bio-restriction_enzyme 1.0.0
Sign up to get free protection for your applications and to get access to all the features.
- data/.document +5 -0
- data/COPYING.txt +121 -0
- data/Gemfile +10 -0
- data/LICENSE.txt +7 -0
- data/README.rdoc +22 -0
- data/Rakefile +53 -0
- data/VERSION +1 -0
- data/bio-restriction_enzyme.gemspec +99 -0
- data/lib/bio-restriction_enzyme.rb +1 -0
- data/lib/bio/util/restriction_enzyme.rb +218 -0
- data/lib/bio/util/restriction_enzyme/analysis.rb +241 -0
- data/lib/bio/util/restriction_enzyme/analysis_basic.rb +209 -0
- data/lib/bio/util/restriction_enzyme/cut_symbol.rb +99 -0
- data/lib/bio/util/restriction_enzyme/double_stranded.rb +313 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/aligned_strands.rb +127 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/cut_location_pair.rb +95 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/cut_location_pair_in_enzyme_notation.rb +30 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/cut_locations.rb +68 -0
- data/lib/bio/util/restriction_enzyme/double_stranded/cut_locations_in_enzyme_notation.rb +99 -0
- data/lib/bio/util/restriction_enzyme/range/cut_range.rb +16 -0
- data/lib/bio/util/restriction_enzyme/range/cut_ranges.rb +39 -0
- data/lib/bio/util/restriction_enzyme/range/horizontal_cut_range.rb +59 -0
- data/lib/bio/util/restriction_enzyme/range/sequence_range.rb +249 -0
- data/lib/bio/util/restriction_enzyme/range/sequence_range/calculated_cuts.rb +236 -0
- data/lib/bio/util/restriction_enzyme/range/sequence_range/fragment.rb +43 -0
- data/lib/bio/util/restriction_enzyme/range/sequence_range/fragments.rb +33 -0
- data/lib/bio/util/restriction_enzyme/range/vertical_cut_range.rb +69 -0
- data/lib/bio/util/restriction_enzyme/single_strand.rb +193 -0
- data/lib/bio/util/restriction_enzyme/single_strand/cut_locations_in_enzyme_notation.rb +127 -0
- data/lib/bio/util/restriction_enzyme/single_strand_complement.rb +15 -0
- data/lib/bio/util/restriction_enzyme/string_formatting.rb +103 -0
- data/test/bio-restriction_enzyme/analysis/test_calculated_cuts.rb +281 -0
- data/test/bio-restriction_enzyme/analysis/test_cut_ranges.rb +87 -0
- data/test/bio-restriction_enzyme/analysis/test_sequence_range.rb +223 -0
- data/test/bio-restriction_enzyme/double_stranded/test_aligned_strands.rb +84 -0
- data/test/bio-restriction_enzyme/double_stranded/test_cut_location_pair.rb +58 -0
- data/test/bio-restriction_enzyme/double_stranded/test_cut_location_pair_in_enzyme_notation.rb +56 -0
- data/test/bio-restriction_enzyme/double_stranded/test_cut_locations.rb +35 -0
- data/test/bio-restriction_enzyme/double_stranded/test_cut_locations_in_enzyme_notation.rb +87 -0
- data/test/bio-restriction_enzyme/single_strand/test_cut_locations_in_enzyme_notation.rb +66 -0
- data/test/bio-restriction_enzyme/test_analysis.rb +228 -0
- data/test/bio-restriction_enzyme/test_cut_symbol.rb +27 -0
- data/test/bio-restriction_enzyme/test_double_stranded.rb +98 -0
- data/test/bio-restriction_enzyme/test_single_strand.rb +131 -0
- data/test/bio-restriction_enzyme/test_single_strand_complement.rb +131 -0
- data/test/bio-restriction_enzyme/test_string_formatting.rb +43 -0
- data/test/helper.rb +17 -0
- data/test/test_bio-restriction_enzyme.rb +21 -0
- metadata +153 -0
@@ -0,0 +1,236 @@
|
|
1
|
+
# bio/util/restriction_enzyme/range/sequence_range/calculated_cuts.rb -
|
2
|
+
|
3
|
+
require 'bio/util/restriction_enzyme'
|
4
|
+
|
5
|
+
module Bio
|
6
|
+
class RestrictionEnzyme
|
7
|
+
class Range
|
8
|
+
class SequenceRange
|
9
|
+
|
10
|
+
# cc = CalculatedCuts.new(@size)
|
11
|
+
# cc.add_cuts_from_cut_ranges(@cut_ranges)
|
12
|
+
# cc.remove_incomplete_cuts
|
13
|
+
#
|
14
|
+
# 1 2 3 4 5 6 7
|
15
|
+
# G A|T T A C A
|
16
|
+
# +-----+
|
17
|
+
# C T A A T|G T
|
18
|
+
# 1 2 3 4 5 6 7
|
19
|
+
#
|
20
|
+
# Primary cut = 2
|
21
|
+
# Complement cut = 5
|
22
|
+
# Horizontal cuts = 3, 4, 5
|
23
|
+
#
|
24
|
+
class CalculatedCuts
|
25
|
+
include CutSymbol
|
26
|
+
include StringFormatting
|
27
|
+
|
28
|
+
# +Array+ of vertical cuts on the primary strand in 0-based index notation
|
29
|
+
attr_reader :vc_primary
|
30
|
+
|
31
|
+
# +Array+ of vertical cuts on the complementary strand in 0-based index notation
|
32
|
+
attr_reader :vc_complement
|
33
|
+
|
34
|
+
# +Array+ of horizontal cuts between strands in 0-based index notation
|
35
|
+
attr_reader :hc_between_strands
|
36
|
+
|
37
|
+
# Set to +true+ if the fragment CalculatedCuts is working on is circular
|
38
|
+
attr_accessor :circular
|
39
|
+
|
40
|
+
#--
|
41
|
+
## An +Array+ with the primary strand with vertical cuts, the horizontal cuts, and the complementary strand with vertical cuts.
|
42
|
+
#attr_reader :strands_for_display
|
43
|
+
#++
|
44
|
+
|
45
|
+
# If +false+ the strands_for_display method needs to be called to update the contents
|
46
|
+
# of @strands_for_display. Becomes out of date whenever add_cuts_from_cut_ranges is called.
|
47
|
+
attr_reader :strands_for_display_current
|
48
|
+
|
49
|
+
# Size of the sequence being digested.
|
50
|
+
attr_reader :size
|
51
|
+
|
52
|
+
def initialize(size=nil, circular=false)
|
53
|
+
@size = size
|
54
|
+
@circular = circular
|
55
|
+
@vc_primary = []
|
56
|
+
@vc_complement = []
|
57
|
+
@hc_between_strands = []
|
58
|
+
end
|
59
|
+
|
60
|
+
# Accepts an +Array+ of CutRange type objects and applies them to
|
61
|
+
# @vc_complement, @vc_primary, and @hc_between_strands.
|
62
|
+
#
|
63
|
+
# ---
|
64
|
+
# *Arguments*
|
65
|
+
# * +cut_ranges+: An +Array+ of HorizontalCutRange or VerticalCutRange objects
|
66
|
+
# *Returns*:: nothing
|
67
|
+
def add_cuts_from_cut_ranges(cut_ranges)
|
68
|
+
@strands_for_display_current = false
|
69
|
+
|
70
|
+
cut_ranges.each do |cut_range|
|
71
|
+
@vc_primary += [cut_range.p_cut_left, cut_range.p_cut_right]
|
72
|
+
@vc_complement += [cut_range.c_cut_left, cut_range.c_cut_right]
|
73
|
+
|
74
|
+
# Add horizontal cut ranges. This may happen from cuts made inbetween a
|
75
|
+
# VerticalCutRange or may be specifically defined by a HorizontalCutRange.
|
76
|
+
if cut_range.class == VerticalCutRange
|
77
|
+
( cut_range.min + 1 ).upto( cut_range.max ){|i| @hc_between_strands << i} if cut_range.min < cut_range.max
|
78
|
+
elsif cut_range.class == HorizontalCutRange
|
79
|
+
( cut_range.hcuts.first ).upto( cut_range.hcuts.last ){|i| @hc_between_strands << i}
|
80
|
+
end
|
81
|
+
end
|
82
|
+
clean_all
|
83
|
+
#return
|
84
|
+
end
|
85
|
+
|
86
|
+
# There may be incomplete cuts made, this method removes the cuts that don't
|
87
|
+
# create sub-sequences for easier processing.
|
88
|
+
#
|
89
|
+
# For example, stray horizontal cuts that do not end with a left
|
90
|
+
# and right separation:
|
91
|
+
#
|
92
|
+
# G A T T A C A
|
93
|
+
# +-- ---
|
94
|
+
# C T|A A T G T
|
95
|
+
#
|
96
|
+
# Or stray vertical cuts:
|
97
|
+
#
|
98
|
+
# G A T T A C A
|
99
|
+
# +-- +
|
100
|
+
# C T|A A T|G T
|
101
|
+
#
|
102
|
+
# However note that for non-circular sequences this would be a successful
|
103
|
+
# cut which would result in a floating 'GT' sub-sequence:
|
104
|
+
#
|
105
|
+
# G A T T A C A
|
106
|
+
# +---
|
107
|
+
# C T A A T|G T
|
108
|
+
#
|
109
|
+
# Blunt cuts are also complete cuts.
|
110
|
+
# ---
|
111
|
+
# *Arguments*
|
112
|
+
# * +size+: (_optional_) Size of the sequence being digested. Defined here or during initalization of CalculatedCuts.
|
113
|
+
# *Returns*:: nothing
|
114
|
+
def remove_incomplete_cuts(size=nil)
|
115
|
+
@strands_for_display_current = false
|
116
|
+
@size = size if size
|
117
|
+
raise IndexError, "Size of the strand must be provided here or during initalization." if !@size.kind_of?(Fixnum) and not @circular
|
118
|
+
|
119
|
+
vcuts = (@vc_primary + @vc_complement).uniq.sort
|
120
|
+
hcuts = @hc_between_strands
|
121
|
+
last_index = @size - 1
|
122
|
+
good_hcuts = []
|
123
|
+
potential_hcuts = []
|
124
|
+
|
125
|
+
if @circular
|
126
|
+
# NOTE
|
127
|
+
# if it's circular we should start at the beginning of a cut for orientation,
|
128
|
+
# scan for it, hack off the first set of hcuts and move them to the back
|
129
|
+
else
|
130
|
+
vcuts.unshift(-1) unless vcuts.include?(-1)
|
131
|
+
vcuts.push(last_index) unless vcuts.include?(last_index)
|
132
|
+
end
|
133
|
+
|
134
|
+
hcuts.each do |hcut|
|
135
|
+
raise IndexError if hcut < -1 or hcut > last_index
|
136
|
+
# skipped a nucleotide
|
137
|
+
potential_hcuts.clear if !potential_hcuts.empty? and (hcut - potential_hcuts.last).abs > 1
|
138
|
+
|
139
|
+
if potential_hcuts.empty?
|
140
|
+
if vcuts.include?( hcut ) and vcuts.include?( hcut - 1 )
|
141
|
+
good_hcuts += [hcut]
|
142
|
+
elsif vcuts.include?( hcut - 1 )
|
143
|
+
potential_hcuts << hcut
|
144
|
+
end
|
145
|
+
else
|
146
|
+
if vcuts.include?( hcut )
|
147
|
+
good_hcuts += potential_hcuts + [hcut]
|
148
|
+
potential_hcuts.clear
|
149
|
+
else
|
150
|
+
potential_hcuts << hcut
|
151
|
+
end
|
152
|
+
end
|
153
|
+
end
|
154
|
+
|
155
|
+
check_vc = lambda do |vertical_cuts, opposing_vcuts|
|
156
|
+
# opposing_vcuts is here only to check for blunt cuts, so there shouldn't
|
157
|
+
# be any out-of-order problems with this
|
158
|
+
good_vc = []
|
159
|
+
vertical_cuts.each { |vc| good_vc << vc if good_hcuts.include?( vc ) or good_hcuts.include?( vc + 1 ) or opposing_vcuts.include?( vc ) }
|
160
|
+
good_vc
|
161
|
+
end
|
162
|
+
|
163
|
+
@vc_primary = check_vc.call(@vc_primary, @vc_complement)
|
164
|
+
@vc_complement = check_vc.call(@vc_complement, @vc_primary)
|
165
|
+
@hc_between_strands = good_hcuts
|
166
|
+
|
167
|
+
clean_all
|
168
|
+
end
|
169
|
+
|
170
|
+
# Sets @strands_for_display_current to +true+ and populates @strands_for_display.
|
171
|
+
#
|
172
|
+
# ---
|
173
|
+
# *Arguments*
|
174
|
+
# * +str1+: (_optional_) For displaying a primary strand. If +nil+ a numbered sequence will be used in place.
|
175
|
+
# * +str2+: (_optional_) For displaying a complementary strand. If +nil+ a numbered sequence will be used in place.
|
176
|
+
# * +vcp+: (_optional_) An array of vertical cut locations on the primary strand. If +nil+ the contents of @vc_primary is used.
|
177
|
+
# * +vcc+: (_optional_) An array of vertical cut locations on the complementary strand. If +nil+ the contents of @vc_complementary is used.
|
178
|
+
# * +hc+: (_optional_) An array of horizontal cut locations between strands. If +nil+ the contents of @hc_between_strands is used.
|
179
|
+
# *Returns*:: +Array+ An array with the primary strand with vertical cuts, the horizontal cuts, and the complementary strand with vertical cuts.
|
180
|
+
#
|
181
|
+
def strands_for_display(str1 = nil, str2 = nil, vcp=nil, vcc=nil, hc=nil)
|
182
|
+
return @strands_for_display if @strands_for_display_current
|
183
|
+
vcs = '|' # Vertical cut symbol
|
184
|
+
hcs = '-' # Horizontal cut symbol
|
185
|
+
vhcs = '+' # Intersection of vertical and horizontal cut symbol
|
186
|
+
|
187
|
+
num_txt_repeat = lambda { num_txt = '0123456789'; (num_txt * ( @size / num_txt.size.to_f ).ceil)[0..@size-1] }
|
188
|
+
(str1 == nil) ? a = num_txt_repeat.call : a = str1.dup
|
189
|
+
(str2 == nil) ? b = num_txt_repeat.call : b = str2.dup
|
190
|
+
|
191
|
+
vcp = @vc_primary if vcp==nil
|
192
|
+
vcc = @vc_complement if vcc==nil
|
193
|
+
hc = @hc_between_strands if hc==nil
|
194
|
+
|
195
|
+
vcuts = (vcp + vcc).uniq.sort
|
196
|
+
|
197
|
+
vcp.reverse.each { |c| a.insert(c+1, vcs) }
|
198
|
+
vcc.reverse.each { |c| b.insert(c+1, vcs) }
|
199
|
+
|
200
|
+
between = ' ' * @size
|
201
|
+
hc.each {|hcut| between[hcut,1] = hcs }
|
202
|
+
|
203
|
+
s_a = add_spacing(a, vcs)
|
204
|
+
s_b = add_spacing(b, vcs)
|
205
|
+
s_bet = add_spacing(between)
|
206
|
+
|
207
|
+
# NOTE watch this for circular
|
208
|
+
i = 0
|
209
|
+
0.upto( s_a.size-1 ) do
|
210
|
+
if (s_a[i,1] == vcs) or (s_b[i,1] == vcs)
|
211
|
+
s_bet[i] = vhcs
|
212
|
+
elsif i != 0 and s_bet[i-1,1] == hcs and s_bet[i+1,1] == hcs
|
213
|
+
s_bet[i] = hcs
|
214
|
+
end
|
215
|
+
i+=1
|
216
|
+
end
|
217
|
+
|
218
|
+
@strands_for_display_current = true
|
219
|
+
@strands_for_display = [s_a, s_bet, s_b]
|
220
|
+
end
|
221
|
+
|
222
|
+
#########
|
223
|
+
protected
|
224
|
+
#########
|
225
|
+
|
226
|
+
# remove nil values, remove duplicate values, and
|
227
|
+
# sort @vc_primary, @vc_complement, and @hc_between_strands
|
228
|
+
def clean_all
|
229
|
+
[@vc_primary, @vc_complement, @hc_between_strands].collect { |a| a.delete(nil); a.uniq!; a.sort! }
|
230
|
+
end
|
231
|
+
|
232
|
+
end # CalculatedCuts
|
233
|
+
end # SequenceRange
|
234
|
+
end # Range
|
235
|
+
end # RestrictionEnzyme
|
236
|
+
end # Bio
|
@@ -0,0 +1,43 @@
|
|
1
|
+
# bio/util/restriction_enzyme/range/sequence_range/fragment.rb -
|
2
|
+
|
3
|
+
require 'bio/util/restriction_enzyme'
|
4
|
+
|
5
|
+
module Bio
|
6
|
+
class RestrictionEnzyme
|
7
|
+
class Range
|
8
|
+
class SequenceRange
|
9
|
+
|
10
|
+
class Fragment
|
11
|
+
|
12
|
+
attr_reader :size
|
13
|
+
|
14
|
+
def initialize( primary_bin, complement_bin )
|
15
|
+
@primary_bin = primary_bin
|
16
|
+
@complement_bin = complement_bin
|
17
|
+
end
|
18
|
+
|
19
|
+
DisplayFragment = Struct.new(:primary, :complement, :p_left, :p_right, :c_left, :c_right)
|
20
|
+
|
21
|
+
def for_display(p_str=nil, c_str=nil)
|
22
|
+
df = DisplayFragment.new
|
23
|
+
df.primary = ''
|
24
|
+
df.complement = ''
|
25
|
+
|
26
|
+
both_bins = (@primary_bin + @complement_bin).sort.uniq
|
27
|
+
both_bins.each do |item|
|
28
|
+
@primary_bin.include?(item) ? df.primary << p_str[item] : df.primary << ' '
|
29
|
+
@complement_bin.include?(item) ? df.complement << c_str[item] : df.complement << ' '
|
30
|
+
end
|
31
|
+
|
32
|
+
df.p_left = @primary_bin.first
|
33
|
+
df.p_right = @primary_bin.last
|
34
|
+
df.c_left = @complement_bin.first
|
35
|
+
df.c_right = @complement_bin.last
|
36
|
+
|
37
|
+
df
|
38
|
+
end
|
39
|
+
end # Fragment
|
40
|
+
end # SequenceRange
|
41
|
+
end # Range
|
42
|
+
end # RestrictionEnzyme
|
43
|
+
end # Bio
|
@@ -0,0 +1,33 @@
|
|
1
|
+
# bio/util/restriction_enzyme/analysis/fragments.rb -
|
2
|
+
|
3
|
+
require 'bio/util/restriction_enzyme'
|
4
|
+
|
5
|
+
module Bio
|
6
|
+
class RestrictionEnzyme
|
7
|
+
class Range
|
8
|
+
class SequenceRange
|
9
|
+
|
10
|
+
class Fragments < Array
|
11
|
+
|
12
|
+
attr_accessor :primary
|
13
|
+
attr_accessor :complement
|
14
|
+
|
15
|
+
def initialize(primary, complement)
|
16
|
+
@primary = primary
|
17
|
+
@complement = complement
|
18
|
+
end
|
19
|
+
|
20
|
+
DisplayFragment = Struct.new(:primary, :complement)
|
21
|
+
|
22
|
+
def for_display(p_str=nil, c_str=nil)
|
23
|
+
p_str ||= @primary
|
24
|
+
c_str ||= @complement
|
25
|
+
pretty_fragments = []
|
26
|
+
self.each { |fragment| pretty_fragments << fragment.for_display(p_str, c_str) }
|
27
|
+
pretty_fragments
|
28
|
+
end
|
29
|
+
end # Fragments
|
30
|
+
end # SequenceRange
|
31
|
+
end # Range
|
32
|
+
end # RestrictionEnzyme
|
33
|
+
end # Bio
|
@@ -0,0 +1,69 @@
|
|
1
|
+
# bio/util/restriction_enzyme/range/vertical_cut_range.rb -
|
2
|
+
|
3
|
+
require 'bio/util/restriction_enzyme'
|
4
|
+
|
5
|
+
module Bio
|
6
|
+
class RestrictionEnzyme
|
7
|
+
class Range
|
8
|
+
|
9
|
+
# FIXME docs are kind of out of date. Change this to VerticalAndHorizontalCutRange
|
10
|
+
class VerticalCutRange < CutRange
|
11
|
+
attr_reader :p_cut_left, :p_cut_right
|
12
|
+
attr_reader :c_cut_left, :c_cut_right
|
13
|
+
attr_reader :min, :max
|
14
|
+
attr_reader :range
|
15
|
+
|
16
|
+
# VerticalCutRange provides an extremely raw, yet precise, method of
|
17
|
+
# defining the location of cuts on primary and complementary sequences.
|
18
|
+
#
|
19
|
+
# Many VerticalCutRange objects are used with HorizontalCutRange objects
|
20
|
+
# to be contained in CutRanges to define the cut pattern that a
|
21
|
+
# specific enzyme may make.
|
22
|
+
#
|
23
|
+
# VerticalCutRange takes up to four possible cuts, two on the primary
|
24
|
+
# strand and two on the complementary strand. In typical usage
|
25
|
+
# you will want to make a single cut on the primary strand and a single
|
26
|
+
# cut on the complementary strand.
|
27
|
+
#
|
28
|
+
# However, you can construct it with whatever cuts you desire to accomadate
|
29
|
+
# the most eccentric of imaginary restriction enzymes.
|
30
|
+
#
|
31
|
+
# ---
|
32
|
+
# *Arguments*
|
33
|
+
# * +p_cut_left+: (_optional_) Left-most cut on the primary strand. +nil+ to skip
|
34
|
+
# * +p_cut_right+: (_optional_) Right-most cut on the primary strand. +nil+ to skip
|
35
|
+
# * +c_cut_left+: (_optional_) Left-most cut on the complementary strand. +nil+ to skip
|
36
|
+
# * +c_cut_right+: (_optional_) Right-most cut on the complementary strand. +nil+ to skip
|
37
|
+
# *Returns*:: nothing
|
38
|
+
def initialize( p_cut_left=nil, p_cut_right=nil, c_cut_left=nil, c_cut_right=nil )
|
39
|
+
@p_cut_left = p_cut_left
|
40
|
+
@p_cut_right = p_cut_right
|
41
|
+
@c_cut_left = c_cut_left
|
42
|
+
@c_cut_right = c_cut_right
|
43
|
+
|
44
|
+
a = [@p_cut_left, @c_cut_left, @p_cut_right, @c_cut_right]
|
45
|
+
a.delete(nil)
|
46
|
+
a.sort!
|
47
|
+
@min = a.first
|
48
|
+
@max = a.last
|
49
|
+
|
50
|
+
@range = nil
|
51
|
+
@range = (@min..@max) unless @min == nil or @max == nil
|
52
|
+
return
|
53
|
+
end
|
54
|
+
|
55
|
+
# Check if a location falls within the minimum or maximum values of this
|
56
|
+
# range.
|
57
|
+
#
|
58
|
+
# ---
|
59
|
+
# *Arguments*
|
60
|
+
# * +i+: Location to check if it is included in the range
|
61
|
+
# *Returns*:: +true+ _or_ +false+
|
62
|
+
def include?(i)
|
63
|
+
return false if @range == nil
|
64
|
+
@range.include?(i)
|
65
|
+
end
|
66
|
+
end # VerticalCutRange
|
67
|
+
end # Range
|
68
|
+
end # RestrictionEnzyme
|
69
|
+
end # Bio
|
@@ -0,0 +1,193 @@
|
|
1
|
+
# bio/util/restriction_enzyme/single_strand.rb - Single strand of a restriction enzyme sequence
|
2
|
+
|
3
|
+
require 'bio/util/restriction_enzyme'
|
4
|
+
require 'bio/sequence'
|
5
|
+
|
6
|
+
module Bio
|
7
|
+
class RestrictionEnzyme
|
8
|
+
|
9
|
+
# A single strand of restriction enzyme sequence pattern with a 5' to 3'
|
10
|
+
# orientation.
|
11
|
+
#
|
12
|
+
# DoubleStranded puts the SingleStrand and SingleStrandComplement together to
|
13
|
+
# create the sequence pattern with cuts on both strands.
|
14
|
+
#
|
15
|
+
class SingleStrand < Bio::Sequence::NA
|
16
|
+
|
17
|
+
autoload :CutLocationsInEnzymeNotation, 'bio/util/restriction_enzyme/single_strand/cut_locations_in_enzyme_notation'
|
18
|
+
|
19
|
+
include CutSymbol
|
20
|
+
include StringFormatting
|
21
|
+
|
22
|
+
# The cut locations in enzyme notation. Contains a
|
23
|
+
# CutLocationsInEnzymeNotation object set when the SingleStrand
|
24
|
+
# object is initialized.
|
25
|
+
attr_reader :cut_locations_in_enzyme_notation
|
26
|
+
|
27
|
+
# The cut locations transformed from enzyme index notation to 0-based
|
28
|
+
# array index notation. Contains an Array.
|
29
|
+
attr_reader :cut_locations
|
30
|
+
|
31
|
+
# Orientation of the strand, 5' to 3'
|
32
|
+
def orientation; [5,3]; end
|
33
|
+
|
34
|
+
# Constructor for a Bio::RestrictionEnzyme::StingleStrand object.
|
35
|
+
#
|
36
|
+
# A single strand of restriction enzyme sequence pattern with a 5' to 3' orientation.
|
37
|
+
#
|
38
|
+
# ---
|
39
|
+
# *Arguments*
|
40
|
+
# * +sequence+: (_required_) The enzyme sequence.
|
41
|
+
# * +c+: (_optional_) Cut locations in enzyme notation.
|
42
|
+
# See Bio::RestrictionEnzyme::SingleStrand::CutLocationsInEnzymeNotation
|
43
|
+
#
|
44
|
+
# *Constraints*
|
45
|
+
# * +sequence+ cannot contain immediately adjacent cut symbols (ex. atg^^c).
|
46
|
+
# * +c+ is in enzyme index notation and therefore cannot contain a 0.
|
47
|
+
# * If +c+ is omitted, +sequence+ must contain a cut symbol.
|
48
|
+
# * You cannot provide both a sequence with cut symbols and provide cut locations - ambiguous.
|
49
|
+
#
|
50
|
+
# +sequence+ must be a kind of:
|
51
|
+
# * String
|
52
|
+
# * Bio::Sequence::NA
|
53
|
+
# * Bio::RestrictionEnzyme::SingleStrand
|
54
|
+
#
|
55
|
+
# +c+ must be a kind of:
|
56
|
+
# * Bio::RestrictionEnzyme::SingleStrand::CutLocationsInEnzymeNotation
|
57
|
+
# * Integer, one or more
|
58
|
+
# * Array
|
59
|
+
#
|
60
|
+
# *Returns*:: nothing
|
61
|
+
def initialize( sequence, *c )
|
62
|
+
c.flatten! # if an array was supplied as an argument
|
63
|
+
# NOTE t| 2009-09-19 commented out for library efficiency
|
64
|
+
# validate_args(sequence, c)
|
65
|
+
sequence = sequence.downcase
|
66
|
+
|
67
|
+
if sequence =~ re_cut_symbol
|
68
|
+
@cut_locations_in_enzyme_notation = CutLocationsInEnzymeNotation.new( strip_padding(sequence) )
|
69
|
+
else
|
70
|
+
@cut_locations_in_enzyme_notation = CutLocationsInEnzymeNotation.new( c )
|
71
|
+
end
|
72
|
+
|
73
|
+
@stripped = Bio::Sequence::NA.new( strip_cuts_and_padding( sequence ) )
|
74
|
+
super( pattern )
|
75
|
+
@cut_locations = @cut_locations_in_enzyme_notation.to_array_index
|
76
|
+
return
|
77
|
+
end
|
78
|
+
|
79
|
+
# Returns true if this enzyme is palindromic with its reverse complement.
|
80
|
+
# Does not report if the +cut_locations+ are palindromic or not.
|
81
|
+
#
|
82
|
+
# Examples:
|
83
|
+
# * This would be palindromic:
|
84
|
+
# 5' - ATGCAT - 3'
|
85
|
+
# TACGTA
|
86
|
+
#
|
87
|
+
# * This would not be palindromic:
|
88
|
+
# 5' - ATGCGTA - 3'
|
89
|
+
# TACGCAT
|
90
|
+
#
|
91
|
+
# ---
|
92
|
+
# *Arguments*
|
93
|
+
# * _none_
|
94
|
+
# *Returns*:: +true+ _or_ +false+
|
95
|
+
def palindromic?
|
96
|
+
@stripped.reverse_complement == @stripped
|
97
|
+
end
|
98
|
+
|
99
|
+
# Sequence pattern with no cut symbols and no 'n' padding.
|
100
|
+
# * <code>SingleStrand.new('garraxt', [-2, 1, 7]).stripped # => "garraxt"</code>
|
101
|
+
attr_reader :stripped
|
102
|
+
|
103
|
+
# The sequence with 'n' padding and cut symbols.
|
104
|
+
# * <code>SingleStrand.new('garraxt', [-2, 1, 7]).with_cut_symbols # => "n^ng^arraxt^n"</code>
|
105
|
+
#
|
106
|
+
# ---
|
107
|
+
# *Arguments*
|
108
|
+
# * _none_
|
109
|
+
# *Returns*:: The sequence with 'n' padding and cut symbols.
|
110
|
+
def with_cut_symbols
|
111
|
+
s = pattern
|
112
|
+
@cut_locations_in_enzyme_notation.to_array_index.sort.reverse.each { |c| s.insert(c+1, cut_symbol) }
|
113
|
+
s
|
114
|
+
end
|
115
|
+
|
116
|
+
# The sequence with 'n' padding on the left and right for cuts larger than the sequence.
|
117
|
+
# * <code>SingleStrand.new('garraxt', [-2, 1, 7]).pattern # => "nngarraxtn"</code>
|
118
|
+
#
|
119
|
+
# ---
|
120
|
+
# *Arguments*
|
121
|
+
# * _none_
|
122
|
+
# *Returns*:: The sequence with 'n' padding on the left and right for cuts larger than the sequence.
|
123
|
+
def pattern
|
124
|
+
return stripped if @cut_locations_in_enzyme_notation.min == nil
|
125
|
+
left = (@cut_locations_in_enzyme_notation.min < 0 ? 'n' * @cut_locations_in_enzyme_notation.min.abs : '')
|
126
|
+
|
127
|
+
# Add one more 'n' if a cut is at the last position
|
128
|
+
right = ( (@cut_locations_in_enzyme_notation.max >= @stripped.length) ? ('n' * (@cut_locations_in_enzyme_notation.max - @stripped.length + 1)) : '')
|
129
|
+
[left, stripped, right].join('')
|
130
|
+
end
|
131
|
+
|
132
|
+
# The sequence with 'n' pads, cut symbols, and spacing for alignment.
|
133
|
+
# * <code>SingleStrand.new('garraxt', [-2, 1, 7]).with_spaces # => "n^n g^a r r a x t^n"</code>
|
134
|
+
#
|
135
|
+
# ---
|
136
|
+
# *Arguments*
|
137
|
+
# * _none_
|
138
|
+
# *Returns*:: The sequence with 'n' pads, cut symbols, and spacing for alignment.
|
139
|
+
def with_spaces
|
140
|
+
add_spacing( with_cut_symbols )
|
141
|
+
end
|
142
|
+
|
143
|
+
#########
|
144
|
+
protected
|
145
|
+
#########
|
146
|
+
|
147
|
+
def validate_args( input_pattern, input_cut_locations )
|
148
|
+
unless input_pattern.kind_of?(String)
|
149
|
+
err = "input_pattern is not a String, Bio::Sequence::NA, or Bio::RestrictionEnzyme::SingleStrand object\n"
|
150
|
+
err += "pattern: #{input_pattern}\n"
|
151
|
+
err += "class: #{input_pattern.class}"
|
152
|
+
raise ArgumentError, err
|
153
|
+
end
|
154
|
+
|
155
|
+
if ( input_pattern =~ re_cut_symbol ) and !input_cut_locations.empty?
|
156
|
+
err = "Cut symbol found in sequence, but cut locations were also supplied. Ambiguous.\n"
|
157
|
+
err += "pattern: #{input_pattern}\n"
|
158
|
+
err += "symbol: #{cut_symbol}\n"
|
159
|
+
err += "locations: #{input_cut_locations.inspect}"
|
160
|
+
raise ArgumentError, err
|
161
|
+
end
|
162
|
+
|
163
|
+
input_pattern.each_byte do |c|
|
164
|
+
c = c.chr.downcase
|
165
|
+
unless Bio::NucleicAcid::NAMES.has_key?(c) or c == 'x' or c == 'X' or c == cut_symbol
|
166
|
+
err = "Invalid character in pattern.\n"
|
167
|
+
err += "Not a nucleotide or representation of possible nucleotides. See Bio::NucleicAcid::NAMES for more information.\n"
|
168
|
+
err += "char: #{c}\n"
|
169
|
+
err += "input_pattern: #{input_pattern}"
|
170
|
+
raise ArgumentError, err
|
171
|
+
end
|
172
|
+
end
|
173
|
+
end
|
174
|
+
|
175
|
+
# Tadayoshi Funaba's method as discussed in Programming Ruby 2ed, p390
|
176
|
+
def self.once(*ids)
|
177
|
+
for id in ids
|
178
|
+
module_eval <<-"end;"
|
179
|
+
alias_method :__#{id.__id__}__, :#{id.to_s}
|
180
|
+
private :__#{id.__id__}__
|
181
|
+
def #{id.to_s}(*args, &block)
|
182
|
+
(@__#{id.__id__}__ ||= [__#{id.__id__}__(*args, &block)])[0]
|
183
|
+
end
|
184
|
+
end;
|
185
|
+
end
|
186
|
+
end
|
187
|
+
private_class_method :once
|
188
|
+
|
189
|
+
once :pattern, :with_cut_symbols, :with_spaces, :to_re
|
190
|
+
|
191
|
+
end # SingleStrand
|
192
|
+
end # RestrictionEnzyme
|
193
|
+
end # Bio
|