dna_sequence_aligner 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- data/.gitignore +8 -0
- data/History +10 -0
- data/LICENSE +22 -0
- data/README.rdoc +58 -0
- data/Rakefile +45 -0
- data/VERSION +1 -0
- data/bin/dna_sequence_aligner +61 -0
- data/bin/dna_translator.rb +59 -0
- data/lib/bio/alignment/dna_sequence.rb +313 -0
- data/older/align_all.rb +160 -0
- data/older/align_to_template.rb +143 -0
- data/reference/clustalw_opts.txt +73 -0
- data/script/fasta_compile_annotated.rb +19 -0
- data/spec/align_spec.rb +67 -0
- data/spec/spec_helper.rb +6 -0
- data/spec/testfiles/HA-mKSR1-KSRF1.txt +19 -0
- data/spec/testfiles/HA-mKSR1-KSRF2.txt +20 -0
- data/spec/testfiles/HA-mKSR1-KSRF3.txt +20 -0
- data/spec/testfiles/HA-mKSR1-KSRF4.txt +20 -0
- data/spec/testfiles/HA-mKSR1-KSRF5.txt +20 -0
- data/spec/testfiles/HA-mKSR1-OXL33.txt +20 -0
- data/spec/testfiles/KSR1_mouse_NM_013571_in_HA_pREX.ANNOTATED.fasta +77 -0
- data/spec/testfiles/testcase.fasta +55 -0
- metadata +99 -0
data/.gitignore
ADDED
data/History
ADDED
data/LICENSE
ADDED
@@ -0,0 +1,22 @@
|
|
1
|
+
The MIT License
|
2
|
+
|
3
|
+
Copyright (c) 2010 Howard Hughes Medical Institute
|
4
|
+
Authored by John T. Prince
|
5
|
+
|
6
|
+
Permission is hereby granted, free of charge, to any person obtaining a copy
|
7
|
+
of this software and associated documentation files (the "Software"), to deal
|
8
|
+
in the Software without restriction, including without limitation the rights
|
9
|
+
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
10
|
+
copies of the Software, and to permit persons to whom the Software is
|
11
|
+
furnished to do so, subject to the following conditions:
|
12
|
+
|
13
|
+
The above copyright notice and this permission notice shall be included in
|
14
|
+
all copies or substantial portions of the Software.
|
15
|
+
|
16
|
+
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
17
|
+
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
18
|
+
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
19
|
+
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
20
|
+
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
21
|
+
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
22
|
+
THE SOFTWARE.
|
data/README.rdoc
ADDED
@@ -0,0 +1,58 @@
|
|
1
|
+
= DNASequenceAligner
|
2
|
+
|
3
|
+
dna_sequence_aligner assumes you have a template dna sequence. All other DNA
|
4
|
+
sequences are matched up with the template and then they are all merged into
|
5
|
+
one template-centric alignment. The output was custom designed to show
|
6
|
+
coverage at a glance in a template-centric fashion.
|
7
|
+
|
8
|
+
The software is also written so that you can annotate your template fasta file
|
9
|
+
with comments (must lead with a '#' character).
|
10
|
+
|
11
|
+
== Dependencies
|
12
|
+
|
13
|
+
*Clustalw* must be installed (*clustalw* package in ubuntu/debian) and generally
|
14
|
+
accessible.
|
15
|
+
|
16
|
+
[Bioruby is heavily relied on, but it is explicitly stated as a gem dependency
|
17
|
+
so you shouldn't have to worry about it if installed by gem]
|
18
|
+
|
19
|
+
== Examples
|
20
|
+
|
21
|
+
The executable is the main item of interest. It takes one (or more) sequence
|
22
|
+
files. Your template should be the first fasta encountered.
|
23
|
+
|
24
|
+
dna_sequence_aligner template.fasta others.fasta > output.aligned.txt
|
25
|
+
|
26
|
+
# sequences in separate files
|
27
|
+
dna_sequence_aligner template.fasta other1.fasta other2.fasta > output.aligned.txt
|
28
|
+
|
29
|
+
# all sequences in one file (template first)
|
30
|
+
dna_sequence_aligner all_seqs.fasta > output.aligned.txt
|
31
|
+
|
32
|
+
A comment (#) aware DNA sequence translator is provided to check and see if
|
33
|
+
things are in register and so forth. It outputs the DNA sequence and protein
|
34
|
+
sequence below it.
|
35
|
+
|
36
|
+
# -s 2 is a 2 nucleotide frameshift
|
37
|
+
dna_translator.rb -s 2 dna_annotated.fasta > protein.txt
|
38
|
+
|
39
|
+
== Legend
|
40
|
+
|
41
|
+
all gaps <blank>
|
42
|
+
template gap ^
|
43
|
+
gap below template .
|
44
|
+
agreement =
|
45
|
+
all bad matches ^
|
46
|
+
non-consensus ?
|
47
|
+
|
48
|
+
== NOTE
|
49
|
+
|
50
|
+
This is very much alpha software at the moment. It was written in a time
|
51
|
+
crunch and so it is a little rough around the edges. However, key components
|
52
|
+
have specs written and appear to work properly. If I have to do more
|
53
|
+
alignments or you send me pull requests then this may get to be nicer
|
54
|
+
software.
|
55
|
+
|
56
|
+
== Copyright
|
57
|
+
|
58
|
+
See LICENSE
|
data/Rakefile
ADDED
@@ -0,0 +1,45 @@
|
|
1
|
+
|
2
|
+
require 'rubygems'
|
3
|
+
require 'rake'
|
4
|
+
require 'jeweler'
|
5
|
+
require 'rake/testtask'
|
6
|
+
# require 'rcov/rcovtask'
|
7
|
+
|
8
|
+
NAME = "dna_sequence_aligner"
|
9
|
+
WEBSITE_BASE = "website"
|
10
|
+
WEBSITE_OUTPUT = WEBSITE_BASE + "/output"
|
11
|
+
|
12
|
+
gemspec = Gem::Specification.new do |s|
|
13
|
+
s.name = NAME
|
14
|
+
s.authors = ["John T. Prince"]
|
15
|
+
s.email = "jtprince@gmail.com"
|
16
|
+
s.homepage = "http://jtprince.github.com/" + NAME
|
17
|
+
s.summary = "does high pairwise alignment of sequencing reads with a template"
|
18
|
+
s.description = "does high pairwise alignment of sequencing reads with a template using bioruby and clustalw. gives template-centric output."
|
19
|
+
s.add_dependency("bio")
|
20
|
+
s.add_development_dependency("spec-more")
|
21
|
+
end
|
22
|
+
|
23
|
+
Jeweler::Tasks.new(gemspec)
|
24
|
+
|
25
|
+
Rake::TestTask.new(:spec) do |spec|
|
26
|
+
spec.libs << 'lib' << 'spec'
|
27
|
+
spec.pattern = 'spec/**/*_spec.rb'
|
28
|
+
spec.verbose = true
|
29
|
+
end
|
30
|
+
|
31
|
+
require 'rake/rdoctask'
|
32
|
+
Rake::RDocTask.new do |rdoc|
|
33
|
+
base_rdoc_output_dir = WEBSITE_OUTPUT + '/rdoc'
|
34
|
+
version = File.read('VERSION')
|
35
|
+
rdoc.rdoc_dir = base_rdoc_output_dir + "/#{version}"
|
36
|
+
rdoc.title = NAME + ' ' + version
|
37
|
+
rdoc.rdoc_files.include('README*')
|
38
|
+
rdoc.rdoc_files.include('lib/**/*.rb')
|
39
|
+
end
|
40
|
+
|
41
|
+
task :default => :spec
|
42
|
+
|
43
|
+
task :build => :gemspec
|
44
|
+
|
45
|
+
# credit: Rakefile modeled after Jeweler's
|
data/VERSION
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
0.0.2
|
@@ -0,0 +1,61 @@
|
|
1
|
+
#!/usr/bin/ruby
|
2
|
+
|
3
|
+
require 'bio'
|
4
|
+
require 'optparse'
|
5
|
+
|
6
|
+
require 'bio/alignment/dna_sequence'
|
7
|
+
|
8
|
+
# returns an Array of entry objects. The method will remove any commented
|
9
|
+
# lines first
|
10
|
+
def fasta_entries(file)
|
11
|
+
clean_string = IO.read(file).split("\n").reject {|line| line =~ /^\#/ }.join("\n")
|
12
|
+
io = StringIO.new clean_string
|
13
|
+
objects = []
|
14
|
+
Bio::FlatFile.auto(io) do |ff|
|
15
|
+
ff.each_entry do |entry|
|
16
|
+
objects << entry
|
17
|
+
end
|
18
|
+
end
|
19
|
+
objects
|
20
|
+
end
|
21
|
+
|
22
|
+
DNAReads = Bio::Alignment::DNASequenceReads
|
23
|
+
|
24
|
+
opt = DNAReads::ALIGN_OPTS.dup
|
25
|
+
|
26
|
+
op = OptionParser.new do |op|
|
27
|
+
op.banner = "usage: #{File.basename(__FILE__)} <template>.fasta <read>.txt ..."
|
28
|
+
op.separator " "
|
29
|
+
op.on("--fidelity-length <#{opt[:fidelity_length]}>", Integer, "min length of correct reads on the ends") {|v| opt[:fidelity_length] = v }
|
30
|
+
op.separator " "
|
31
|
+
op.on("--type <DNA|PROTEIN>", "type of bio sequences") {|v| opt[:type] = v }
|
32
|
+
op.on("--gapopen <#{opt[:gapopen]}>", Float, "gap opening penalty") {|v| opt[:gapopen] = v }
|
33
|
+
op.on("--gapext <#{opt[:gapext]}>", Float, "gap extension penalty") {|v| opt[:gapext] = v }
|
34
|
+
op.on("--dnamatrix <String>", "DNA weight matrix IUB|CLUSTALW") {|v| opt[:dnamatrix] = v }
|
35
|
+
op.separator " "
|
36
|
+
op.on("-n", "--no-consensus", "use original seq for fidelity (not cons.)") {|v| opt[:consensus_fidelity] = false }
|
37
|
+
op.separator " "
|
38
|
+
op.separator "the first sequence is assumed the template sequence"
|
39
|
+
|
40
|
+
end
|
41
|
+
|
42
|
+
if ARGV.size == 0
|
43
|
+
puts op
|
44
|
+
exit
|
45
|
+
end
|
46
|
+
|
47
|
+
|
48
|
+
labels = nil
|
49
|
+
files = ARGV.map
|
50
|
+
fasta_entries = files.inject([]) {|ar, file| ar.push( *fasta_entries(file) ) }
|
51
|
+
bioseqs = fasta_entries.map {|entry| Bio::Sequence::NA.new(entry.seq) }
|
52
|
+
labels = fasta_entries.map {|entry| entry.definition }
|
53
|
+
|
54
|
+
pairwise = DNAReads.align_pairwise(bioseqs, opt)
|
55
|
+
|
56
|
+
(template, others) = DNAReads.merge_pairwise(pairwise)
|
57
|
+
template_label = labels.shift
|
58
|
+
|
59
|
+
DNAReads.print_align(STDOUT, others, labels, :template => template, :template_label => template_label, :chars => 30)
|
60
|
+
|
61
|
+
|
@@ -0,0 +1,59 @@
|
|
1
|
+
#!/usr/bin/ruby
|
2
|
+
|
3
|
+
require 'bio'
|
4
|
+
require 'optparse'
|
5
|
+
|
6
|
+
opt = {
|
7
|
+
:frameshift => 0
|
8
|
+
}
|
9
|
+
op = OptionParser.new do |op|
|
10
|
+
op.banner = "usage: #{File.basename(__FILE__)} <dnaseq>.fasta"
|
11
|
+
op.on("-s", "--shift <int>", Integer, "frameshift") {|v| opt[:frameshift] = v }
|
12
|
+
end
|
13
|
+
op.parse!
|
14
|
+
|
15
|
+
frameshift = opt[:frameshift]
|
16
|
+
p frameshift
|
17
|
+
|
18
|
+
if ARGV.size == 0
|
19
|
+
puts op
|
20
|
+
exit
|
21
|
+
end
|
22
|
+
|
23
|
+
file = ARGV.shift
|
24
|
+
string = IO.read(file).split("\n").reject {|line| line =~ /^\#/ }.join("\n")
|
25
|
+
st = StringIO.new(string)
|
26
|
+
ff = Bio::FlatFile.auto(st)
|
27
|
+
|
28
|
+
seqs = []
|
29
|
+
ff.each_entry do |entry|
|
30
|
+
seq = entry.seq
|
31
|
+
seqs << seq[frameshift..-1]
|
32
|
+
end
|
33
|
+
|
34
|
+
length = 70
|
35
|
+
|
36
|
+
seqs.each do |seq|
|
37
|
+
bsq = Bio::Sequence::NA.new(seq)
|
38
|
+
protseq = bsq.translate
|
39
|
+
start = 0
|
40
|
+
loop do
|
41
|
+
break if start >= seq.length
|
42
|
+
frag = seq[start, length]
|
43
|
+
puts frag
|
44
|
+
prot_line = (start...(start+length)).to_a.map do |x|
|
45
|
+
if x % 3 == 0
|
46
|
+
prot_i = x / 3
|
47
|
+
protseq[prot_i,1]
|
48
|
+
else
|
49
|
+
" "
|
50
|
+
end
|
51
|
+
end.join
|
52
|
+
puts prot_line
|
53
|
+
start += length
|
54
|
+
end
|
55
|
+
print "NUM START/STOP CODONS: "
|
56
|
+
puts protseq.to_s.split("").select {|v| v == '*' }.size
|
57
|
+
end
|
58
|
+
|
59
|
+
|
@@ -0,0 +1,313 @@
|
|
1
|
+
|
2
|
+
|
3
|
+
module Bio
|
4
|
+
module Alignment
|
5
|
+
module DNASequenceReads
|
6
|
+
|
7
|
+
module_function
|
8
|
+
CLUSTALW_OPTS = %w(gapopen gapext dnamatrix type)
|
9
|
+
|
10
|
+
# returns the index of the starting run of good chars
|
11
|
+
def find_start_good_section(iupac_concensus_string, min_length)
|
12
|
+
good_char_count = 0
|
13
|
+
char_index = 0
|
14
|
+
iupac_concensus_string.each_char do |char|
|
15
|
+
if char =~ /[^\?\-Nn]/
|
16
|
+
good_char_count += 1
|
17
|
+
if good_char_count >= min_length
|
18
|
+
break
|
19
|
+
end
|
20
|
+
else
|
21
|
+
good_char_count = 0
|
22
|
+
end
|
23
|
+
char_index += 1
|
24
|
+
end
|
25
|
+
char_index - (good_char_count - 1)
|
26
|
+
end
|
27
|
+
|
28
|
+
# returns (start, length) where min_length reads are correct
|
29
|
+
def find_good_section(iupac_concensus_string, min_length)
|
30
|
+
start = find_start_good_section(iupac_concensus_string, min_length)
|
31
|
+
from_end = find_start_good_section(iupac_concensus_string.reverse, min_length)
|
32
|
+
length = iupac_concensus_string.length - start - from_end
|
33
|
+
if length < 0
|
34
|
+
nil
|
35
|
+
else
|
36
|
+
[start, length]
|
37
|
+
end
|
38
|
+
end
|
39
|
+
|
40
|
+
def hash_opts_to_clustalopts(hash)
|
41
|
+
array = []
|
42
|
+
hash.each do |k,v|
|
43
|
+
if CLUSTALW_OPTS.include?(k.to_s)
|
44
|
+
array << "-#{k}=#{v}"
|
45
|
+
end
|
46
|
+
end
|
47
|
+
array
|
48
|
+
end
|
49
|
+
|
50
|
+
def lstrip_dash(string)
|
51
|
+
chr = first_non_dash_char(string)
|
52
|
+
string[chr..-1]
|
53
|
+
end
|
54
|
+
|
55
|
+
def strip_dash(string)
|
56
|
+
ls = lstrip_dash(string)
|
57
|
+
lstrip_dash(ls.reverse).reverse
|
58
|
+
end
|
59
|
+
|
60
|
+
def first_non_dash_char(string)
|
61
|
+
char_cnt = 0
|
62
|
+
string.each_char do |char|
|
63
|
+
if char != '-'
|
64
|
+
break
|
65
|
+
end
|
66
|
+
char_cnt += 1
|
67
|
+
end
|
68
|
+
char_cnt
|
69
|
+
end
|
70
|
+
|
71
|
+
def clustal_align(bioseqs, factory)
|
72
|
+
al = Bio::Alignment.new(bioseqs)
|
73
|
+
al.do_align(factory)
|
74
|
+
end
|
75
|
+
|
76
|
+
ALIGN_OPTS = {
|
77
|
+
:type => 'DNA',
|
78
|
+
:gapopen => 20,
|
79
|
+
:gapext => 20,
|
80
|
+
:dnamatrix => 'IUB', # "IUB" || "CLUSTALW"
|
81
|
+
:fidelity_length => 10,
|
82
|
+
:consensus_fidelity => true,
|
83
|
+
}
|
84
|
+
|
85
|
+
# returns high quality pairwise alignments
|
86
|
+
# based on the fidelity_length option
|
87
|
+
def align_pairwise(bioseqs, opt={})
|
88
|
+
factory = Bio::ClustalW.new
|
89
|
+
clustal_opts = hash_opts_to_clustalopts(opt)
|
90
|
+
factory.options = clustal_opts
|
91
|
+
template = bioseqs.shift
|
92
|
+
start_length = []
|
93
|
+
pairwise_aligns = bioseqs.map do |bseq|
|
94
|
+
clust_al = clustal_align([template, bseq], factory)
|
95
|
+
cl_cons = clust_al.consensus
|
96
|
+
aligned_string = clust_al[1].to_s
|
97
|
+
#(st, len) = find_good_section(aligned_string, opt[:fidelity_length])
|
98
|
+
seq_to_use =
|
99
|
+
if opt[:consensus_fidelity]
|
100
|
+
cl_cons
|
101
|
+
else
|
102
|
+
aligned_string
|
103
|
+
end
|
104
|
+
(st, len) = find_good_section(seq_to_use, opt[:fidelity_length])
|
105
|
+
if st
|
106
|
+
pristine = aligned_string[st, len].gsub('-','') # pristine read (ends removed)
|
107
|
+
clustal_align([template.to_s, Bio::Sequence::NA.new(pristine)], factory)
|
108
|
+
else
|
109
|
+
warn "a sequence does not meeting min fidelity! using original alignment"
|
110
|
+
clust_al
|
111
|
+
end
|
112
|
+
|
113
|
+
end
|
114
|
+
end
|
115
|
+
|
116
|
+
# assumes all were aligned to the same template (the first of a pair)
|
117
|
+
def merge_pairwise(aligns)
|
118
|
+
ps = aligns.map do |align|
|
119
|
+
seqs = []
|
120
|
+
align.each do |bioseq|
|
121
|
+
seqs << bioseq.to_s
|
122
|
+
end
|
123
|
+
seqs
|
124
|
+
end
|
125
|
+
template = []
|
126
|
+
#m,x,n
|
127
|
+
x = 2
|
128
|
+
ftemp = ps.first.first
|
129
|
+
nmax = ps.map {|pair| pair.first.size }.max
|
130
|
+
mmax = ps.size
|
131
|
+
mar = (0...mmax).to_a
|
132
|
+
others = mar.map { [] }
|
133
|
+
ns = mar.map { 0 }
|
134
|
+
tn = 0
|
135
|
+
on = 0
|
136
|
+
(0...nmax).each do |n|
|
137
|
+
(t_dsh, t_no_dsh) = mar.partition do |m|
|
138
|
+
# this is RUBY 1.8 ONLY!!
|
139
|
+
ps[m][0][ns[m]] == 45 # '-' is ascii 45
|
140
|
+
end
|
141
|
+
|
142
|
+
# if a template has a dash, all other off-templates need a dash
|
143
|
+
if t_dsh.size > 0
|
144
|
+
template[tn] = 45
|
145
|
+
t_no_dsh.each do |m|
|
146
|
+
# don't update these guys counter
|
147
|
+
others[m][tn] = 45
|
148
|
+
end
|
149
|
+
t_dsh.each do |m|
|
150
|
+
others[m][tn] = ps[m][1][ns[m]]
|
151
|
+
ns[m] += 1
|
152
|
+
end
|
153
|
+
else # no dashes in the template
|
154
|
+
t_no_dsh.each do |m|
|
155
|
+
others[m][tn] = ps[m][1][ns[m]]
|
156
|
+
end
|
157
|
+
template[tn] = ps[0][0][ns[0]]
|
158
|
+
ns.map!{|v| v+1 }
|
159
|
+
end
|
160
|
+
tn += 1
|
161
|
+
end
|
162
|
+
[cs_to_s(template), others.map! {|ar| cs_to_s(ar) } ]
|
163
|
+
end
|
164
|
+
|
165
|
+
def cs_to_s(ar)
|
166
|
+
ar.map {|v| v.nil? ? '-' : v.chr }.join
|
167
|
+
end
|
168
|
+
|
169
|
+
# adjust all pairwise alignments to fit each other
|
170
|
+
|
171
|
+
#consensus_template = []
|
172
|
+
#max_length = pairs_of_strings.map {|pair| pair.first.size }.max
|
173
|
+
#(0...max_length).each do |n|
|
174
|
+
# pairs_of_strings.map {|pair| pair.map {|st| st[n] } }
|
175
|
+
#end
|
176
|
+
|
177
|
+
# assumes the first is the template
|
178
|
+
def consensus_string_and_stats(strings)
|
179
|
+
as_chars = strings.map {|v| v.split("") }
|
180
|
+
stats = Array.new(6, 0)
|
181
|
+
consensus_string = as_chars.shift.zip(*as_chars).map do |chrs|
|
182
|
+
consensus_bool_ar = Array.new(6)
|
183
|
+
symbols = [' '] + %w(^ = . ^ ?)
|
184
|
+
all_gaps = 0
|
185
|
+
template_gap = 1
|
186
|
+
agreement = 2
|
187
|
+
gap_below_template = 3
|
188
|
+
all_bad_matches = 4
|
189
|
+
non_consensus = 5
|
190
|
+
|
191
|
+
first = chrs.shift
|
192
|
+
if [first, *chrs].all? {|v| v.nil? or (v == '-') }
|
193
|
+
consensus_bool_ar[all_gaps] = true
|
194
|
+
elsif first == '-'
|
195
|
+
consensus_bool_ar[template_gap] = true
|
196
|
+
elsif chrs.all? {|v| v == '-'}
|
197
|
+
consensus_bool_ar[gap_below_template] = true
|
198
|
+
elsif chrs.all? {|v| (v == '-') or (v == first) }
|
199
|
+
consensus_bool_ar[agreement] = true
|
200
|
+
elsif chrs.all? {|v| (v == '-') or (v != first) }
|
201
|
+
consensus_bool_ar[all_bad_matches] = true
|
202
|
+
else
|
203
|
+
consensus_bool_ar[non_consensus] = true
|
204
|
+
end
|
205
|
+
consensus_bool_ar.each_with_index {|v,i| stats[i] += 1 if v }
|
206
|
+
symbols[consensus_bool_ar.index(true)]
|
207
|
+
end.join
|
208
|
+
[consensus_string, stats]
|
209
|
+
end
|
210
|
+
|
211
|
+
|
212
|
+
def exactly_chars(string, n)
|
213
|
+
at_least = "%#{n}s" % string
|
214
|
+
at_least[0,n]
|
215
|
+
end
|
216
|
+
|
217
|
+
|
218
|
+
# all gaps <blank>
|
219
|
+
# template gap ^
|
220
|
+
# gap below template .
|
221
|
+
# agreement =
|
222
|
+
# all bad matches ^
|
223
|
+
# non-consensus ?
|
224
|
+
#
|
225
|
+
# accepts :template => template_sequence
|
226
|
+
def print_align(io, sequences, labels, opts={})
|
227
|
+
opts = {:cutoff => 70, :start => 0, :chars => 20}.merge(opts)
|
228
|
+
(start, length, chars) = opts.values_at(:start, :cutoff, :chars)
|
229
|
+
spacer = " "
|
230
|
+
|
231
|
+
if opts[:template]
|
232
|
+
sequences.unshift(opts[:template])
|
233
|
+
labels.unshift(opts[:template_label])
|
234
|
+
end
|
235
|
+
|
236
|
+
all_stats = Array.new(6,0)
|
237
|
+
loop do
|
238
|
+
fin = false
|
239
|
+
|
240
|
+
max_length = 0
|
241
|
+
lines = []
|
242
|
+
consensus_line = ""
|
243
|
+
fragments = sequences.map do |string|
|
244
|
+
fin = (start >= string.length )
|
245
|
+
break if fin
|
246
|
+
|
247
|
+
string_frag = string[start, length]
|
248
|
+
|
249
|
+
string_frag
|
250
|
+
end ; break if fin
|
251
|
+
|
252
|
+
doubles = fragments.zip(labels)
|
253
|
+
|
254
|
+
doubles = doubles.select {|frag, _| (frag.size > 0) && (frag =~ /[^-]/) }
|
255
|
+
|
256
|
+
max_length = doubles.map {|frag, _| frag.size }.max
|
257
|
+
|
258
|
+
(cs, stats) = consensus_string_and_stats( doubles.map {|frag,_| frag } )
|
259
|
+
all_stats = all_stats.zip(stats).map {|a,b| a + b }
|
260
|
+
|
261
|
+
doubles.push( [cs, "<CONSENSUS>"] )
|
262
|
+
|
263
|
+
lines = doubles.map {|frag, label| [exactly_chars(label, chars),spacer,frag].join }
|
264
|
+
|
265
|
+
## the counters at the top of the line
|
266
|
+
start_s = start.to_s
|
267
|
+
finish_s = (start + max_length).to_s
|
268
|
+
count_line_gap = max_length - (start_s.size + finish_s.size)
|
269
|
+
count_line = [start_s, spacer]
|
270
|
+
unless count_line_gap < 1
|
271
|
+
count_line << " " * count_line_gap
|
272
|
+
end
|
273
|
+
io.puts [exactly_chars("", chars), spacer, count_line.join].join
|
274
|
+
|
275
|
+
io.puts lines.join("\n")
|
276
|
+
|
277
|
+
io.puts " " # separator between lines
|
278
|
+
start += length
|
279
|
+
end
|
280
|
+
end
|
281
|
+
|
282
|
+
# # accepts :template => template_sequence
|
283
|
+
#def print_align(io, sequences, labels, opts={})
|
284
|
+
#opts = {:cutoff => 100, :start => 0, :chars => 20}.merge(opts)
|
285
|
+
#(start, length, chars) = opts.values_at(:start, :cutoff, :chars)
|
286
|
+
#spacer = " "
|
287
|
+
|
288
|
+
#loop do
|
289
|
+
#fin = false
|
290
|
+
|
291
|
+
### the counters at the top of the line
|
292
|
+
#start_s = start.to_s
|
293
|
+
#finish_s = (start + length).to_s
|
294
|
+
#count_line_gap = length - (start_s.size + finish_s.size)
|
295
|
+
|
296
|
+
#count_line = [start_s, " " * count_line_gap, finish_s].join
|
297
|
+
#io.puts [exactly_chars("", chars), spacer, count_line].join
|
298
|
+
|
299
|
+
#sequences.zip(labels) do |string, label|
|
300
|
+
#fin = (start >= string.length )
|
301
|
+
#break if fin
|
302
|
+
#io.puts "#{exactly_chars(label, chars)}#{spacer}#{string[start,length]}"
|
303
|
+
#end
|
304
|
+
#io.puts " "
|
305
|
+
#break if fin
|
306
|
+
#start += length
|
307
|
+
#end
|
308
|
+
#end
|
309
|
+
|
310
|
+
|
311
|
+
end
|
312
|
+
end
|
313
|
+
end
|