ms-spectral_summing 0.0.1
Sign up to get free protection for your applications and to get access to all the features.
- data/LICENSE.txt +20 -0
- data/README.rdoc +19 -0
- data/lib/spectral_summing.rb +157 -0
- metadata +56 -0
data/LICENSE.txt
ADDED
@@ -0,0 +1,20 @@
|
|
1
|
+
Copyright (c) 2011 Ryan Taylor
|
2
|
+
|
3
|
+
Permission is hereby granted, free of charge, to any person obtaining
|
4
|
+
a copy of this software and associated documentation files (the
|
5
|
+
"Software"), to deal in the Software without restriction, including
|
6
|
+
without limitation the rights to use, copy, modify, merge, publish,
|
7
|
+
distribute, sublicense, and/or sell copies of the Software, and to
|
8
|
+
permit persons to whom the Software is furnished to do so, subject to
|
9
|
+
the following conditions:
|
10
|
+
|
11
|
+
The above copyright notice and this permission notice shall be
|
12
|
+
included in all copies or substantial portions of the Software.
|
13
|
+
|
14
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
|
15
|
+
EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
|
16
|
+
MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
|
17
|
+
NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE
|
18
|
+
LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION
|
19
|
+
OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION
|
20
|
+
WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
|
data/README.rdoc
ADDED
@@ -0,0 +1,19 @@
|
|
1
|
+
= spectral_summing
|
2
|
+
|
3
|
+
Description goes here.
|
4
|
+
|
5
|
+
== Contributing to spectral_summing
|
6
|
+
|
7
|
+
* Check out the latest master to make sure the feature hasn't been implemented or the bug hasn't been fixed yet
|
8
|
+
* Check out the issue tracker to make sure someone already hasn't requested it and/or contributed it
|
9
|
+
* Fork the project
|
10
|
+
* Start a feature/bugfix branch
|
11
|
+
* Commit and push until you are happy with your contribution
|
12
|
+
* Make sure to add tests for it. This is important so I don't break it in a future version unintentionally.
|
13
|
+
* Please try not to mess with the Rakefile, version, or history. If you want to have your own version, or is otherwise necessary, that is fine, but please isolate to its own commit so I can cherry-pick around it.
|
14
|
+
|
15
|
+
== Copyright
|
16
|
+
|
17
|
+
Copyright (c) 2011 Ryan Taylor. See LICENSE.txt for
|
18
|
+
further details.
|
19
|
+
|
@@ -0,0 +1,157 @@
|
|
1
|
+
Spectrum = Struct.new(:spectrum, :scan_num, :scan_time, :scan_range, :precursor_mass, :charge_states, :intensities, :mz_values)
|
2
|
+
|
3
|
+
class Parser
|
4
|
+
attr_accessor :spectra
|
5
|
+
def initialize(file)
|
6
|
+
@file = file
|
7
|
+
end
|
8
|
+
def parse(file = nil)
|
9
|
+
file ||= @file
|
10
|
+
require 'ms/msrun'
|
11
|
+
@spectra = []
|
12
|
+
Ms::Msrun.open(file) do |ms|
|
13
|
+
ms.each(:ms_level => 2) do |scan|
|
14
|
+
@spectra << Spectrum.new(scan, scan.num, scan.time, (scan.start_mz..scan.end_mz), scan.precursor.mz, scan.precursor.charge_states, scan.spectrum.intensities, scan.spectrum.mzs)
|
15
|
+
end
|
16
|
+
end
|
17
|
+
end
|
18
|
+
def parse_by_scan_num(scan_nums, file = nil)
|
19
|
+
file ||= @file
|
20
|
+
require 'ms/msrun'
|
21
|
+
@spectra = []
|
22
|
+
Ms::Msrun.open(file) do |ms|
|
23
|
+
ms.each(:ms_level => 2) do |scan|
|
24
|
+
if scan_nums.include?(scan.num)
|
25
|
+
@spectra << Spectrum.new(scan, scan.num, scan.time, (scan.start_mz..scan.end_mz), scan.precursor.mz, scan.precursor.charge_states, scan.spectrum.intensities, scan.spectrum.mzs)
|
26
|
+
end
|
27
|
+
end
|
28
|
+
end
|
29
|
+
end
|
30
|
+
end
|
31
|
+
|
32
|
+
class Combiner
|
33
|
+
Defaults = {:bin_window => 0.1, :window_size => 4, :precursor_mass_tolerance_in_ppm => 10, :tolerant => false}
|
34
|
+
attr_accessor :output_spectra
|
35
|
+
def initialize(spectra = nil, opts = {})
|
36
|
+
@spectra = spectra
|
37
|
+
@opts = Defaults.merge(opts)
|
38
|
+
end
|
39
|
+
def combine(spectrum1, spectrum2)
|
40
|
+
tolerance = calculate_daltons_from_ppm(spectrum1.precursor_mass, @opts[:precursor_mass_tolerance_in_ppm] )
|
41
|
+
if tolerance.include?(spectrum2.precursor_mass) or @opts[:tolerant]
|
42
|
+
data_arr = summer(spectrum1.mz_values, spectrum1.intensities, spectrum2.mz_values, spectrum2.intensities)
|
43
|
+
end
|
44
|
+
data_arr
|
45
|
+
end
|
46
|
+
def summer(x1,y1,x2,y2) # What should this return?
|
47
|
+
endpoints = (x1+x2).each.minmax
|
48
|
+
bin_width = @opts[:bin_window]
|
49
|
+
num_bins = ((endpoints.last - endpoints.first)/bin_width).ceil
|
50
|
+
data_x = [endpoints.first+bin_width/2.0]
|
51
|
+
data_y = Array.new(num_bins, 0)
|
52
|
+
j, k = 0,0
|
53
|
+
one = [x1,y1]; two = [x2,y2]
|
54
|
+
if x1.first == endpoints.first
|
55
|
+
data_x[0] = x1.first
|
56
|
+
data_y[0] += y1.first
|
57
|
+
y1[0] = 0
|
58
|
+
elsif x2.first == endpoints.first
|
59
|
+
data_x[0] = x2.first
|
60
|
+
data_y[0] += y2.first
|
61
|
+
y2[0] = 0
|
62
|
+
end
|
63
|
+
(1..num_bins-1).each do |i|
|
64
|
+
data_x[i] = data_x[i-1] + bin_width
|
65
|
+
check = data_x[i] + bin_width/2.0
|
66
|
+
#puts "check= #{check}"
|
67
|
+
if one.first[j]
|
68
|
+
while one.first[j] < check
|
69
|
+
data_y[i] += one.last[j]
|
70
|
+
j += 1
|
71
|
+
break if one.first[j].nil?
|
72
|
+
end
|
73
|
+
end
|
74
|
+
if two.first[k]
|
75
|
+
while two.first[k] < check
|
76
|
+
data_y[i] += two.last[k]
|
77
|
+
k += 1
|
78
|
+
break if two.first[k].nil?
|
79
|
+
end
|
80
|
+
end
|
81
|
+
end
|
82
|
+
[data_x, data_y]
|
83
|
+
end
|
84
|
+
def combine_for_more_combining(spectrum1, spectrum2)
|
85
|
+
arr = combine(spectrum1, spectrum2)
|
86
|
+
joined_spectrum = Spectrum.new()
|
87
|
+
joined_spectrum.precursor_mass = (spectrum1.precursor_mass + spectrum2.precursor_mass)/2.0
|
88
|
+
joined_spectrum.mz_values = arr.first
|
89
|
+
joined_spectrum.intensities = arr.last
|
90
|
+
# Spectrum = Struct.new(:spectrum, :scan_num, :scan_time, :scan_range, :precursor_mass, :charge_states, :intensities, :mz_values)
|
91
|
+
joined_spectrum
|
92
|
+
end
|
93
|
+
def calculate_daltons_from_ppm(mass, ppm)
|
94
|
+
diff = ppm*mass/1e6
|
95
|
+
(mass-diff)..(mass+diff)
|
96
|
+
end
|
97
|
+
def to_mgf(spectrum, filename)
|
98
|
+
File.open(filename,'w') do |out|
|
99
|
+
out.puts "BEGIN IONS"
|
100
|
+
out.puts "TITLE=Spec1:#{spectrum.precursor_mass}_#{spectrum.charge_states.first}"
|
101
|
+
out.puts "CHARGE=#{spectrum.charge_states.to_s}+"
|
102
|
+
# our current mzML parser doesn't have scan.time implemented...
|
103
|
+
spectrum.mz_values.each_with_index do |mz, i|
|
104
|
+
intensity = spectrum.intensities[i]
|
105
|
+
out.puts "#{"%.5f" % mz}/t#{"%.5f" % intensity}" unless intensity == 0
|
106
|
+
end
|
107
|
+
out.puts "END IONS"
|
108
|
+
end
|
109
|
+
end
|
110
|
+
def combine_to_mgf(spectrum1, spectrum2, filename) # Thanks JOHN!!! Ms-Msrun 0.3.6
|
111
|
+
results = combine(spectrum1, spectrum2)
|
112
|
+
File.open(filename, 'w') do |out|
|
113
|
+
out.puts "BEGIN IONS"
|
114
|
+
out.puts "TITLE=Spec1:#{spectrum1.precursor_mass}_Spec2:#{spectrum2.precursor_mass}.#{spectrum1.scan_num}_#{spectrum2.scan_num}_#{spectrum1.charge_states.first}"
|
115
|
+
out.puts "CHARGE=#{spectrum1.charge_states.to_s}+"
|
116
|
+
# our current mzML parser doesn't have scan.time implemented...
|
117
|
+
results.first.each_with_index do |mz, i|
|
118
|
+
intensity = results.last[i]
|
119
|
+
out.puts "#{"%.5f" % mz}/t#{"%.5f" % intensity}" unless intensity == 0
|
120
|
+
end
|
121
|
+
out.puts "END IONS"
|
122
|
+
end
|
123
|
+
end
|
124
|
+
end
|
125
|
+
|
126
|
+
if ARGV.size == 0 or ARGV.size % 2 != 0
|
127
|
+
puts "Usage: #{__FILE__} input_file.mzXML scan_nums.txt input_file2.mzXML scan_nums2.txt ... "
|
128
|
+
puts "NOTE: scan_nums.txt files must have a new line break between each integer value."
|
129
|
+
puts 'Returns input_file_input_file2_..._input_file(n).mgf'
|
130
|
+
exit
|
131
|
+
else
|
132
|
+
mzXMLs = []
|
133
|
+
scan_nums = []
|
134
|
+
while ARGV.size > 0
|
135
|
+
mzXMLs << ARGV.shift
|
136
|
+
scan_nums << ARGV.shift
|
137
|
+
end
|
138
|
+
scan_nums.map {|file| IO.readlines(file) }
|
139
|
+
# Parse the files and put the data into spectra objects, held within the list of all spectra to combine.
|
140
|
+
spectras = []
|
141
|
+
mzXML.each_with_index do |file, i|
|
142
|
+
@parse_object = Parser.new(file)
|
143
|
+
@parse_object.parse_by_scan_num(scan_nums[i])
|
144
|
+
spectras << @parse_object.spectra
|
145
|
+
end
|
146
|
+
combined_spectrum = spectras.shift
|
147
|
+
combiner = Combiner.new(combined_spectrum)
|
148
|
+
spectras.each do |spectrum|
|
149
|
+
combined_spectrum = combiner.combine_for_more_combining(combined_spectrum, spectrum)
|
150
|
+
end
|
151
|
+
combiner.to_mgf(combined_spectrum, 'combined_multiple_files.mgf')
|
152
|
+
end
|
153
|
+
|
154
|
+
|
155
|
+
|
156
|
+
|
157
|
+
|
metadata
ADDED
@@ -0,0 +1,56 @@
|
|
1
|
+
--- !ruby/object:Gem::Specification
|
2
|
+
name: ms-spectral_summing
|
3
|
+
version: !ruby/object:Gem::Version
|
4
|
+
prerelease:
|
5
|
+
version: 0.0.1
|
6
|
+
platform: ruby
|
7
|
+
authors:
|
8
|
+
- Ryan M Taylor
|
9
|
+
autorequire:
|
10
|
+
bindir: bin
|
11
|
+
cert_chain: []
|
12
|
+
|
13
|
+
date: 2011-06-27 00:00:00 Z
|
14
|
+
dependencies: []
|
15
|
+
|
16
|
+
description: This is the utility built for summing of individual MS(n) spectra in order to bolster the signal of weak fragmentation. It provides an API and a command-line interface for general use.
|
17
|
+
email: ryanmt@byu.net
|
18
|
+
executables: []
|
19
|
+
|
20
|
+
extensions: []
|
21
|
+
|
22
|
+
extra_rdoc_files: []
|
23
|
+
|
24
|
+
files:
|
25
|
+
- README.rdoc
|
26
|
+
- LICENSE.txt
|
27
|
+
- lib/spectral_summing.rb
|
28
|
+
homepage: https://github.com/princelab/spectral_summing
|
29
|
+
licenses: []
|
30
|
+
|
31
|
+
post_install_message:
|
32
|
+
rdoc_options: []
|
33
|
+
|
34
|
+
require_paths:
|
35
|
+
- lib
|
36
|
+
required_ruby_version: !ruby/object:Gem::Requirement
|
37
|
+
none: false
|
38
|
+
requirements:
|
39
|
+
- - ">="
|
40
|
+
- !ruby/object:Gem::Version
|
41
|
+
version: "0"
|
42
|
+
required_rubygems_version: !ruby/object:Gem::Requirement
|
43
|
+
none: false
|
44
|
+
requirements:
|
45
|
+
- - ">="
|
46
|
+
- !ruby/object:Gem::Version
|
47
|
+
version: "0"
|
48
|
+
requirements: []
|
49
|
+
|
50
|
+
rubyforge_project:
|
51
|
+
rubygems_version: 1.7.2
|
52
|
+
signing_key:
|
53
|
+
specification_version: 3
|
54
|
+
summary: Ms-spectral_summing provides a utility for the combination of multiple scans from mzXML files into a single MGF file. It provides both an API and a generic use via the command line. This relies upon the proven utility of the ms-msrun library.
|
55
|
+
test_files: []
|
56
|
+
|