mspire 0.4.9 → 0.5.0
Sign up to get free protection for your applications and to get access to all the features.
- data/README +27 -17
- data/changelog.txt +31 -62
- data/lib/ms/calc.rb +32 -0
- data/lib/ms/data/interleaved.rb +60 -0
- data/lib/ms/data/lazy_io.rb +73 -0
- data/lib/ms/data/lazy_string.rb +15 -0
- data/lib/ms/data/simple.rb +59 -0
- data/lib/ms/data/transposed.rb +41 -0
- data/lib/ms/data.rb +57 -0
- data/lib/ms/format/format_error.rb +12 -0
- data/lib/ms/spectrum.rb +25 -384
- data/lib/ms/support/binary_search.rb +126 -0
- data/lib/ms.rb +10 -10
- metadata +38 -350
- data/INSTALL +0 -58
- data/README.rdoc +0 -18
- data/Rakefile +0 -330
- data/bin/aafreqs.rb +0 -23
- data/bin/bioworks2excel.rb +0 -14
- data/bin/bioworks_to_pepxml.rb +0 -148
- data/bin/bioworks_to_pepxml_gui.rb +0 -225
- data/bin/fasta_shaker.rb +0 -5
- data/bin/filter_and_validate.rb +0 -5
- data/bin/gi2annot.rb +0 -14
- data/bin/id_class_anal.rb +0 -112
- data/bin/id_precision.rb +0 -172
- data/bin/ms_to_lmat.rb +0 -67
- data/bin/pepproph_filter.rb +0 -16
- data/bin/prob_validate.rb +0 -6
- data/bin/protein_summary.rb +0 -6
- data/bin/protxml2prots_peps.rb +0 -32
- data/bin/raw_to_mzXML.rb +0 -55
- data/bin/run_percolator.rb +0 -122
- data/bin/sqt_group.rb +0 -26
- data/bin/srf_group.rb +0 -27
- data/bin/srf_to_sqt.rb +0 -40
- data/lib/align/chams.rb +0 -78
- data/lib/align.rb +0 -154
- data/lib/archive/targz.rb +0 -94
- data/lib/bsearch.rb +0 -120
- data/lib/core_extensions.rb +0 -16
- data/lib/fasta.rb +0 -626
- data/lib/gi.rb +0 -124
- data/lib/group_by.rb +0 -10
- data/lib/index_by.rb +0 -11
- data/lib/merge_deep.rb +0 -21
- data/lib/ms/converter/mzxml.rb +0 -77
- data/lib/ms/gradient_program.rb +0 -170
- data/lib/ms/msrun.rb +0 -244
- data/lib/ms/msrun_index.rb +0 -108
- data/lib/ms/parser/mzdata/axml.rb +0 -67
- data/lib/ms/parser/mzdata/dom.rb +0 -175
- data/lib/ms/parser/mzdata/libxml.rb +0 -7
- data/lib/ms/parser/mzdata.rb +0 -31
- data/lib/ms/parser/mzxml/axml.rb +0 -70
- data/lib/ms/parser/mzxml/dom.rb +0 -182
- data/lib/ms/parser/mzxml/hpricot.rb +0 -253
- data/lib/ms/parser/mzxml/libxml.rb +0 -19
- data/lib/ms/parser/mzxml/regexp.rb +0 -122
- data/lib/ms/parser/mzxml/rexml.rb +0 -72
- data/lib/ms/parser/mzxml/xmlparser.rb +0 -248
- data/lib/ms/parser/mzxml.rb +0 -282
- data/lib/ms/parser.rb +0 -108
- data/lib/ms/precursor.rb +0 -25
- data/lib/ms/scan.rb +0 -81
- data/lib/mspire.rb +0 -4
- data/lib/pi_zero.rb +0 -244
- data/lib/qvalue.rb +0 -161
- data/lib/roc.rb +0 -187
- data/lib/sample_enzyme.rb +0 -160
- data/lib/scan_i.rb +0 -21
- data/lib/spec_id/aa_freqs.rb +0 -170
- data/lib/spec_id/bioworks.rb +0 -497
- data/lib/spec_id/digestor.rb +0 -138
- data/lib/spec_id/mass.rb +0 -179
- data/lib/spec_id/parser/proph.rb +0 -335
- data/lib/spec_id/precision/filter/cmdline.rb +0 -218
- data/lib/spec_id/precision/filter/interactive.rb +0 -134
- data/lib/spec_id/precision/filter/output.rb +0 -148
- data/lib/spec_id/precision/filter.rb +0 -637
- data/lib/spec_id/precision/output.rb +0 -60
- data/lib/spec_id/precision/prob/cmdline.rb +0 -160
- data/lib/spec_id/precision/prob/output.rb +0 -94
- data/lib/spec_id/precision/prob.rb +0 -249
- data/lib/spec_id/proph/pep_summary.rb +0 -104
- data/lib/spec_id/proph/prot_summary.rb +0 -484
- data/lib/spec_id/proph.rb +0 -4
- data/lib/spec_id/protein_summary.rb +0 -489
- data/lib/spec_id/sequest/params.rb +0 -316
- data/lib/spec_id/sequest/pepxml.rb +0 -1458
- data/lib/spec_id/sequest.rb +0 -33
- data/lib/spec_id/sqt.rb +0 -349
- data/lib/spec_id/srf.rb +0 -973
- data/lib/spec_id.rb +0 -778
- data/lib/spec_id_xml.rb +0 -99
- data/lib/transmem/phobius.rb +0 -147
- data/lib/transmem/toppred.rb +0 -368
- data/lib/transmem.rb +0 -157
- data/lib/validator/aa.rb +0 -48
- data/lib/validator/aa_est.rb +0 -112
- data/lib/validator/background.rb +0 -77
- data/lib/validator/bias.rb +0 -95
- data/lib/validator/cmdline.rb +0 -431
- data/lib/validator/decoy.rb +0 -107
- data/lib/validator/digestion_based.rb +0 -70
- data/lib/validator/probability.rb +0 -51
- data/lib/validator/prot_from_pep.rb +0 -234
- data/lib/validator/q_value.rb +0 -32
- data/lib/validator/transmem.rb +0 -272
- data/lib/validator/true_pos.rb +0 -46
- data/lib/validator.rb +0 -197
- data/lib/xml.rb +0 -38
- data/lib/xml_style_parser.rb +0 -119
- data/lib/xmlparser_wrapper.rb +0 -19
- data/release_notes.txt +0 -2
- data/script/compile_and_plot_smriti_final.rb +0 -97
- data/script/create_little_pepxml.rb +0 -61
- data/script/degenerate_peptides.rb +0 -47
- data/script/estimate_fpr_by_cysteine.rb +0 -226
- data/script/extract_gradient_programs.rb +0 -56
- data/script/find_cysteine_background.rb +0 -137
- data/script/genuine_tps_and_probs.rb +0 -136
- data/script/get_apex_values_rexml.rb +0 -44
- data/script/histogram_probs.rb +0 -61
- data/script/mascot_fix_pepxml.rb +0 -123
- data/script/msvis.rb +0 -42
- data/script/mzXML2timeIndex.rb +0 -25
- data/script/peps_per_bin.rb +0 -67
- data/script/prep_dir.rb +0 -121
- data/script/simple_protein_digestion.rb +0 -27
- data/script/smriti_final_analysis.rb +0 -103
- data/script/sqt_to_meta.rb +0 -24
- data/script/top_hit_per_scan.rb +0 -67
- data/script/toppred_to_yaml.rb +0 -47
- data/script/tpp_installer.rb +0 -249
- data/specs/align_spec.rb +0 -79
- data/specs/bin/bioworks_to_pepxml_spec.rb +0 -79
- data/specs/bin/fasta_shaker_spec.rb +0 -259
- data/specs/bin/filter_and_validate__multiple_vals_helper.yaml +0 -199
- data/specs/bin/filter_and_validate_spec.rb +0 -180
- data/specs/bin/ms_to_lmat_spec.rb +0 -34
- data/specs/bin/prob_validate_spec.rb +0 -86
- data/specs/bin/protein_summary_spec.rb +0 -14
- data/specs/fasta_spec.rb +0 -354
- data/specs/gi_spec.rb +0 -22
- data/specs/load_bin_path.rb +0 -7
- data/specs/merge_deep_spec.rb +0 -13
- data/specs/ms/gradient_program_spec.rb +0 -77
- data/specs/ms/msrun_spec.rb +0 -498
- data/specs/ms/parser_spec.rb +0 -92
- data/specs/ms/spectrum_spec.rb +0 -87
- data/specs/pi_zero_spec.rb +0 -115
- data/specs/qvalue_spec.rb +0 -39
- data/specs/roc_spec.rb +0 -251
- data/specs/rspec_autotest.rb +0 -149
- data/specs/sample_enzyme_spec.rb +0 -126
- data/specs/spec_helper.rb +0 -135
- data/specs/spec_id/aa_freqs_spec.rb +0 -52
- data/specs/spec_id/bioworks_spec.rb +0 -148
- data/specs/spec_id/digestor_spec.rb +0 -75
- data/specs/spec_id/precision/filter/cmdline_spec.rb +0 -20
- data/specs/spec_id/precision/filter/output_spec.rb +0 -31
- data/specs/spec_id/precision/filter_spec.rb +0 -246
- data/specs/spec_id/precision/prob_spec.rb +0 -44
- data/specs/spec_id/precision/prob_spec_helper.rb +0 -0
- data/specs/spec_id/proph/pep_summary_spec.rb +0 -98
- data/specs/spec_id/proph/prot_summary_spec.rb +0 -128
- data/specs/spec_id/protein_summary_spec.rb +0 -189
- data/specs/spec_id/sequest/params_spec.rb +0 -68
- data/specs/spec_id/sequest/pepxml_spec.rb +0 -374
- data/specs/spec_id/sequest_spec.rb +0 -38
- data/specs/spec_id/sqt_spec.rb +0 -246
- data/specs/spec_id/srf_spec.rb +0 -172
- data/specs/spec_id/srf_spec_helper.rb +0 -139
- data/specs/spec_id_helper.rb +0 -33
- data/specs/spec_id_spec.rb +0 -366
- data/specs/spec_id_xml_spec.rb +0 -33
- data/specs/transmem/phobius_spec.rb +0 -425
- data/specs/transmem/toppred_spec.rb +0 -298
- data/specs/transmem_spec.rb +0 -60
- data/specs/transmem_spec_shared.rb +0 -64
- data/specs/validator/aa_est_spec.rb +0 -66
- data/specs/validator/aa_spec.rb +0 -40
- data/specs/validator/background_spec.rb +0 -67
- data/specs/validator/bias_spec.rb +0 -122
- data/specs/validator/decoy_spec.rb +0 -51
- data/specs/validator/fasta_helper.rb +0 -26
- data/specs/validator/prot_from_pep_spec.rb +0 -141
- data/specs/validator/transmem_spec.rb +0 -146
- data/specs/validator/true_pos_spec.rb +0 -58
- data/specs/validator_helper.rb +0 -33
- data/specs/xml_spec.rb +0 -12
- data/test_files/000_pepxml18_small.xml +0 -206
- data/test_files/020a.mzXML.timeIndex +0 -4710
- data/test_files/4-03-03_mzXML/000.mzXML.timeIndex +0 -3973
- data/test_files/4-03-03_mzXML/020.mzXML.timeIndex +0 -3872
- data/test_files/4-03-03_small-prot.xml +0 -321
- data/test_files/4-03-03_small.xml +0 -3876
- data/test_files/7MIX_STD_110802_1.sequest_params_fragment.srf +0 -0
- data/test_files/bioworks-3.3_10prots.xml +0 -5999
- data/test_files/bioworks31.params +0 -77
- data/test_files/bioworks32.params +0 -62
- data/test_files/bioworks33.params +0 -63
- data/test_files/bioworks_single_run_small.xml +0 -7237
- data/test_files/bioworks_small.fasta +0 -212
- data/test_files/bioworks_small.params +0 -63
- data/test_files/bioworks_small.phobius +0 -109
- data/test_files/bioworks_small.toppred.out +0 -2847
- data/test_files/bioworks_small.xml +0 -5610
- data/test_files/bioworks_with_INV_small.xml +0 -3753
- data/test_files/bioworks_with_SHUFF_small.xml +0 -2503
- 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 +0 -304
- data/test_files/messups.fasta +0 -297
- data/test_files/opd1/000.my_answer.100lines.xml +0 -101
- data/test_files/opd1/000.tpp_1.2.3.first10.xml +0 -115
- data/test_files/opd1/000.tpp_2.9.2.first10.xml +0 -126
- data/test_files/opd1/000.v2.1.mzXML.timeIndex +0 -3748
- data/test_files/opd1/000_020-prot.png +0 -0
- data/test_files/opd1/000_020_3prots-prot.mod_initprob.xml +0 -62
- data/test_files/opd1/000_020_3prots-prot.xml +0 -62
- data/test_files/opd1/opd1_cat_inv_small-prot.xml +0 -139
- data/test_files/opd1/sequest.3.1.params +0 -77
- data/test_files/opd1/sequest.3.2.params +0 -62
- data/test_files/opd1/twenty_scans.mzXML +0 -418
- data/test_files/opd1/twenty_scans.v2.1.mzXML +0 -382
- data/test_files/opd1/twenty_scans_answ.lmat +0 -0
- data/test_files/opd1/twenty_scans_answ.lmata +0 -9
- data/test_files/opd1_020_beginning.RAW +0 -0
- data/test_files/opd1_2runs_2mods/data/020.mzData.xml +0 -683
- data/test_files/opd1_2runs_2mods/data/020.readw.mzXML +0 -382
- data/test_files/opd1_2runs_2mods/data/040.mzData.xml +0 -683
- data/test_files/opd1_2runs_2mods/data/040.readw.mzXML +0 -382
- data/test_files/opd1_2runs_2mods/data/README.txt +0 -6
- data/test_files/opd1_2runs_2mods/interact-opd1_mods__small.xml +0 -753
- data/test_files/orbitrap_mzData/000_cut.xml +0 -1920
- data/test_files/pepproph_small.xml +0 -4691
- data/test_files/phobius.small.noheader.txt +0 -50
- data/test_files/phobius.small.small.txt +0 -53
- data/test_files/s01_anC1_ld020mM.key.txt +0 -25
- data/test_files/s01_anC1_ld020mM.meth +0 -0
- data/test_files/small.fasta +0 -297
- data/test_files/small.sqt +0 -87
- data/test_files/smallraw.RAW +0 -0
- data/test_files/tf_bioworks2excel.bioXML +0 -14340
- data/test_files/tf_bioworks2excel.txt.actual +0 -1035
- data/test_files/toppred.small.out +0 -416
- data/test_files/toppred.xml.out +0 -318
- data/test_files/validator_hits_separate/bias_bioworks_small_HS.fasta +0 -7
- data/test_files/validator_hits_separate/bioworks_small_HS.xml +0 -5651
- data/test_files/yeast_gly_small-prot.xml +0 -265
- data/test_files/yeast_gly_small.1.0_1.0_1.0.parentTimes +0 -6
- data/test_files/yeast_gly_small.xml +0 -3807
- data/test_files/yeast_gly_small2.parentTimes +0 -6
data/lib/spec_id/mass.rb
DELETED
@@ -1,179 +0,0 @@
|
|
1
|
-
|
2
|
-
class Mass
|
3
|
-
# http://expasy.org/tools/findmod/findmod_masses.html
|
4
|
-
# still need to add the modifications
|
5
|
-
MONO = {
|
6
|
-
:A => 71.03711,
|
7
|
-
:R => 156.10111,
|
8
|
-
:N => 114.04293,
|
9
|
-
:D => 115.02694,
|
10
|
-
:C => 103.00919,
|
11
|
-
:E => 129.04259,
|
12
|
-
:Q => 128.05858,
|
13
|
-
:G => 57.02146,
|
14
|
-
:H => 137.05891,
|
15
|
-
:I => 113.08406,
|
16
|
-
:L => 113.08406,
|
17
|
-
:K => 128.09496,
|
18
|
-
:M => 131.04049,
|
19
|
-
:F => 147.06841,
|
20
|
-
:P => 97.05276,
|
21
|
-
:S => 87.03203,
|
22
|
-
:T => 101.04768,
|
23
|
-
:W => 186.07931,
|
24
|
-
:Y => 163.06333,
|
25
|
-
:V => 99.06841,
|
26
|
-
|
27
|
-
# uncommon
|
28
|
-
:B => 172.048405, # average of aspartic acid and asparagine
|
29
|
-
:U => 150.95364, # (selenocysteine) http://www.matrix-science.com/help/aa_help.html
|
30
|
-
:X => 118.805716, # the average of the mono masses of the 20 amino acids
|
31
|
-
:* => 118.805716, # same as X
|
32
|
-
:Z => (129.04259 + 128.05858) / 2, # average glutamic acid and glutamine
|
33
|
-
|
34
|
-
# elements etc.
|
35
|
-
:h => 1.00783,
|
36
|
-
#:h_plus => 1.00728, # this is the mass I had
|
37
|
-
:h_plus => 1.007276, # this is the mass used by mascot merge.pl
|
38
|
-
:o => 15.9949146,
|
39
|
-
:h2o => 18.01056,
|
40
|
-
}
|
41
|
-
AVG = {
|
42
|
-
:A => 71.0788,
|
43
|
-
:R => 156.1875,
|
44
|
-
:N => 114.1038,
|
45
|
-
:D => 115.0886,
|
46
|
-
:C => 103.1388,
|
47
|
-
:E => 129.1155,
|
48
|
-
:Q => 128.1307,
|
49
|
-
:G => 57.0519,
|
50
|
-
:H => 137.1411,
|
51
|
-
:I => 113.1594,
|
52
|
-
:L => 113.1594,
|
53
|
-
:K => 128.1741,
|
54
|
-
:M => 131.1926,
|
55
|
-
:F => 147.1766,
|
56
|
-
:P => 97.1167,
|
57
|
-
:S => 87.0782,
|
58
|
-
:T => 101.1051,
|
59
|
-
:W => 186.2132,
|
60
|
-
:Y => 163.1760,
|
61
|
-
:V => 99.1326,
|
62
|
-
|
63
|
-
# uncommon
|
64
|
-
:B => 172.1405, # average of aspartic acid and asparagine
|
65
|
-
:U => 150.03, # (selenocysteine) http://www.matrix-science.com/help/aa_help.html
|
66
|
-
:X => 118.88603, # the average of the masses of the 20 amino acids
|
67
|
-
:* => 118.88603, # same as X
|
68
|
-
:Z => (129.1155+ 128.1307) / 2, # average glutamic acid and glutamine
|
69
|
-
|
70
|
-
# elements etc.
|
71
|
-
:h => 1.00794,
|
72
|
-
:h_plus => 1.00739,
|
73
|
-
:o => 15.9994,
|
74
|
-
:h2o => 18.01524,
|
75
|
-
}
|
76
|
-
|
77
|
-
# returns a fresh hash where it has been added to each amino acid the amount
|
78
|
-
# specified in the array of a PepXML::Modifications object
|
79
|
-
# if static_terminal_mods given than will create the following keys as
|
80
|
-
# symbols as necessary:
|
81
|
-
# add_C_term_protein
|
82
|
-
# add_C_term_peptide
|
83
|
-
# add_N_term_protein
|
84
|
-
# add_N_term_peptide
|
85
|
-
def self.add_static_masses(monoisotopic, static_mods, static_terminal_mods=nil)
|
86
|
-
hash_to_use =
|
87
|
-
if monoisotopic
|
88
|
-
Mass::MONO
|
89
|
-
else
|
90
|
-
Mass::AVG
|
91
|
-
end
|
92
|
-
copy_hash = hash_to_use.dup
|
93
|
-
static_mods.each do |mod|
|
94
|
-
copy_hash[mod.aminoacid.to_sym] += mod.massdiff
|
95
|
-
end
|
96
|
-
static_terminal_mods.each do |mod|
|
97
|
-
if x = mod.protein_terminus
|
98
|
-
# its a protein terminus modification
|
99
|
-
case x
|
100
|
-
when 'n'
|
101
|
-
copy_hash[:add_N_term_protein] = mod.massdiff
|
102
|
-
when 'c'
|
103
|
-
copy_hash[:add_C_term_protein] = mod.massdiff
|
104
|
-
end
|
105
|
-
else
|
106
|
-
# its a peptide terminus modification
|
107
|
-
case mod.terminus
|
108
|
-
when 'n'
|
109
|
-
copy_hash[:add_N_term_peptide] = mod.massdiff
|
110
|
-
when 'c'
|
111
|
-
copy_hash[:add_C_term_peptide] = mod.massdiff
|
112
|
-
end
|
113
|
-
end
|
114
|
-
end
|
115
|
-
copy_hash
|
116
|
-
end
|
117
|
-
|
118
|
-
# returns an array of masses parallel to array passed in
|
119
|
-
# If you want the mass with H+, then pass in the mass as h_plus
|
120
|
-
# The mass hash must repond to
|
121
|
-
# :h2o (water)
|
122
|
-
# and at least the twenty amino acids (by string or symbol)
|
123
|
-
# The mass hash may respond to :add_N_term_peptide or :add_C_term_peptide
|
124
|
-
# in which case these will be added to the final mass
|
125
|
-
def self.masses(aaseqs, mass_hash=Mass::MONO, h_plus=0.0)
|
126
|
-
final_add = mass_hash[:h2o] + h_plus
|
127
|
-
[:add_N_term_peptide, :add_C_term_peptide].each do |sym|
|
128
|
-
if mass_hash.key?(sym)
|
129
|
-
final_add += mass_hash[sym]
|
130
|
-
end
|
131
|
-
end
|
132
|
-
hash_by_aa_string = {}
|
133
|
-
mass_hash.each {|k,v| hash_by_aa_string[k.to_s] = mass_hash[k] }
|
134
|
-
|
135
|
-
aaseqs.map do |pep_aaseqs|
|
136
|
-
sum = 0.0
|
137
|
-
aaseq.split('').each do |let|
|
138
|
-
sum += hash_by_aa_string[let]
|
139
|
-
end
|
140
|
-
mh_plus = sum + final_add
|
141
|
-
end
|
142
|
-
end
|
143
|
-
|
144
|
-
|
145
|
-
end
|
146
|
-
|
147
|
-
class Mass::Calculator
|
148
|
-
|
149
|
-
# mass_hash must respond to :h2o or 'h2o'. This is added to represent the
|
150
|
-
# tails of the peptide. add_extra is outside of that (e.g., an H+)
|
151
|
-
def initialize(mass_hash, add_extra=0.0)
|
152
|
-
@mass_hash = mass_hash_to_s(mass_hash)
|
153
|
-
@final_add = @mass_hash['h2o'] + add_extra
|
154
|
-
end
|
155
|
-
|
156
|
-
def mass_hash_to_s(mass_hash)
|
157
|
-
new_hash = {}
|
158
|
-
mass_hash.each do |k,v|
|
159
|
-
new_hash[k.to_s] = v
|
160
|
-
end
|
161
|
-
new_hash
|
162
|
-
end
|
163
|
-
|
164
|
-
def masses(aaseqs)
|
165
|
-
aaseqs.map do |aaseq|
|
166
|
-
sum = @final_add # <- add in the initialization
|
167
|
-
aaseq.split('').each do |let|
|
168
|
-
if @mass_hash.key? let
|
169
|
-
sum += @mass_hash[let]
|
170
|
-
else
|
171
|
-
abort "LETTER not found in mass_hash: #{let}"
|
172
|
-
end
|
173
|
-
end
|
174
|
-
sum
|
175
|
-
end
|
176
|
-
end
|
177
|
-
|
178
|
-
end
|
179
|
-
|
data/lib/spec_id/parser/proph.rb
DELETED
@@ -1,335 +0,0 @@
|
|
1
|
-
require 'xml_style_parser'
|
2
|
-
require 'spec_id/sequest/pepxml'
|
3
|
-
|
4
|
-
|
5
|
-
module SpecID ; end
|
6
|
-
module SpecID::Parser ; end
|
7
|
-
|
8
|
-
|
9
|
-
class SpecID::Parser::PepProph
|
10
|
-
include XMLStyleParser
|
11
|
-
|
12
|
-
# gets the protein (and adds the pephit to the protein)
|
13
|
-
def get_protein(search_hit, name, description, global_prot_hash)
|
14
|
-
prot =
|
15
|
-
if global_prot_hash.key?(name)
|
16
|
-
global_prot_hash[name]
|
17
|
-
else
|
18
|
-
prt = Proph::PepSummary::Prot.new([name, description, []])
|
19
|
-
global_prot_hash[name] = prt
|
20
|
-
end
|
21
|
-
prot.peps << search_hit
|
22
|
-
prot
|
23
|
-
end
|
24
|
-
|
25
|
-
def initialize(parse_type=:spec_id, version='3.0')
|
26
|
-
@method = parse_type
|
27
|
-
@version = version
|
28
|
-
implemented = %w(AXML LibXML)
|
29
|
-
klass_s = XMLStyleParser.available_xml_parsers.select {|v| implemented.include?(v) }.first
|
30
|
-
case klass_s
|
31
|
-
when 'AXML'
|
32
|
-
@get_root_node_from_file = Proc.new do |file|
|
33
|
-
AXML.parse_file(file)
|
34
|
-
end
|
35
|
-
when 'LibXML' # LibXML is buggy on some machines...
|
36
|
-
@get_root_node_from_file = Proc.new do |file|
|
37
|
-
doc = XML::Document.file(file)
|
38
|
-
doc.root
|
39
|
-
end
|
40
|
-
else
|
41
|
-
raise NotImplementedError, "Can only parse with #{implemented.join(', ')} right now"
|
42
|
-
end
|
43
|
-
end
|
44
|
-
|
45
|
-
# returns the spec_id object
|
46
|
-
# :global_prot_hash is a hash if you have multiple of these files to be
|
47
|
-
# combined
|
48
|
-
def spec_id(file, opts={})
|
49
|
-
|
50
|
-
raise NotImplementedError, "cannot do #{@version} yet" if @version.nil? or @version < '3.0'
|
51
|
-
spec_id_obj =
|
52
|
-
if x = opts[:spec_id]
|
53
|
-
x
|
54
|
-
else
|
55
|
-
Proph::PepSummary.new
|
56
|
-
end
|
57
|
-
global_prot_hash =
|
58
|
-
if y = opts[:global_prot_hash]
|
59
|
-
y
|
60
|
-
else
|
61
|
-
{}
|
62
|
-
end
|
63
|
-
msms_pipeline_analysis_n = @get_root_node_from_file.call(file)
|
64
|
-
spec_id_obj.peptideprophet_summary = msms_pipeline_analysis_n.find_first("descendant::peptideprophet_summary")
|
65
|
-
|
66
|
-
|
67
|
-
spec_id_obj.msms_run_summaries = msms_pipeline_analysis_n.find('child::msms_run_summary').map do |msms_run_summary_n|
|
68
|
-
parse_msms_run_summary(msms_run_summary_n, global_prot_hash)
|
69
|
-
end
|
70
|
-
|
71
|
-
peps = []
|
72
|
-
spec_id_obj.msms_run_summaries.each do |mrs|
|
73
|
-
mrs.spectrum_queries.each do |sq|
|
74
|
-
sq.search_results.each do |sr|
|
75
|
-
peps.push( *(sr.search_hits) )
|
76
|
-
end
|
77
|
-
end
|
78
|
-
end
|
79
|
-
spec_id_obj.peps = peps
|
80
|
-
spec_id_obj.prots = global_prot_hash.values
|
81
|
-
spec_id_obj
|
82
|
-
end
|
83
|
-
|
84
|
-
# returns an msms_run_summary object
|
85
|
-
def parse_msms_run_summary(msms_run_summary_n, global_prot_hash)
|
86
|
-
msms_run_summary_obj = Sequest::PepXML::MSMSRunSummary.new
|
87
|
-
|
88
|
-
msms_run_summary_obj.from_pepxml_node(msms_run_summary_n)
|
89
|
-
sample_enzyme_n = msms_run_summary_n.find_first("child::sample_enzyme")
|
90
|
-
msms_run_summary_obj.sample_enzyme = SampleEnzyme.from_pepxml_node( sample_enzyme_n )
|
91
|
-
|
92
|
-
search_summary_n = sample_enzyme_n.find_first("following-sibling::search_summary")
|
93
|
-
spectrum_queries_nds = search_summary_n.find("following-sibling::spectrum_query")
|
94
|
-
|
95
|
-
msms_run_summary_obj.spectrum_queries = spectrum_queries_nds.map do |sq_n|
|
96
|
-
|
97
|
-
sq = Sequest::PepXML::SpectrumQuery.from_pepxml_node(sq_n)
|
98
|
-
sq.search_results = sq_n.children.map do |sr_n|
|
99
|
-
sr = Sequest::PepXML::SearchResult.new
|
100
|
-
sr.search_hits = sr_n.children.map do |sh_n|
|
101
|
-
sh = Proph::PepSummary::Pep.new # descended from SearchHit
|
102
|
-
sh.from_pepxml_node(sh_n)
|
103
|
-
sh.spectrum_query = sq
|
104
|
-
prots = [ get_protein(sh, sh_n['protein'], sh_n['protein_descr'], global_prot_hash) ]
|
105
|
-
## alternative proteins:
|
106
|
-
if sh.num_tot_proteins > 1
|
107
|
-
sh_n.find('child::alternative_protein').each do |alt_prot_n|
|
108
|
-
prots << get_protein(sh, alt_prot_n['protein'], alt_prot_n['protein_descr'], global_prot_hash)
|
109
|
-
end
|
110
|
-
end
|
111
|
-
sh.prots = prots
|
112
|
-
|
113
|
-
if modinfo_node = sh_n.find_first("child::modification_info")
|
114
|
-
sh.modification_info = Sequest::PepXML::SearchHit::ModificationInfo.from_pepxml_node(modinfo_node)
|
115
|
-
end
|
116
|
-
|
117
|
-
|
118
|
-
## search scores:
|
119
|
-
sh_n.find("child::search_score").each do |ss_n|
|
120
|
-
case ss_n['name']
|
121
|
-
when 'deltacnstar'
|
122
|
-
sh.deltacnstar = ss_n['value'].to_i
|
123
|
-
when 'xcorr'
|
124
|
-
sh.xcorr = ss_n['value'].to_f
|
125
|
-
when 'deltacn'
|
126
|
-
sh.deltacn = ss_n['value'].to_f
|
127
|
-
when 'spscore'
|
128
|
-
sh.spscore = ss_n['value'].to_f
|
129
|
-
when 'sprank'
|
130
|
-
sh.sprank = ss_n['value'].to_i
|
131
|
-
end
|
132
|
-
end
|
133
|
-
sh
|
134
|
-
end
|
135
|
-
sr
|
136
|
-
end
|
137
|
-
sq
|
138
|
-
end
|
139
|
-
|
140
|
-
## NOTE: this is currently just the xml node!!!! TODO: wrap everything up
|
141
|
-
#into a better search summary object (to eventually depracate the params object)
|
142
|
-
msms_run_summary_obj.search_summary = msms_run_summary_n
|
143
|
-
msms_run_summary_obj
|
144
|
-
end
|
145
|
-
|
146
|
-
end
|
147
|
-
|
148
|
-
class SpecID::Parser::ProtProph
|
149
|
-
include XMLStyleParser
|
150
|
-
Split_unique_stripped_peptides_re = /\+/
|
151
|
-
|
152
|
-
def initialize(parse_type=:spec_id, version='4')
|
153
|
-
@method = parse_type
|
154
|
-
@version = version
|
155
|
-
|
156
|
-
implemented = %w(AXML LibXML)
|
157
|
-
klass_s = XMLStyleParser.available_xml_parsers.select {|v| implemented.include?(v) }.first
|
158
|
-
case klass_s
|
159
|
-
when 'AXML'
|
160
|
-
#puts "parsing with AXML (XMLParser based)" if $VERBOSE
|
161
|
-
@get_root_node_from_file = Proc.new do |file|
|
162
|
-
AXML.parse_file(file)
|
163
|
-
end
|
164
|
-
when 'LibXML' # LibXML is buggy on some machines...
|
165
|
-
#puts "parsing with LibXML" if $VERBOSE
|
166
|
-
@get_root_node_from_file = Proc.new do |file|
|
167
|
-
doc = XML::Document.file(file)
|
168
|
-
doc.root
|
169
|
-
end
|
170
|
-
else
|
171
|
-
raise NotImplementedError, "Can only parse with #{implemented.join(', ')} right now"
|
172
|
-
end
|
173
|
-
end
|
174
|
-
|
175
|
-
# returns the spec_id object
|
176
|
-
def spec_id(file, opts={})
|
177
|
-
raise NotImplementedError, "cannot do #{@version} yet" if @version != '4'
|
178
|
-
spec_id_obj =
|
179
|
-
if x = opts[:spec_id]
|
180
|
-
x
|
181
|
-
else
|
182
|
-
Proph::ProtSummary.new
|
183
|
-
end
|
184
|
-
protein_summary_n = @get_root_node_from_file.call(file)
|
185
|
-
|
186
|
-
#protein_summary_n = scan_for_first(doc, 'protein_summary')
|
187
|
-
|
188
|
-
# protein_summary_header_n = protein_summary_n.child
|
189
|
-
# could grab some of this info if we wanted...
|
190
|
-
|
191
|
-
pep_hash = {}
|
192
|
-
prot_hash = {}
|
193
|
-
protein_groups = []
|
194
|
-
|
195
|
-
# get all the proteins from inside protein groups
|
196
|
-
protein_group_name = 'protein_group'
|
197
|
-
get_protein_summary_header = true
|
198
|
-
protein_summary_n.each do |protein_group_n|
|
199
|
-
if get_protein_summary_header
|
200
|
-
protein_summary_header_n = protein_group_n
|
201
|
-
get_protein_summary_header = false
|
202
|
-
elsif protein_group_n.name == protein_group_name
|
203
|
-
protein_groups << get_proteins(protein_group_n, pep_hash, prot_hash)
|
204
|
-
end
|
205
|
-
end
|
206
|
-
|
207
|
-
# need to finalize hash stuff
|
208
|
-
pep_hash.each do |k,pep|
|
209
|
-
new_prots = []
|
210
|
-
pep.prots.each do |prot_or_string|
|
211
|
-
if prot_or_string.is_a?(Proph::Prot)
|
212
|
-
new_prots << prot_or_string
|
213
|
-
else
|
214
|
-
prt = prot_hash[prot_or_string]
|
215
|
-
if prt.nil?
|
216
|
-
# this is an indistinguishable protein!
|
217
|
-
else
|
218
|
-
new_prots << prt
|
219
|
-
end
|
220
|
-
end
|
221
|
-
end
|
222
|
-
pep.prots = new_prots
|
223
|
-
end
|
224
|
-
|
225
|
-
spec_id_obj.peps = pep_hash.values
|
226
|
-
spec_id_obj.prots = prot_hash.values
|
227
|
-
spec_id_obj.prot_groups = protein_groups
|
228
|
-
spec_id_obj
|
229
|
-
end
|
230
|
-
|
231
|
-
# takes a Y or N and gives true/false
|
232
|
-
def booleanize(string)
|
233
|
-
case string
|
234
|
-
when 'Y'
|
235
|
-
true
|
236
|
-
when 'N'
|
237
|
-
false
|
238
|
-
else
|
239
|
-
nil
|
240
|
-
end
|
241
|
-
end
|
242
|
-
|
243
|
-
# assumes that all the rest of the nodes are protein_groups
|
244
|
-
# pep_hash is hashed on aaseq OR modified peptide amino acid sequence (if
|
245
|
-
# modified) + charge
|
246
|
-
# (as far as I can tell, all protein entries are unique!)
|
247
|
-
# returns a ProtGroup object
|
248
|
-
def get_proteins(protein_group_node, pep_hash, prot_hash)
|
249
|
-
|
250
|
-
protein_group_proteins = []
|
251
|
-
|
252
|
-
protein_group_node.each do |protein_n|
|
253
|
-
raise(Exception, "not expecting anything but protein's, got: #{protein_n.name}") if protein_n.name != 'protein'
|
254
|
-
# probability peps protein_name n_indistinguishable_proteins percent_coverage unique_stripped_peptides group_sibling_id total_number_peptides pct_spectrum_ids description
|
255
|
-
|
256
|
-
# get the description
|
257
|
-
# INITIALIZE the protein and set key
|
258
|
-
n = protein_n
|
259
|
-
protein_name = n['protein_name']
|
260
|
-
peps = []
|
261
|
-
protein = Proph::Prot.new( [protein_name, n['probability'].to_f,
|
262
|
-
n['n_indistinguishable_proteins'].to_i,
|
263
|
-
n['percent_coverage'].to_f,
|
264
|
-
n['unique_stripped_peptides'].split(Split_unique_stripped_peptides_re),
|
265
|
-
n['group_sibling_id'], n['total_number_peptides'].to_i,
|
266
|
-
n['pct_spectrum_ids'].to_f, nil,
|
267
|
-
peps ])
|
268
|
-
protein_group_proteins << protein
|
269
|
-
prot_hash[protein_name] = protein
|
270
|
-
|
271
|
-
# traverse through the peptides (and annotation)
|
272
|
-
protein_n.each do |protein_sub_n|
|
273
|
-
# create a proteins array for each peptide
|
274
|
-
proteins = [protein]
|
275
|
-
|
276
|
-
if protein_sub_n.name == 'annotation'
|
277
|
-
protein.description = protein_sub_n['protein_description']
|
278
|
-
end
|
279
|
-
if protein_sub_n.name == 'peptide'
|
280
|
-
peptide_n = protein_sub_n
|
281
|
-
# peptide_sequence charge initial_probability nsp_adjusted_probability weight is_nondegenerate_evidence n_enzymatic_termini n_sibling_peptides n_sibling_peptides_bin n_instances is_contributing_evidence calc_neutral_pep_mass modification_info prots
|
282
|
-
# get modifications, if any
|
283
|
-
|
284
|
-
n = peptide_n
|
285
|
-
peptide_sequence = n['peptide_sequence']
|
286
|
-
charge = n['charge'].to_i
|
287
|
-
|
288
|
-
# GET list of all proteins and modifications
|
289
|
-
|
290
|
-
mod_info = nil
|
291
|
-
peptide_hash_string = peptide_sequence
|
292
|
-
if peptide_n.child?
|
293
|
-
peptide_n.each do |pep_sub_n|
|
294
|
-
case pep_sub_n.name
|
295
|
-
when 'peptide_parent_protein'
|
296
|
-
# NOTE! the proteins list will have strings until the assoc.
|
297
|
-
# prot is found!
|
298
|
-
proteins << pep_sub_n['protein_name']
|
299
|
-
when 'modification_info'
|
300
|
-
masses = pep_sub_n.map do |mod_aa_mass_n|
|
301
|
-
Sequest::PepXML::SearchHit::ModificationInfo::ModAminoacidMass.new([mod_aa_mass_n['position'].to_i, mod_aa_mass_n['mass'].to_f])
|
302
|
-
end
|
303
|
-
peptide_hash_string = pep_sub_n['modified_peptide']
|
304
|
-
mod_info = Sequest::PepXML::SearchHit::ModificationInfo.new([peptide_hash_string, masses])
|
305
|
-
end
|
306
|
-
end
|
307
|
-
end
|
308
|
-
|
309
|
-
key = [peptide_hash_string, charge]
|
310
|
-
peptide =
|
311
|
-
if pep_hash.key? key
|
312
|
-
pep_hash[key]
|
313
|
-
else
|
314
|
-
pep = Proph::Prot::Pep.new([peptide_sequence, charge,
|
315
|
-
n['initial_probability'].to_f, n['nsp_adjusted_probability'].to_f,
|
316
|
-
n['weight'].to_f, booleanize(n['is_nondegenerate_evidence']),
|
317
|
-
n['n_enzymatic_termini'].to_i, n['n_sibling_peptides'].to_f,
|
318
|
-
n['n_sibling_peptides'].to_i, n['n_instances'].to_i,
|
319
|
-
booleanize(n['is_contributing_evidence']),
|
320
|
-
n['calc_neutral_pep_mass'].to_f, mod_info, proteins] )
|
321
|
-
pep_hash[key] = pep
|
322
|
-
pep
|
323
|
-
end
|
324
|
-
peps << peptide
|
325
|
-
end
|
326
|
-
end # end protein children
|
327
|
-
end
|
328
|
-
Proph::ProtGroup.new(:prots => protein_group_proteins, :group_number => protein_group_node['group_number'].to_i, :probability => protein_group_node['probability'].to_f)
|
329
|
-
end
|
330
|
-
|
331
|
-
def parse(file, opts)
|
332
|
-
send(@method, file, opts)
|
333
|
-
end
|
334
|
-
|
335
|
-
end
|