exodb 0.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/contributors.txt +1 -0
- data/exodb.gemspec +35 -0
- data/genome/process_genome_seq.rb +22 -0
- data/lib/exodb/addon/string.rb +26 -0
- data/lib/exodb/addon.rb +13 -0
- data/lib/exodb/datamodel/locationfield.rb +103 -0
- data/lib/exodb/datamodel/reference.rb +387 -0
- data/lib/exodb/datamodel/region.rb +51 -0
- data/lib/exodb/datamodel/source.rb +122 -0
- data/lib/exodb/datamodel/variant.rb +89 -0
- data/lib/exodb/datamodel/xrefsfield.rb +42 -0
- data/lib/exodb/datamodel.rb +19 -0
- data/lib/exodb/dbconnection.rb +83 -0
- data/lib/exodb/exception.rb +18 -0
- data/lib/exodb/usermanage.rb +84 -0
- data/lib/exodb/utils/upload_generef.rb +163 -0
- data/lib/exodb/utils/upload_var.rb +60 -0
- data/lib/exodb/utils.rb +42 -0
- data/lib/exodb/vcf.rb +193 -0
- data/lib/exodb/version.rb +15 -0
- data/lib/exodb.rb +44 -0
- data/session.yml +6 -0
- metadata +122 -0
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: bd0cec2b7ef4791ab9686827bf8d31409152af2a
|
4
|
+
data.tar.gz: 117c7eb770d5473a76909af778017f2557288982
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 6b7cd7602e7bda8da25c1799e5fbc0fd3221e04397b52a54cb4c1b5b2691b6cfea96d1e114bfc1f218529d747614544876da7eb78d8258ef3ee41a082d22eee2
|
7
|
+
data.tar.gz: 5699679e8fb8834af7c4e7f42ca2f399c549c015b1fa07781240a9a9f76d01a56951ba72af04645254232d588a6c1c9424034f23ec03791098bd57a0e3d5bf3c
|
data/contributors.txt
ADDED
@@ -0,0 +1 @@
|
|
1
|
+
Natapol Pornputtapong
|
data/exodb.gemspec
ADDED
@@ -0,0 +1,35 @@
|
|
1
|
+
# -*- encoding: utf-8 -*-
|
2
|
+
$:.push File.expand_path("../lib", __FILE__)
|
3
|
+
require "exodb/version"
|
4
|
+
|
5
|
+
Gem::Specification.new do |s|
|
6
|
+
s.name = 'exodb'
|
7
|
+
s.version = Exodb::VERSION
|
8
|
+
s.date = '2014-10-31'
|
9
|
+
s.platform = Gem::Platform::RUBY
|
10
|
+
|
11
|
+
s.summary = "A library for exome sequencing data management development"
|
12
|
+
s.description = "A library for exome sequencing data management"
|
13
|
+
s.authors = ["Natapol Pornputtapong"]
|
14
|
+
s.email = 'natapol.por@gmail.com'
|
15
|
+
|
16
|
+
s.homepage = 'http://rubygems.org/gems/dactyls'
|
17
|
+
s.license = 'GPL'
|
18
|
+
|
19
|
+
# s.rubyforge_project = "neography"
|
20
|
+
|
21
|
+
s.files = `git ls-files`.split("\n")
|
22
|
+
s.test_files = `git ls-files -- {test,spec,features}/*`.split("\n")
|
23
|
+
s.executables = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
|
24
|
+
s.require_paths = ["lib"]
|
25
|
+
|
26
|
+
s.add_dependency "mongoid", "~> 3.1"
|
27
|
+
s.add_dependency "bio", "~> 1.4"
|
28
|
+
s.add_dependency "highline", "~> 1.6"
|
29
|
+
s.add_dependency "pry", "~> 0.10"
|
30
|
+
|
31
|
+
|
32
|
+
# s.add_development_dependency "rspec", ">= 2.11"
|
33
|
+
# s.add_dependency "httpclient", ">= 2.3.3"
|
34
|
+
|
35
|
+
end
|
@@ -0,0 +1,22 @@
|
|
1
|
+
#
|
2
|
+
# Exodus
|
3
|
+
# Copyright (C) 2014
|
4
|
+
#
|
5
|
+
# author: Natapol Pornputtapong <natapol.por@gmail.com>
|
6
|
+
#
|
7
|
+
# Documentation: Natapol Pornputtapong (RDoc'd and embellished by William Webber)
|
8
|
+
#
|
9
|
+
|
10
|
+
# raise "Please, use ruby 1.9.0 or later." if RUBY_VERSION < "1.9.0"
|
11
|
+
|
12
|
+
require 'bio'
|
13
|
+
|
14
|
+
|
15
|
+
Dir.glob('hs_ref_GRCh37*.fa').each do |file|
|
16
|
+
flatfile = Bio::FlatFile.open(Bio::FastaFormat, file)
|
17
|
+
flatfile.each do |e|
|
18
|
+
outfile = File.open("#{e.acc_version}.fa", 'w')
|
19
|
+
outfile.write(e.to_s)
|
20
|
+
outfile.close()
|
21
|
+
end
|
22
|
+
end
|
@@ -0,0 +1,26 @@
|
|
1
|
+
#
|
2
|
+
# Exodus
|
3
|
+
# Copyright (C) 2014
|
4
|
+
#
|
5
|
+
# author: Natapol Pornputtapong <natapol.por@gmail.com>
|
6
|
+
#
|
7
|
+
# Documentation: Natapol Pornputtapong (RDoc'd and embellished by William Webber)
|
8
|
+
#
|
9
|
+
|
10
|
+
# raise "Please, use ruby 1.9.0 or later." if RUBY_VERSION < "1.9.0"
|
11
|
+
|
12
|
+
class String
|
13
|
+
|
14
|
+
def is_miriam?
|
15
|
+
return self =~ /^urn:miriam:/
|
16
|
+
end
|
17
|
+
|
18
|
+
def id
|
19
|
+
return self.is_miriam? ? self.split(':', 4)[-1] : ''
|
20
|
+
end
|
21
|
+
|
22
|
+
def namespace
|
23
|
+
return self.is_miriam? ? self.split(':', 4)[2] : ''
|
24
|
+
end
|
25
|
+
|
26
|
+
end
|
data/lib/exodb/addon.rb
ADDED
@@ -0,0 +1,13 @@
|
|
1
|
+
#
|
2
|
+
# Exodus
|
3
|
+
# Copyright (C) 2014
|
4
|
+
#
|
5
|
+
# author: Natapol Pornputtapong <natapol.por@gmail.com>
|
6
|
+
#
|
7
|
+
# Documentation: Natapol Pornputtapong (RDoc'd and embellished by William Webber)
|
8
|
+
#
|
9
|
+
|
10
|
+
# raise "Please, use ruby 1.9.0 or later." if RUBY_VERSION < "1.9.0"
|
11
|
+
|
12
|
+
require 'exodb/addon/string.rb'
|
13
|
+
|
@@ -0,0 +1,103 @@
|
|
1
|
+
#
|
2
|
+
# Exodb
|
3
|
+
# Copyright (C) 2014
|
4
|
+
#
|
5
|
+
# author: Natapol Pornputtapong <natapol.por@gmail.com>
|
6
|
+
#
|
7
|
+
# Documentation: Natapol Pornputtapong (RDoc'd and embellished by William Webber)
|
8
|
+
#
|
9
|
+
|
10
|
+
# raise "Please, use ruby 1.9.0 or later." if RUBY_VERSION < "1.9.0"
|
11
|
+
|
12
|
+
module Exodb
|
13
|
+
|
14
|
+
module LocationField
|
15
|
+
|
16
|
+
extend ActiveSupport::Concern
|
17
|
+
|
18
|
+
included do
|
19
|
+
field :location, type: Hash #{chromosome: '', start: x, stop: x}
|
20
|
+
index({location: 1}, background: true)
|
21
|
+
end
|
22
|
+
|
23
|
+
module ClassMethods
|
24
|
+
|
25
|
+
def cover?(loc_str)
|
26
|
+
dat = loc_str.split(/(:|\.\.)/)
|
27
|
+
if dat[4]
|
28
|
+
querystr = {:'location.chromosome' => dat[0], :'location.start'.lte => dat[2].to_i, :'location.stop'.gte => dat[4].to_i}
|
29
|
+
else
|
30
|
+
querystr = {:'location.chromosome' => dat[0], :'location.start'.lte => dat[2].to_i, :'location.stop'.gte => dat[2].to_i}
|
31
|
+
end
|
32
|
+
return self.where(querystr)
|
33
|
+
end
|
34
|
+
|
35
|
+
def intersect?(loc_str)
|
36
|
+
dat = loc_str.split(/(:|\.\.)/)
|
37
|
+
querystr = {:'$or' => [{:'location.chromosome' => dat[0], :'location.start'.lte => dat[2].to_i, :'location.stop'.gte => dat[2].to_i}, {:'location.chromosome' => dat[0], :'location.start'.lte => dat[4].to_i, :'location.stop'.gte => dat[4].to_i}]}
|
38
|
+
return self.where(querystr)
|
39
|
+
end
|
40
|
+
|
41
|
+
def in?(loc_str)
|
42
|
+
dat = loc_str.split(/(:|\.\.)/)
|
43
|
+
querystr = {:'location.chromosome' => dat[0], :'location.start'.gte => dat[2].to_i, :'location.stop'.lte => dat[4].to_i}
|
44
|
+
return self.where(querystr)
|
45
|
+
end
|
46
|
+
|
47
|
+
#def converse
|
48
|
+
# self.where({}).each do |e|
|
49
|
+
# if e[:location][:coordinates]
|
50
|
+
# oldlocation = e[:location]
|
51
|
+
# if oldlocation[:coordinates][0].is_a?(Array)
|
52
|
+
# e[:location] = {chromosome: oldlocation[:coordinates][0][0], start: oldlocation[:coordinates][0][1], stop: oldlocation[:coordinates][1][1]}
|
53
|
+
# else
|
54
|
+
# e[:location] = {chromosome: oldlocation[:coordinates][0], start: oldlocation[:coordinates][1], stop: oldlocation[:coordinates][1]}
|
55
|
+
# end
|
56
|
+
# p e.save!
|
57
|
+
# end
|
58
|
+
# end
|
59
|
+
#end
|
60
|
+
end
|
61
|
+
|
62
|
+
# get the start position of gene rely on the genome
|
63
|
+
#
|
64
|
+
# @return [Integer] start position of gene
|
65
|
+
def start
|
66
|
+
self[:location]['start']
|
67
|
+
end
|
68
|
+
|
69
|
+
# get the end position of gene rely on the genome
|
70
|
+
#
|
71
|
+
# @return [Integer] end position of gene
|
72
|
+
def stop
|
73
|
+
self[:location]['stop']
|
74
|
+
end
|
75
|
+
|
76
|
+
alias_method :end, :stop
|
77
|
+
|
78
|
+
# get the chromosome
|
79
|
+
#
|
80
|
+
# @return [Integer] chromosome
|
81
|
+
def chromosome
|
82
|
+
self[:location]['chromosome']
|
83
|
+
end
|
84
|
+
|
85
|
+
# Assign gene location in format of chromosome_number:start..stop
|
86
|
+
#
|
87
|
+
# @param [String] gene location in format of chromosome_number:start..stop
|
88
|
+
def parse_location(loc_str)
|
89
|
+
dat = loc_str.split(/(:|\.\.)/)
|
90
|
+
if dat[4]
|
91
|
+
self[:location] = {chromosome: dat[0], start: dat[2].to_i, stop: dat[4].to_i}
|
92
|
+
else
|
93
|
+
self[:location] = {chromosome: dat[0], start: dat[2].to_i, stop: dat[2].to_i}
|
94
|
+
end
|
95
|
+
|
96
|
+
end
|
97
|
+
|
98
|
+
def location_str
|
99
|
+
return "#{self.chromosome}:#{[self.start, self.stop].uniq.join('..')}"
|
100
|
+
end
|
101
|
+
end
|
102
|
+
|
103
|
+
end
|
@@ -0,0 +1,387 @@
|
|
1
|
+
#
|
2
|
+
# Exodb
|
3
|
+
# Copyright (C) 2014
|
4
|
+
#
|
5
|
+
# author: Natapol Pornputtapong <natapol.por@gmail.com>
|
6
|
+
#
|
7
|
+
# Documentation: Natapol Pornputtapong (RDoc'd and embellished by William Webber)
|
8
|
+
#
|
9
|
+
|
10
|
+
# raise "Please, use ruby 1.9.0 or later." if RUBY_VERSION < "1.9.0"
|
11
|
+
|
12
|
+
module Exodb
|
13
|
+
|
14
|
+
class Reference
|
15
|
+
|
16
|
+
include Mongoid::Document
|
17
|
+
include Mongoid::Versioning
|
18
|
+
include Mongoid::Timestamps
|
19
|
+
|
20
|
+
include Exodb::XrefsField
|
21
|
+
|
22
|
+
field :oid, type: String
|
23
|
+
|
24
|
+
end
|
25
|
+
|
26
|
+
class Variantref < Reference
|
27
|
+
|
28
|
+
PATTERN = /(?<gene>[A-Z0-9]+)-?(?<position>[0-9,]*|[is]?)(?<to>[A-Z=]*)/
|
29
|
+
SILENTSIGN = '='
|
30
|
+
|
31
|
+
include Exodb::LocationField
|
32
|
+
|
33
|
+
field :reference, type: String
|
34
|
+
field :alternate, type: String
|
35
|
+
|
36
|
+
end
|
37
|
+
|
38
|
+
class Incidence
|
39
|
+
|
40
|
+
include Mongoid::Document
|
41
|
+
|
42
|
+
field :cancertype, type: String
|
43
|
+
field :position, type: String # refseq id of chromomose
|
44
|
+
field :occur, type: Array
|
45
|
+
field :casenumber, type: Integer
|
46
|
+
|
47
|
+
embedded_in :generef
|
48
|
+
|
49
|
+
end
|
50
|
+
|
51
|
+
class Generef < Reference
|
52
|
+
|
53
|
+
include Exodb::LocationField
|
54
|
+
|
55
|
+
field :sequence, type: String
|
56
|
+
field :chrrefseq, type: String # refseq id of chromomose
|
57
|
+
field :strand, type: String
|
58
|
+
field :psuedo, type: Boolean
|
59
|
+
field :genomeref, type: String
|
60
|
+
|
61
|
+
index({sequence: 'text'}, background: true)
|
62
|
+
|
63
|
+
has_many :genes
|
64
|
+
embeds_many :splices
|
65
|
+
embeds_many :incidences
|
66
|
+
|
67
|
+
validates_format_of :chrrefseq, with: /\A(urn:miriam:refseq)/
|
68
|
+
|
69
|
+
|
70
|
+
# Download sequence from web service please use by caution. NCBI will block scamming sequest
|
71
|
+
#
|
72
|
+
def dl_seq!
|
73
|
+
|
74
|
+
case self.chrrefseq
|
75
|
+
when /\Aurn:miriam:refseq:/
|
76
|
+
self.sequence = Bio::FastaFormat.new(Bio::NCBI::REST.efetch(self.chrrefseq.split(':', 4), {"db"=>"nucleotide", "rettype"=>"fasta", "retmode"=>"text", "seq_start"=>self.start, "seq_stop"=>self.end})).seq
|
77
|
+
end
|
78
|
+
|
79
|
+
self.save!
|
80
|
+
|
81
|
+
end
|
82
|
+
|
83
|
+
# Download gene symbol from HGNC service
|
84
|
+
#
|
85
|
+
def dl_symbol!
|
86
|
+
|
87
|
+
baseuri = "http://rest.genenames.org/search"
|
88
|
+
|
89
|
+
|
90
|
+
query = ""
|
91
|
+
|
92
|
+
if self.get_xref('urn:miriam:refseq')
|
93
|
+
query = "#{baseuri}/refseq_accession/#{self.chrrefseq.id.split('.')[0]}"
|
94
|
+
elsif self.get_xref('urn:miriam:ncbigene')
|
95
|
+
query = ""
|
96
|
+
end
|
97
|
+
|
98
|
+
if !query.empty?
|
99
|
+
response = JSON.parse(open(query, 'Accept' => 'application/json').read)['response']
|
100
|
+
if !response['docs'].empty?
|
101
|
+
|
102
|
+
response['docs'].each do |e|
|
103
|
+
self.add_to_set(:xrefs, "urn:miriam:hgnc:#{e["hgnc_id"]}")
|
104
|
+
self.add_to_set(:xrefs, "urn:miriam:hgnc.symbol:#{e["symbol"]}")
|
105
|
+
end
|
106
|
+
|
107
|
+
self.save!
|
108
|
+
|
109
|
+
end
|
110
|
+
|
111
|
+
end
|
112
|
+
|
113
|
+
end
|
114
|
+
|
115
|
+
# Download incident data from TCGA
|
116
|
+
#
|
117
|
+
def dl_incidence!
|
118
|
+
|
119
|
+
if self.get_xref('urn:miriam:hgnc.symbol')
|
120
|
+
|
121
|
+
cancerstudies = []
|
122
|
+
|
123
|
+
open("http://www.cbioportal.org/public-portal/webservice.do?cmd=getCancerStudies") {|f|
|
124
|
+
f.each_line {|line| cancerstudies.push(line.chomp.split("\t")[0])}
|
125
|
+
}
|
126
|
+
|
127
|
+
incidents = {}
|
128
|
+
totalcase = {}
|
129
|
+
|
130
|
+
cancerstudies.each do |study|
|
131
|
+
|
132
|
+
totalcase[study] = 0 if !totalcase.has_key?(study)
|
133
|
+
|
134
|
+
open("http://www.cbioportal.org/public-portal/webservice.do?cmd=getCaseLists&cancer_study_id=#{study}") do |f|
|
135
|
+
f.each_line do |line|
|
136
|
+
totalcase[study] += line.chomp.split(/\t/)[4].split(' ').length if line =~ /\tSequenced Tumors\t/
|
137
|
+
end
|
138
|
+
end
|
139
|
+
|
140
|
+
incidents[study] = {} if !incidents.has_key?(study)
|
141
|
+
|
142
|
+
open("http://www.cbioportal.org/public-portal/webservice.do?cmd=getMutationData&genetic_profile_id=#{study}_mutations&gene_list=#{self.get_xref('urn:miriam:hgnc.symbol').id}") do |f|
|
143
|
+
f.each_line do |line|
|
144
|
+
dat = line.chomp.split(/\t/)
|
145
|
+
|
146
|
+
if dat[5] == 'Missense_Mutation'
|
147
|
+
|
148
|
+
incidents[study][dat[7].split(/(\d+)/)[1]] = [] if !incidents[study].has_key?(dat[7].split(/(\d+)/)[1])
|
149
|
+
incidents[study][dat[7].split(/(\d+)/)[1]].push(dat[2])
|
150
|
+
|
151
|
+
end
|
152
|
+
|
153
|
+
end
|
154
|
+
|
155
|
+
|
156
|
+
end
|
157
|
+
end
|
158
|
+
|
159
|
+
self.incidences.clear if self.incidences
|
160
|
+
|
161
|
+
incidents.each_pair do |cancertype, v|
|
162
|
+
v.each_pair do |position, occur|
|
163
|
+
self.incidences << Incidence.new({cancertype: cancertype, position: position, occur: occur.uniq.sort, casenumber: totalcase[cancertype]})
|
164
|
+
end
|
165
|
+
end
|
166
|
+
|
167
|
+
self.save!
|
168
|
+
|
169
|
+
end
|
170
|
+
|
171
|
+
end
|
172
|
+
|
173
|
+
# return sequence as Bio::Sequence object
|
174
|
+
#
|
175
|
+
# @return [Bio::Sequence] the contents reversed lexically
|
176
|
+
def to_seq
|
177
|
+
return self.sequence ? Bio::Sequence.auto(self.sequence) : Bio::Sequence.auto("")
|
178
|
+
end
|
179
|
+
|
180
|
+
# return longest splice of this gene
|
181
|
+
def longest_splice()
|
182
|
+
length = 0
|
183
|
+
longest = nil
|
184
|
+
self.splices.each do |e|
|
185
|
+
|
186
|
+
if e.prot_len > length
|
187
|
+
length = e.prot_len
|
188
|
+
longest = e
|
189
|
+
end
|
190
|
+
|
191
|
+
end
|
192
|
+
|
193
|
+
return longest
|
194
|
+
end
|
195
|
+
|
196
|
+
# Check that this gene has any splice variant
|
197
|
+
#
|
198
|
+
# @return [Boolean] true if has any splices
|
199
|
+
def has_splices?
|
200
|
+
return self.splices.exists?
|
201
|
+
end
|
202
|
+
|
203
|
+
# Check if Generef has sequence
|
204
|
+
#
|
205
|
+
# @return [Boolean] Return true if there is a sequence
|
206
|
+
def has_sequence?()
|
207
|
+
return self[:sequence] ? true : false
|
208
|
+
end
|
209
|
+
|
210
|
+
# Check if Generef can translate
|
211
|
+
#
|
212
|
+
# @return [Boolean] Return true if this can be translate
|
213
|
+
def can_translated?()
|
214
|
+
return self.has_sequence? && self.has_splices? && self.longest_splice != nil ? true : false
|
215
|
+
end
|
216
|
+
|
217
|
+
# Get gene symbol
|
218
|
+
#
|
219
|
+
# @return [String] Return gene symbol or any id from xrefs or 'nosymbol'
|
220
|
+
def symbol
|
221
|
+
|
222
|
+
if self.get_xref('urn:miriam:hgnc.symbol')
|
223
|
+
return self.get_xref('urn:miriam:hgnc.symbol').id
|
224
|
+
elsif self.xrefs && !self.xrefs.empty?
|
225
|
+
return self.xrefs.sort[0].id
|
226
|
+
else
|
227
|
+
return 'nosymbol'
|
228
|
+
end
|
229
|
+
|
230
|
+
end
|
231
|
+
|
232
|
+
end
|
233
|
+
|
234
|
+
class Splice
|
235
|
+
|
236
|
+
include Mongoid::Document
|
237
|
+
|
238
|
+
include Exodb::XrefsField
|
239
|
+
|
240
|
+
field :exon, type: Array
|
241
|
+
field :cds, type: Array
|
242
|
+
|
243
|
+
embedded_in :generef
|
244
|
+
|
245
|
+
# join exon or cds position into a string
|
246
|
+
#
|
247
|
+
# @param [Array] input array exon or cds
|
248
|
+
# @param [Interger] Position to stop positive value for forward read negative value for complement
|
249
|
+
#
|
250
|
+
# @return [String] a string in start..end,start..end,...
|
251
|
+
def get_join_str(arr, position = 0)
|
252
|
+
|
253
|
+
reducer = self.generef.start - 1
|
254
|
+
tmparr = []
|
255
|
+
found = false
|
256
|
+
|
257
|
+
if position > 0
|
258
|
+
add = true
|
259
|
+
arr.each do |e|
|
260
|
+
|
261
|
+
if e[0] <= position && position <= e[1]
|
262
|
+
tmparr.push([e[0], position])
|
263
|
+
add = false
|
264
|
+
found = true
|
265
|
+
else
|
266
|
+
tmparr.push(e) if add
|
267
|
+
end
|
268
|
+
|
269
|
+
end
|
270
|
+
elsif position < 0
|
271
|
+
position = position.abs
|
272
|
+
add = false
|
273
|
+
arr.each do |e|
|
274
|
+
|
275
|
+
if e[0] <= position && position <= e[1]
|
276
|
+
tmparr.push([position, e[1]])
|
277
|
+
add = true
|
278
|
+
found = true
|
279
|
+
else
|
280
|
+
tmparr.push(e) if add
|
281
|
+
end
|
282
|
+
|
283
|
+
end
|
284
|
+
else
|
285
|
+
tmparr = arr
|
286
|
+
end
|
287
|
+
|
288
|
+
tmparr = [] if !found && position != 0
|
289
|
+
str = []
|
290
|
+
|
291
|
+
tmparr.each do |e|
|
292
|
+
str.push("#{e[0] - reducer}..#{e[1] - reducer}")
|
293
|
+
end
|
294
|
+
return str.join(',')
|
295
|
+
|
296
|
+
end
|
297
|
+
|
298
|
+
def get_exon_join(position = 0)
|
299
|
+
get_join_str(self[:exon], position)
|
300
|
+
end
|
301
|
+
|
302
|
+
def get_cds_join(position = 0)
|
303
|
+
get_join_str(self[:cds], position)
|
304
|
+
end
|
305
|
+
|
306
|
+
# Get spliced DNA sequence
|
307
|
+
#
|
308
|
+
# @return [Bio::Sequence] an DNA sequence
|
309
|
+
def get_dna_seq
|
310
|
+
parent = self.generef
|
311
|
+
return parent.strand == '+' ? parent.to_seq.splicing("join(#{self.get_exon_join})") : parent.to_seq.splicing("complement(join(#{self.get_exon_join}))")
|
312
|
+
end
|
313
|
+
|
314
|
+
# Get spliced RNA sequence
|
315
|
+
#
|
316
|
+
# @return [Bio::Sequence] an RNA sequence
|
317
|
+
def get_mrna_seq
|
318
|
+
parent = self.generef
|
319
|
+
return parent.strand == '+' ? parent.to_seq.splicing("join(#{self.get_exon_join})").rna : parent.to_seq.splicing("complement(join(#{self.get_exon_join}))").rna
|
320
|
+
end
|
321
|
+
|
322
|
+
# Get spliced coding region sequence
|
323
|
+
#
|
324
|
+
# @param [Integer] end position to get sequence
|
325
|
+
#
|
326
|
+
# @return [Bio::Sequence] an coding region sequence
|
327
|
+
def get_cds_seq(position = 0)
|
328
|
+
|
329
|
+
parent = self.generef
|
330
|
+
if parent.strand == '+'
|
331
|
+
join = self.get_cds_join(position)
|
332
|
+
return !join.empty? ? parent.to_seq.splicing("join(#{join})") : ""
|
333
|
+
else
|
334
|
+
join = self.get_cds_join(-position)
|
335
|
+
return !join.empty? ? parent.to_seq.splicing("join(#{join})") : ""
|
336
|
+
end
|
337
|
+
|
338
|
+
end
|
339
|
+
|
340
|
+
# Get spliced protein sequence
|
341
|
+
#
|
342
|
+
# @return [Bio::Sequence] an protein sequence
|
343
|
+
def get_prot_seq
|
344
|
+
parent = self.generef
|
345
|
+
return parent.strand == '+' ? parent.to_seq.splicing("join(#{self.get_cds_join})").translate : parent.to_seq.splicing("complement(join(#{self.get_cds_join}))").translate
|
346
|
+
end
|
347
|
+
|
348
|
+
# get length of spliced RNA
|
349
|
+
#
|
350
|
+
# @return [Integer] length of spliced RNA
|
351
|
+
def rna_len
|
352
|
+
return self.get_mrna_seq.length
|
353
|
+
end
|
354
|
+
|
355
|
+
# get length of protein product
|
356
|
+
#
|
357
|
+
# @return [Integer] length of protein product
|
358
|
+
def prot_len
|
359
|
+
return self.get_prot_seq.length
|
360
|
+
end
|
361
|
+
|
362
|
+
# Get the codon sequence at the giving position base on position of amino acid
|
363
|
+
#
|
364
|
+
# @param [Integer] codon position
|
365
|
+
# @return [Bio::Sequence] the codon at given position
|
366
|
+
def get_codon(codon_pos)
|
367
|
+
return self.get_cds_seq().subseq(((codon_pos - 1) * 3) + 1 , ((codon_pos - 1) * 3) + 3)
|
368
|
+
end
|
369
|
+
|
370
|
+
# convert genomic position to codon position
|
371
|
+
#
|
372
|
+
# @param [Integer] genomic position
|
373
|
+
# @return [Array] Return all information of codon at given position
|
374
|
+
def get_prot_pos(pos)
|
375
|
+
|
376
|
+
seqlen = self.get_cds_seq(pos).length
|
377
|
+
if seqlen != 0
|
378
|
+
return [(seqlen - 1) / 3, (seqlen - 1) % 3]
|
379
|
+
else
|
380
|
+
return []
|
381
|
+
end
|
382
|
+
|
383
|
+
end
|
384
|
+
|
385
|
+
end
|
386
|
+
|
387
|
+
end
|
@@ -0,0 +1,51 @@
|
|
1
|
+
#
|
2
|
+
# Exodb
|
3
|
+
# Copyright (C) 2014
|
4
|
+
#
|
5
|
+
# author: Natapol Pornputtapong <natapol.por@gmail.com>
|
6
|
+
#
|
7
|
+
# Documentation: Natapol Pornputtapong (RDoc'd and embellished by William Webber)
|
8
|
+
#
|
9
|
+
|
10
|
+
# raise "Please, use ruby 1.9.0 or later." if RUBY_VERSION < "1.9.0"
|
11
|
+
|
12
|
+
|
13
|
+
module Exodb
|
14
|
+
|
15
|
+
class Region
|
16
|
+
|
17
|
+
include Mongoid::Document
|
18
|
+
include Mongoid::Timestamps
|
19
|
+
|
20
|
+
end
|
21
|
+
|
22
|
+
class Gene < Region
|
23
|
+
|
24
|
+
include Mongoid::Versioning
|
25
|
+
include Exodb::LocationField
|
26
|
+
|
27
|
+
field :symbol, type: String
|
28
|
+
field :loh, type: Boolean
|
29
|
+
|
30
|
+
embeds_many :aacids
|
31
|
+
belongs_to :generef
|
32
|
+
belongs_to :cell
|
33
|
+
|
34
|
+
index({'symbol' => 1, 'aacids.position' => 1}, background: true)
|
35
|
+
end
|
36
|
+
|
37
|
+
class Aacid < Region
|
38
|
+
|
39
|
+
field :position, type: Integer # position referenced to the first codon from the longest splice variant
|
40
|
+
field :refcodon, type: String
|
41
|
+
field :refaa, type: String
|
42
|
+
field :altcodon, type: Hash
|
43
|
+
field :inhcodon, type: Hash
|
44
|
+
field :isoform, type: Array
|
45
|
+
|
46
|
+
embedded_in :gene
|
47
|
+
has_many :variants
|
48
|
+
|
49
|
+
end
|
50
|
+
|
51
|
+
end
|