bio-alignment 0.0.3 → 0.0.4
Sign up to get free protection for your applications and to get access to all the features.
- data/README.md +20 -5
- data/VERSION +1 -1
- data/features/bioruby-feature.rb +80 -0
- data/features/bioruby.feature +23 -0
- data/lib/bio-alignment/alignment.rb +5 -0
- data/lib/bio-alignment/bioruby.rb +22 -0
- data/lib/bio-alignment/pal2nal.rb +3 -3
- metadata +20 -17
data/README.md
CHANGED
@@ -41,6 +41,19 @@ aligmment (note codon gaps are represented by '---')
|
|
41
41
|
end
|
42
42
|
```
|
43
43
|
|
44
|
+
### BioRuby Sequence objects
|
45
|
+
|
46
|
+
The BioAlignment supports BioRuby's Bio::Sequence objects:
|
47
|
+
|
48
|
+
```ruby
|
49
|
+
require 'bio' # BioRuby
|
50
|
+
require 'bio-alignment/bioruby' # make Bio::Sequence enumerable
|
51
|
+
|
52
|
+
aln = Alignment.new
|
53
|
+
aln << Bio::Sequence::NA.new("atgcatgcaaaa")
|
54
|
+
aln << Bio::Sequence::NA.new("atg---tcaaaa")
|
55
|
+
```
|
56
|
+
|
44
57
|
### Pal2nal
|
45
58
|
|
46
59
|
A protein (amino acid) to nucleotide alignment would first load
|
@@ -82,16 +95,18 @@ Write a (simple) version of pal2nal would be something like
|
|
82
95
|
end
|
83
96
|
```
|
84
97
|
|
85
|
-
With amino acid aln1 and nucleotide aln2 loaded, the library version
|
98
|
+
With amino acid aln1 and nucleotide aln2 loaded, the library version
|
99
|
+
includes validation, and is the shorter command
|
86
100
|
|
87
101
|
```ruby
|
88
|
-
aln3 = aln1.pal2nal(aln2)
|
102
|
+
aln3 = aln1.pal2nal(aln2, :codon_table => 3)
|
89
103
|
```
|
90
104
|
|
91
|
-
|
105
|
+
resulting in the codon alignment.
|
92
106
|
|
93
|
-
The API documentation is online. For more code examples see
|
94
|
-
./
|
107
|
+
The API documentation is online. For more code examples see
|
108
|
+
[./spec/*.rb](https://github.com/pjotrp/bioruby-alignment/tree/master/spec) and
|
109
|
+
[./features/*](https://github.com/pjotrp/bioruby-alignment/tree/master/features).
|
95
110
|
|
96
111
|
## Cite
|
97
112
|
|
data/VERSION
CHANGED
@@ -1 +1 @@
|
|
1
|
-
0.0.
|
1
|
+
0.0.4
|
@@ -0,0 +1,80 @@
|
|
1
|
+
require 'bio' # yes, we use BioRuby here
|
2
|
+
|
3
|
+
$: << 'lib'
|
4
|
+
|
5
|
+
require 'bio-alignment/bioruby'
|
6
|
+
|
7
|
+
Given /^I have multiple Bio::Sequence objects$/ do
|
8
|
+
@list = []
|
9
|
+
# Read a Fasta file
|
10
|
+
fasta = Bio::FlatFile.open(Bio::FastaFormat, 'test/data/fasta/codon/codon-alignment.fa')
|
11
|
+
fasta.each_entry do |f|
|
12
|
+
naseq = f.naseq
|
13
|
+
# test we can index the sequence
|
14
|
+
['a','-'].index(naseq[0]).should_not be nil
|
15
|
+
@list << naseq # inject Bio::Sequence object
|
16
|
+
end
|
17
|
+
end
|
18
|
+
|
19
|
+
When /^I assign BioAlignment$/ do
|
20
|
+
@aln = Alignment.new
|
21
|
+
end
|
22
|
+
|
23
|
+
Then /^it should accept the objects$/ do
|
24
|
+
@list.each do | bioruby_naseq |
|
25
|
+
@aln.sequences << bioruby_naseq
|
26
|
+
end
|
27
|
+
end
|
28
|
+
|
29
|
+
Then /^and return a partial sequence$/ do
|
30
|
+
@aln.rows[0][0..8].should == 'atgcccact'
|
31
|
+
end
|
32
|
+
|
33
|
+
Then /^be indexable$/ do
|
34
|
+
@aln.rows[0][0].should == 'a'
|
35
|
+
end
|
36
|
+
|
37
|
+
# ---
|
38
|
+
|
39
|
+
Given /^I have multiple Bio::Sequence::AA objects$/ do
|
40
|
+
@aalist = []
|
41
|
+
# Read a Fasta file
|
42
|
+
fasta = Bio::FlatFile.open(Bio::FastaFormat, 'test/data/fasta/codon/aa-alignment.fa')
|
43
|
+
fasta.each_entry do |f|
|
44
|
+
aaseq = f.aaseq
|
45
|
+
@aalist << aaseq # inject Bio::Sequence object
|
46
|
+
end
|
47
|
+
end
|
48
|
+
|
49
|
+
When /^I assign BioAlignment for AA$/ do
|
50
|
+
@aa_aln = Alignment.new
|
51
|
+
end
|
52
|
+
|
53
|
+
Then /^it should accept the Bio::Sequence::AA objects$/ do
|
54
|
+
@aalist.each do | bioruby_aaseq |
|
55
|
+
@aa_aln.sequences << bioruby_aaseq
|
56
|
+
end
|
57
|
+
end
|
58
|
+
|
59
|
+
Then /^and return a partial AA sequence$/ do
|
60
|
+
@aa_aln.rows[0][0..8].should == 'MPTRLDIVG'
|
61
|
+
end
|
62
|
+
|
63
|
+
Then /^be AA indexable$/ do
|
64
|
+
@aa_aln.rows[0][0].should == 'M'
|
65
|
+
end
|
66
|
+
|
67
|
+
# ----
|
68
|
+
|
69
|
+
Given /^I have a BioAlignment$/ do
|
70
|
+
pending # express the regexp above with the code you wish you had
|
71
|
+
end
|
72
|
+
|
73
|
+
When /^I convert$/ do
|
74
|
+
pending # express the regexp above with the code you wish you had
|
75
|
+
end
|
76
|
+
|
77
|
+
Then /^I should have a Bio::Alignment$/ do
|
78
|
+
pending # express the regexp above with the code you wish you had
|
79
|
+
end
|
80
|
+
|
@@ -0,0 +1,23 @@
|
|
1
|
+
Feature: BioAlignment should play with BioRuby
|
2
|
+
In order to use BioRuby functionality
|
3
|
+
I want to convert BioAlignment to Bio::Alignment
|
4
|
+
And I want to support Bio::Sequence objects
|
5
|
+
|
6
|
+
Scenario: Use Bio::Sequence to fill BioAlignment
|
7
|
+
Given I have multiple Bio::Sequence objects
|
8
|
+
When I assign BioAlignment
|
9
|
+
Then it should accept the objects
|
10
|
+
And and return a partial sequence
|
11
|
+
And be indexable
|
12
|
+
|
13
|
+
Scenario: Use Bio::Sequence to fill BioAlignment with AA
|
14
|
+
Given I have multiple Bio::Sequence::AA objects
|
15
|
+
When I assign BioAlignment for AA
|
16
|
+
Then it should accept the Bio::Sequence::AA objects
|
17
|
+
And and return a partial AA sequence
|
18
|
+
And be AA indexable
|
19
|
+
|
20
|
+
Scenario: Convert BioAlignment to Bio::Alignment
|
21
|
+
Given I have a BioAlignment
|
22
|
+
When I convert
|
23
|
+
Then I should have a Bio::Alignment
|
@@ -3,6 +3,7 @@
|
|
3
3
|
require 'bio-alignment/pal2nal'
|
4
4
|
|
5
5
|
module Bio
|
6
|
+
|
6
7
|
module BioAlignment
|
7
8
|
|
8
9
|
class Alignment
|
@@ -17,6 +18,10 @@ module Bio
|
|
17
18
|
|
18
19
|
alias rows sequences
|
19
20
|
|
21
|
+
# def [] index <- need matrix
|
22
|
+
# rows[index]
|
23
|
+
# end
|
24
|
+
|
20
25
|
def each
|
21
26
|
rows.each { | seq | yield seq }
|
22
27
|
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
module Bio
|
2
|
+
# Here we override BioRuby Sequence classes, so they are enumerable
|
3
|
+
class Sequence
|
4
|
+
class NA
|
5
|
+
include Enumerable
|
6
|
+
def each
|
7
|
+
to_s.each_byte do | c |
|
8
|
+
yield c
|
9
|
+
end
|
10
|
+
end
|
11
|
+
end
|
12
|
+
class AA
|
13
|
+
include Enumerable
|
14
|
+
def each
|
15
|
+
to_s.each_byte do | c |
|
16
|
+
yield c
|
17
|
+
end
|
18
|
+
end
|
19
|
+
end
|
20
|
+
end
|
21
|
+
end
|
22
|
+
|
@@ -3,14 +3,14 @@
|
|
3
3
|
module Bio
|
4
4
|
module BioAlignment
|
5
5
|
module Pal2Nal
|
6
|
-
def pal2nal nt_aln
|
6
|
+
def pal2nal nt_aln, options = { :codon_table => 1 }
|
7
7
|
aa_aln = self
|
8
8
|
codon_aln = Alignment.new
|
9
9
|
aa_aln.each_with_index do | aaseq, i |
|
10
10
|
ntseq = nt_aln.sequences[i]
|
11
11
|
raise "pal2nal sequence IDs do not match (for #{aaseq.id} != #{ntseq.id})" if aaseq.id != ntseq.id
|
12
12
|
raise "pal2nal sequence size does not match (for #{aaseq.id}'s #{aaseq.to_s.size}!= #{ntseq.to_s.size * 3})" if aaseq.id != ntseq.id
|
13
|
-
codonseq = CodonSequence.new(ntseq.id, ntseq.seq)
|
13
|
+
codonseq = CodonSequence.new(ntseq.id, ntseq.seq, options)
|
14
14
|
|
15
15
|
codon_pos = 0
|
16
16
|
result = []
|
@@ -26,7 +26,7 @@ module Bio
|
|
26
26
|
codon.to_s
|
27
27
|
end
|
28
28
|
end
|
29
|
-
codon_seq = CodonSequence.new(aaseq.id, result.join(''))
|
29
|
+
codon_seq = CodonSequence.new(aaseq.id, result.join(''), options)
|
30
30
|
codon_aln.sequences << codon_seq
|
31
31
|
end
|
32
32
|
codon_aln
|
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: bio-alignment
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.0.
|
4
|
+
version: 0.0.4
|
5
5
|
prerelease:
|
6
6
|
platform: ruby
|
7
7
|
authors:
|
@@ -9,11 +9,11 @@ authors:
|
|
9
9
|
autorequire:
|
10
10
|
bindir: bin
|
11
11
|
cert_chain: []
|
12
|
-
date: 2012-02-
|
12
|
+
date: 2012-02-06 00:00:00.000000000Z
|
13
13
|
dependencies:
|
14
14
|
- !ruby/object:Gem::Dependency
|
15
15
|
name: bio-logger
|
16
|
-
requirement: &
|
16
|
+
requirement: &16310560 !ruby/object:Gem::Requirement
|
17
17
|
none: false
|
18
18
|
requirements:
|
19
19
|
- - ! '>='
|
@@ -21,10 +21,10 @@ dependencies:
|
|
21
21
|
version: '0'
|
22
22
|
type: :runtime
|
23
23
|
prerelease: false
|
24
|
-
version_requirements: *
|
24
|
+
version_requirements: *16310560
|
25
25
|
- !ruby/object:Gem::Dependency
|
26
26
|
name: bio
|
27
|
-
requirement: &
|
27
|
+
requirement: &16309720 !ruby/object:Gem::Requirement
|
28
28
|
none: false
|
29
29
|
requirements:
|
30
30
|
- - ! '>='
|
@@ -32,10 +32,10 @@ dependencies:
|
|
32
32
|
version: 1.4.2
|
33
33
|
type: :runtime
|
34
34
|
prerelease: false
|
35
|
-
version_requirements: *
|
35
|
+
version_requirements: *16309720
|
36
36
|
- !ruby/object:Gem::Dependency
|
37
37
|
name: bio-bigbio
|
38
|
-
requirement: &
|
38
|
+
requirement: &16309060 !ruby/object:Gem::Requirement
|
39
39
|
none: false
|
40
40
|
requirements:
|
41
41
|
- - ! '>'
|
@@ -43,10 +43,10 @@ dependencies:
|
|
43
43
|
version: 0.1.3
|
44
44
|
type: :development
|
45
45
|
prerelease: false
|
46
|
-
version_requirements: *
|
46
|
+
version_requirements: *16309060
|
47
47
|
- !ruby/object:Gem::Dependency
|
48
48
|
name: cucumber
|
49
|
-
requirement: &
|
49
|
+
requirement: &16308000 !ruby/object:Gem::Requirement
|
50
50
|
none: false
|
51
51
|
requirements:
|
52
52
|
- - ! '>='
|
@@ -54,10 +54,10 @@ dependencies:
|
|
54
54
|
version: '0'
|
55
55
|
type: :development
|
56
56
|
prerelease: false
|
57
|
-
version_requirements: *
|
57
|
+
version_requirements: *16308000
|
58
58
|
- !ruby/object:Gem::Dependency
|
59
59
|
name: rspec
|
60
|
-
requirement: &
|
60
|
+
requirement: &16306500 !ruby/object:Gem::Requirement
|
61
61
|
none: false
|
62
62
|
requirements:
|
63
63
|
- - ~>
|
@@ -65,10 +65,10 @@ dependencies:
|
|
65
65
|
version: 2.3.0
|
66
66
|
type: :development
|
67
67
|
prerelease: false
|
68
|
-
version_requirements: *
|
68
|
+
version_requirements: *16306500
|
69
69
|
- !ruby/object:Gem::Dependency
|
70
70
|
name: bundler
|
71
|
-
requirement: &
|
71
|
+
requirement: &16305460 !ruby/object:Gem::Requirement
|
72
72
|
none: false
|
73
73
|
requirements:
|
74
74
|
- - ~>
|
@@ -76,10 +76,10 @@ dependencies:
|
|
76
76
|
version: 1.0.0
|
77
77
|
type: :development
|
78
78
|
prerelease: false
|
79
|
-
version_requirements: *
|
79
|
+
version_requirements: *16305460
|
80
80
|
- !ruby/object:Gem::Dependency
|
81
81
|
name: jeweler
|
82
|
-
requirement: &
|
82
|
+
requirement: &16304680 !ruby/object:Gem::Requirement
|
83
83
|
none: false
|
84
84
|
requirements:
|
85
85
|
- - ~>
|
@@ -87,7 +87,7 @@ dependencies:
|
|
87
87
|
version: 1.7.0
|
88
88
|
type: :development
|
89
89
|
prerelease: false
|
90
|
-
version_requirements: *
|
90
|
+
version_requirements: *16304680
|
91
91
|
description: Alignment handler for multiple sequence alignments (MSA)
|
92
92
|
email: pjotr.public01@thebird.nl
|
93
93
|
executables:
|
@@ -106,12 +106,15 @@ files:
|
|
106
106
|
- VERSION
|
107
107
|
- bin/bio-alignment
|
108
108
|
- doc/bio-alignment-design.md
|
109
|
+
- features/bioruby-feature.rb
|
110
|
+
- features/bioruby.feature
|
109
111
|
- features/codon-feature.rb
|
110
112
|
- features/codon.feature
|
111
113
|
- features/pal2nal-feature.rb
|
112
114
|
- features/pal2nal.feature
|
113
115
|
- lib/bio-alignment.rb
|
114
116
|
- lib/bio-alignment/alignment.rb
|
117
|
+
- lib/bio-alignment/bioruby.rb
|
115
118
|
- lib/bio-alignment/codonsequence.rb
|
116
119
|
- lib/bio-alignment/pal2nal.rb
|
117
120
|
- lib/bio-alignment/sequence.rb
|
@@ -138,7 +141,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
|
|
138
141
|
version: '0'
|
139
142
|
segments:
|
140
143
|
- 0
|
141
|
-
hash: -
|
144
|
+
hash: -237499918493109825
|
142
145
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
143
146
|
none: false
|
144
147
|
requirements:
|