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/fasta.rb
DELETED
@@ -1,626 +0,0 @@
|
|
1
|
-
require 'sample_enzyme'
|
2
|
-
require 'each_index'
|
3
|
-
require 'optparse'
|
4
|
-
require 'delegate'
|
5
|
-
require 'hash_by'
|
6
|
-
require 'digest/md5'
|
7
|
-
|
8
|
-
|
9
|
-
tmp = $VERBOSE ; $VERBOSE = nil
|
10
|
-
class String
|
11
|
-
|
12
|
-
def each_index
|
13
|
-
(0...self.size).each do |c|
|
14
|
-
yield c
|
15
|
-
end
|
16
|
-
end
|
17
|
-
|
18
|
-
# modifies and returns self
|
19
|
-
def shuffle!
|
20
|
-
each_index {|j| i = rand(size-j); self[j], self[j+i] = self[j+i], self[j]}
|
21
|
-
self
|
22
|
-
end
|
23
|
-
|
24
|
-
def shuffle
|
25
|
-
out = self.dup
|
26
|
-
out.shuffle!
|
27
|
-
out
|
28
|
-
end
|
29
|
-
|
30
|
-
end
|
31
|
-
$VERBOSE = tmp
|
32
|
-
|
33
|
-
|
34
|
-
module FastaManipulation ; end
|
35
|
-
|
36
|
-
class Fasta < DelegateClass(Array)
|
37
|
-
include FastaManipulation
|
38
|
-
SHUFF_PREFIX = "SHUFF_"
|
39
|
-
SHUFF_FILE_POSTFIX = "_SHUFF"
|
40
|
-
CAT_SHUFF_FILE_POSTFIX = "_CAT_SHUFF"
|
41
|
-
FILE_CONNECTOR = "__"
|
42
|
-
INV_PREFIX = "INV_"
|
43
|
-
INV_FILE_POSTFIX = "_INV"
|
44
|
-
CAT_INV_FILE_POSTFIX = "_CAT_INV"
|
45
|
-
|
46
|
-
attr_writer :prots
|
47
|
-
# this will probably be relative
|
48
|
-
attr_accessor :filename
|
49
|
-
|
50
|
-
# for backwards compatibility
|
51
|
-
def prots
|
52
|
-
@prots
|
53
|
-
end
|
54
|
-
|
55
|
-
def self.to_fasta(file_or_obj)
|
56
|
-
if file_or_obj.is_a? Fasta
|
57
|
-
file_or_obj
|
58
|
-
else
|
59
|
-
Fasta.new(file_or_obj)
|
60
|
-
end
|
61
|
-
end
|
62
|
-
|
63
|
-
# arg can be:
|
64
|
-
# Fasta::Prot objects (Array)
|
65
|
-
# filename (String)
|
66
|
-
# Another Fasta object (Fasta) (shallow copy!)
|
67
|
-
def initialize(arg=nil, filename=nil)
|
68
|
-
@filename = filename
|
69
|
-
@prots = []
|
70
|
-
if arg
|
71
|
-
if arg.is_a? Fasta
|
72
|
-
self.prots = arg.prots
|
73
|
-
self.filename = arg.filename
|
74
|
-
elsif arg.is_a? Array
|
75
|
-
@prots = arg
|
76
|
-
else
|
77
|
-
read_file(arg)
|
78
|
-
end
|
79
|
-
end
|
80
|
-
super(@prots)
|
81
|
-
end
|
82
|
-
|
83
|
-
# uses the filename (if available, otherwise returning nil) to grab the md5 sum of the file
|
84
|
-
def md5_sum
|
85
|
-
if File.exist?(@filename)
|
86
|
-
Digest::MD5.hexdigest(File.read(@filename))
|
87
|
-
else
|
88
|
-
nil
|
89
|
-
end
|
90
|
-
end
|
91
|
-
|
92
|
-
# returns the length of the file (in terms of the total number of amino
|
93
|
-
# acids represented)
|
94
|
-
def aa_seq_length
|
95
|
-
tot = 0
|
96
|
-
self.each do |prot|
|
97
|
-
tot += prot.aaseq.size
|
98
|
-
end
|
99
|
-
tot
|
100
|
-
end
|
101
|
-
|
102
|
-
# searches proteins for a match to the exact sequence and returns a single
|
103
|
-
# protein header (with > & no newline)
|
104
|
-
# exact matches). nil if no matches
|
105
|
-
def header_from_exact_sequence(aaseq)
|
106
|
-
hash = self.hash_by(:aaseq)
|
107
|
-
answ = hash[aaseq].map{|v| v.header}
|
108
|
-
if answ.size == 1
|
109
|
-
answ
|
110
|
-
elsif answ.size == 0
|
111
|
-
nil
|
112
|
-
else
|
113
|
-
answ
|
114
|
-
end
|
115
|
-
end
|
116
|
-
|
117
|
-
# searches all headers to see if they include input string
|
118
|
-
# returns true if one matches, false otherwise
|
119
|
-
# (remember that headers are not stored with newline chars but do contain
|
120
|
-
# beginning '>'
|
121
|
-
def included_in_header?(input)
|
122
|
-
@prots.any? do |prot|
|
123
|
-
prot.header.include? input
|
124
|
-
end
|
125
|
-
end
|
126
|
-
|
127
|
-
# takes an io object or string (which is the fasta data) This is not as
|
128
|
-
# stringent as 'read_file' which is recommended for industrial type use. For
|
129
|
-
# instance, this will fail if your newlines are different in your file from
|
130
|
-
# those defined on your operating system. If you have a string, simply pass
|
131
|
-
# in StringIO.new(your_string) to be read.
|
132
|
-
# returns self
|
133
|
-
def load(io)
|
134
|
-
current_prot = nil
|
135
|
-
current_aaseq = nil
|
136
|
-
@prots.clear
|
137
|
-
io.each do |line|
|
138
|
-
if line[0,1] == '>'
|
139
|
-
current_prot = Prot.new
|
140
|
-
@prots << current_prot
|
141
|
-
current_prot.header = line.chomp
|
142
|
-
current_aaseq = ''
|
143
|
-
current_prot.aaseq = current_aaseq
|
144
|
-
elsif (line =~ /[^ ]/) && (line.size > 1)
|
145
|
-
current_aaseq << line.chomp
|
146
|
-
end
|
147
|
-
end
|
148
|
-
self
|
149
|
-
end
|
150
|
-
|
151
|
-
# uses 'load' to create a fasta object from a fasta string
|
152
|
-
def self.from_string(string)
|
153
|
-
Fasta.new.load(StringIO.new(string))
|
154
|
-
end
|
155
|
-
|
156
|
-
# Reads fasta files (under windows or unix newlines)
|
157
|
-
# Always outputs LF separated files
|
158
|
-
# Checks that the first character per line is '>' or character class [A-Za-z*]
|
159
|
-
# returns a fasta object for stringing commands
|
160
|
-
# if fn not given, will read the :filename attribute
|
161
|
-
# will set :filename to fn is given
|
162
|
-
def read_file(fn=nil)
|
163
|
-
@filename = fn if fn
|
164
|
-
first_char_re = /[A-Za-z*]/o
|
165
|
-
obj = nil
|
166
|
-
regex = /(\r\n)|\n/o
|
167
|
-
fh = File.new(fn).binmode
|
168
|
-
lines = fh.read.split(regex)
|
169
|
-
fh.close
|
170
|
-
first_char = nil
|
171
|
-
lines.each do |line|
|
172
|
-
if line =~ /[^ \n\r]/
|
173
|
-
first_char = line[0,1]
|
174
|
-
if first_char == '>'
|
175
|
-
obj = Prot.new
|
176
|
-
@prots << obj
|
177
|
-
obj.header = line.dup
|
178
|
-
elsif first_char =~ first_char_re
|
179
|
-
obj.aaseq << line.chomp
|
180
|
-
else
|
181
|
-
raise "Line not in fasta format (between arrows): -->#{line}<--"
|
182
|
-
end
|
183
|
-
end
|
184
|
-
end
|
185
|
-
self
|
186
|
-
end
|
187
|
-
|
188
|
-
# if no fn, will write to :filename attribute
|
189
|
-
def write_file(fn=nil)
|
190
|
-
fn = @out unless fn
|
191
|
-
File.open(fn, "wb") do |out|
|
192
|
-
@prots.each do |prot|
|
193
|
-
out.print(prot.to_s)
|
194
|
-
end
|
195
|
-
end
|
196
|
-
end
|
197
|
-
|
198
|
-
# duplicates the object (deep copy)
|
199
|
-
def dup
|
200
|
-
other = self.class.new
|
201
|
-
other.filename = self.filename
|
202
|
-
self.prots.each do |prot|
|
203
|
-
other.prots << prot.dup
|
204
|
-
end
|
205
|
-
other
|
206
|
-
end
|
207
|
-
|
208
|
-
end
|
209
|
-
|
210
|
-
class FastaShaker
|
211
|
-
|
212
|
-
def reverse(fasta_file_or_obj, opts={})
|
213
|
-
shake_it(:reverse, fasta_file_or_obj, opts)
|
214
|
-
end
|
215
|
-
|
216
|
-
def shuffle(fasta_file_or_obj, opts={})
|
217
|
-
shake_it(:shuffle, fasta_file_or_obj, opts)
|
218
|
-
end
|
219
|
-
|
220
|
-
# sets the outbound filename attribute from opts
|
221
|
-
def create_filename(fasta, method, opts={})
|
222
|
-
file = fasta.filename || 'fasta'
|
223
|
-
filebase = file.sub(/\..*$/,'')
|
224
|
-
parts = [filebase]
|
225
|
-
parts << 'cat' if opts[:cat]
|
226
|
-
parts << method
|
227
|
-
parts << 'prefix' << opts[:prefix] if opts[:prefix]
|
228
|
-
parts << 'fraction' << opts[:fraction] if opts[:fraction]
|
229
|
-
parts << 'tryptic_peptides' if opts[:tryptic_peptides]
|
230
|
-
parts.join("_") << ".fasta"
|
231
|
-
end
|
232
|
-
|
233
|
-
protected
|
234
|
-
def shake_it(method, fasta_file_or_obj, opt)
|
235
|
-
fasta = Fasta.to_fasta(fasta_file_or_obj)
|
236
|
-
if opt[:cat] && !opt[:prefix]
|
237
|
-
message = "WARNING: concatenated proteins don't have unique headers\n[you probably wanted to use the '--prefix' option!]"
|
238
|
-
warn message
|
239
|
-
end
|
240
|
-
|
241
|
-
unless opt[:out]
|
242
|
-
opt[:out] = create_filename(fasta, method, opt)
|
243
|
-
end
|
244
|
-
|
245
|
-
## CAT (save an original copy)
|
246
|
-
fasta_orig = fasta.dup if opt[:cat]
|
247
|
-
|
248
|
-
## FRACTION the proteins
|
249
|
-
if f = opt[:fraction]
|
250
|
-
prefix = nil
|
251
|
-
if f > 1.0
|
252
|
-
prefix = proc {|cnt| "f#{cnt}_" }
|
253
|
-
end
|
254
|
-
fasta = fasta.fraction_of_prots(f, prefix)
|
255
|
-
end
|
256
|
-
|
257
|
-
## PREFIX the proteins
|
258
|
-
if pre = opt[:prefix]
|
259
|
-
fasta.header_prefix!(pre)
|
260
|
-
end
|
261
|
-
|
262
|
-
## MODIFY the proteins
|
263
|
-
fasta.aaseq!((method.to_s + '!').to_sym, opt[:tryptic_peptides])
|
264
|
-
|
265
|
-
## CAT (finish it up)
|
266
|
-
if opt[:cat]
|
267
|
-
fasta_orig << fasta
|
268
|
-
fasta = fasta_orig
|
269
|
-
end
|
270
|
-
|
271
|
-
## WRITE out the file
|
272
|
-
fasta.write_file(opt[:out])
|
273
|
-
end
|
274
|
-
|
275
|
-
|
276
|
-
|
277
|
-
|
278
|
-
#############################################
|
279
|
-
# END MAIN METHODS
|
280
|
-
#############################################
|
281
|
-
|
282
|
-
# takes command line input, and sends it to shake
|
283
|
-
def FastaShaker.shake_from_argv(argv)
|
284
|
-
opt = {}
|
285
|
-
|
286
|
-
opts = OptionParser.new do |op|
|
287
|
-
prog = File.basename(__FILE__)
|
288
|
-
op.banner = "USAGE: #{prog} <method> [OPTIONS] <file>.fasta"
|
289
|
-
op.separator " <method> = reverse | shuffle"
|
290
|
-
op.separator ""
|
291
|
-
op.separator "fasta_shaker is kind of like a salt shaker:"
|
292
|
-
op.separator "shake up your fasta proteins and let them"
|
293
|
-
op.separator "season your dinner (hopefully a protein dinner). Mmmm."
|
294
|
-
op.separator "false identification rates never tasted so good :)"
|
295
|
-
op.separator ""
|
296
|
-
op.on("-c", "--cat", "catenates the output to copy of original") {|v| opt[:cat] = v }
|
297
|
-
op.on("-o", "--out <string>", "name of output file (default is descriptive)") {|v| opt[:out] = v }
|
298
|
-
op.on("-p", "--prefix <string>", "give a header prefix to modified prots") {|v| opt[:prefix] = v }
|
299
|
-
op.on("-f", "--fraction <float>", Float, "creates some fraction of proteins") {|v| opt[:fraction] = v }
|
300
|
-
op.separator " [if fraction > 1 then the tag 'f<frac#>_' prefixed to proteins"
|
301
|
-
op.separator " (after any given prefix) so that proteins are unique]"
|
302
|
-
op.on("--tryptic_peptides", "applies method to [KR][^P] peptides") {|v| opt[:tryptic_peptides] = v }
|
303
|
-
|
304
|
-
op.separator ""
|
305
|
-
op.separator "EXAMPLES: "
|
306
|
-
op.separator " #{prog} reverse file.fasta -o protein_aa_sequence_reversed.fasta"
|
307
|
-
op.separator " #{prog} shuffle file.fasta -o protein_aa_sequence_shuffled.fasta"
|
308
|
-
op.separator " #{prog} shuffle file.fasta -c -p SH_ -o normal_cat_shuffled_with_prefix.fasta"
|
309
|
-
op.separator " #{prog} reverse file.fasta --tryptic_peptides tryptic_peptides_reversed.fasta"
|
310
|
-
end
|
311
|
-
|
312
|
-
#p argv
|
313
|
-
opts.parse!(argv)
|
314
|
-
|
315
|
-
if argv.size < 2
|
316
|
-
puts opts
|
317
|
-
exit
|
318
|
-
end
|
319
|
-
|
320
|
-
(method, file) = argv
|
321
|
-
fs = FastaShaker.new
|
322
|
-
fs.send(method.to_sym, file, opt)
|
323
|
-
end
|
324
|
-
|
325
|
-
private
|
326
|
-
|
327
|
-
|
328
|
-
|
329
|
-
end
|
330
|
-
|
331
|
-
module FastaManipulation
|
332
|
-
|
333
|
-
# concatenates the filenames like this:
|
334
|
-
# cat_filenames('fn1.ext1', 'fn2.ext2', '__') # -> 'fn1__fn2.ext1'
|
335
|
-
# the path and extension of the first filename are kept intact.
|
336
|
-
# other files only use the basename (with no extension)
|
337
|
-
def self.cat_filenames(filenames, connector="")
|
338
|
-
fn1 = filenames.shift
|
339
|
-
fn1_ext = File.extname(fn1)
|
340
|
-
filenames.collect! do |fn|
|
341
|
-
fn_ext = File.extname(fn)
|
342
|
-
fn_base_no_ext = File.basename(fn, fn_ext)
|
343
|
-
end
|
344
|
-
con_filenames = filenames.join(connector)
|
345
|
-
fn1.gsub(/#{Regexp.escape(fn1_ext)}$/, connector + con_filenames + fn1_ext)
|
346
|
-
end
|
347
|
-
|
348
|
-
# returns a new fasta object using some fraction of proteins randomly
|
349
|
-
# selected (fraction may be > 1). Always rounds up. Will not choose a
|
350
|
-
# protein twice unless all other proteins have been chosen
|
351
|
-
#
|
352
|
-
# fraction_prefix ensures that a unique header is given even if multiple
|
353
|
-
# fraction of proteins are being created
|
354
|
-
# fraction_cnt = (prot_cnt/num_prots).floor.to_i
|
355
|
-
# so for the first n proteins, it will be 0,
|
356
|
-
# the 2n proteins will be 1, etc.
|
357
|
-
# e.g. prefix_proc = proc {|frac_cnt| "f#{frac_cnt}_" }
|
358
|
-
# would give headers like this: >f0_<some_real_header>,
|
359
|
-
# >f1_<some_real_header>, ...
|
360
|
-
def fraction_of_prots(fraction=1, prefix_proc=nil)
|
361
|
-
new_num = (fraction.to_f * self.prots.size).ceil
|
362
|
-
arr = []
|
363
|
-
orig_num_prots = @prots.size
|
364
|
-
|
365
|
-
# initialize
|
366
|
-
new_prots = @prots.map {|prt| prt.dup }
|
367
|
-
frac_cnt = 0
|
368
|
-
ind_cnt = 0
|
369
|
-
prt_cnt = orig_num_prots
|
370
|
-
while ind_cnt < new_num
|
371
|
-
arr << new_prots.delete_at(rand(new_prots.size))
|
372
|
-
if prefix_proc
|
373
|
-
prefix = prefix_proc.call(frac_cnt)
|
374
|
-
arr.last.header_prefix!(prefix)
|
375
|
-
end
|
376
|
-
prt_cnt -= 1 # index
|
377
|
-
if prt_cnt == 0
|
378
|
-
frac_cnt += 1
|
379
|
-
new_prots = @prots.map {|prt| prt.dup }
|
380
|
-
prt_cnt = orig_num_prots
|
381
|
-
end
|
382
|
-
ind_cnt += 1
|
383
|
-
end
|
384
|
-
fasta_fraction = Fasta.new(arr)
|
385
|
-
end
|
386
|
-
|
387
|
-
# Convenience method to concatenate an array of fasta files. Filenames are
|
388
|
-
# concatenated according to 'cat_filenames') and prefixes the proteins
|
389
|
-
# according to the values in 'file_prot_header_prefixes' array
|
390
|
-
def self.cat_and_prefix(files, file_prot_header_prefixes=nil, file_connector=nil)
|
391
|
-
fastas = files.collect do |file|
|
392
|
-
Fasta.new.read_file(file)
|
393
|
-
end
|
394
|
-
outfile = cat_filenames(files, file_connector)
|
395
|
-
if file_prot_header_prefixes
|
396
|
-
file_prot_header_prefixes.each_with_index do |prefix,i|
|
397
|
-
fastas[i].header_prefix!(prefix) if prefix
|
398
|
-
end
|
399
|
-
end
|
400
|
-
fasta1 = fastas.shift
|
401
|
-
fastas.each do |fasta|
|
402
|
-
fasta1 << fasta
|
403
|
-
end
|
404
|
-
fasta1.write_file(outfile)
|
405
|
-
outfile
|
406
|
-
end
|
407
|
-
|
408
|
-
def <<(other)
|
409
|
-
# case when with class names uses === operator
|
410
|
-
case other
|
411
|
-
when Fasta
|
412
|
-
@prots.push(*(other.prots))
|
413
|
-
when Fasta::Prot
|
414
|
-
@prots.push(other)
|
415
|
-
end
|
416
|
-
end
|
417
|
-
|
418
|
-
# method = :shuffle! | :reverse!
|
419
|
-
def aaseq!(method_as_symbol=:shuffle!, tryptic_peptides=false)
|
420
|
-
if tryptic_peptides
|
421
|
-
@prots.each {|prot| prot.tryptic_peptides!( method_as_symbol) }
|
422
|
-
else
|
423
|
-
@prots.each {|prot| prot.aaseq!(method_as_symbol) }
|
424
|
-
end
|
425
|
-
end
|
426
|
-
|
427
|
-
# shuffles the aa sequence of each protein (each protein within itself)
|
428
|
-
def aaseq_shuffle!
|
429
|
-
@prots.each {|prot| prot.shuffle! }
|
430
|
-
end
|
431
|
-
|
432
|
-
# shuffles the aa sequence of each protein (each protein within itself)
|
433
|
-
def aaseq_invert!
|
434
|
-
@prots.each {|prot| prot.invert! }
|
435
|
-
end
|
436
|
-
|
437
|
-
|
438
|
-
def aaseq_invert_tryptic_peptides!
|
439
|
-
@prots.each {|prot| prot.invert_tryptic_peptides! }
|
440
|
-
end
|
441
|
-
|
442
|
-
def aaseq_shuffle_tryptic_peptides!
|
443
|
-
@prots.each {|prot| prot.invert_tryptic_peptides! }
|
444
|
-
end
|
445
|
-
|
446
|
-
def header_prefix!(prefix)
|
447
|
-
@prots.each do |prot|
|
448
|
-
prot.header_prefix!(prefix)
|
449
|
-
end
|
450
|
-
end
|
451
|
-
|
452
|
-
end
|
453
|
-
|
454
|
-
# requires that object respond_to? :reference
|
455
|
-
module ProteinReferenceable
|
456
|
-
# gives the string up to the first space (without the leading '>')
|
457
|
-
def first_entry
|
458
|
-
ref = reference
|
459
|
-
if ref
|
460
|
-
if ref.size > 1
|
461
|
-
ls_ref = ref.lstrip
|
462
|
-
index = ls_ref.index(' ')
|
463
|
-
if index
|
464
|
-
ls_ref[0...index]
|
465
|
-
else
|
466
|
-
ls_ref.dup
|
467
|
-
end
|
468
|
-
else
|
469
|
-
''
|
470
|
-
end
|
471
|
-
else
|
472
|
-
nil
|
473
|
-
end
|
474
|
-
end
|
475
|
-
|
476
|
-
end
|
477
|
-
|
478
|
-
|
479
|
-
|
480
|
-
|
481
|
-
class Fasta::Prot
|
482
|
-
include ProteinReferenceable
|
483
|
-
|
484
|
-
# header given as full line with starting '>' (but no newline chars!).
|
485
|
-
# aaseq also given without any newline chars
|
486
|
-
attr_accessor :header, :aaseq
|
487
|
-
def initialize(header=nil, aaseq=nil)
|
488
|
-
@header = header || ''
|
489
|
-
if aaseq
|
490
|
-
@aaseq = aaseq
|
491
|
-
else
|
492
|
-
@aaseq = ""
|
493
|
-
end
|
494
|
-
end
|
495
|
-
|
496
|
-
def ==(other)
|
497
|
-
other && other.class == self.class && other.aaseq == self.aaseq && other.header == self.header
|
498
|
-
end
|
499
|
-
|
500
|
-
# gives the string up to the first space (without the leading '>')
|
501
|
-
def first_entry
|
502
|
-
|
503
|
-
if @header
|
504
|
-
if @header.size > 1
|
505
|
-
index = @header.index(' ')
|
506
|
-
if index
|
507
|
-
@header[1...index]
|
508
|
-
else
|
509
|
-
@header[1..-1]
|
510
|
-
end
|
511
|
-
else
|
512
|
-
''
|
513
|
-
end
|
514
|
-
else
|
515
|
-
nil
|
516
|
-
end
|
517
|
-
end
|
518
|
-
|
519
|
-
# returns the fasta header information without the leading '>'
|
520
|
-
def reference
|
521
|
-
@header[1..-1]
|
522
|
-
end
|
523
|
-
|
524
|
-
# returns the value after the first '|' and before the second '|'
|
525
|
-
# according to this regexp: /\|(.*?)\|/
|
526
|
-
# This will typically be the gi code
|
527
|
-
# Returns nil if it doesn't match
|
528
|
-
def gi
|
529
|
-
if @header =~ /\|(.*?)\|/
|
530
|
-
$1.dup
|
531
|
-
else
|
532
|
-
nil
|
533
|
-
end
|
534
|
-
end
|
535
|
-
|
536
|
-
# convenience
|
537
|
-
def invert_tryptic_peptides! ; tryptic_peptides!(:reverse) end
|
538
|
-
def shuffle_tryptic_peptides! ; tryptic_peptides!(:shuffle) end
|
539
|
-
|
540
|
-
# modifies tryptic peptides as given by SampleEnzyme.tryptic(@aaseq)
|
541
|
-
# [cuts after K or R but not if followed by a P]
|
542
|
-
# if method_as_symbol = :reverse
|
543
|
-
# :reverse | :shuffle OR :reverse! | :shuffle!
|
544
|
-
# aaseq = 'ABCKCDERDEKDGEKWXYRRKDER'
|
545
|
-
# -> 'ABCKCDERDEKDGEKWXYRRKDER'
|
546
|
-
def tryptic_peptides!(method_as_symbol)
|
547
|
-
peps = SampleEnzyme.tryptic(@aaseq)
|
548
|
-
ends_in_RK = /[KR]/o
|
549
|
-
|
550
|
-
## if the last peptide doesn't end in R or K we want to flip it completely
|
551
|
-
last_pep_special = nil
|
552
|
-
if peps.last[-1,1] !~ /[KR]/
|
553
|
-
last_pep_special = peps.pop
|
554
|
-
end
|
555
|
-
rev_peps = peps.map{|pep| pep[0..-2].send(method_as_symbol) << pep[-1]}
|
556
|
-
if last_pep_special
|
557
|
-
rev_peps << last_pep_special.send(method_as_symbol)
|
558
|
-
end
|
559
|
-
@aaseq = rev_peps.join
|
560
|
-
end
|
561
|
-
|
562
|
-
# takes :reverse! | :shuffle!
|
563
|
-
def aaseq!(method_as_symbol)
|
564
|
-
@aaseq.send(method_as_symbol)
|
565
|
-
end
|
566
|
-
|
567
|
-
def invert!
|
568
|
-
@aaseq.reverse!
|
569
|
-
end
|
570
|
-
|
571
|
-
def shuffle!
|
572
|
-
@aaseq.shuffle!
|
573
|
-
end
|
574
|
-
|
575
|
-
# adds a prefix to the protein header (which comes after the '>' char) if
|
576
|
-
# one is not already there.
|
577
|
-
def header_prefix!(prefix)
|
578
|
-
unless @header =~ /^>#{Regexp.escape(prefix)}/
|
579
|
-
@header.gsub!(/^>/, ">#{prefix}")
|
580
|
-
end
|
581
|
-
end
|
582
|
-
|
583
|
-
def dup
|
584
|
-
self.class.new(@header.dup, @aaseq.dup)
|
585
|
-
end
|
586
|
-
|
587
|
-
# returns the header line and aaseq with trailing newlines as one might find
|
588
|
-
# in a fasta file
|
589
|
-
def to_s
|
590
|
-
@header + "\n" + @aaseq + "\n"
|
591
|
-
end
|
592
|
-
|
593
|
-
end
|
594
|
-
|
595
|
-
|
596
|
-
# For reference, my code is about 15X faster than the first code I wrote
|
597
|
-
# below! It turns out that the major slowdown is in the randomize routine.
|
598
|
-
# Using my own randomize routine with the below way of reading fasta
|
599
|
-
# files is 2X faster than below (in other words, my reader is 2X as fasta).
|
600
|
-
#
|
601
|
-
##!/usr/bin/ruby -w
|
602
|
-
#
|
603
|
-
#require 'bio'
|
604
|
-
#
|
605
|
-
#SHUFF_EXT = "_shuffled"
|
606
|
-
#
|
607
|
-
#if ARGV.size < 1
|
608
|
-
# puts <<END
|
609
|
-
#usage: #{File.basename(__FILE__)} file.fasta ... # -> file#{SHUFF_EXT}.fasta ...
|
610
|
-
#Shuffles the amino acid sequence of each protein.
|
611
|
-
#END
|
612
|
-
# exit
|
613
|
-
#end
|
614
|
-
#
|
615
|
-
#ARGV.each do |fn|
|
616
|
-
# fn_ext = File.extname(fn)
|
617
|
-
# fn_out = fn.gsub(fn_ext, SHUFF_EXT + fn_ext)
|
618
|
-
# File.open(fn_out, "w") do |fh|
|
619
|
-
# f = Bio::FlatFile.auto(fn)
|
620
|
-
# f.each_entry do |e|
|
621
|
-
# fh.puts '>' + e.definition
|
622
|
-
# fh.puts e.aaseq.randomize
|
623
|
-
# end
|
624
|
-
# end
|
625
|
-
#end
|
626
|
-
by=:protein, num=1
|