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/gi.rb
DELETED
@@ -1,124 +0,0 @@
|
|
1
|
-
require 'open-uri'
|
2
|
-
require 'rexml/document'
|
3
|
-
require 'rexml/streamlistener'
|
4
|
-
|
5
|
-
$ANNOTS = []
|
6
|
-
|
7
|
-
class GIListener
|
8
|
-
include REXML
|
9
|
-
include StreamListener
|
10
|
-
|
11
|
-
attr_accessor :annotations
|
12
|
-
|
13
|
-
def initialize
|
14
|
-
@get_title = false
|
15
|
-
@annotations = []
|
16
|
-
end
|
17
|
-
|
18
|
-
def tag_start(name, attributes)
|
19
|
-
#puts "NAME" + name
|
20
|
-
#p attributes
|
21
|
-
if name == "Item" && attributes["Name"] == "Title"
|
22
|
-
@get_title = true
|
23
|
-
end
|
24
|
-
end
|
25
|
-
|
26
|
-
def text(text)
|
27
|
-
#puts "TEXT: " + text + @get_title.to_s
|
28
|
-
if @get_title
|
29
|
-
#puts "GETTING TITLE!"
|
30
|
-
@annotations.push text.chomp
|
31
|
-
@get_title = false
|
32
|
-
end
|
33
|
-
end
|
34
|
-
|
35
|
-
end
|
36
|
-
|
37
|
-
|
38
|
-
|
39
|
-
class GI
|
40
|
-
BATCH_SIZE = 500
|
41
|
-
# takes an array of gi numbers and returns an array of annotation
|
42
|
-
# This allows use of the batch search mode on NCBI
|
43
|
-
# returns nil if no internet connection
|
44
|
-
def self.gi2annot(list_of_gi_numbers)
|
45
|
-
annots = []
|
46
|
-
loop do
|
47
|
-
batch = list_of_gi_numbers.slice!(0..BATCH_SIZE)
|
48
|
-
if batch.size == 0 then break end
|
49
|
-
string = batch.join(",")
|
50
|
-
url = "http://eutils.ncbi.nlm.nih.gov/entrez/eutils/esummary.fcgi?db=protein&retmode=xml&id=#{string}"
|
51
|
-
#puts url
|
52
|
-
begin
|
53
|
-
open(url) do |handle|
|
54
|
-
if handle.is_a? StringIO
|
55
|
-
io_input = handle
|
56
|
-
else
|
57
|
-
io_input = handle.read
|
58
|
-
end
|
59
|
-
annots.push( *(parse_etool_output(io_input)) )
|
60
|
-
end
|
61
|
-
rescue SocketError
|
62
|
-
return nil
|
63
|
-
end
|
64
|
-
end
|
65
|
-
annots
|
66
|
-
end
|
67
|
-
|
68
|
-
protected
|
69
|
-
# Returns a list of Annotation strings
|
70
|
-
def self.parse_etool_output(handle)
|
71
|
-
listener = GIListener.new
|
72
|
-
parser = REXML::Parsers::StreamParser.new(handle, listener)
|
73
|
-
parser.parse
|
74
|
-
listener.annotations
|
75
|
-
end
|
76
|
-
|
77
|
-
|
78
|
-
end
|
79
|
-
|
80
|
-
|
81
|
-
|
82
|
-
=begin
|
83
|
-
|
84
|
-
<?xml version="1.0" encoding="ISO-8859-1"?>
|
85
|
-
<!DOCTYPE eSummaryResult PUBLIC "-//NLM//DTD eSummaryResult, 11 May 2002//EN" "http://www.ncbi.nlm.nih.gov/entrez/query/DTD/eSummary_041029.dtd">
|
86
|
-
<eSummaryResult>
|
87
|
-
|
88
|
-
<DocSum>
|
89
|
-
<Id>24115498</Id>
|
90
|
-
<Item Name="Caption" Type="String">NP_710008</Item>
|
91
|
-
<Item Name="Title" Type="String">chaperonin GroEL [Shigella flexneri 2a str. 301]</Item>
|
92
|
-
<Item Name="Extra" Type="String">gi|24115498|ref|NP_710008.1|[24115498]</Item>
|
93
|
-
<Item Name="Gi" Type="Integer">24115498</Item>
|
94
|
-
<Item Name="CreateDate" Type="String">2002/10/16</Item>
|
95
|
-
|
96
|
-
<Item Name="UpdateDate" Type="String">2006/04/03</Item>
|
97
|
-
<Item Name="Flags" Type="Integer">512</Item>
|
98
|
-
<Item Name="TaxId" Type="Integer">198214</Item>
|
99
|
-
<Item Name="Status" Type="String">live</Item>
|
100
|
-
<Item Name="ReplacedBy" Type="String"></Item>
|
101
|
-
<Item Name="Comment" Type="String"><![CDATA[ ]]></Item>
|
102
|
-
</DocSum>
|
103
|
-
|
104
|
-
|
105
|
-
<DocSum>
|
106
|
-
<Id>434011</Id>
|
107
|
-
<Item Name="Caption" Type="String">CAA24741</Item>
|
108
|
-
|
109
|
-
<Item Name="Title" Type="String">unnamed protein product [Escherichia coli]</Item>
|
110
|
-
<Item Name="Extra" Type="String">gi|434011|emb|CAA24741.1|[434011]</Item>
|
111
|
-
<Item Name="Gi" Type="Integer">434011</Item>
|
112
|
-
<Item Name="CreateDate" Type="String">1983/12/06</Item>
|
113
|
-
<Item Name="UpdateDate" Type="String">2005/04/18</Item>
|
114
|
-
<Item Name="Flags" Type="Integer">0</Item>
|
115
|
-
<Item Name="TaxId" Type="Integer">562</Item>
|
116
|
-
<Item Name="Status" Type="String">live</Item>
|
117
|
-
<Item Name="ReplacedBy" Type="String"></Item>
|
118
|
-
|
119
|
-
<Item Name="Comment" Type="String"><![CDATA[ ]]></Item>
|
120
|
-
</DocSum>
|
121
|
-
|
122
|
-
</eSummaryResult>
|
123
|
-
|
124
|
-
=end
|
data/lib/group_by.rb
DELETED
data/lib/index_by.rb
DELETED
data/lib/merge_deep.rb
DELETED
@@ -1,21 +0,0 @@
|
|
1
|
-
|
2
|
-
class Hash
|
3
|
-
|
4
|
-
# any hashes within the hash will also be merged to the level specifid
|
5
|
-
def merge_deep(hash2, level=1)
|
6
|
-
if level == 1
|
7
|
-
tmp_opts = {}
|
8
|
-
self.each do |k,v|
|
9
|
-
if (v.is_a?(Hash) and hash2[k].is_a?(Hash))
|
10
|
-
tmp_opts[k] = v.merge(hash2[k])
|
11
|
-
end
|
12
|
-
end
|
13
|
-
opts = self.merge(hash2)
|
14
|
-
opts.merge!(tmp_opts)
|
15
|
-
opts
|
16
|
-
else
|
17
|
-
raise NotImplementedError, "need to implement level > 1"
|
18
|
-
end
|
19
|
-
end
|
20
|
-
end
|
21
|
-
|
data/lib/ms/converter/mzxml.rb
DELETED
@@ -1,77 +0,0 @@
|
|
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
|
-
|
data/lib/ms/gradient_program.rb
DELETED
@@ -1,170 +0,0 @@
|
|
1
|
-
|
2
|
-
# This is modeled after the Thermo gradient
|
3
|
-
class GradientProgram
|
4
|
-
attr_accessor :time_points
|
5
|
-
attr_accessor :pump_type
|
6
|
-
# array of solvents parallel to TimePoint percentages array
|
7
|
-
attr_accessor :solvents
|
8
|
-
|
9
|
-
def initialize(pump_type, time_points=[], solvents=[])
|
10
|
-
@pump_type = pump_type
|
11
|
-
@time_points = time_points
|
12
|
-
@solvents = solvents
|
13
|
-
end
|
14
|
-
|
15
|
-
def ==(other)
|
16
|
-
self.class == other.class and @pump_type==other.pump_type and @solvents == other.solvents and @time_points == other.time_points
|
17
|
-
end
|
18
|
-
|
19
|
-
# gets the first gradient program encountered in the filehandle
|
20
|
-
def self.get_gradient_program(fh)
|
21
|
-
thermo_newline = "\n\000"
|
22
|
-
#gtable = "g\000r\000a\000d\000i\000e\000n\000t\000 \000t\000a\000b\000l\000e"
|
23
|
-
gradient = "[Gg]\000r\000a\000d\000i\000e\000n\000t\000 \000"
|
24
|
-
|
25
|
-
|
26
|
-
xcal_2x = gradient + "t\000a\000b\000l\000e\000:\000"
|
27
|
-
xcal_1x = gradient + "P\000r\000o\000g\000r\000a\000m\000:\000"
|
28
|
-
xcal_2x_regexp = Regexp.new(xcal_2x)
|
29
|
-
xcal_1x_regexp = Regexp.new(xcal_1x)
|
30
|
-
find_gtable_regexp = Regexp.new(gradient)
|
31
|
-
|
32
|
-
found_one_2x = false
|
33
|
-
found_one_1x = false
|
34
|
-
pump_type = ''
|
35
|
-
fh.each(thermo_newline) do |line|
|
36
|
-
# first identify the line, then
|
37
|
-
if line =~ find_gtable_regexp
|
38
|
-
if line =~ xcal_1x_regexp
|
39
|
-
pump_type = '' ## have to look way back in file for this
|
40
|
-
found_one_1x = true
|
41
|
-
break
|
42
|
-
elsif line =~ xcal_2x_regexp
|
43
|
-
grab_pump_type_regexp = /(.*) .g.r.a.d.i.e.n.t. .t.a.b.l.e/
|
44
|
-
pump_type = read_thermo_string(grab_pump_type_regexp.match(line).captures[0])
|
45
|
-
found_one_2x = true
|
46
|
-
break
|
47
|
-
end
|
48
|
-
end
|
49
|
-
end
|
50
|
-
if found_one_2x
|
51
|
-
fh.gets(thermo_newline) # nothing
|
52
|
-
table_headers = fh.gets(thermo_newline)
|
53
|
-
time_points = []
|
54
|
-
while (line = fh.gets(thermo_newline)) != thermo_newline
|
55
|
-
# 0 0.00 95.0 5.0 0.0 0.0 38.0 x
|
56
|
-
# 1 1.00 90.0 10.0 0.0 0.0 38.0 o
|
57
|
-
|
58
|
-
pieces = table_row_to_pieces(line, '2.0')
|
59
|
-
time_points << TimePoint.new(pieces[1].to_f, pieces[6].to_f, pieces[2,4].map{|x| x.to_f })
|
60
|
-
end
|
61
|
-
GradientProgram.new(pump_type, time_points, %w(A B C D))
|
62
|
-
elsif found_one_1x
|
63
|
-
fh.gets(thermo_newline) # nothing
|
64
|
-
table_headers = fh.gets(thermo_newline)
|
65
|
-
time_points = []
|
66
|
-
null_char_regexp = Regexp.new("^\000\000\000\000")
|
67
|
-
while (line = fh.gets(thermo_newline)) !~ null_char_regexp
|
68
|
-
pieces = table_row_to_pieces(line, '1.0')
|
69
|
-
time_points << TimePoint.new(pieces[1].to_f, pieces[6].to_f, pieces[2,4].map{|x| x.to_f })
|
70
|
-
end
|
71
|
-
GradientProgram.new(pump_type, time_points, %w(A B C D))
|
72
|
-
else
|
73
|
-
nil
|
74
|
-
end
|
75
|
-
end
|
76
|
-
|
77
|
-
# returns the elements of a gradient table row properly cast
|
78
|
-
# NOTE: Xcal 2.X starts index with 0, 1.X starts with 1
|
79
|
-
# (and this is how it will be returned!)
|
80
|
-
# NOTE: Xcal 1.X will be shorter by one (doesn't have the o/x string!)
|
81
|
-
# [(Int) index, time (Float), %A (Float), %B (Float), %C (Float), %D (Float),
|
82
|
-
# FlowRate (Float), o/x (String)]
|
83
|
-
def self.table_row_to_pieces(line,xcal_version='2.0')
|
84
|
-
string = read_thermo_string(line)
|
85
|
-
if xcal_version >= '2.0'
|
86
|
-
# at first, I thought you could just split on spaces, but the table is
|
87
|
-
# designed to have a certain number of chars per column padded with
|
88
|
-
# spaces. This is hte way to do it.
|
89
|
-
index = string[0,4].to_i
|
90
|
-
(tm, a, b, c, d) = (0...5).to_a.map do |x|
|
91
|
-
string[(x*6)+4,6].rstrip.to_f
|
92
|
-
end
|
93
|
-
fr = string[34,7].rstrip.to_f
|
94
|
-
ox = string[41,4].rstrip
|
95
|
-
[index, tm, a, b, c, d, fr, ox]
|
96
|
-
else
|
97
|
-
index = string[0,5].lstrip.to_i # correct
|
98
|
-
tm = string[5,13].lstrip.to_f # correct
|
99
|
-
#puts "**" + string[18,16] + "**"
|
100
|
-
fr = string[18,16].lstrip.to_f
|
101
|
-
(a,b,c,d) = (0..3).to_a.map do |x|
|
102
|
-
string[(x*8)+34, 8].lstrip.to_f # correct
|
103
|
-
end
|
104
|
-
[index, tm, a, b, c, d, fr]
|
105
|
-
end
|
106
|
-
end
|
107
|
-
|
108
|
-
# takes a filehandle
|
109
|
-
# returns an array of gradient programs from a thermo filehandle.
|
110
|
-
# Acceptable file types include a .meth file and a .raw file
|
111
|
-
def self.all_from_handle(fh)
|
112
|
-
# 0005340: 3000 2e00 3000 3000 0a00 0a00 5300 6100 0...0.0.....S.a.
|
113
|
-
# 0005350: 6d00 7000 6c00 6500 2000 5000 7500 6d00 m.p.l.e. .P.u.m.
|
114
|
-
# 0005360: 7000 2000 6700 7200 6100 6400 6900 6500 p. .g.r.a.d.i.e.
|
115
|
-
# 0005370: 6e00 7400 2000 7400 6100 6200 6c00 6500 n.t. .t.a.b.l.e.
|
116
|
-
# 0005380: 3a00 0a00 0a00 4e00 6f00 2e00 2000 5400 :.....N.o... .T.
|
117
|
-
# 0005390: 6900 6d00 6500 2000 2000 4100 2500 2000 i.m.e. . .A.%. .
|
118
|
-
# 00053a0: 2000 2000 2000 4200 2500 2000 2000 2000 . . .B.%. . . .
|
119
|
-
# 00053b0: 2000 4300 2500 2000 2000 2000 2000 4400 .C.%. . . . .D.
|
120
|
-
# 00053c0: 2500 2000 2000 2000 2000 b500 6c00 2f00 %. . . . ...l./.
|
121
|
-
# 00053d0: 6d00 6900 6e00 2000 0a00 3000 2000 2000 m.i.n. ...0. . .
|
122
|
-
# 00053e0: 2000 3000 2e00 3000 3000 2000 2000 3000 .0...0.0. . .0.
|
123
|
-
# 00053f0: 2e00 3000 2000 2000 2000 3000 2e00 3000 ..0. . . .0...0.
|
124
|
-
# 0005400: 2000 2000 2000 3100 3000 3000 2e00 3000 . . .1.0.0...0.
|
125
|
-
programs = []
|
126
|
-
while (gp = get_gradient_program(fh))
|
127
|
-
programs << gp
|
128
|
-
end
|
129
|
-
programs
|
130
|
-
end
|
131
|
-
|
132
|
-
def self.read_thermo_string(string)
|
133
|
-
chars = []
|
134
|
-
(0...string.size).step(2) do |i|
|
135
|
-
chars << string[i,1]
|
136
|
-
end
|
137
|
-
chars.join
|
138
|
-
end
|
139
|
-
|
140
|
-
def self.read_thermo_string_as_hex(string)
|
141
|
-
chars = []
|
142
|
-
(0...string.size).step(4) do |i|
|
143
|
-
chars << string[i,2]
|
144
|
-
end
|
145
|
-
[chars.join].pack('H*')
|
146
|
-
end
|
147
|
-
|
148
|
-
|
149
|
-
end
|
150
|
-
|
151
|
-
class GradientProgram::TimePoint
|
152
|
-
# time in minutes
|
153
|
-
attr_accessor :time
|
154
|
-
# flow_rate in ul/min
|
155
|
-
attr_accessor :flow_rate
|
156
|
-
# percentages
|
157
|
-
attr_accessor :percentages
|
158
|
-
|
159
|
-
def initialize(time=nil, flow_rate=nil, percentages=[])
|
160
|
-
@time = time
|
161
|
-
@flow_rate = flow_rate
|
162
|
-
@percentages = percentages
|
163
|
-
end
|
164
|
-
|
165
|
-
def ==(other)
|
166
|
-
self.class == other.class and @time==other.time and @flow_rate == other.flow_rate and @percentages == other.percentages
|
167
|
-
end
|
168
|
-
end
|
169
|
-
|
170
|
-
|
data/lib/ms/msrun.rb
DELETED
@@ -1,244 +0,0 @@
|
|
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
|
-
MSRunDefaultOpts = { :lazy => :string }
|
14
|
-
|
15
|
-
attr_accessor :start_time, :end_time
|
16
|
-
attr_accessor :scans
|
17
|
-
# (just for reference) the type of file this is (as symbol)
|
18
|
-
attr_accessor :filetype
|
19
|
-
# (just for reference) the version string of this type of file
|
20
|
-
attr_accessor :version
|
21
|
-
# the total number of scans
|
22
|
-
attr_writer :scan_count
|
23
|
-
|
24
|
-
|
25
|
-
#### # [note: precursor intensities not guaranteed to exist unless :
|
26
|
-
# TODO: may need to eliminate unavailable precursor intensities if they
|
27
|
-
# doing lazy evaluation?? or it becomes lazy too??
|
28
|
-
|
29
|
-
# OPTIONS:
|
30
|
-
# :lazy => :string | :not | :no_spectra | :io
|
31
|
-
# :string = (default) stores each spectrum as a base64 decoded
|
32
|
-
# string that is further processed into Arrays of Floats when m/z
|
33
|
-
# or intensity information is access. This lazy evaluation
|
34
|
-
# should work on most files.
|
35
|
-
# :not = all information is read into memory and parsed into
|
36
|
-
# objects. Should only be used for small-medium files (< 80MB on
|
37
|
-
# a machine with 2GB memory)
|
38
|
-
# :no_spectra = if no peak information is required use this to
|
39
|
-
# avoid the overhead of parsing and creating spectra.
|
40
|
-
# :io = stores the io object and indices into spectrum data.
|
41
|
-
# When spectral information is requested (m/z or intensity
|
42
|
-
# information) then the spectrum is read from the io object and
|
43
|
-
# evaluated (requires an open io object when spectrum information
|
44
|
-
# is requested)
|
45
|
-
def initialize(file_or_io=nil, opts={})
|
46
|
-
if opts[:lazy] == :io
|
47
|
-
if !file_or_io.is_a?(IO)
|
48
|
-
raise ArgumentError, "Caller must provide an IO object (rather than filename) if using {:lazy => :io}"
|
49
|
-
end
|
50
|
-
end
|
51
|
-
myopts = MSRunDefaultOpts.merge(opts)
|
52
|
-
myopts[:msrun] = self
|
53
|
-
if file_or_io
|
54
|
-
filetype_and_version = MS::Parser.filetype_and_version(file_or_io)
|
55
|
-
parser = MS::Parser.new(filetype_and_version, :msrun, myopts)
|
56
|
-
parser.parse(file_or_io, myopts)
|
57
|
-
#MS::Parser.new(filetype_and_version, :msrun).parse(file, myopts)
|
58
|
-
(@filetype, @version) = filetype_and_version
|
59
|
-
end
|
60
|
-
end
|
61
|
-
|
62
|
-
# This will automatically use :lazy => :io, open the file, and close it
|
63
|
-
# after the block returns.
|
64
|
-
# MS::MSRun.open("file.mzXML") do |ms|
|
65
|
-
# ms.scans.each {|scan| ... do something }
|
66
|
-
# end
|
67
|
-
def self.open(filename, opts={})
|
68
|
-
File.open(filename) do |fh|
|
69
|
-
ms = MS::MSRun.new(fh, {:lazy => :io}.merge(opts))
|
70
|
-
yield(ms)
|
71
|
-
end
|
72
|
-
end
|
73
|
-
|
74
|
-
# 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,
|
75
|
-
# ...
|
76
|
-
def scan_counts
|
77
|
-
ar = []
|
78
|
-
ar[0] = 0
|
79
|
-
scans.each do |sc|
|
80
|
-
level = sc.ms_level
|
81
|
-
unless ar[level]
|
82
|
-
ar[level] = 0
|
83
|
-
end
|
84
|
-
ar[level] += 1
|
85
|
-
ar[0] += 1
|
86
|
-
end
|
87
|
-
ar
|
88
|
-
end
|
89
|
-
|
90
|
-
def scan_count(mslevel=0)
|
91
|
-
if mslevel == 0
|
92
|
-
@scan_count
|
93
|
-
else
|
94
|
-
num = 0
|
95
|
-
scans.each do |sc|
|
96
|
-
if sc.ms_level == mslevel
|
97
|
-
num += 1
|
98
|
-
end
|
99
|
-
end
|
100
|
-
num
|
101
|
-
end
|
102
|
-
end
|
103
|
-
|
104
|
-
# for level 1, finds first scan and asks if it has start_mz/end_mz
|
105
|
-
# attributes. for other levels, asks for start_mz/ end_mz and takes the
|
106
|
-
# min/max. If start_mz and end_mz are not found, goes through every scan
|
107
|
-
# finding the max/min first and last m/z. returns [start_mz (rounded down to
|
108
|
-
# nearest int), end_mz (rounded up to nearest int)]
|
109
|
-
def start_and_end_mz(mslevel=1)
|
110
|
-
if mslevel == 1
|
111
|
-
# special case for mslevel 1 (where we expect scans to be same length)
|
112
|
-
scans.each do |sc|
|
113
|
-
if sc.ms_level == mslevel
|
114
|
-
if sc.start_mz && sc.end_mz
|
115
|
-
return [sc.start_mz, sc.end_mz]
|
116
|
-
end
|
117
|
-
break
|
118
|
-
end
|
119
|
-
end
|
120
|
-
end
|
121
|
-
hi_mz = nil
|
122
|
-
lo_mz = nil
|
123
|
-
# see if we have start_mz and end_mz for the level we want
|
124
|
-
# set the initial hi_mz and lo_mz in any case
|
125
|
-
have_start_end_mz = false
|
126
|
-
scans.each do |sc|
|
127
|
-
if sc.ms_level == mslevel
|
128
|
-
if sc.start_mz && sc.end_mz
|
129
|
-
lo_mz = sc.start_mz
|
130
|
-
hi_mz = sc.end_mz
|
131
|
-
else
|
132
|
-
mz_ar = sc.spectrum.mzs
|
133
|
-
hi_mz = mz_ar.last
|
134
|
-
lo_mz = mz_ar.first
|
135
|
-
end
|
136
|
-
break
|
137
|
-
end
|
138
|
-
end
|
139
|
-
if have_start_end_mz
|
140
|
-
scans.each do |sc|
|
141
|
-
if sc.ms_level == mslevel
|
142
|
-
if sc.start_mz < lo_mz
|
143
|
-
lo_mz = sc.start_mz
|
144
|
-
end
|
145
|
-
if sc.end_mz > hi_mz
|
146
|
-
hi_mz = sc.end_mz
|
147
|
-
end
|
148
|
-
end
|
149
|
-
end
|
150
|
-
else
|
151
|
-
# didn't have the attributes (find by brute force)
|
152
|
-
scans.each do |sc|
|
153
|
-
if sc.ms_level == mslevel
|
154
|
-
mz_ar = sc.spectrum.mzs
|
155
|
-
if mz_ar.last > hi_mz
|
156
|
-
hi_mz = mz_ar.last
|
157
|
-
end
|
158
|
-
if mz_ar.last < lo_mz
|
159
|
-
lo_mz = mz_ar.last
|
160
|
-
end
|
161
|
-
end
|
162
|
-
end
|
163
|
-
end
|
164
|
-
[lo_mz.floor, hi_mz.ceil]
|
165
|
-
end
|
166
|
-
|
167
|
-
# returns an array of precursor mz by scan number
|
168
|
-
# returns only the m/z of the FIRST precursor if multiple
|
169
|
-
def precursor_mz_by_scan_num
|
170
|
-
ar = Array.new(@scans.size + 1)
|
171
|
-
@scans.each do |scan|
|
172
|
-
if prec = scan.precursor
|
173
|
-
ar[scan.num] = prec.mz
|
174
|
-
else
|
175
|
-
ar[scan.num] = nil
|
176
|
-
end
|
177
|
-
end
|
178
|
-
ar
|
179
|
-
end
|
180
|
-
|
181
|
-
# returns an array of times and parallel array of spectra objects.
|
182
|
-
# ms_level = 0 then all spectra and times
|
183
|
-
# ms_level = 1 then all spectra of ms_level 1
|
184
|
-
def times_and_spectra(ms_level=0)
|
185
|
-
spectra = []
|
186
|
-
if ms_level == 0
|
187
|
-
times = @scans.map do |scan|
|
188
|
-
spectra << scan.spectrum
|
189
|
-
scan.time
|
190
|
-
end
|
191
|
-
[times, spectra]
|
192
|
-
else # choose a particular ms_level
|
193
|
-
times = []
|
194
|
-
@scans.each do |scan|
|
195
|
-
if ms_level == scan.ms_level
|
196
|
-
spectra << scan.spectrum
|
197
|
-
times << scan.time
|
198
|
-
end
|
199
|
-
end
|
200
|
-
[times, spectra]
|
201
|
-
end
|
202
|
-
end
|
203
|
-
|
204
|
-
# same as the instance method (creates an object without spectrum and calls
|
205
|
-
# instance method of the same name)
|
206
|
-
def self.precursor_mz_by_scan_num(file)
|
207
|
-
self.new(file, :lazy => :no_spectra, :fix_bad_tags => true).precursor_mz_by_scan_num
|
208
|
-
end
|
209
|
-
|
210
|
-
# only adds the parent if one is not already present!
|
211
|
-
def self.add_parent_scan(scans, add_intensities=false)
|
212
|
-
#start = Time.now
|
213
|
-
prev_scan = nil
|
214
|
-
parent_stack = [nil]
|
215
|
-
## we want to set the level to be the first mslevel we come to
|
216
|
-
prev_level = scans.first.ms_level
|
217
|
-
scans.each do |scan|
|
218
|
-
#next unless scan ## the first one is nil, (others?)
|
219
|
-
level = scan.ms_level
|
220
|
-
if prev_level < level
|
221
|
-
parent_stack.unshift prev_scan
|
222
|
-
end
|
223
|
-
if prev_level > level
|
224
|
-
(prev_level - level).times do parent_stack.shift end
|
225
|
-
end
|
226
|
-
if scan.ms_level > 1
|
227
|
-
precursor = scan.precursor
|
228
|
-
#precursor.parent = parent_stack.first # that's the next line's
|
229
|
-
precursor[2] = parent_stack.first unless precursor[2]
|
230
|
-
#precursor.intensity
|
231
|
-
if add_intensities
|
232
|
-
precursor[1] = precursor[2].spectrum.intensity_at_mz(precursor[0])
|
233
|
-
end
|
234
|
-
end
|
235
|
-
prev_level = level
|
236
|
-
prev_scan = scan
|
237
|
-
end
|
238
|
-
#puts "TOOK #{Time.now - start} secs"
|
239
|
-
end
|
240
|
-
|
241
|
-
end
|
242
|
-
|
243
|
-
|
244
|
-
|