
1071
|
-
if args ; set_from_hash(args) end
|
1072
|
-
end
|
1073
|
-
|
1074
|
-
def method_missing(symbol, *args)
|
1075
|
-
if @params ; @params.send(symbol, *args) end
|
1076
|
-
end
|
1077
|
-
|
1078
|
-
def search_id
|
1079
|
-
if @search_id ; @search_id
|
1080
|
-
else ; '1' end
|
1081
|
-
end
|
1082
|
-
|
1083
|
-
|
1084
|
-
def to_pepxml
|
1085
|
-
element_xml(:search_summary, [:base_name, :search_engine, :precursor_mass_type, :fragment_mass_type, :out_data_type, :out_data, :search_id]) do
|
1086
|
-
search_database.to_pepxml +
|
1087
|
-
short_element_xml(:enzymatic_search_constraint, [:enzyme, :max_num_internal_cleavages, :min_number_termini]) +
|
1088
|
-
@modifications.to_pepxml +
|
1089
|
-
@params.pepxml_parameters
|
1090
|
-
end
|
1091
|
-
end
|
1092
|
-
|
1093
|
-
end
|
1094
|
-
|
1095
|
-
class Sequest::PepXML::Modifications
|
1096
|
-
include SpecIDXML
|
1097
|
-
|
1098
|
-
# sequest params object
|
1099
|
-
attr_accessor :params
|
1100
|
-
# array holding AAModifications
|
1101
|
-
attr_accessor :aa_mods
|
1102
|
-
# array holding TerminalModifications
|
1103
|
-
attr_accessor :term_mods
|
1104
|
-
# a hash of all differential modifications present by aa_one_letter_symbol
|
1105
|
-
# and special_symbol. This is NOT the mass difference but the total mass {
|
1106
|
-
# 'M*' => 155.5, 'S@' => 190.3 }. NOTE: Since the termini are dependent on
|
1107
|
-
# the amino acid sequence, they are give the *differential* mass. The
|
1108
|
-
# termini are given the special symbol as in sequest e.g. '[' => 12.22, #
|
1109
|
-
# cterminus ']' => 14.55 # nterminus
|
1110
|
-
attr_accessor :masses_by_diff_mod_hash
|
1111
|
-
# a hash, key is [AA_one_letter_symbol.to_sym, difference.to_f]
|
1112
|
-
# values are the special_symbols
|
1113
|
-
attr_accessor :mod_symbols_hash
|
1114
|
-
|
1115
|
-
# The modification symbols string looks like this:
|
1116
|
-
# (M* +15.90000) (M# +29.00000) (S@ +80.00000) (C^ +12.00000) (ct[ +12.33000) (nt] +14.20000)
|
1117
|
-
# ct is cterminal peptide (differential)
|
1118
|
-
# nt is nterminal peptide (differential)
|
1119
|
-
# the C is just cysteine
|
1120
|
-
# will set_modifications and masses_by_diff_mod hash
|
1121
|
-
def initialize(params, modification_symbols_string='')
|
1122
|
-
@params = params
|
1123
|
-
set_modifications(params, modification_symbols_string)
|
1124
|
-
end
|
1125
|
-
|
1126
|
-
# set the masses_by_diff_mod and mod_symbols_hash from
|
1127
|
-
def set_hashes(modification_symbols_string)
|
1128
|
-
|
1129
|
-
@mod_symbols_hash = {}
|
1130
|
-
@masses_by_diff_mod = {}
|
1131
|
-
if (modification_symbols_string == nil || modification_symbols_string == '')
|
1132
|
-
return nil
|
1133
|
-
end
|
1134
|
-
table = @params.mass_table
|
1135
|
-
modification_symbols_string.split(/\)\s+\(/).each do |mod|
|
1136
|
-
if mod =~ /\(?(\w+)(.) (.[\d\.]+)\)?/
|
1137
|
-
if $1 == 'ct' || $1 == 'nt'
|
1138
|
-
mass_diff = $3.to_f
|
1139
|
-
@masses_by_diff_mod[$2] = mass_diff
|
1140
|
-
@mod_symbols_hash[[$1, mass_diff]] = $2.dup
|
1141
|
-
else
|
1142
|
-
symbol_string = $2.dup
|
1143
|
-
mass_diff = $3.to_f
|
1144
|
-
$1.split('').each do |aa|
|
1145
|
-
aa_as_sym = aa.to_sym
|
1146
|
-
@masses_by_diff_mod[aa+symbol_string] = mass_diff + table[aa_as_sym]
|
1147
|
-
@mod_symbols_hash[[aa_as_sym, mass_diff]] = symbol_string
|
1148
|
-
end
|
1149
|
-
end
|
1150
|
-
end
|
1151
|
-
end
|
1152
|
-
end
|
1153
|
-
|
1154
|
-
# given a bare peptide (no end pieces) returns a ModificationInfo object
|
1155
|
-
# e.g. given "]PEPT*IDE", NOT 'K.PEPTIDE.R'
|
1156
|
-
# if there are no modifications, returns nil
|
1157
|
-
def modification_info(peptide)
|
1158
|
-
if @masses_by_diff_mod.size == 0
|
1159
|
-
return nil
|
1160
|
-
end
|
1161
|
-
hash = {}
|
1162
|
-
hash[:modified_peptide] = peptide.dup
|
1163
|
-
hsh = @masses_by_diff_mod
|
1164
|
-
table = @params.mass_table
|
1165
|
-
h = table[:h] # this? or h_plus ??
|
1166
|
-
oh = table[:o] + h
|
1167
|
-
## only the termini can match a single char
|
1168
|
-
if hsh.key? peptide[0,1]
|
1169
|
-
# AA + H + differential_mod
|
1170
|
-
hash[:mod_nterm_mass] = table[peptide[1,1].to_sym] + h + hsh[peptide[0,1]]
|
1171
|
-
peptide = peptide[1...(peptide.size)]
|
1172
|
-
end
|
1173
|
-
if hsh.key? peptide[(peptide.size-1),1]
|
1174
|
-
# AA + OH + differential_mod
|
1175
|
-
hash[:mod_cterm_mass] = table[peptide[(peptide.size-2),1].to_sym] + oh + hsh[peptide[-1,1]]
|
1176
|
-
peptide.slice!( 0..-2 )
|
1177
|
-
peptide = peptide[0...(peptide.size-1)]
|
1178
|
-
end
|
1179
|
-
mod_array = []
|
1180
|
-
(0...peptide.size).each do |i|
|
1181
|
-
if hsh.key? peptide[i,2]
|
1182
|
-
mod_array << [ i+1 , hsh[peptide[i,2]] ]
|
1183
|
-
end
|
1184
|
-
end
|
1185
|
-
if mod_array.size > 0
|
1186
|
-
hash[:mod_aminoacid_mass_array] = mod_array
|
1187
|
-
end
|
1188
|
-
if hash.size > 1 # if there is more than just the modified peptide there
|
1189
|
-
Sequest::PepXML::SearchHit::ModificationInfo.new(hash)
|
1190
|
-
else
|
1191
|
-
nil
|
1192
|
-
end
|
1193
|
-
end
|
1194
|
-
|
1195
|
-
# 1. sets aa_mods and term_mods from a sequest params object
|
1196
|
-
# 2. sets @params
|
1197
|
-
# 3. sets @masses_by_diff_mod
|
1198
|
-
def set_modifications(params, modification_symbols_string)
|
1199
|
-
@params = params
|
1200
|
-
|
1201
|
-
set_hashes(modification_symbols_string)
|
1202
|
-
|
1203
|
-
####################################
|
1204
|
-
## static mods
|
1205
|
-
####################################
|
1206
|
-
|
1207
|
-
static_mods = [] # [[one_letter_amino_acid.to_sym, add_amount.to_f], ...]
|
1208
|
-
static_terminal_mods = [] # e.g. [add_Cterm_peptide, amount.to_f]
|
1209
|
-
|
1210
|
-
params.mods.each do |k,v|
|
1211
|
-
v_to_f = v.to_f
|
1212
|
-
if v_to_f != 0.0
|
1213
|
-
if k =~ /add_(\w)_/
|
1214
|
-
static_mods << [$1.to_sym, v_to_f]
|
1215
|
-
else
|
1216
|
-
static_terminal_mods << [k, v_to_f]
|
1217
|
-
end
|
1218
|
-
end
|
1219
|
-
end
|
1220
|
-
aa_hash = params.mass_table
|
1221
|
-
|
1222
|
-
## Create the static_mods objects
|
1223
|
-
static_mods.map! do |mod|
|
1224
|
-
hash = {
|
1225
|
-
:aminoacid => mod[0].to_s,
|
1226
|
-
:massdiff => mod[1].to_plus_minus_string,
|
1227
|
-
:mass => aa_hash[mod[0]] + mod[1],
|
1228
|
-
:variable => 'N',
|
1229
|
-
:binary => 'Y',
|
1230
|
-
}
|
1231
|
-
Sequest::PepXML::AAModification.new(hash)
|
1232
|
-
end
|
1233
|
-
|
1234
|
-
## Create the static_terminal_mods objects
|
1235
|
-
static_terminal_mods.map! do |mod|
|
1236
|
-
terminus = if mod[0] =~ /Cterm/ ; 'c'
|
1237
|
-
else ; 'n' # only two possible termini
|
1238
|
-
end
|
1239
|
-
protein_terminus = case mod[0]
|
1240
|
-
when /Nterm_protein/ ; 'n'
|
1241
|
-
when /Cterm_protein/ ; 'c'
|
1242
|
-
else nil
|
1243
|
-
end
|
1244
|
-
|
1245
|
-
# create the hash
|
1246
|
-
hash = {
|
1247
|
-
:terminus => terminus,
|
1248
|
-
:massdiff => mod[1].to_plus_minus_string,
|
1249
|
-
:variable => 'N',
|
1250
|
-
:description => mod[0],
|
1251
|
-
}
|
1252
|
-
hash[:protein_terminus] = protein_terminus if protein_terminus
|
1253
|
-
Sequest::PepXML::TerminalModification.new(hash)
|
1254
|
-
end
|
1255
|
-
#################################
|
1256
|
-
# Variable Mods:
|
1257
|
-
#################################
|
1258
|
-
arr = params.diff_search_options.rstrip.split(/\s+/)
|
1259
|
-
# [aa.to_sym, diff.to_f]
|
1260
|
-
variable_mods = []
|
1261
|
-
(0...arr.size).step(2) do |i|
|
1262
|
-
if arr[i].to_f != 0.0
|
1263
|
-
variable_mods << [arr[i+1], arr[i].to_f]
|
1264
|
-
end
|
1265
|
-
end
|
1266
|
-
mod_objects = []
|
1267
|
-
variable_mods.each do |mod|
|
1268
|
-
mod[0].split('').each do |aa|
|
1269
|
-
hash = {
|
1270
|
-
|
1271
|
-
:aminoacid => aa,
|
1272
|
-
:massdiff => mod[1].to_plus_minus_string,
|
1273
|
-
:mass => aa_hash[aa.to_sym] + mod[1],
|
1274
|
-
:variable => 'Y',
|
1275
|
-
:binary => 'N',
|
1276
|
-
:symbol => @mod_symbols_hash[[aa.to_sym, mod[1]]],
|
1277
|
-
}
|
1278
|
-
mod_objects << Sequest::PepXML::AAModification.new(hash)
|
1279
|
-
end
|
1280
|
-
end
|
1281
|
-
variable_mods = mod_objects
|
1282
|
-
#################################
|
1283
|
-
# TERMINAL Variable Mods:
|
1284
|
-
#################################
|
1285
|
-
# These are always peptide, not protein termini (for sequest)
|
1286
|
-
(nterm_diff, cterm_diff) = params.term_diff_search_options.rstrip.split(/\s+/).map{|v| v.to_f }
|
1287
|
-
|
1288
|
-
to_add = []
|
1289
|
-
if nterm_diff != 0.0
|
1290
|
-
to_add << ['n',nterm_diff.to_plus_minus_string, @mod_symbols_hash[:nt, nterm_diff]]
|
1291
|
-
end
|
1292
|
-
if cterm_diff != 0.0
|
1293
|
-
to_add << ['c', cterm_diff.to_plus_minus_string, @mod_symbols_hash[:ct, cterm_diff]]
|
1294
|
-
end
|
1295
|
-
|
1296
|
-
variable_terminal_mods = to_add.map do |term, mssdiff, symb|
|
1297
|
-
hash = {
|
1298
|
-
:terminus => term,
|
1299
|
-
:massdiff => mssdiff,
|
1300
|
-
:variable => 'Y',
|
1301
|
-
:symbol => symb,
|
1302
|
-
}
|
1303
|
-
Sequest::PepXML::TerminalModification.new(hash)
|
1304
|
-
end
|
1305
|
-
|
1306
|
-
#########################
|
1307
|
-
# COLLECT THEM
|
1308
|
-
#########################
|
1309
|
-
@aa_mods = static_mods + variable_mods
|
1310
|
-
@term_mods = static_terminal_mods + variable_terminal_mods
|
1311
|
-
end
|
1312
|
-
|
1313
|
-
## Generates the pepxml for static and differential amino acid mods based on
|
1314
|
-
## sequest object
|
1315
|
-
def to_pepxml
|
1316
|
-
st = ''
|
1317
|
-
if @aa_mods
|
1318
|
-
st << @aa_mods.map {|v| v.to_pepxml }.join
|
1319
|
-
end
|
1320
|
-
if @term_mods
|
1321
|
-
st << @term_mods.map {|v| v.to_pepxml }.join
|
1322
|
-
end
|
1323
|
-
st
|
1324
|
-
end
|
1325
|
-
|
3
|
+
module Sequest
|
1326
4
|
end
|
1327
5
|
|
1328
|
-
# Modified aminoacid, static or variable
|
1329
|
-
# unless otherwise stated, all attributes can be anything
|
1330
|
-
class Sequest::PepXML::AAModification
|
1331
|
-
include SpecIDXML
|
1332
|
-
|
1333
|
-
# The amino acid (one letter code)
|
1334
|
-
attr_accessor :aminoacid
|
1335
|
-
# Must be a string!!!!
|
1336
|
-
# Mass difference with respect to unmodified aminoacid, must begin with
|
1337
|
-
# either + (nonnegative) or - [e.g. +1.05446 or -2.3342]
|
1338
|
-
# consider Numeric#to_plus_minus_string at top
|
1339
|
-
attr_accessor :massdiff
|
1340
|
-
# Mass of modified aminoacid
|
1341
|
-
attr_accessor :mass
|
1342
|
-
# Y if both modified and unmodified aminoacid could be present in the
|
1343
|
-
# dataset, N if only modified aminoacid can be present
|
1344
|
-
attr_accessor :variable
|
1345
|
-
# whether modification can reside only at protein terminus (specified 'n',
|
1346
|
-
# 'c', or 'nc')
|
1347
|
-
attr_accessor :peptide_terminus
|
1348
|
-
# Special symbol used by search engine to designate this modification
|
1349
|
-
attr_accessor :symbol
|
1350
|
-
# Y if each peptide must have only modified or unmodified aminoacid, N if a
|
1351
|
-
# peptide may contain both modified and unmodified aminoacid
|
1352
|
-
attr_accessor :binary
|
1353
|
-
|
1354
|
-
def initialize(hash=nil)
|
1355
|
-
instance_var_set_from_hash(hash) if hash # can use unless there are weird methods
|
1356
|
-
end
|
1357
|
-
|
1358
|
-
def to_pepxml
|
1359
|
-
short_element_xml_from_instance_vars("aminoacid_modification")
|
1360
|
-
end
|
1361
|
-
|
1362
|
-
end
|
1363
|
-
|
1364
|
-
# Modified aminoacid, static or variable
|
1365
|
-
class Sequest::PepXML::TerminalModification
|
1366
|
-
include SpecIDXML
|
1367
|
-
|
1368
|
-
# n for N-terminus, c for C-terminus
|
1369
|
-
attr_accessor :terminus
|
1370
|
-
# Mass difference with respect to unmodified terminus
|
1371
|
-
attr_accessor :massdiff
|
1372
|
-
# Mass of modified terminus
|
1373
|
-
attr_accessor :mass
|
1374
|
-
# Y if both modified and unmodified terminus could be present in the
|
1375
|
-
# dataset, N if only modified terminus can be present
|
1376
|
-
attr_accessor :variable
|
1377
|
-
# Special symbol used by search engine to designate this modification
|
1378
|
-
attr_accessor :symbol
|
1379
|
-
# whether modification can reside only at protein terminus (specified n or
|
1380
|
-
# c)
|
1381
|
-
attr_accessor :protein_terminus
|
1382
|
-
attr_accessor :description
|
1383
|
-
|
1384
|
-
def initialize(hash=nil)
|
1385
|
-
instance_var_set_from_hash(hash) if hash # can use unless there are weird methods
|
1386
|
-
end
|
1387
|
-
|
1388
|
-
def to_pepxml
|
1389
|
-
short_element_xml_from_instance_vars("terminal_modification")
|
1390
|
-
end
|
1391
|
-
end
|
1392
|
-
|
1393
|
-
|
1394
|
-
class Sequest::PepXML::SearchDatabase
|
1395
|
-
include SpecIDXML
|
1396
|
-
attr_accessor :local_path
|
1397
|
-
attr_writer :seq_type
|
1398
|
-
# Takes a SequestParams object
|
1399
|
-
# Sets :local_path from the params object attr :database
|
1400
|
-
def initialize(params=nil, args=nil)
|
1401
|
-
@seq_type = nil
|
1402
|
-
if params
|
1403
|
-
@local_path = params.database
|
1404
|
-
end
|
1405
|
-
if args ; set_from_hash(args) end
|
1406
|
-
end
|
1407
|
-
|
1408
|
-
def seq_type
|
1409
|
-
if @seq_type ; @seq_type
|
1410
|
-
else
|
1411
|
-
if @local_path =~ /\.fasta/
|
1412
|
-
'AA'
|
1413
|
-
else
|
1414
|
-
abort "Don't recognize type from your database local path: #{@local_path}"
|
1415
|
-
end
|
1416
|
-
end
|
1417
|
-
end
|
1418
|
-
|
1419
|
-
def to_pepxml
|
1420
|
-
short_element_xml_and_att_string(:search_database, "local_path=\"#{local_path}\" type=\"#{seq_type}\"")
|
1421
|
-
end
|
1422
|
-
|
1423
|
-
end
|
1424
|
-
|
1425
|
-
class Sequest::PepXML::SpectrumQuery
|
1426
|
-
include SpecIDXML
|
1427
|
-
|
1428
|
-
# basename_noext.first_scan.last_scan.charge
|
1429
|
-
attr_accessor :spectrum
|
1430
|
-
attr_accessor :start_scan
|
1431
|
-
attr_accessor :end_scan
|
1432
|
-
attr_accessor :precursor_neutral_mass
|
1433
|
-
attr_accessor :index
|
1434
|
-
attr_accessor :search_results
|
1435
|
-
|
1436
|
-
# this is a string
|
1437
|
-
attr_accessor :assumed_charge
|
1438
|
-
attr_accessor :pepxml_version
|
1439
|
-
|
1440
|
-
# sets the search_results array
|
1441
|
-
# if block given, sets search_results to return value
|
1442
|
-
def initialize(hash=nil)
|
1443
|
-
if block_given? ; @search_results = yield
|
1444
|
-
else ; @search_results = []
|
1445
|
-
end
|
1446
|
-
if hash ; set_from_hash(hash) end
|
1447
|
-
end
|
1448
|
-
|
1449
|
-
############################################################
|
1450
|
-
# FOR PEPXML:
|
1451
|
-
############################################################
|
1452
|
-
def to_pepxml
|
1453
|
-
case Sequest::PepXML.pepxml_version
|
1454
|
-
when 18
|
1455
|
-
element_xml("spectrum_query", [:spectrum, :start_scan, :end_scan, :precursor_neutral_mass, :assumed_charge, :index]) do
|
1456
|
-
@search_results.collect { |sr| sr.to_pepxml }.join
|
1457
|
-
end
|
1458
|
-
when 0
|
1459
|
-
#element_xml("search_result", [:spectrum, :start_scan, :end_scan, :precursor_neutral_mass, :assumed_charge, :index]) do
|
1460
|
-
# @search_results.collect { |search_result|
|
1461
|
-
# search_result.to_pepxml
|
1462
|
-
# }.join("\n")
|
1463
|
-
#end
|
1464
|
-
end
|
1465
|
-
end
|
1466
|
-
|
1467
|
-
# Returns the precursor_neutral based on the scans and an array indexed by
|
1468
|
-
# scan numbers. first and last scan and charge should be integers.
|
1469
|
-
# This is the precursor_mz - h_plus!
|
1470
|
-
# by=:prec_mz_arr|:deltamass
|
1471
|
-
# if prec_mz_arr then the following arguments must be supplied:
|
1472
|
-
# :first_scan = int, :last_scan = int, :prec_mz_arr = array with the precursor
|
1473
|
-
# m/z for each product scan, :charge = int
|
1474
|
-
# if deltamass then the following arguments must be supplied:
|
1475
|
-
# m_plus_h = float, deltamass = float
|
1476
|
-
# For both flavors, a final additional argument 'average_weights'
|
1477
|
-
# can be used. If true (default), average weights will be used, if false,
|
1478
|
-
# monoisotopic weights (currently this is simply the mass of the proton)
|
1479
|
-
def self.calc_precursor_neutral_mass(by, *args)
|
1480
|
-
average_weights = true
|
1481
|
-
case by
|
1482
|
-
when :prec_mz_arr
|
1483
|
-
(first_scan, last_scan, prec_mz_arr, charge, average_weights) = args
|
1484
|
-
when :deltamass
|
1485
|
-
(m_plus_h, deltamass, average_weights) = args
|
1486
|
-
end
|
1487
|
-
|
1488
|
-
if average_weights
|
1489
|
-
mass_h_plus = SpecID::AVG[:h_plus]
|
1490
|
-
else
|
1491
|
-
mass_h_plus = SpecID::MONO[:h_plus]
|
1492
|
-
end
|
1493
|
-
|
1494
|
-
case by
|
1495
|
-
when :prec_mz_arr
|
1496
|
-
mz = nil
|
1497
|
-
if first_scan != last_scan
|
1498
|
-
sum = 0.0
|
1499
|
-
tot_num = 0
|
1500
|
-
(first_scan..last_scan).each do |scan|
|
1501
|
-
val = prec_mz_arr[scan]
|
1502
|
-
if val # if the scan is not an mslevel 2
|
1503
|
-
sum += val.to_f
|
1504
|
-
tot_num += 1
|
1505
|
-
end
|
1506
|
-
end
|
1507
|
-
mz = sum/tot_num.to_f
|
1508
|
-
else
|
1509
|
-
mz = prec_mz_arr[first_scan].to_f
|
1510
|
-
end
|
1511
|
-
charge * (mz - mass_h_plus)
|
1512
|
-
when :deltamass
|
1513
|
-
m_plus_h - mass_h_plus + deltamass
|
1514
|
-
else
|
1515
|
-
abort "don't recognize 'by' in calc_precursor_neutral_mass: #{by}"
|
1516
|
-
end
|
1517
|
-
end
|
1518
|
-
|
1519
|
-
end
|
1520
|
-
|
1521
|
-
|
1522
|
-
|
1523
|
-
Sequest::PepXML::SearchHit = ArrayClass.new( %w( hit_rank peptide peptide_prev_aa peptide_next_aa protein num_tot_proteins num_matched_ions tot_num_ions calc_neutral_pep_mass massdiff num_tol_term num_missed_cleavages is_rejected deltacnstar xcorr deltacn spscore sprank modification_info) )
|
1524
|
-
|
1525
|
-
# hit_rank=0 peptide=1 peptide_prev_aa=2 peptide_next_aa=3 protein=4 num_tot_proteins=5 num_matched_ions=6 tot_num_ions=7 calc_neutral_pep_mass=8 massdiff=9 num_tol_term=10 num_missed_cleavages=11 is_rejected=12 deltacnstar=13 xcorr=14 deltacn=15 spscore=16 sprank=17 modification_info=18
|
1526
|
-
|
1527
|
-
class Sequest::PepXML::SearchHit
|
1528
|
-
include SpecIDXML
|
1529
|
-
|
1530
|
-
Non_standard_amino_acid_char_re = /[^A-Z\.\-]/
|
1531
|
-
|
1532
|
-
|
1533
|
-
# These are all search_score elements:
|
1534
|
-
|
1535
|
-
# 1 if there is no second ranked hit, 0 otherwise
|
1536
|
-
|
1537
|
-
tmp_verb = $VERBOSE
|
1538
|
-
$VERBOSE = nil
|
1539
|
-
def initialize(hash=nil)
|
1540
|
-
super(@@arr_size)
|
1541
|
-
if hash
|
1542
|
-
self[0,19] = [hash[:hit_rank], hash[:peptide], hash[:peptide_prev_aa], hash[:peptide_next_aa], hash[:protein], hash[:num_tot_proteins], hash[:num_matched_ions], hash[:tot_num_ions], hash[:calc_neutral_pep_mass], hash[:massdiff], hash[:num_tol_term], hash[:num_missed_cleavages], hash[:is_rejected], hash[:deltacnstar], hash[:xcorr], hash[:deltacn], hash[:spscore], hash[:sprank], hash[:modification_info]]
|
1543
|
-
end
|
1544
|
-
self
|
1545
|
-
end
|
1546
|
-
$VERBOSE = tmp_verb
|
1547
|
-
|
1548
|
-
def inspect
|
1549
|
-
var = @@attributes.map do |m| "#{m}:#{self.send(m)}" end.join(" ")
|
1550
|
-
"#<SearchHit #{var}>"
|
1551
|
-
end
|
1552
|
-
|
1553
|
-
# requires Params object and full sequence (with heads and tails)
|
1554
|
-
def self.calc_num_missed_cleavages(params, sequence)
|
1555
|
-
num_missed = 0
|
1556
|
-
split_after, except_before = params.enzyme_specificity
|
1557
|
-
first, middle, last = SpecID::Pep.split_sequence(sequence)
|
1558
|
-
arr = middle.scan(/[#{split_after}][^#{except_before}]/)
|
1559
|
-
return arr.size
|
1560
|
-
end
|
1561
|
-
|
1562
|
-
# requires Params object and full sequence (with heads and tails)
|
1563
|
-
def self.calc_num_tol_term(params, sequence)
|
1564
|
-
num_tol = 0
|
1565
|
-
split_after, except_before = params.enzyme_specificity
|
1566
|
-
first, middle, last = SpecID::Pep.split_sequence(sequence)
|
1567
|
-
last_of_middle = middle[-1,1]
|
1568
|
-
first_of_middle = middle[0,1]
|
1569
|
-
if ( split_after.include?(first) && !except_before.include?(first_of_middle) ) || first == '-'
|
1570
|
-
num_tol += 1
|
1571
|
-
end
|
1572
|
-
if split_after.include?(last_of_middle) && !except_before.include?(last) || last == '-'
|
1573
|
-
num_tol += 1
|
1574
|
-
end
|
1575
|
-
return num_tol
|
1576
|
-
end
|
1577
|
-
|
1578
|
-
# Takes ions in the form XX/YY and returns XX, YY
|
1579
|
-
def self.split_ions(ions)
|
1580
|
-
return *(ions.split("/"))
|
1581
|
-
end
|
1582
|
-
|
1583
|
-
def search_score_xml(symbol)
|
1584
|
-
"#{tabs}<search_score name=\"#{symbol}\" value=\"#{send(symbol)}\"/>"
|
1585
|
-
end
|
1586
|
-
|
1587
|
-
def search_scores_xml(*symbol_list)
|
1588
|
-
symbol_list.collect do |sy|
|
1589
|
-
search_score_xml(sy)
|
1590
|
-
end.join("\n") + "\n"
|
1591
|
-
end
|
1592
|
-
|
1593
|
-
def to_pepxml
|
1594
|
-
mod_pepxml =
|
1595
|
-
if self[18]
|
1596
|
-
self[18].to_pepxml
|
1597
|
-
else
|
1598
|
-
''
|
1599
|
-
end
|
1600
|
-
|
1601
|
-
element_xml("search_hit", [:hit_rank, :peptide, :peptide_prev_aa, :peptide_next_aa, :protein, :num_tot_proteins, :num_matched_ions, :tot_num_ions, :calc_neutral_pep_mass, :massdiff, :num_tol_term, :num_missed_cleavages, :is_rejected]) do
|
1602
|
-
mod_pepxml +
|
1603
|
-
search_scores_xml(:xcorr, :deltacn, :deltacnstar, :spscore, :sprank)
|
1604
|
-
end
|
1605
|
-
end
|
1606
|
-
|
1607
|
-
end
|
1608
|
-
|
1609
|
-
# Positions and masses of modifications
|
1610
|
-
class Sequest::PepXML::SearchHit::ModificationInfo
|
1611
|
-
include SpecIDXML
|
1612
|
-
|
1613
|
-
## Should be something like this:
|
1614
|
-
# <modification_info mod_nterm_mass=" " mod_nterm_mass=" " modified_peptide=" ">
|
1615
|
-
# <mod_aminoacid_mass position=" " mass=" "/>
|
1616
|
-
# </modification_info>
|
1617
|
-
|
1618
|
-
|
1619
|
-
# Mass of modified N terminus<
|
1620
|
-
attr_accessor :mod_nterm_mass
|
1621
|
-
# Mass of modified C terminus<
|
1622
|
-
attr_accessor :mod_cterm_mass
|
1623
|
-
# Peptide sequence (with indicated modifications) I'm assuming that the
|
1624
|
-
# native sequest indicators are OK here
|
1625
|
-
attr_accessor :modified_peptide
|
1626
|
-
## A few main types:
|
1627
|
-
|
1628
|
-
# this should be an array of arrays: [[position, modified_mass], ...]
|
1629
|
-
# position ranges from 1 to peptide length
|
1630
|
-
attr_accessor :mod_aminoacid_mass_array
|
1631
|
-
|
1632
|
-
def initialize(hash=nil)
|
1633
|
-
@mod_nterm_mass = nil
|
1634
|
-
@mod_cterm_mass = nil
|
1635
|
-
if hash
|
1636
|
-
instance_var_set_from_hash(hash)
|
1637
|
-
end
|
1638
|
-
end
|
1639
|
-
|
1640
|
-
# Will escape any xml special chars in modified_peptide
|
1641
|
-
def to_pepxml
|
1642
|
-
## Collect the modifications:
|
1643
|
-
mod_strings = []
|
1644
|
-
if @mod_aminoacid_mass_array
|
1645
|
-
mod_strings = @mod_aminoacid_mass_array.map do |ar|
|
1646
|
-
"position=\"#{ar[0]}\" mass=\"#{ar[1]}\""
|
1647
|
-
end
|
1648
|
-
end
|
1649
|
-
## Create the attribute string:
|
1650
|
-
att_parts = []
|
1651
|
-
if @mod_nterm_mass
|
1652
|
-
att_parts << "mod_nterm_mass=\"#{@mod_nterm_mass}\""
|
1653
|
-
end
|
1654
|
-
if @mod_cterm_mass
|
1655
|
-
att_parts << "mod_cterm_mass=\"#{@mod_cterm_mass}\""
|
1656
|
-
end
|
1657
|
-
if @modified_peptide
|
1658
|
-
att_parts << "modified_peptide=\"#{escape_special_chars(@modified_peptide)}\""
|
1659
|
-
end
|
1660
|
-
element_xml_and_att_string('modification_info', att_parts.join(" ")) do
|
1661
|
-
mod_strings.map {|st| short_element_xml_and_att_string('mod_aminoacid_mass', st) }.join
|
1662
|
-
end
|
1663
|
-
end
|
1664
|
-
|
1665
|
-
##
|
1666
|
-
|
1667
|
-
# <modification_info modified_peptide="GC[546]M[147]PSKEVLSAGAHR">
|
1668
|
-
# <mod_aminoacid_mass position="2" mass="545.7160"/>
|
1669
|
-
# <mod_aminoacid_mass position="3" mass="147.1926"/>
|
1670
|
-
# </modification_info>
|
1671
|
-
|
1672
|
-
|
1673
|
-
end
|
1674
|
-
|
1675
|
-
|