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
@@ -1,109 +1,77 @@
|
|
1
|
-
|
2
|
-
|
3
|
-
|
4
|
-
module
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
|
9
|
-
#
|
10
|
-
|
11
|
-
|
12
|
-
|
13
|
-
|
14
|
-
|
15
|
-
# if .mzXML
|
16
|
-
#
|
17
|
-
# if
|
18
|
-
#
|
19
|
-
|
20
|
-
|
21
|
-
|
22
|
-
file
|
23
|
-
|
24
|
-
|
25
|
-
|
26
|
-
|
27
|
-
|
28
|
-
|
29
|
-
|
30
|
-
|
31
|
-
|
32
|
-
|
33
|
-
|
34
|
-
cmd = "#{converter} #{basename}
|
35
|
-
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
|
40
|
-
|
41
|
-
|
42
|
-
|
43
|
-
|
44
|
-
|
45
|
-
|
46
|
-
|
47
|
-
|
48
|
-
|
49
|
-
|
50
|
-
return file_to_mzxml(file + '.
|
51
|
-
elsif File.exist?( file + '.
|
52
|
-
return file_to_mzxml(file + '.
|
53
|
-
|
54
|
-
return
|
55
|
-
|
56
|
-
|
57
|
-
|
58
|
-
|
59
|
-
|
60
|
-
|
61
|
-
|
62
|
-
|
63
|
-
|
64
|
-
|
65
|
-
|
66
|
-
|
67
|
-
|
68
|
-
|
69
|
-
|
70
|
-
|
71
|
-
|
72
|
-
|
73
|
-
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
|
78
|
-
ndata
|
79
|
-
end
|
80
|
-
|
81
|
-
# takes a base64 peaks string and returns an array of alternating m/z and
|
82
|
-
# intensity mzXML as network ordered
|
83
|
-
def base64_peaks_to_array(string, precision=32)
|
84
|
-
b64d = Base64.decode64(string)
|
85
|
-
if precision == 32
|
86
|
-
unpack_code = "g*"
|
87
|
-
elsif precision == 64
|
88
|
-
unpack_code = "G*"
|
89
|
-
end
|
90
|
-
b64d.unpack(unpack_code)
|
91
|
-
end
|
92
|
-
|
93
|
-
# Searchs each path element and returns the first one it finds
|
94
|
-
# returns nil if none found
|
95
|
-
def self.find_mzxml_converter
|
96
|
-
ENV['PATH'].split(/[:;]/).each do |path|
|
97
|
-
Dir.chdir(path) do
|
98
|
-
Potential_mzxml_converters.each do |pc|
|
99
|
-
if File.exist? pc
|
100
|
-
return File.join(path, pc)
|
101
|
-
end
|
102
|
-
end
|
103
|
-
end
|
104
|
-
end
|
105
|
-
nil
|
106
|
-
end
|
107
|
-
|
108
|
-
|
109
|
-
end
|
1
|
+
|
2
|
+
module MS ; end
|
3
|
+
module MS::Converter ; end
|
4
|
+
module MS::Converter::MzXML
|
5
|
+
Potential_mzxml_converters = %w(readw.exe readw t2x)
|
6
|
+
|
7
|
+
# takes PT2.7500000S and returns it as 2.700000 (no PT or S)
|
8
|
+
#def strip_time(time)
|
9
|
+
# return time[2...-1]
|
10
|
+
#end
|
11
|
+
|
12
|
+
# first, converts backslash to forward slash in filename.
|
13
|
+
# if .mzXML returns the filename
|
14
|
+
# if .raw or .RAW converts the file to .mZXML and returns mzXML filename
|
15
|
+
# if no recognized extension, looks for .mzXML file, then .RAW file (and
|
16
|
+
# converts)
|
17
|
+
# aborts if file was not able to be converted
|
18
|
+
# returns nil if a file that can be converted or used was not found
|
19
|
+
def self.file_to_mzxml(file)
|
20
|
+
file.gsub!("\\",'/')
|
21
|
+
old_file = file.dup
|
22
|
+
if file =~ /\.mzXML$/
|
23
|
+
return file
|
24
|
+
elsif file =~ /\.RAW$/i
|
25
|
+
old_file = file.dup
|
26
|
+
## t2x outputs in cwd (so go to the directory of the file!)
|
27
|
+
dir = File.dirname(file)
|
28
|
+
basename = File.basename(file)
|
29
|
+
converter = MS::MzXML.find_mzxml_converter
|
30
|
+
Dir.chdir(dir) do
|
31
|
+
if converter =~ /readw/
|
32
|
+
cmd = "#{converter} #{basename} c #{basename.sub(/\.RAW$/i, '.mzXML')}"
|
33
|
+
else
|
34
|
+
cmd = "#{converter} #{basename}"
|
35
|
+
end
|
36
|
+
#puts cmd
|
37
|
+
#puts `#{cmd}`
|
38
|
+
reply = `#{cmd}`
|
39
|
+
puts reply if $VERBOSE
|
40
|
+
end
|
41
|
+
file.sub!(/\.RAW$/i, '.mzXML')
|
42
|
+
unless File.exist? file
|
43
|
+
abort "Couldn't convert #{old_file} to #{file}"
|
44
|
+
end
|
45
|
+
return file
|
46
|
+
else
|
47
|
+
if File.exist?( file + '.mzXML' )
|
48
|
+
return file_to_mzxml(file + '.mzXML')
|
49
|
+
elsif File.exist?( file + '.RAW' )
|
50
|
+
return file_to_mzxml(file + '.RAW')
|
51
|
+
elsif File.exist?( file + '.raw' )
|
52
|
+
return file_to_mzxml(file + '.raw')
|
53
|
+
else
|
54
|
+
return nil
|
55
|
+
end
|
56
|
+
end
|
57
|
+
|
58
|
+
end
|
59
|
+
|
60
|
+
|
61
|
+
# Searchs each path element and returns the first one it finds
|
62
|
+
# returns nil if none found
|
63
|
+
def self.find_mzxml_converter
|
64
|
+
ENV['PATH'].split(/[:;]/).each do |path|
|
65
|
+
Dir.chdir(path) do
|
66
|
+
Potential_mzxml_converters.each do |pc|
|
67
|
+
if File.exist? pc
|
68
|
+
return File.join(path, pc)
|
69
|
+
end
|
70
|
+
end
|
71
|
+
end
|
72
|
+
end
|
73
|
+
nil
|
74
|
+
end
|
75
|
+
|
76
|
+
end
|
77
|
+
|
@@ -0,0 +1,171 @@
|
|
1
|
+
require 'array_class'
|
2
|
+
|
3
|
+
# This is modeled after the Thermo gradient
|
4
|
+
class GradientProgram
|
5
|
+
attr_accessor :time_points
|
6
|
+
attr_accessor :pump_type
|
7
|
+
# array of solvents parallel to TimePoint percentages array
|
8
|
+
attr_accessor :solvents
|
9
|
+
|
10
|
+
def initialize(pump_type, time_points=[], solvents=[])
|
11
|
+
@pump_type = pump_type
|
12
|
+
@time_points = time_points
|
13
|
+
@solvents = solvents
|
14
|
+
end
|
15
|
+
|
16
|
+
def ==(other)
|
17
|
+
self.class == other.class and @pump_type==other.pump_type and @solvents == other.solvents and @time_points == other.time_points
|
18
|
+
end
|
19
|
+
|
20
|
+
# gets the first gradient program encountered in the filehandle
|
21
|
+
def self.get_gradient_program(fh)
|
22
|
+
thermo_newline = "\n\000"
|
23
|
+
#gtable = "g\000r\000a\000d\000i\000e\000n\000t\000 \000t\000a\000b\000l\000e"
|
24
|
+
gradient = "[Gg]\000r\000a\000d\000i\000e\000n\000t\000 \000"
|
25
|
+
|
26
|
+
|
27
|
+
xcal_2x = gradient + "t\000a\000b\000l\000e\000:\000"
|
28
|
+
xcal_1x = gradient + "P\000r\000o\000g\000r\000a\000m\000:\000"
|
29
|
+
xcal_2x_regexp = Regexp.new(xcal_2x)
|
30
|
+
xcal_1x_regexp = Regexp.new(xcal_1x)
|
31
|
+
find_gtable_regexp = Regexp.new(gradient)
|
32
|
+
|
33
|
+
found_one_2x = false
|
34
|
+
found_one_1x = false
|
35
|
+
pump_type = ''
|
36
|
+
fh.each(thermo_newline) do |line|
|
37
|
+
# first identify the line, then
|
38
|
+
if line =~ find_gtable_regexp
|
39
|
+
if line =~ xcal_1x_regexp
|
40
|
+
pump_type = '' ## have to look way back in file for this
|
41
|
+
found_one_1x = true
|
42
|
+
break
|
43
|
+
elsif line =~ xcal_2x_regexp
|
44
|
+
grab_pump_type_regexp = /(.*) .g.r.a.d.i.e.n.t. .t.a.b.l.e/
|
45
|
+
pump_type = read_thermo_string(grab_pump_type_regexp.match(line).captures[0])
|
46
|
+
found_one_2x = true
|
47
|
+
break
|
48
|
+
end
|
49
|
+
end
|
50
|
+
end
|
51
|
+
if found_one_2x
|
52
|
+
fh.gets(thermo_newline) # nothing
|
53
|
+
table_headers = fh.gets(thermo_newline)
|
54
|
+
time_points = []
|
55
|
+
while (line = fh.gets(thermo_newline)) != thermo_newline
|
56
|
+
# 0 0.00 95.0 5.0 0.0 0.0 38.0 x
|
57
|
+
# 1 1.00 90.0 10.0 0.0 0.0 38.0 o
|
58
|
+
|
59
|
+
pieces = table_row_to_pieces(line, '2.0')
|
60
|
+
time_points << TimePoint.new(pieces[1].to_f, pieces[6].to_f, pieces[2,4].map{|x| x.to_f })
|
61
|
+
end
|
62
|
+
GradientProgram.new(pump_type, time_points, %w(A B C D))
|
63
|
+
elsif found_one_1x
|
64
|
+
fh.gets(thermo_newline) # nothing
|
65
|
+
table_headers = fh.gets(thermo_newline)
|
66
|
+
time_points = []
|
67
|
+
null_char_regexp = Regexp.new("^\000\000\000\000")
|
68
|
+
while (line = fh.gets(thermo_newline)) !~ null_char_regexp
|
69
|
+
pieces = table_row_to_pieces(line, '1.0')
|
70
|
+
time_points << TimePoint.new(pieces[1].to_f, pieces[6].to_f, pieces[2,4].map{|x| x.to_f })
|
71
|
+
end
|
72
|
+
GradientProgram.new(pump_type, time_points, %w(A B C D))
|
73
|
+
else
|
74
|
+
nil
|
75
|
+
end
|
76
|
+
end
|
77
|
+
|
78
|
+
# returns the elements of a gradient table row properly cast
|
79
|
+
# NOTE: Xcal 2.X starts index with 0, 1.X starts with 1
|
80
|
+
# (and this is how it will be returned!)
|
81
|
+
# NOTE: Xcal 1.X will be shorter by one (doesn't have the o/x string!)
|
82
|
+
# [(Int) index, time (Float), %A (Float), %B (Float), %C (Float), %D (Float),
|
83
|
+
# FlowRate (Float), o/x (String)]
|
84
|
+
def self.table_row_to_pieces(line,xcal_version='2.0')
|
85
|
+
string = read_thermo_string(line)
|
86
|
+
if xcal_version >= '2.0'
|
87
|
+
# at first, I thought you could just split on spaces, but the table is
|
88
|
+
# designed to have a certain number of chars per column padded with
|
89
|
+
# spaces. This is hte way to do it.
|
90
|
+
index = string[0,4].to_i
|
91
|
+
(tm, a, b, c, d) = (0...5).to_a.map do |x|
|
92
|
+
string[(x*6)+4,6].rstrip.to_f
|
93
|
+
end
|
94
|
+
fr = string[34,7].rstrip.to_f
|
95
|
+
ox = string[41,4].rstrip
|
96
|
+
[index, tm, a, b, c, d, fr, ox]
|
97
|
+
else
|
98
|
+
index = string[0,5].lstrip.to_i # correct
|
99
|
+
tm = string[5,13].lstrip.to_f # correct
|
100
|
+
#puts "**" + string[18,16] + "**"
|
101
|
+
fr = string[18,16].lstrip.to_f
|
102
|
+
(a,b,c,d) = (0..3).to_a.map do |x|
|
103
|
+
string[(x*8)+34, 8].lstrip.to_f # correct
|
104
|
+
end
|
105
|
+
[index, tm, a, b, c, d, fr]
|
106
|
+
end
|
107
|
+
end
|
108
|
+
|
109
|
+
# takes a filehandle
|
110
|
+
# returns an array of gradient programs from a thermo filehandle.
|
111
|
+
# Acceptable file types include a .meth file and a .raw file
|
112
|
+
def self.all_from_handle(fh)
|
113
|
+
# 0005340: 3000 2e00 3000 3000 0a00 0a00 5300 6100 0...0.0.....S.a.
|
114
|
+
# 0005350: 6d00 7000 6c00 6500 2000 5000 7500 6d00 m.p.l.e. .P.u.m.
|
115
|
+
# 0005360: 7000 2000 6700 7200 6100 6400 6900 6500 p. .g.r.a.d.i.e.
|
116
|
+
# 0005370: 6e00 7400 2000 7400 6100 6200 6c00 6500 n.t. .t.a.b.l.e.
|
117
|
+
# 0005380: 3a00 0a00 0a00 4e00 6f00 2e00 2000 5400 :.....N.o... .T.
|
118
|
+
# 0005390: 6900 6d00 6500 2000 2000 4100 2500 2000 i.m.e. . .A.%. .
|
119
|
+
# 00053a0: 2000 2000 2000 4200 2500 2000 2000 2000 . . .B.%. . . .
|
120
|
+
# 00053b0: 2000 4300 2500 2000 2000 2000 2000 4400 .C.%. . . . .D.
|
121
|
+
# 00053c0: 2500 2000 2000 2000 2000 b500 6c00 2f00 %. . . . ...l./.
|
122
|
+
# 00053d0: 6d00 6900 6e00 2000 0a00 3000 2000 2000 m.i.n. ...0. . .
|
123
|
+
# 00053e0: 2000 3000 2e00 3000 3000 2000 2000 3000 .0...0.0. . .0.
|
124
|
+
# 00053f0: 2e00 3000 2000 2000 2000 3000 2e00 3000 ..0. . . .0...0.
|
125
|
+
# 0005400: 2000 2000 2000 3100 3000 3000 2e00 3000 . . .1.0.0...0.
|
126
|
+
programs = []
|
127
|
+
while (gp = get_gradient_program(fh))
|
128
|
+
programs << gp
|
129
|
+
end
|
130
|
+
programs
|
131
|
+
end
|
132
|
+
|
133
|
+
def self.read_thermo_string(string)
|
134
|
+
chars = []
|
135
|
+
(0...string.size).step(2) do |i|
|
136
|
+
chars << string[i,1]
|
137
|
+
end
|
138
|
+
chars.join
|
139
|
+
end
|
140
|
+
|
141
|
+
def self.read_thermo_string_as_hex(string)
|
142
|
+
chars = []
|
143
|
+
(0...string.size).step(4) do |i|
|
144
|
+
chars << string[i,2]
|
145
|
+
end
|
146
|
+
[chars.join].pack('H*')
|
147
|
+
end
|
148
|
+
|
149
|
+
|
150
|
+
end
|
151
|
+
|
152
|
+
class GradientProgram::TimePoint
|
153
|
+
# time in minutes
|
154
|
+
attr_accessor :time
|
155
|
+
# flow_rate in ul/min
|
156
|
+
attr_accessor :flow_rate
|
157
|
+
# percentages
|
158
|
+
attr_accessor :percentages
|
159
|
+
|
160
|
+
def initialize(time=nil, flow_rate=nil, percentages=[])
|
161
|
+
@time = time
|
162
|
+
@flow_rate = flow_rate
|
163
|
+
@percentages = percentages
|
164
|
+
end
|
165
|
+
|
166
|
+
def ==(other)
|
167
|
+
self.class == other.class and @time==other.time and @flow_rate == other.flow_rate and @percentages == other.percentages
|
168
|
+
end
|
169
|
+
end
|
170
|
+
|
171
|
+
|
data/lib/ms/msrun.rb
ADDED
@@ -0,0 +1,209 @@
|
|
1
|
+
|
2
|
+
require 'ms/scan'
|
3
|
+
require 'ms/parser'
|
4
|
+
require 'ms/msrun_index'
|
5
|
+
require 'ms/converter/mzxml'
|
6
|
+
|
7
|
+
#require 'ms/parser/mzxml'
|
8
|
+
#require 'ms/parser/mzdata'
|
9
|
+
|
10
|
+
module MS; end
|
11
|
+
class MS::MSRun
|
12
|
+
|
13
|
+
attr_accessor :start_time, :end_time
|
14
|
+
attr_accessor :scans
|
15
|
+
# (just for reference) the type of file this is (as symbol)
|
16
|
+
attr_accessor :filetype
|
17
|
+
# (just for reference) the version string of this type of file
|
18
|
+
attr_accessor :version
|
19
|
+
# the total number of scans
|
20
|
+
attr_writer :scan_count
|
21
|
+
|
22
|
+
# should be able to read basic information from a variety of files
|
23
|
+
# this will be written in regexp's because REXML is way too slow, xmlparser
|
24
|
+
# is not guaranteed to be on every system, xmlib is not on win32.
|
25
|
+
# spectra is false, then spectra are not parsed out and included
|
26
|
+
# OPTIONS:
|
27
|
+
# :spectra => *true|false # whether to parse out spectra
|
28
|
+
# [note: precursor intensities not guaranteed to exist unless :spectra == true]
|
29
|
+
def initialize(file=nil, opts={})
|
30
|
+
myopts = opts.dup ; myopts[:msrun] = self
|
31
|
+
if file
|
32
|
+
filetype_and_version = MS::Parser.filetype_and_version(file)
|
33
|
+
MS::Parser.new(filetype_and_version, :msrun).parse(file, myopts)
|
34
|
+
(@filetype, @version) = filetype_and_version
|
35
|
+
end
|
36
|
+
end
|
37
|
+
|
38
|
+
# returns an array, whose indices provide the number of scans in each index level the ms_levels, [0] = all the scans, [1] = mslevel 1, [2] = mslevel 2,
|
39
|
+
# ...
|
40
|
+
def scan_counts
|
41
|
+
ar = []
|
42
|
+
ar[0] = 0
|
43
|
+
scans.each do |sc|
|
44
|
+
level = sc.ms_level
|
45
|
+
unless ar[level]
|
46
|
+
ar[level] = 0
|
47
|
+
end
|
48
|
+
ar[level] += 1
|
49
|
+
ar[0] += 1
|
50
|
+
end
|
51
|
+
ar
|
52
|
+
end
|
53
|
+
|
54
|
+
def scan_count(mslevel=0)
|
55
|
+
if mslevel == 0
|
56
|
+
@scan_count
|
57
|
+
else
|
58
|
+
num = 0
|
59
|
+
scans.each do |sc|
|
60
|
+
if sc.ms_level == mslevel
|
61
|
+
num += 1
|
62
|
+
end
|
63
|
+
end
|
64
|
+
num
|
65
|
+
end
|
66
|
+
end
|
67
|
+
|
68
|
+
# for level 1, finds first scan and asks if it has start_mz/end_mz
|
69
|
+
# attributes. for other levels, asks for start_mz/ end_mz and takes the
|
70
|
+
# min/max. If start_mz and end_mz are not found, goes through every scan
|
71
|
+
# finding the max/min first and last m/z. returns [start_mz (rounded down to
|
72
|
+
# nearest int), end_mz (rounded up to nearest int)]
|
73
|
+
def start_and_end_mz(mslevel=1)
|
74
|
+
if mslevel == 1
|
75
|
+
# special case for mslevel 1 (where we expect scans to be same length)
|
76
|
+
scans.each do |sc|
|
77
|
+
if sc.ms_level == mslevel
|
78
|
+
if sc.start_mz && sc.end_mz
|
79
|
+
return [sc.start_mz, sc.end_mz]
|
80
|
+
end
|
81
|
+
break
|
82
|
+
end
|
83
|
+
end
|
84
|
+
end
|
85
|
+
hi_mz = nil
|
86
|
+
lo_mz = nil
|
87
|
+
# see if we have start_mz and end_mz for the level we want
|
88
|
+
# set the initial hi_mz and lo_mz in any case
|
89
|
+
have_start_end_mz = false
|
90
|
+
scans.each do |sc|
|
91
|
+
if sc.ms_level == mslevel
|
92
|
+
if sc.start_mz && sc.end_mz
|
93
|
+
lo_mz = sc.start_mz
|
94
|
+
hi_mz = sc.end_mz
|
95
|
+
else
|
96
|
+
mz = sc.spectrum.mz
|
97
|
+
hi_mz = mz.last
|
98
|
+
lo_mz = mz.first
|
99
|
+
end
|
100
|
+
break
|
101
|
+
end
|
102
|
+
end
|
103
|
+
if have_start_end_mz
|
104
|
+
scans.each do |sc|
|
105
|
+
if sc.ms_level == mslevel
|
106
|
+
if sc.start_mz < lo_mz
|
107
|
+
lo_mz = sc.start_mz
|
108
|
+
end
|
109
|
+
if sc.end_mz > hi_mz
|
110
|
+
hi_mz = sc.end_mz
|
111
|
+
end
|
112
|
+
end
|
113
|
+
end
|
114
|
+
else
|
115
|
+
# didn't have the attributes (find by brute force)
|
116
|
+
scans.each do |sc|
|
117
|
+
if sc.ms_level == mslevel
|
118
|
+
mz = sc.spectrum.mz
|
119
|
+
if mz.last > hi_mz
|
120
|
+
hi_mz = mz.last
|
121
|
+
end
|
122
|
+
if mz.last < lo_mz
|
123
|
+
lo_mz = mz.last
|
124
|
+
end
|
125
|
+
end
|
126
|
+
end
|
127
|
+
end
|
128
|
+
[lo_mz.floor, hi_mz.ceil]
|
129
|
+
end
|
130
|
+
|
131
|
+
# returns an array of precursor mz by scan number
|
132
|
+
# returns only the m/z of the FIRST precursor if multiple
|
133
|
+
def precursor_mz_by_scan_num
|
134
|
+
ar = Array.new(@scans.size + 1)
|
135
|
+
@scans.each do |scan|
|
136
|
+
if prec = scan.precursors.first
|
137
|
+
ar[scan.num] = prec.mz
|
138
|
+
else
|
139
|
+
ar[scan.num] = nil
|
140
|
+
end
|
141
|
+
end
|
142
|
+
ar
|
143
|
+
end
|
144
|
+
|
145
|
+
# returns an array of times and parallel array of spectra objects.
|
146
|
+
# ms_level = 0 then all spectra and times
|
147
|
+
# ms_level = 1 then all spectra of ms_level 1
|
148
|
+
def times_and_spectra(ms_level=0)
|
149
|
+
spectra = []
|
150
|
+
if ms_level == 0
|
151
|
+
times = @scans.map do |scan|
|
152
|
+
spectra << scan.spectrum
|
153
|
+
scan.time
|
154
|
+
end
|
155
|
+
[times, spectra]
|
156
|
+
else # choose a particular ms_level
|
157
|
+
times = []
|
158
|
+
@scans.each do |scan|
|
159
|
+
if ms_level == scan.ms_level
|
160
|
+
spectra << scan.spectrum
|
161
|
+
times << scan.time
|
162
|
+
end
|
163
|
+
end
|
164
|
+
[times, spectra]
|
165
|
+
end
|
166
|
+
end
|
167
|
+
|
168
|
+
# same as the instance method (creates an object without spectrum and calls
|
169
|
+
# instance method of the same name)
|
170
|
+
def self.precursor_mz_by_scan_num(file)
|
171
|
+
self.new(file, :spectra => false).precursor_mz_by_scan_num
|
172
|
+
end
|
173
|
+
|
174
|
+
# only adds the parent if one is not already present!
|
175
|
+
def self.add_parent_scan(scans, add_intensities=false)
|
176
|
+
#start = Time.now
|
177
|
+
prev_scan = nil
|
178
|
+
parent_stack = [nil]
|
179
|
+
## we want to set the level to be the first mslevel we come to
|
180
|
+
prev_level = scans.first.ms_level
|
181
|
+
scans.each do |scan|
|
182
|
+
#next unless scan ## the first one is nil, (others?)
|
183
|
+
level = scan.ms_level
|
184
|
+
if prev_level < level
|
185
|
+
parent_stack.unshift prev_scan
|
186
|
+
end
|
187
|
+
if prev_level > level
|
188
|
+
(prev_level - level).times do parent_stack.shift end
|
189
|
+
end
|
190
|
+
if scan.ms_level > 1
|
191
|
+
scan.precursors.each do |precursor|
|
192
|
+
#precursor.parent = parent_stack.first # that's the next line's
|
193
|
+
precursor[2] = parent_stack.first unless precursor[2]
|
194
|
+
#precursor.intensity
|
195
|
+
if add_intensities
|
196
|
+
precursor[1] = precursor[2].spectrum.intensity_at_mz(precursor[0])
|
197
|
+
end
|
198
|
+
end
|
199
|
+
end
|
200
|
+
prev_level = level
|
201
|
+
prev_scan = scan
|
202
|
+
end
|
203
|
+
#puts "TOOK #{Time.now - start} secs"
|
204
|
+
end
|
205
|
+
|
206
|
+
end
|
207
|
+
|
208
|
+
|
209
|
+
|
@@ -1,11 +1,7 @@
|
|
1
|
+
require 'ms/scan'
|
2
|
+
require 'ms/parser'
|
1
3
|
|
2
|
-
|
3
|
-
require 'spec/mzxml/parser'
|
4
|
-
require 'spec/mzdata/parser'
|
5
|
-
|
6
|
-
module Spec; end
|
7
|
-
|
8
|
-
class Spec::MSRunIndex
|
4
|
+
class MS::MSRunIndex
|
9
5
|
# basename_noext is the base name of the file (with NO extensions)
|
10
6
|
attr_accessor :scans_by_num
|
11
7
|
attr_reader :basename_noext
|
@@ -32,7 +28,7 @@ class Spec::MSRunIndex
|
|
32
28
|
# index_file has one row for each scan:
|
33
29
|
# ms_level scan_num time [prec_mz prec_inten]
|
34
30
|
# also consider getting this data directly from the mzXML file
|
35
|
-
# via the
|
31
|
+
# via the MS::MzXML::Parser.get_msrun_index command
|
36
32
|
def set_from_index_file(index_file)
|
37
33
|
self.basename_noext = index_file
|
38
34
|
@scans_by_num = []
|
@@ -41,7 +37,7 @@ class Spec::MSRunIndex
|
|
41
37
|
next if line !~ /\d/ || line =~ /^#/
|
42
38
|
line.chomp!
|
43
39
|
arr = line.split(" ")
|
44
|
-
scan =
|
40
|
+
scan = MS::Scan.new(arr[1].to_i, arr[0].to_i, arr[2].to_f)
|
45
41
|
if scan.ms_level > 1
|
46
42
|
scan.prec_mz = arr[3].to_f
|
47
43
|
scan.prec_inten = arr[4].to_f
|
@@ -49,7 +45,7 @@ class Spec::MSRunIndex
|
|
49
45
|
@scans_by_num[scan.num] = scan
|
50
46
|
end
|
51
47
|
end
|
52
|
-
|
48
|
+
MS::Scan.add_parent_scan(@scans_by_num)
|
53
49
|
end
|
54
50
|
|
55
51
|
# Takes a .mzXML file or .timeIndex file (currently)
|
@@ -73,7 +69,7 @@ class Spec::MSRunIndex
|
|
73
69
|
# returns a new
|
74
70
|
def set_from_mzxml(file)
|
75
71
|
self.basename_noext = file
|
76
|
-
@scans_by_num =
|
72
|
+
@scans_by_num = MS::Parser.new(file, :scans_by_num).parse(file)
|
77
73
|
end
|
78
74
|
|
79
75
|
# writes the index to filename
|
@@ -109,33 +105,4 @@ class Spec::MSRunIndex
|
|
109
105
|
end
|
110
106
|
|
111
107
|
|
112
|
-
class Spec::MSRun
|
113
|
-
|
114
|
-
# scan_count is an array [0] is all the scans, [1] is mslevel 1, [2] is mslevel 2, etc
|
115
|
-
attr_accessor :scan_count, :start_time, :end_time, :start_mz, :end_mz
|
116
|
-
|
117
|
-
# returns an array indexed by scan number where the precursor mz is recorded
|
118
|
-
# for each fragment (ms2) ion
|
119
|
-
# The precursor mz will be a String!
|
120
|
-
def self.precursor_mz_by_scan(file)
|
121
|
-
extname = File.extname(file)
|
122
|
-
case extname
|
123
|
-
when '.mzXML' || '.timeIndex'
|
124
|
-
klass = Spec::MzXML::Parser
|
125
|
-
when '.xml'
|
126
|
-
klass = Spec::MzData::Parser
|
127
|
-
when '' # they want us to figure out the right extension
|
128
|
-
if File.exist? file + '.xml'
|
129
|
-
klass = Spec::MzData::Parser
|
130
|
-
else
|
131
|
-
# This will cover .timeIndex, .mzXML and .RAW
|
132
|
-
klass = Spec::MzXML::Parser
|
133
|
-
end
|
134
|
-
else
|
135
|
-
abort "files of extension #{extname} are not currently supported"
|
136
|
-
end
|
137
|
-
klass.new.precursor_mz_by_scan(file)
|
138
|
-
end
|
139
|
-
|
140
|
-
end
|
141
108
|
|