exodb 0.1.2 → 0.1.3
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/lib/exodb.rb +23 -0
- data/lib/exodb/addon/string.rb +139 -0
- data/lib/exodb/constant.rb +64 -0
- data/lib/exodb/datamodel.rb +4 -1
- data/lib/exodb/datamodel/genelocfield.rb +177 -0
- data/lib/exodb/datamodel/generef.rb +193 -0
- data/lib/exodb/datamodel/isoform.rb +237 -0
- data/lib/exodb/datamodel/reference.rb +23 -327
- data/lib/exodb/datamodel/region.rb +7 -5
- data/lib/exodb/datamodel/source.rb +1 -10
- data/lib/exodb/datamodel/variant.rb +14 -81
- data/lib/exodb/datamodel/varlocfield.rb +106 -0
- data/lib/exodb/datamodel/xrefsfield.rb +4 -0
- data/lib/exodb/extra.rb +17 -0
- data/lib/exodb/extra/upload.rb +43 -0
- data/lib/exodb/{utils → extra}/upload_generef.rb +35 -21
- data/lib/exodb/rositza/load.rb +56 -42
- data/lib/exodb/utils.rb +1 -2
- data/lib/exodb/utils/ensemblrest.rb +31 -3
- data/lib/exodb/utils/miriamrest.rb +23 -0
- data/lib/exodb/version.rb +1 -1
- metadata +10 -3
- data/lib/exodb/datamodel/locationfield.rb +0 -116
@@ -0,0 +1,193 @@
|
|
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 Chrref < Reference
|
15
|
+
|
16
|
+
include Exodb::GeneLocationField
|
17
|
+
|
18
|
+
index({oid: 1}, background: true)
|
19
|
+
|
20
|
+
end
|
21
|
+
|
22
|
+
class Generef < Reference
|
23
|
+
|
24
|
+
include Exodb::GeneLocationField
|
25
|
+
|
26
|
+
@@expanding = 500
|
27
|
+
|
28
|
+
field :psuedo, type: Boolean
|
29
|
+
|
30
|
+
index({sequence: 'text'}, background: true)
|
31
|
+
index({oid: 1, psudo: 1, chrrefseq: 1, assembly: 1}, background: true)
|
32
|
+
|
33
|
+
has_many :genes
|
34
|
+
embeds_many :isoforms
|
35
|
+
embeds_many :occurrents
|
36
|
+
|
37
|
+
validates_format_of :chrrefseq, with: /\A(urn:miriam:refseq)/
|
38
|
+
|
39
|
+
#oid = "chrrefseq:start..stop"
|
40
|
+
|
41
|
+
def self.expanding
|
42
|
+
return @@expanding
|
43
|
+
end
|
44
|
+
|
45
|
+
# Download gene symbol from HGNC service
|
46
|
+
#
|
47
|
+
def dl_symbol!
|
48
|
+
|
49
|
+
baseuri = "http://rest.genenames.org/search"
|
50
|
+
|
51
|
+
|
52
|
+
query = ""
|
53
|
+
|
54
|
+
if self.get_xref('urn:miriam:refseq')
|
55
|
+
query = "#{baseuri}/refseq_accession/#{self.chrrefseq.id.split('.')[0]}"
|
56
|
+
elsif self.get_xref('urn:miriam:ncbigene')
|
57
|
+
query = ""
|
58
|
+
end
|
59
|
+
|
60
|
+
if !query.empty?
|
61
|
+
response = JSON.parse(open(query, 'Accept' => 'application/json').read)['response']
|
62
|
+
if !response['docs'].empty?
|
63
|
+
|
64
|
+
response['docs'].each do |e|
|
65
|
+
self.add_to_set(:xrefs, "urn:miriam:hgnc:#{e["hgnc_id"]}")
|
66
|
+
self.add_to_set(:xrefs, "urn:miriam:hgnc.symbol:#{e["symbol"]}")
|
67
|
+
end
|
68
|
+
|
69
|
+
self.save!
|
70
|
+
|
71
|
+
end
|
72
|
+
|
73
|
+
end
|
74
|
+
|
75
|
+
end
|
76
|
+
|
77
|
+
# Download incident data from TCGA
|
78
|
+
#
|
79
|
+
def dl_occurrent!
|
80
|
+
|
81
|
+
if self.get_xref('urn:miriam:hgnc.symbol')
|
82
|
+
|
83
|
+
cancerstudies = []
|
84
|
+
|
85
|
+
open("http://www.cbioportal.org/public-portal/webservice.do?cmd=getCancerStudies") {|f|
|
86
|
+
f.each_line {|line| cancerstudies.push(line.chomp.split("\t")[0])}
|
87
|
+
}
|
88
|
+
|
89
|
+
occurrents = {}
|
90
|
+
totalcase = {}
|
91
|
+
|
92
|
+
cancerstudies.each do |study|
|
93
|
+
|
94
|
+
totalcase[study] = 0 if !totalcase.has_key?(study)
|
95
|
+
|
96
|
+
open("http://www.cbioportal.org/public-portal/webservice.do?cmd=getCaseLists&cancer_study_id=#{study}") do |f|
|
97
|
+
f.each_line do |line|
|
98
|
+
totalcase[study] += line.chomp.split(/\t/)[4].split(' ').length if line =~ /\tSequenced Tumors\t/
|
99
|
+
end
|
100
|
+
end
|
101
|
+
|
102
|
+
occurrents[study] = {} if !occurrents.has_key?(study)
|
103
|
+
|
104
|
+
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|
|
105
|
+
f.each_line do |line|
|
106
|
+
dat = line.chomp.split(/\t/)
|
107
|
+
|
108
|
+
if dat[5] == 'Missense_Mutation'
|
109
|
+
|
110
|
+
occurrents[study][dat[7].split(/(\d+)/)[1]] = [] if !occurrents[study].has_key?(dat[7].split(/(\d+)/)[1])
|
111
|
+
occurrents[study][dat[7].split(/(\d+)/)[1]].push(dat[2])
|
112
|
+
|
113
|
+
end
|
114
|
+
|
115
|
+
end
|
116
|
+
|
117
|
+
|
118
|
+
end
|
119
|
+
end
|
120
|
+
|
121
|
+
self.occurrents.clear if self.occurrents
|
122
|
+
|
123
|
+
occurrents.each_pair do |cancertype, v|
|
124
|
+
v.each_pair do |position, occur|
|
125
|
+
self.occurrents << Occurrent.new({cancertype: cancertype, position: position, occur: occur.uniq.sort, casenumber: totalcase[cancertype]})
|
126
|
+
end
|
127
|
+
end
|
128
|
+
|
129
|
+
self.save!
|
130
|
+
|
131
|
+
end
|
132
|
+
|
133
|
+
end
|
134
|
+
|
135
|
+
# return longest splice of this gene
|
136
|
+
def longest_splice()
|
137
|
+
length = 0
|
138
|
+
longest = nil
|
139
|
+
self.isoforms.each do |e|
|
140
|
+
|
141
|
+
if e.prot_len > length
|
142
|
+
length = e.prot_len
|
143
|
+
longest = e
|
144
|
+
end
|
145
|
+
|
146
|
+
end
|
147
|
+
|
148
|
+
return longest
|
149
|
+
end
|
150
|
+
|
151
|
+
alias_method :longest_isoform, :longest_splice
|
152
|
+
|
153
|
+
# Check that this gene has any splice variant
|
154
|
+
#
|
155
|
+
# @return [Boolean] true if has any splices
|
156
|
+
def has_splices?
|
157
|
+
return self.isoforms.exists?
|
158
|
+
end
|
159
|
+
|
160
|
+
alias_method :has_isoforms?, :has_splices?
|
161
|
+
|
162
|
+
# Check if Generef has sequence
|
163
|
+
#
|
164
|
+
# @return [Boolean] Return true if there is a sequence
|
165
|
+
def has_sequence?()
|
166
|
+
return self[:sequence] ? true : false
|
167
|
+
end
|
168
|
+
|
169
|
+
# Check if Generef can translate
|
170
|
+
#
|
171
|
+
# @return [Boolean] Return true if this can be translate
|
172
|
+
def can_translated?()
|
173
|
+
return self.has_sequence? && self.has_splices? && self.longest_splice != nil ? true : false
|
174
|
+
end
|
175
|
+
|
176
|
+
# Get gene symbol
|
177
|
+
#
|
178
|
+
# @return [String] Return gene symbol or any id from xrefs or 'nosymbol'
|
179
|
+
def symbol
|
180
|
+
|
181
|
+
if self.get_xref('urn:miriam:hgnc.symbol')
|
182
|
+
return self.get_xref('urn:miriam:hgnc.symbol').id
|
183
|
+
elsif self.xrefs && !self.xrefs.empty?
|
184
|
+
return self.xrefs.sort[0].id
|
185
|
+
else
|
186
|
+
return 'nosymbol'
|
187
|
+
end
|
188
|
+
|
189
|
+
end
|
190
|
+
|
191
|
+
end
|
192
|
+
|
193
|
+
end
|
@@ -0,0 +1,237 @@
|
|
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 Isoform
|
15
|
+
|
16
|
+
include Mongoid::Document
|
17
|
+
|
18
|
+
include Exodb::XrefsField
|
19
|
+
|
20
|
+
field :exon, type: Array # array of [start, stop]
|
21
|
+
field :cds, type: Array # array of [start, stop]
|
22
|
+
|
23
|
+
embedded_in :generef
|
24
|
+
|
25
|
+
# generate genbank style location string
|
26
|
+
#
|
27
|
+
# @param [Symbol] field to generate [:exon, :cds]
|
28
|
+
# @param [Symbol] type to generate [:rel, :abs, :trela]
|
29
|
+
#
|
30
|
+
# @return [String] a location string
|
31
|
+
def genbank_loc(field, type)
|
32
|
+
|
33
|
+
reducer = case type.to_sym
|
34
|
+
when :rel
|
35
|
+
self.generef[:start] - 1
|
36
|
+
when :trela
|
37
|
+
self.generef[:seqstart] - 1
|
38
|
+
else
|
39
|
+
0
|
40
|
+
end
|
41
|
+
|
42
|
+
loc = []
|
43
|
+
|
44
|
+
self[field.to_sym].each do |pos|
|
45
|
+
loc.push("#{pos[0] - reducer}..#{pos[1] - reducer}")
|
46
|
+
end
|
47
|
+
|
48
|
+
return self.generef.strand == '+' ? "join(#{loc.join(',')})" : "complement(join(#{loc.join(',')}))"
|
49
|
+
end
|
50
|
+
|
51
|
+
protected :genbank_loc
|
52
|
+
|
53
|
+
# Get exon location
|
54
|
+
#
|
55
|
+
# @return [Bio::Locations] of exon
|
56
|
+
def exon_location
|
57
|
+
return Bio::Locations.new(genbank_loc(:exon, :abs))
|
58
|
+
end
|
59
|
+
|
60
|
+
# Get exon location
|
61
|
+
#
|
62
|
+
# @return [Bio::Locations] of exon
|
63
|
+
def cds_location
|
64
|
+
return Bio::Locations.new(genbank_loc(:cds, :abs))
|
65
|
+
end
|
66
|
+
|
67
|
+
# Get spliced RNA sequence
|
68
|
+
#
|
69
|
+
# @return [Bio::Sequence] an RNA sequence
|
70
|
+
def mrna_seq
|
71
|
+
return self.return self.generef.whole_seq.splice(genbank_loc(:exon, :trela)).rna
|
72
|
+
end
|
73
|
+
|
74
|
+
# Get spliced coding region sequence
|
75
|
+
#
|
76
|
+
# @param [Integer] end position to get sequence
|
77
|
+
#
|
78
|
+
# @return [Bio::Sequence] an coding region sequence
|
79
|
+
def cds_seq
|
80
|
+
return self.generef.whole_seq.splice(genbank_loc(:cds, :trela))
|
81
|
+
end
|
82
|
+
|
83
|
+
# Get spliced protein sequence
|
84
|
+
#
|
85
|
+
# @return [Bio::Sequence] an protein sequence
|
86
|
+
def prot_seq
|
87
|
+
return self.cds_seq().translate
|
88
|
+
end
|
89
|
+
|
90
|
+
# get length of spliced RNA
|
91
|
+
#
|
92
|
+
# @return [Integer] length of spliced RNA
|
93
|
+
def mrna_len
|
94
|
+
return self.exon_location.length
|
95
|
+
end
|
96
|
+
|
97
|
+
# get length of protein product
|
98
|
+
#
|
99
|
+
# @return [Integer] length of protein product
|
100
|
+
def prot_len
|
101
|
+
return self.cds_location.length
|
102
|
+
end
|
103
|
+
|
104
|
+
# Get the codon sequence at the giving position base on position of amino acid
|
105
|
+
#
|
106
|
+
# @param [Integer] codon position
|
107
|
+
# @return [Bio::Sequence] the codon at given position
|
108
|
+
def codon_at(codon_pos)
|
109
|
+
return self.cds_seq.subseq(((codon_pos - 1) * 3) + 1 , ((codon_pos - 1) * 3) + 3)
|
110
|
+
end
|
111
|
+
|
112
|
+
# convert genomic position to cds position
|
113
|
+
#
|
114
|
+
# @param [Integer] genomic position
|
115
|
+
# @return [Integer] Return all information of cds at given position
|
116
|
+
def genomic2cds_pos(pos)
|
117
|
+
cds_location.relative(pos)
|
118
|
+
end
|
119
|
+
|
120
|
+
# convert genomic position to cds position
|
121
|
+
#
|
122
|
+
# @param [Integer] genomic position
|
123
|
+
# @return [Array] Return [codon and position in codon]
|
124
|
+
def genomic2prot_pos(pos)
|
125
|
+
cds_location.relative(pos, :aa)
|
126
|
+
end
|
127
|
+
|
128
|
+
# get splice related position 1-3 base into exon and 3-8 base into intron
|
129
|
+
#
|
130
|
+
# @return [Array] Return position of splice related site in array of [start, stop]
|
131
|
+
# SPL-D splice_donor_variant SO:0001575
|
132
|
+
# SPL-A splice_acceptor_variant SO:0001574
|
133
|
+
# SPL-R splice_region_variant SO:0001630
|
134
|
+
def splice_rel_location
|
135
|
+
|
136
|
+
if @splice_location == nil
|
137
|
+
|
138
|
+
results = {}
|
139
|
+
right = nil
|
140
|
+
|
141
|
+
self[:exon].each do |exon|
|
142
|
+
if !right.blank?
|
143
|
+
if self.generef.strand == '+'
|
144
|
+
results[right + 1] = 'SPL-D'
|
145
|
+
results[right + 2] = 'SPL-D'
|
146
|
+
results[exon[0] - 1] = 'SPL-A'
|
147
|
+
results[exon[0] - 2] = 'SPL-A'
|
148
|
+
else
|
149
|
+
results[right + 1] = 'SPL-A'
|
150
|
+
results[right + 2] = 'SPL-A'
|
151
|
+
results[exon[0] - 1] = 'SPL-D'
|
152
|
+
results[exon[0] - 2] = 'SPL-D'
|
153
|
+
end
|
154
|
+
|
155
|
+
Range.new(right - 2, right).each {|e| results[e] = 'SPL-R'}
|
156
|
+
Range.new(right + 3, right + 8).each {|e| results[e] = 'SPL-R'}
|
157
|
+
Range.new(exon[0], exon[0] + 2).each {|e| results[e] = 'SPL-R'}
|
158
|
+
Range.new(exon[0] - 3, exon[0] - 8).each {|e| results[e] = 'SPL-R'}
|
159
|
+
|
160
|
+
right = exon[1]
|
161
|
+
else
|
162
|
+
right = exon[1]
|
163
|
+
end
|
164
|
+
end
|
165
|
+
|
166
|
+
@splice_location = results
|
167
|
+
return results
|
168
|
+
else
|
169
|
+
return @splice_location
|
170
|
+
end
|
171
|
+
|
172
|
+
end
|
173
|
+
|
174
|
+
def utr5location
|
175
|
+
return Bio::Locations.new(self.generef.strand == '+' ? "#{self[:exon][0][0]}..#{self[:cds][0][0] - 1}" : "complement(#{self[:cds][-1][1] + 1}..#{self[:exon][-1][1]})")
|
176
|
+
end
|
177
|
+
|
178
|
+
def utr3location
|
179
|
+
return Bio::Locations.new(self.generef.strand == '+' ? "#{self[:cds][-1][1] + 1}..#{self[:exon][-1][1]}" : "complement(#{self[:exon][0][0]}..#{self[:cds][0][0] - 1})")
|
180
|
+
end
|
181
|
+
|
182
|
+
# predict efect of variants
|
183
|
+
#
|
184
|
+
# @param [array] list of variants
|
185
|
+
#
|
186
|
+
# @return [array] list of predicted effect
|
187
|
+
# SPL-D splice_donor_variant SO:0001575
|
188
|
+
# SPL-A splice_acceptor_variant SO:0001574
|
189
|
+
# SPL-R splice_region_variant SO:0001630
|
190
|
+
# COD-SS
|
191
|
+
# COD-SN
|
192
|
+
# COD-DS
|
193
|
+
# COD-DN
|
194
|
+
# COD-IS
|
195
|
+
# COD-IN
|
196
|
+
# UTR-3
|
197
|
+
# UTR-5
|
198
|
+
# INT
|
199
|
+
# INI
|
200
|
+
# STO-L
|
201
|
+
# STO-G
|
202
|
+
# PRO
|
203
|
+
# TFB
|
204
|
+
def effect_pred(position, alt)
|
205
|
+
|
206
|
+
results = []
|
207
|
+
|
208
|
+
prot_pos = genomic2prot_pos(position)
|
209
|
+
|
210
|
+
if prot_pos
|
211
|
+
case alt
|
212
|
+
when /^-([ATCG])+/
|
213
|
+
results.push({vartype: $1.length % 3 == 0 ? 'COD-DS' : 'COD-DN'})
|
214
|
+
when /^\+([ATCG])+/
|
215
|
+
results.push({vartype: ($1.length - 1) % 3 == 0 ? 'COD-IS' : 'COD-IN'})
|
216
|
+
else
|
217
|
+
results.push({vartype: 'COD-SS'})
|
218
|
+
end
|
219
|
+
else
|
220
|
+
#case
|
221
|
+
#when test
|
222
|
+
# #code
|
223
|
+
#when test
|
224
|
+
# #code
|
225
|
+
#else
|
226
|
+
# results.push({vartype: 'INT'})
|
227
|
+
#end
|
228
|
+
end
|
229
|
+
|
230
|
+
results.push({vartype: splice_rel_location[position]}) if splice_rel_location.has_key?(position)
|
231
|
+
|
232
|
+
return results
|
233
|
+
|
234
|
+
end
|
235
|
+
end
|
236
|
+
|
237
|
+
end
|
@@ -28,7 +28,7 @@ module Exodb
|
|
28
28
|
PATTERN = /(?<gene>[A-Z0-9]+)-?(?<position>[0-9,]*|[is]?)(?<to>[A-Z=]*)/
|
29
29
|
SILENTSIGN = '='
|
30
30
|
|
31
|
-
include Exodb::
|
31
|
+
include Exodb::VarLocationField
|
32
32
|
|
33
33
|
field :reference, type: String
|
34
34
|
field :alternate, type: String
|
@@ -48,339 +48,35 @@ module Exodb
|
|
48
48
|
|
49
49
|
end
|
50
50
|
|
51
|
-
class
|
52
|
-
|
53
|
-
include Exodb::GenomeLocationField
|
54
|
-
|
55
|
-
field :sequence, type: String
|
56
|
-
field :chrrefseq, type: String # refseq id of chromomose
|
57
|
-
field :psuedo, type: Boolean
|
58
|
-
field :genomeref, type: String
|
59
|
-
|
60
|
-
index({sequence: 'text'}, background: true)
|
61
|
-
|
62
|
-
has_many :genes
|
63
|
-
embeds_many :isoforms
|
64
|
-
embeds_many :occurrents
|
65
|
-
|
66
|
-
validates_format_of :chrrefseq, with: /\A(urn:miriam:refseq)/
|
67
|
-
|
68
|
-
|
69
|
-
# Download sequence from web service please use by caution. NCBI will block scamming sequest
|
70
|
-
#
|
71
|
-
def dl_seq!
|
72
|
-
|
73
|
-
case self.chrrefseq
|
74
|
-
when /\Aurn:miriam:refseq:/
|
75
|
-
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
|
76
|
-
end
|
77
|
-
|
78
|
-
self.save!
|
79
|
-
|
80
|
-
end
|
81
|
-
|
82
|
-
# Download gene symbol from HGNC service
|
83
|
-
#
|
84
|
-
def dl_symbol!
|
85
|
-
|
86
|
-
baseuri = "http://rest.genenames.org/search"
|
87
|
-
|
88
|
-
|
89
|
-
query = ""
|
90
|
-
|
91
|
-
if self.get_xref('urn:miriam:refseq')
|
92
|
-
query = "#{baseuri}/refseq_accession/#{self.chrrefseq.id.split('.')[0]}"
|
93
|
-
elsif self.get_xref('urn:miriam:ncbigene')
|
94
|
-
query = ""
|
95
|
-
end
|
96
|
-
|
97
|
-
if !query.empty?
|
98
|
-
response = JSON.parse(open(query, 'Accept' => 'application/json').read)['response']
|
99
|
-
if !response['docs'].empty?
|
100
|
-
|
101
|
-
response['docs'].each do |e|
|
102
|
-
self.add_to_set(:xrefs, "urn:miriam:hgnc:#{e["hgnc_id"]}")
|
103
|
-
self.add_to_set(:xrefs, "urn:miriam:hgnc.symbol:#{e["symbol"]}")
|
104
|
-
end
|
105
|
-
|
106
|
-
self.save!
|
107
|
-
|
108
|
-
end
|
109
|
-
|
110
|
-
end
|
111
|
-
|
112
|
-
end
|
113
|
-
|
114
|
-
# Download incident data from TCGA
|
115
|
-
#
|
116
|
-
def dl_occurrent!
|
117
|
-
|
118
|
-
if self.get_xref('urn:miriam:hgnc.symbol')
|
119
|
-
|
120
|
-
cancerstudies = []
|
121
|
-
|
122
|
-
open("http://www.cbioportal.org/public-portal/webservice.do?cmd=getCancerStudies") {|f|
|
123
|
-
f.each_line {|line| cancerstudies.push(line.chomp.split("\t")[0])}
|
124
|
-
}
|
125
|
-
|
126
|
-
occurrents = {}
|
127
|
-
totalcase = {}
|
128
|
-
|
129
|
-
cancerstudies.each do |study|
|
130
|
-
|
131
|
-
totalcase[study] = 0 if !totalcase.has_key?(study)
|
132
|
-
|
133
|
-
open("http://www.cbioportal.org/public-portal/webservice.do?cmd=getCaseLists&cancer_study_id=#{study}") do |f|
|
134
|
-
f.each_line do |line|
|
135
|
-
totalcase[study] += line.chomp.split(/\t/)[4].split(' ').length if line =~ /\tSequenced Tumors\t/
|
136
|
-
end
|
137
|
-
end
|
138
|
-
|
139
|
-
occurrents[study] = {} if !occurrents.has_key?(study)
|
140
|
-
|
141
|
-
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|
|
142
|
-
f.each_line do |line|
|
143
|
-
dat = line.chomp.split(/\t/)
|
144
|
-
|
145
|
-
if dat[5] == 'Missense_Mutation'
|
146
|
-
|
147
|
-
occurrents[study][dat[7].split(/(\d+)/)[1]] = [] if !occurrents[study].has_key?(dat[7].split(/(\d+)/)[1])
|
148
|
-
occurrents[study][dat[7].split(/(\d+)/)[1]].push(dat[2])
|
149
|
-
|
150
|
-
end
|
151
|
-
|
152
|
-
end
|
153
|
-
|
154
|
-
|
155
|
-
end
|
156
|
-
end
|
157
|
-
|
158
|
-
self.occurrents.clear if self.occurrents
|
159
|
-
|
160
|
-
occurrents.each_pair do |cancertype, v|
|
161
|
-
v.each_pair do |position, occur|
|
162
|
-
self.occurrents << Occurrent.new({cancertype: cancertype, position: position, occur: occur.uniq.sort, casenumber: totalcase[cancertype]})
|
163
|
-
end
|
164
|
-
end
|
165
|
-
|
166
|
-
self.save!
|
167
|
-
|
168
|
-
end
|
169
|
-
|
170
|
-
end
|
171
|
-
|
172
|
-
# return sequence as Bio::Sequence object
|
173
|
-
#
|
174
|
-
# @return [Bio::Sequence] the contents reversed lexically
|
175
|
-
def to_seq
|
176
|
-
return self.sequence ? Bio::Sequence.auto(self.sequence) : Bio::Sequence.auto("")
|
177
|
-
end
|
178
|
-
|
179
|
-
# return longest splice of this gene
|
180
|
-
def longest_splice()
|
181
|
-
length = 0
|
182
|
-
longest = nil
|
183
|
-
self.isoforms.each do |e|
|
184
|
-
|
185
|
-
if e.prot_len > length
|
186
|
-
length = e.prot_len
|
187
|
-
longest = e
|
188
|
-
end
|
189
|
-
|
190
|
-
end
|
191
|
-
|
192
|
-
return longest
|
193
|
-
end
|
194
|
-
|
195
|
-
# Check that this gene has any splice variant
|
196
|
-
#
|
197
|
-
# @return [Boolean] true if has any splices
|
198
|
-
def has_splices?
|
199
|
-
return self.isoforms.exists?
|
200
|
-
end
|
201
|
-
|
202
|
-
# Check if Generef has sequence
|
203
|
-
#
|
204
|
-
# @return [Boolean] Return true if there is a sequence
|
205
|
-
def has_sequence?()
|
206
|
-
return self[:sequence] ? true : false
|
207
|
-
end
|
208
|
-
|
209
|
-
# Check if Generef can translate
|
210
|
-
#
|
211
|
-
# @return [Boolean] Return true if this can be translate
|
212
|
-
def can_translated?()
|
213
|
-
return self.has_sequence? && self.has_splices? && self.longest_splice != nil ? true : false
|
214
|
-
end
|
215
|
-
|
216
|
-
# Get gene symbol
|
217
|
-
#
|
218
|
-
# @return [String] Return gene symbol or any id from xrefs or 'nosymbol'
|
219
|
-
def symbol
|
220
|
-
|
221
|
-
if self.get_xref('urn:miriam:hgnc.symbol')
|
222
|
-
return self.get_xref('urn:miriam:hgnc.symbol').id
|
223
|
-
elsif self.xrefs && !self.xrefs.empty?
|
224
|
-
return self.xrefs.sort[0].id
|
225
|
-
else
|
226
|
-
return 'nosymbol'
|
227
|
-
end
|
228
|
-
|
229
|
-
end
|
230
|
-
|
231
|
-
end
|
232
|
-
|
233
|
-
class Isoform
|
51
|
+
class Mapping
|
234
52
|
|
235
53
|
include Mongoid::Document
|
236
54
|
|
237
|
-
|
238
|
-
|
239
|
-
field :
|
240
|
-
field :
|
241
|
-
|
242
|
-
|
243
|
-
|
244
|
-
|
245
|
-
#
|
246
|
-
|
247
|
-
|
248
|
-
|
249
|
-
|
250
|
-
|
251
|
-
|
252
|
-
|
253
|
-
|
254
|
-
|
255
|
-
|
256
|
-
if position > 0
|
257
|
-
add = true
|
258
|
-
arr.each do |e|
|
259
|
-
|
260
|
-
if e[0] <= position && position <= e[1]
|
261
|
-
tmparr.push([e[0], position])
|
262
|
-
add = false
|
263
|
-
found = true
|
264
|
-
else
|
265
|
-
tmparr.push(e) if add
|
266
|
-
end
|
267
|
-
|
268
|
-
end
|
269
|
-
elsif position < 0
|
270
|
-
position = position.abs
|
271
|
-
add = false
|
272
|
-
arr.each do |e|
|
273
|
-
|
274
|
-
if e[0] <= position && position <= e[1]
|
275
|
-
tmparr.push([position, e[1]])
|
276
|
-
add = true
|
277
|
-
found = true
|
278
|
-
else
|
279
|
-
tmparr.push(e) if add
|
280
|
-
end
|
281
|
-
|
282
|
-
end
|
283
|
-
else
|
284
|
-
tmparr = arr
|
285
|
-
end
|
286
|
-
|
287
|
-
tmparr = [] if !found && position != 0
|
288
|
-
str = []
|
289
|
-
|
290
|
-
tmparr.each do |e|
|
291
|
-
str.push("#{e[0] - reducer}..#{e[1] - reducer}")
|
292
|
-
end
|
293
|
-
return str.join(',')
|
294
|
-
|
295
|
-
end
|
296
|
-
|
297
|
-
def get_exon_join(position = 0)
|
298
|
-
get_join_str(self[:exon], position)
|
299
|
-
end
|
300
|
-
|
301
|
-
def get_cds_join(position = 0)
|
302
|
-
get_join_str(self[:cds], position)
|
303
|
-
end
|
304
|
-
|
305
|
-
# Get spliced DNA sequence
|
306
|
-
#
|
307
|
-
# @return [Bio::Sequence] an DNA sequence
|
308
|
-
def get_dna_seq
|
309
|
-
parent = self.generef
|
310
|
-
return parent.strand == '+' ? parent.to_seq.splicing("join(#{self.get_exon_join})") : parent.to_seq.splicing("complement(join(#{self.get_exon_join}))")
|
311
|
-
end
|
312
|
-
|
313
|
-
# Get spliced RNA sequence
|
314
|
-
#
|
315
|
-
# @return [Bio::Sequence] an RNA sequence
|
316
|
-
def get_mrna_seq
|
317
|
-
parent = self.generef
|
318
|
-
return parent.strand == '+' ? parent.to_seq.splicing("join(#{self.get_exon_join})").rna : parent.to_seq.splicing("complement(join(#{self.get_exon_join}))").rna
|
319
|
-
end
|
320
|
-
|
321
|
-
# Get spliced coding region sequence
|
322
|
-
#
|
323
|
-
# @param [Integer] end position to get sequence
|
324
|
-
#
|
325
|
-
# @return [Bio::Sequence] an coding region sequence
|
326
|
-
def get_cds_seq(position = 0)
|
327
|
-
|
328
|
-
parent = self.generef
|
329
|
-
if parent.strand == '+'
|
330
|
-
join = self.get_cds_join(position)
|
331
|
-
return !join.empty? ? parent.to_seq.splicing("join(#{join})") : ""
|
332
|
-
else
|
333
|
-
join = self.get_cds_join(-position)
|
334
|
-
return !join.empty? ? parent.to_seq.splicing("join(#{join})") : ""
|
55
|
+
field :chr, type: String
|
56
|
+
field :start, type: Integer
|
57
|
+
field :stop, type: Integer
|
58
|
+
field :tchr, type: String
|
59
|
+
field :tstart, type: Integer
|
60
|
+
field :tstop, type: Integer
|
61
|
+
field :coeff, type: Integer # coefficient for conversion
|
62
|
+
field :from, type: String # from assembly version
|
63
|
+
field :to, type: String # to assembly version
|
64
|
+
|
65
|
+
index({oid: 1, chr: 1, start: 1, stop: 1, from: 1, to: 1}, background: true)
|
66
|
+
|
67
|
+
def self.convert(locstr, target = Exodb::LATESTASSEMBLY)
|
68
|
+
begin
|
69
|
+
query = parse_locstr(locstr)
|
70
|
+
return self.where({from: query['assembly'], to: target, :start.lte => query[:pos], :stop.gte => query[:pos]}).first.convert(query[:pos])
|
71
|
+
rescue
|
72
|
+
|
335
73
|
end
|
336
|
-
|
337
74
|
end
|
338
75
|
|
339
|
-
|
340
|
-
|
341
|
-
# @return [Bio::Sequence] an protein sequence
|
342
|
-
def get_prot_seq
|
343
|
-
parent = self.generef
|
344
|
-
return parent.strand == '+' ? parent.to_seq.splicing("join(#{self.get_cds_join})").translate : parent.to_seq.splicing("complement(join(#{self.get_cds_join}))").translate
|
345
|
-
end
|
346
|
-
|
347
|
-
# get length of spliced RNA
|
348
|
-
#
|
349
|
-
# @return [Integer] length of spliced RNA
|
350
|
-
def rna_len
|
351
|
-
return self.get_mrna_seq.length
|
352
|
-
end
|
353
|
-
|
354
|
-
# get length of protein product
|
355
|
-
#
|
356
|
-
# @return [Integer] length of protein product
|
357
|
-
def prot_len
|
358
|
-
return self.get_prot_seq.length
|
359
|
-
end
|
360
|
-
|
361
|
-
# Get the codon sequence at the giving position base on position of amino acid
|
362
|
-
#
|
363
|
-
# @param [Integer] codon position
|
364
|
-
# @return [Bio::Sequence] the codon at given position
|
365
|
-
def get_codon(codon_pos)
|
366
|
-
return self.get_cds_seq().subseq(((codon_pos - 1) * 3) + 1 , ((codon_pos - 1) * 3) + 3)
|
367
|
-
end
|
368
|
-
|
369
|
-
# convert genomic position to codon position
|
370
|
-
#
|
371
|
-
# @param [Integer] genomic position
|
372
|
-
# @return [Array] Return all information of codon at given position
|
373
|
-
def get_prot_pos(pos)
|
374
|
-
|
375
|
-
seqlen = self.get_cds_seq(pos).length
|
376
|
-
if seqlen != 0
|
377
|
-
return [((seqlen - 1) / 3) + 1, ((seqlen - 1) % 3) + 1]
|
378
|
-
else
|
379
|
-
return []
|
380
|
-
end
|
381
|
-
|
76
|
+
def convert(pos)
|
77
|
+
return "#{self[:tchr]}:#{(coeff > 0 ? tstart : tstop) + ((pos - self[:start]) * coeff)}:#{to}"
|
382
78
|
end
|
383
79
|
|
384
80
|
end
|
385
81
|
|
386
|
-
end
|
82
|
+
end
|