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
data/lib/bsearch.rb
ADDED
@@ -0,0 +1,120 @@
|
|
1
|
+
#
|
2
|
+
# Ruby/Bsearch - a binary search library for Ruby.
|
3
|
+
#
|
4
|
+
# Copyright (C) 2001 Satoru Takabayashi <satoru@namazu.org>
|
5
|
+
# All rights reserved.
|
6
|
+
# This is free software with ABSOLUTELY NO WARRANTY.
|
7
|
+
#
|
8
|
+
# You can redistribute it and/or modify it under the terms of
|
9
|
+
# the Ruby's licence.
|
10
|
+
#
|
11
|
+
# Example:
|
12
|
+
#
|
13
|
+
# % irb -r ./bsearch.rb
|
14
|
+
# >> %w(a b c c c d e f).bsearch_first {|x| x <=> "c"}
|
15
|
+
# => 2
|
16
|
+
# >> %w(a b c c c d e f).bsearch_last {|x| x <=> "c"}
|
17
|
+
# => 4
|
18
|
+
# >> %w(a b c e f).bsearch_first {|x| x <=> "c"}
|
19
|
+
# => 2
|
20
|
+
# >> %w(a b e f).bsearch_first {|x| x <=> "c"}
|
21
|
+
# => nil
|
22
|
+
# >> %w(a b e f).bsearch_last {|x| x <=> "c"}
|
23
|
+
# => nil
|
24
|
+
# >> %w(a b e f).bsearch_lower_boundary {|x| x <=> "c"}
|
25
|
+
# => 2
|
26
|
+
# >> %w(a b e f).bsearch_upper_boundary {|x| x <=> "c"}
|
27
|
+
# => 2
|
28
|
+
# >> %w(a b c c c d e f).bsearch_range {|x| x <=> "c"}
|
29
|
+
# => 2...5
|
30
|
+
# >> %w(a b c d e f).bsearch_range {|x| x <=> "c"}
|
31
|
+
# => 2...3
|
32
|
+
# >> %w(a b d e f).bsearch_range {|x| x <=> "c"}
|
33
|
+
# => 2...2
|
34
|
+
|
35
|
+
module Bsearch
|
36
|
+
VERSION = '1.5'
|
37
|
+
end
|
38
|
+
|
39
|
+
class Array
|
40
|
+
#
|
41
|
+
# The binary search algorithm is extracted from Jon Bentley's
|
42
|
+
# Programming Pearls 2nd ed. p.93
|
43
|
+
#
|
44
|
+
|
45
|
+
#
|
46
|
+
# Return the lower boundary. (inside)
|
47
|
+
#
|
48
|
+
def bsearch_lower_boundary (range = 0 ... self.length, &block)
|
49
|
+
lower = range.first() -1
|
50
|
+
upper = if range.exclude_end? then range.last else range.last + 1 end
|
51
|
+
while lower + 1 != upper
|
52
|
+
mid = ((lower + upper) / 2).to_i # for working with mathn.rb (Rational)
|
53
|
+
if yield(self[mid]) < 0
|
54
|
+
lower = mid
|
55
|
+
else
|
56
|
+
upper = mid
|
57
|
+
end
|
58
|
+
end
|
59
|
+
return upper
|
60
|
+
end
|
61
|
+
|
62
|
+
#
|
63
|
+
# This method searches the FIRST occurrence which satisfies a
|
64
|
+
# condition given by a block in binary fashion and return the
|
65
|
+
# index of the first occurrence. Return nil if not found.
|
66
|
+
#
|
67
|
+
def bsearch_first (range = 0 ... self.length, &block)
|
68
|
+
boundary = bsearch_lower_boundary(range, &block)
|
69
|
+
if boundary >= self.length || yield(self[boundary]) != 0
|
70
|
+
return nil
|
71
|
+
else
|
72
|
+
return boundary
|
73
|
+
end
|
74
|
+
end
|
75
|
+
|
76
|
+
alias bsearch bsearch_first
|
77
|
+
|
78
|
+
#
|
79
|
+
# Return the upper boundary. (outside)
|
80
|
+
#
|
81
|
+
def bsearch_upper_boundary (range = 0 ... self.length, &block)
|
82
|
+
lower = range.first() -1
|
83
|
+
upper = if range.exclude_end? then range.last else range.last + 1 end
|
84
|
+
while lower + 1 != upper
|
85
|
+
mid = ((lower + upper) / 2).to_i # for working with mathn.rb (Rational)
|
86
|
+
if yield(self[mid]) <= 0
|
87
|
+
lower = mid
|
88
|
+
else
|
89
|
+
upper = mid
|
90
|
+
end
|
91
|
+
end
|
92
|
+
return lower + 1 # outside of the matching range.
|
93
|
+
end
|
94
|
+
|
95
|
+
#
|
96
|
+
# This method searches the LAST occurrence which satisfies a
|
97
|
+
# condition given by a block in binary fashion and return the
|
98
|
+
# index of the last occurrence. Return nil if not found.
|
99
|
+
#
|
100
|
+
def bsearch_last (range = 0 ... self.length, &block)
|
101
|
+
# `- 1' for canceling `lower + 1' in bsearch_upper_boundary.
|
102
|
+
boundary = bsearch_upper_boundary(range, &block) - 1
|
103
|
+
|
104
|
+
if (boundary <= -1 || yield(self[boundary]) != 0)
|
105
|
+
return nil
|
106
|
+
else
|
107
|
+
return boundary
|
108
|
+
end
|
109
|
+
end
|
110
|
+
|
111
|
+
#
|
112
|
+
# Return the search result as a Range object.
|
113
|
+
#
|
114
|
+
def bsearch_range (range = 0 ... self.length, &block)
|
115
|
+
lower = bsearch_lower_boundary(range, &block)
|
116
|
+
upper = bsearch_upper_boundary(range, &block)
|
117
|
+
return lower ... upper
|
118
|
+
end
|
119
|
+
end
|
120
|
+
|
data/lib/fasta.rb
CHANGED
@@ -1,5 +1,9 @@
|
|
1
1
|
require 'sample_enzyme'
|
2
2
|
require 'each_index'
|
3
|
+
require 'optparse'
|
4
|
+
require 'delegate'
|
5
|
+
require 'hash_by'
|
6
|
+
require 'digest/md5'
|
3
7
|
|
4
8
|
|
5
9
|
tmp = $VERBOSE ; $VERBOSE = nil
|
@@ -27,8 +31,10 @@ end
|
|
27
31
|
$VERBOSE = tmp
|
28
32
|
|
29
33
|
|
34
|
+
module FastaManipulation ; end
|
30
35
|
|
31
|
-
class Fasta
|
36
|
+
class Fasta < DelegateClass(Array)
|
37
|
+
include FastaManipulation
|
32
38
|
SHUFF_PREFIX = "SHUFF_"
|
33
39
|
SHUFF_FILE_POSTFIX = "_SHUFF"
|
34
40
|
CAT_SHUFF_FILE_POSTFIX = "_CAT_SHUFF"
|
@@ -37,21 +43,124 @@ class Fasta
|
|
37
43
|
INV_FILE_POSTFIX = "_INV"
|
38
44
|
CAT_INV_FILE_POSTFIX = "_CAT_INV"
|
39
45
|
|
40
|
-
|
46
|
+
attr_writer :prots
|
47
|
+
# this will probably be relative
|
48
|
+
attr_accessor :filename
|
41
49
|
|
42
|
-
|
43
|
-
|
44
|
-
|
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))
|
45
87
|
else
|
46
|
-
|
88
|
+
nil
|
47
89
|
end
|
48
90
|
end
|
49
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
|
+
|
50
156
|
# Reads fasta files (under windows or unix newlines)
|
51
157
|
# Always outputs LF separated files
|
52
158
|
# Checks that the first character per line is '>' or character class [A-Za-z*]
|
53
159
|
# returns a fasta object for stringing commands
|
54
|
-
|
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
|
55
164
|
first_char_re = /[A-Za-z*]/o
|
56
165
|
obj = nil
|
57
166
|
regex = /(\r\n)|\n/o
|
@@ -76,14 +185,151 @@ class Fasta
|
|
76
185
|
self
|
77
186
|
end
|
78
187
|
|
79
|
-
#
|
80
|
-
|
81
|
-
|
82
|
-
|
83
|
-
|
84
|
-
|
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)
|
85
323
|
end
|
86
324
|
|
325
|
+
private
|
326
|
+
|
327
|
+
|
328
|
+
|
329
|
+
end
|
330
|
+
|
331
|
+
module FastaManipulation
|
332
|
+
|
87
333
|
# concatenates the filenames like this:
|
88
334
|
# cat_filenames('fn1.ext1', 'fn2.ext2', '__') # -> 'fn1__fn2.ext1'
|
89
335
|
# the path and extension of the first filename are kept intact.
|
@@ -99,18 +345,6 @@ class Fasta
|
|
99
345
|
fn1.gsub(/#{Regexp.escape(fn1_ext)}$/, connector + con_filenames + fn1_ext)
|
100
346
|
end
|
101
347
|
|
102
|
-
# Convenience method for creating a modified file with a particular method
|
103
|
-
# from Fasta. Returns the name of the output file.
|
104
|
-
def self.modify_file(file, method, file_postfix="", prot_header_prefix=nil)
|
105
|
-
file_out = prefix_extension(file, file_postfix)
|
106
|
-
fasta = Fasta.new
|
107
|
-
fasta.read_file(file)
|
108
|
-
fasta.send(method)
|
109
|
-
fasta.header_prefix!(prot_header_prefix) if prot_header_prefix
|
110
|
-
fasta.write_file(file_out)
|
111
|
-
file_out
|
112
|
-
end
|
113
|
-
|
114
348
|
# returns a new fasta object using some fraction of proteins randomly
|
115
349
|
# selected (fraction may be > 1). Always rounds up. Will not choose a
|
116
350
|
# protein twice unless all other proteins have been chosen
|
@@ -150,30 +384,6 @@ class Fasta
|
|
150
384
|
fasta_fraction = Fasta.new(arr)
|
151
385
|
end
|
152
386
|
|
153
|
-
# Convenience method for modifying some fraction of the proteins of a file
|
154
|
-
# and concatenating it to a copy of the original. Returns the name of the
|
155
|
-
# output file.
|
156
|
-
def self.modify_fraction_and_cat_to_file(file, method, fraction=1, file_postfix=nil, prot_header_prefix=nil)
|
157
|
-
#puts [file, method, fraction, file_postfix, prot_header_prefix].join("*")
|
158
|
-
file_postfix = "" unless file_postfix
|
159
|
-
fasta = Fasta.new
|
160
|
-
fasta.read_file(file)
|
161
|
-
outfile = prefix_extension(file, file_postfix)
|
162
|
-
other_fasta = fasta.fraction_of_prots(fraction)
|
163
|
-
other_fasta.send(method)
|
164
|
-
other_fasta.header_prefix!(prot_header_prefix) if prot_header_prefix
|
165
|
-
fasta << other_fasta
|
166
|
-
fasta.write_file(outfile)
|
167
|
-
return outfile
|
168
|
-
end
|
169
|
-
|
170
|
-
# Convenience method for modifying a file and concatenating it to a copy of
|
171
|
-
# the original. Returns th name of the output file.
|
172
|
-
def self.modify_and_cat_to_file(file, method, file_postfix=nil, prot_header_prefix=nil)
|
173
|
-
fraction = 1
|
174
|
-
modify_fraction_and_cat_to_file(file, method, fraction, file_postfix, prot_header_prefix)
|
175
|
-
end
|
176
|
-
|
177
387
|
# Convenience method to concatenate an array of fasta files. Filenames are
|
178
388
|
# concatenated according to 'cat_filenames') and prefixes the proteins
|
179
389
|
# according to the values in 'file_prot_header_prefixes' array
|
@@ -196,35 +406,13 @@ class Fasta
|
|
196
406
|
end
|
197
407
|
|
198
408
|
def <<(other)
|
199
|
-
|
200
|
-
|
201
|
-
|
202
|
-
|
203
|
-
|
204
|
-
|
205
|
-
@prots.each_with_index do |prot, index|
|
206
|
-
if other_prots[index] != prot
|
207
|
-
return false
|
208
|
-
end
|
209
|
-
end
|
210
|
-
return true
|
211
|
-
end
|
212
|
-
|
213
|
-
def write_file(fn)
|
214
|
-
File.open(fn, "wb") do |out|
|
215
|
-
@prots.each do |prot|
|
216
|
-
out.print(prot.to_s)
|
217
|
-
end
|
218
|
-
end
|
219
|
-
end
|
220
|
-
|
221
|
-
# duplicates the object (deep copy)
|
222
|
-
def dup
|
223
|
-
other = self.class.new
|
224
|
-
self.prots.each do |prot|
|
225
|
-
other.prots << prot.dup
|
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)
|
226
415
|
end
|
227
|
-
other
|
228
416
|
end
|
229
417
|
|
230
418
|
# method = :shuffle! | :reverse!
|
@@ -260,10 +448,39 @@ class Fasta
|
|
260
448
|
prot.header_prefix!(prefix)
|
261
449
|
end
|
262
450
|
end
|
263
|
-
|
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
|
+
|
264
476
|
end
|
265
477
|
|
478
|
+
|
479
|
+
|
480
|
+
|
266
481
|
class Fasta::Prot
|
482
|
+
include ProteinReferenceable
|
483
|
+
|
267
484
|
# header given as full line with starting '>' (but no newline chars!).
|
268
485
|
# aaseq also given without any newline chars
|
269
486
|
attr_accessor :header, :aaseq
|
@@ -280,15 +497,30 @@ class Fasta::Prot
|
|
280
497
|
other && other.class == self.class && other.aaseq == self.aaseq && other.header == self.header
|
281
498
|
end
|
282
499
|
|
283
|
-
#
|
284
|
-
def
|
285
|
-
|
286
|
-
|
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
|
287
514
|
else
|
288
|
-
|
515
|
+
nil
|
289
516
|
end
|
290
517
|
end
|
291
518
|
|
519
|
+
# returns the fasta header information without the leading '>'
|
520
|
+
def reference
|
521
|
+
@header[1..-1]
|
522
|
+
end
|
523
|
+
|
292
524
|
# returns the value after the first '|' and before the second '|'
|
293
525
|
# according to this regexp: /\|(.*?)\|/
|
294
526
|
# This will typically be the gi code
|
@@ -314,7 +546,7 @@ class Fasta::Prot
|
|
314
546
|
def tryptic_peptides!(method_as_symbol)
|
315
547
|
peps = SampleEnzyme.tryptic(@aaseq)
|
316
548
|
ends_in_RK = /[KR]/o
|
317
|
-
|
549
|
+
|
318
550
|
## if the last peptide doesn't end in R or K we want to flip it completely
|
319
551
|
last_pep_special = nil
|
320
552
|
if peps.last[-1,1] !~ /[KR]/
|
@@ -360,7 +592,7 @@ class Fasta::Prot
|
|
360
592
|
|
361
593
|
end
|
362
594
|
|
363
|
-
|
595
|
+
|
364
596
|
# For reference, my code is about 15X faster than the first code I wrote
|
365
597
|
# below! It turns out that the major slowdown is in the randomize routine.
|
366
598
|
# Using my own randomize routine with the below way of reading fasta
|
@@ -391,4 +623,4 @@ end
|
|
391
623
|
# end
|
392
624
|
# end
|
393
625
|
#end
|
394
|
-
|
626
|
+
by=:protein, num=1
|
data/lib/group_by.rb
ADDED
data/lib/index_by.rb
ADDED
data/lib/merge_deep.rb
ADDED
@@ -0,0 +1,21 @@
|
|
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
|
+
|