bio 1.5.1 → 2.0.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.travis.yml +35 -36
- data/ChangeLog +911 -2554
- data/{gemfiles/Gemfile.travis-ruby2.2 → Gemfile} +0 -3
- data/KNOWN_ISSUES.rdoc +10 -13
- data/LEGAL +0 -10
- data/README.rdoc +40 -96
- data/README_DEV.rdoc +5 -5
- data/RELEASE_NOTES.rdoc +118 -234
- data/Rakefile +13 -43
- data/appveyor.yml +29 -0
- data/bioruby.gemspec +18 -81
- data/bioruby.gemspec.erb +8 -28
- data/doc/ChangeLog-1.5.0 +2919 -0
- data/doc/RELEASE_NOTES-1.5.0.rdoc +285 -0
- data/doc/Tutorial.rd +6 -108
- data/doc/Tutorial.rd.html +19 -98
- data/gemfiles/Gemfile.travis-jruby1.8 +3 -5
- data/gemfiles/Gemfile.travis-jruby1.9 +0 -3
- data/gemfiles/Gemfile.travis-rbx +0 -3
- data/gemfiles/Gemfile.travis-ruby1.8 +3 -5
- data/gemfiles/Gemfile.travis-ruby1.9 +0 -3
- data/gemfiles/Gemfile.windows +6 -0
- data/gemfiles/prepare-gemspec.rb +4 -0
- data/lib/bio.rb +0 -10
- data/lib/bio/appl/blast/genomenet.rb +4 -4
- data/lib/bio/appl/blast/report.rb +40 -8
- data/lib/bio/appl/fasta/format10.rb +2 -1
- data/lib/bio/command.rb +10 -0
- data/lib/bio/data/codontable.rb +99 -3
- data/lib/bio/db/aaindex.rb +74 -5
- data/lib/bio/db/gff.rb +3 -1
- data/lib/bio/db/kegg/common.rb +14 -0
- data/lib/bio/db/kegg/genes.rb +26 -0
- data/lib/bio/db/kegg/pathway.rb +5 -11
- data/lib/bio/db/soft.rb +2 -2
- data/lib/bio/io/flatfile/autodetection.rb +5 -0
- data/lib/bio/io/togows.rb +5 -5
- data/lib/bio/map.rb +4 -4
- data/lib/bio/sequence/format.rb +1 -0
- data/lib/bio/util/restriction_enzyme/range/sequence_range/calculated_cuts.rb +1 -1
- data/lib/bio/util/sirna.rb +2 -0
- data/lib/bio/version.rb +6 -8
- data/sample/color_scheme_aa.rb +82 -0
- data/sample/color_scheme_na.rb +5 -6
- data/sample/fastq2html.cwl +23 -0
- data/sample/fastq2html.rb +94 -0
- data/sample/fastq2html.testdata.yaml +5 -0
- data/sample/na2aa.cwl +23 -0
- data/sample/na2aa.rb +11 -25
- data/sample/na2aa.testdata.yaml +7 -0
- data/sample/rev_comp.cwl +23 -0
- data/sample/rev_comp.rb +20 -0
- data/sample/rev_comp.testdata.yaml +7 -0
- data/sample/test_restriction_enzyme_long.rb +1 -1
- data/test/network/bio/db/kegg/test_genes_hsa7422.rb +91 -0
- data/test/unit/bio/appl/blast/test_report.rb +4 -4
- data/test/unit/bio/data/test_codontable.rb +3 -0
- data/test/unit/bio/db/test_gff.rb +5 -0
- data/test/unit/bio/test_alignment.rb +2 -2
- metadata +20 -77
- data/bin/bioruby +0 -47
- data/bin/br_biofetch.rb +0 -71
- data/bin/br_bioflat.rb +0 -293
- data/bin/br_biogetseq.rb +0 -45
- data/bin/br_pmfetch.rb +0 -422
- data/lib/bio/appl/blast/xmlparser.rb +0 -236
- data/lib/bio/db/biosql/biosql_to_biosequence.rb +0 -78
- data/lib/bio/db/biosql/sequence.rb +0 -444
- data/lib/bio/db/phyloxml/phyloxml.xsd +0 -582
- data/lib/bio/db/phyloxml/phyloxml_elements.rb +0 -1197
- data/lib/bio/db/phyloxml/phyloxml_parser.rb +0 -1001
- data/lib/bio/db/phyloxml/phyloxml_writer.rb +0 -227
- data/lib/bio/io/biosql/ar-biosql.rb +0 -257
- data/lib/bio/io/biosql/biosql.rb +0 -39
- data/lib/bio/io/biosql/config/database.yml +0 -21
- data/lib/bio/io/sql.rb +0 -79
- data/lib/bio/shell.rb +0 -44
- data/lib/bio/shell/core.rb +0 -578
- data/lib/bio/shell/demo.rb +0 -146
- data/lib/bio/shell/interface.rb +0 -217
- data/lib/bio/shell/irb.rb +0 -94
- data/lib/bio/shell/object.rb +0 -71
- data/lib/bio/shell/plugin/blast.rb +0 -42
- data/lib/bio/shell/plugin/codon.rb +0 -218
- data/lib/bio/shell/plugin/das.rb +0 -58
- data/lib/bio/shell/plugin/emboss.rb +0 -23
- data/lib/bio/shell/plugin/entry.rb +0 -137
- data/lib/bio/shell/plugin/flatfile.rb +0 -101
- data/lib/bio/shell/plugin/midi.rb +0 -430
- data/lib/bio/shell/plugin/ncbirest.rb +0 -68
- data/lib/bio/shell/plugin/obda.rb +0 -45
- data/lib/bio/shell/plugin/psort.rb +0 -56
- data/lib/bio/shell/plugin/seq.rb +0 -248
- data/lib/bio/shell/plugin/togows.rb +0 -40
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/bioruby_generator.rb +0 -29
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_classes.rhtml +0 -4
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_log.rhtml +0 -27
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_methods.rhtml +0 -11
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_modules.rhtml +0 -4
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/_variables.rhtml +0 -7
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby-bg.gif +0 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby-gem.png +0 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby-link.gif +0 -0
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby.css +0 -368
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby.rhtml +0 -47
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby_controller.rb +0 -144
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/bioruby_helper.rb +0 -47
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/commands.rhtml +0 -8
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/history.rhtml +0 -10
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/index.rhtml +0 -26
- data/lib/bio/shell/rails/vendor/plugins/bioruby/generators/bioruby/templates/spinner.gif +0 -0
- data/lib/bio/shell/script.rb +0 -25
- data/lib/bio/shell/setup.rb +0 -108
- data/lib/bio/shell/web.rb +0 -102
- data/sample/test_phyloxml_big.rb +0 -205
- data/setup.rb +0 -1600
- data/test/data/phyloxml/apaf.xml +0 -666
- data/test/data/phyloxml/bcl_2.xml +0 -2097
- data/test/data/phyloxml/made_up.xml +0 -144
- data/test/data/phyloxml/ncbi_taxonomy_mollusca_short.xml +0 -65
- data/test/data/phyloxml/phyloxml_examples.xml +0 -415
- data/test/unit/bio/db/biosql/tc_biosql.rb +0 -114
- data/test/unit/bio/db/biosql/ts_suite_biosql.rb +0 -8
- data/test/unit/bio/db/test_phyloxml.rb +0 -821
- data/test/unit/bio/db/test_phyloxml_writer.rb +0 -334
- data/test/unit/bio/shell/plugin/test_seq.rb +0 -187
- data/test/unit/bio/test_shell.rb +0 -20
@@ -1,78 +0,0 @@
|
|
1
|
-
#
|
2
|
-
# = bio/db/biosql/biosql_to_biosequence.rb - Bio::SQL::Sequence to Bio::Sequence adapter module
|
3
|
-
#
|
4
|
-
# Copyright:: Copyright (C) 2008
|
5
|
-
# Naohisa Goto <ng@bioruby.org>,
|
6
|
-
# Raoul Jean Pierre Bonnal
|
7
|
-
# License:: The Ruby License
|
8
|
-
#
|
9
|
-
# $Id:$
|
10
|
-
#
|
11
|
-
|
12
|
-
require 'bio/sequence'
|
13
|
-
require 'bio/sequence/adapter'
|
14
|
-
require 'bio/sequence/dblink'
|
15
|
-
|
16
|
-
# Internal use only. Normal users should not use this module.
|
17
|
-
#
|
18
|
-
# Bio::SQL::Sequence to Bio::Sequence adapter module.
|
19
|
-
# It is internally used in Bio::SQL::Sequence#to_biosequence.
|
20
|
-
#
|
21
|
-
module Bio::Sequence::Adapter::BioSQL
|
22
|
-
|
23
|
-
extend Bio::Sequence::Adapter
|
24
|
-
|
25
|
-
private
|
26
|
-
|
27
|
-
def_biosequence_adapter :seq
|
28
|
-
|
29
|
-
def_biosequence_adapter :entry_id
|
30
|
-
|
31
|
-
def_biosequence_adapter :primary_accession
|
32
|
-
|
33
|
-
def_biosequence_adapter :secondary_accessions
|
34
|
-
|
35
|
-
def_biosequence_adapter :molecule_type
|
36
|
-
|
37
|
-
#--
|
38
|
-
#TODO: identify where is stored data_class in biosql
|
39
|
-
#++
|
40
|
-
|
41
|
-
def_biosequence_adapter :data_class
|
42
|
-
|
43
|
-
def_biosequence_adapter :definition, :description
|
44
|
-
|
45
|
-
def_biosequence_adapter :topology
|
46
|
-
|
47
|
-
def_biosequence_adapter :date_created
|
48
|
-
|
49
|
-
def_biosequence_adapter :date_modified
|
50
|
-
#do |bs|
|
51
|
-
# Date.parse(bs.date_modified.to_s).strftime("%d-%b-%Y").upcase
|
52
|
-
# end
|
53
|
-
|
54
|
-
def_biosequence_adapter :division
|
55
|
-
|
56
|
-
def_biosequence_adapter :sequence_version
|
57
|
-
|
58
|
-
def_biosequence_adapter :keywords
|
59
|
-
|
60
|
-
def_biosequence_adapter :species
|
61
|
-
|
62
|
-
def_biosequence_adapter :classification, :taxonomy
|
63
|
-
|
64
|
-
def_biosequence_adapter :references
|
65
|
-
|
66
|
-
def_biosequence_adapter :features
|
67
|
-
|
68
|
-
def_biosequence_adapter :comments
|
69
|
-
|
70
|
-
def_biosequence_adapter :other_seqids do |orig|
|
71
|
-
orig.identifier.split(',').collect do |dblink|
|
72
|
-
database, id = dblink.split(':')
|
73
|
-
Bio::Sequence::DBLink.new(database,id)
|
74
|
-
end
|
75
|
-
end
|
76
|
-
|
77
|
-
end #module Bio::Sequence::Adapter::BioSQL
|
78
|
-
|
@@ -1,444 +0,0 @@
|
|
1
|
-
|
2
|
-
#TODO save on db reading from a genbank or embl object
|
3
|
-
module Bio
|
4
|
-
class SQL
|
5
|
-
|
6
|
-
|
7
|
-
|
8
|
-
class Sequence
|
9
|
-
private
|
10
|
-
# example
|
11
|
-
# bioentry_qualifier_anchor :molecule_type, :synonym=>'mol_type'
|
12
|
-
# this function creates other 3 functions, molecule_type, molecule_type=, molecule_type_update
|
13
|
-
#molecule_type => return an array of strings, where each string is the value associated with the qualifier, ordered by rank.
|
14
|
-
#molecule_type=value add a bioentry_qualifier value to the table
|
15
|
-
#molecule_type_update(value, rank) update an entry of the table with an existing rank
|
16
|
-
#the method inferr the qualifier term from the name of the first symbol, or you can specify a synonym to use
|
17
|
-
|
18
|
-
#creating an object with to_biosql is transaction safe.
|
19
|
-
|
20
|
-
#TODO: implement setting for more than a qualifier-vale.
|
21
|
-
def self.bioentry_qualifier_anchor(sym, *args)
|
22
|
-
options = args.first || Hash.new
|
23
|
-
#options.assert_valid_keys(:rank,:synonym,:multi)
|
24
|
-
method_reader = sym.to_s.to_sym
|
25
|
-
method_writer_operator = (sym.to_s+"=").to_sym
|
26
|
-
method_writer_modder = (sym.to_s+"_update").to_sym
|
27
|
-
synonym = options[:synonym].nil? ? sym.to_s : options[:synonym]
|
28
|
-
|
29
|
-
#DELETE #Bio::SQL::Term.create(:name=>synonym, :ontology=> Bio::SQL::Ontology.find_by_name('Annotation Tags')) unless Bio::SQL::Term.exists?(:name =>synonym)
|
30
|
-
send :define_method, method_reader do
|
31
|
-
#return an array of bioentry_qualifier_values
|
32
|
-
begin
|
33
|
-
#DELETE ontology_annotation_tags = Ontology.find_or_create({:name=>'Annotation Tags'})
|
34
|
-
term = Term.first(:conditions=>["name = ?",synonym]) || Term.create({:name => synonym, :ontology=> Ontology.first(:conditions=>["name = ?",'Annotation Tags'])})
|
35
|
-
bioentry_qualifier_values = @entry.bioentry_qualifier_values.all(:conditions=>["term_id = ?",term.term_id])
|
36
|
-
data = bioentry_qualifier_values.map{|row| row.value} unless bioentry_qualifier_values.nil?
|
37
|
-
begin
|
38
|
-
# this block try to check if the data retrived is a
|
39
|
-
# Date or not and change it according to GenBank/EMBL format
|
40
|
-
# in that case return a string
|
41
|
-
# otherwise the []
|
42
|
-
Date.parse(data.to_s).strftime("%d-%b-%Y").upcase
|
43
|
-
rescue ArgumentError, TypeError, NoMethodError, NameError
|
44
|
-
data
|
45
|
-
end
|
46
|
-
rescue Exception => e
|
47
|
-
puts "Reader Error: #{synonym} #{e.message}"
|
48
|
-
end
|
49
|
-
end
|
50
|
-
|
51
|
-
send :define_method, method_writer_operator do |value|
|
52
|
-
begin
|
53
|
-
#DELETE ontology_annotation_tags = Ontology.find_or_create({:name=>'Annotation Tags'})
|
54
|
-
term = Term.first(:conditions=>["name = ?",synonym]) || Term.create({:name => synonym, :ontology=> Ontology.first(:conditions=>["name = ?",'Annotation Tags'])})
|
55
|
-
datas = @entry.bioentry_qualifier_values.all(:conditions=>["term_id = ?",term.term_id])
|
56
|
-
#add an element incrementing the rank or setting the first to 1
|
57
|
-
be_qu_va=@entry.bioentry_qualifier_values.build({:term=>term, :rank=>(datas.empty? ? 1 : datas.last.rank.succ), :value=>value})
|
58
|
-
be_qu_va.save
|
59
|
-
rescue Exception => e
|
60
|
-
puts "WriterOperator= Error: #{synonym} #{e.message}"
|
61
|
-
end
|
62
|
-
end
|
63
|
-
|
64
|
-
send :define_method, method_writer_modder do |value, rank|
|
65
|
-
begin
|
66
|
-
#DELETE ontology_annotation_tags = Ontology.find_or_create({:name=>'Annotation Tags'})
|
67
|
-
term = Term.first(:conditions=>["name = ?",synonym]) || Term.create({:name => synonym, :ontology=> Ontology.first(:conditions=>["name = ?",'Annotation Tags'])})
|
68
|
-
data = @entry.bioentry_qualifier_values.all(:term_id=>term.term_id, :rank=>rank)
|
69
|
-
if data.nil?
|
70
|
-
send method_writer_operator, value
|
71
|
-
else
|
72
|
-
data.value=value
|
73
|
-
data.save
|
74
|
-
end
|
75
|
-
rescue Exception => e
|
76
|
-
puts "WriterModder Error: #{synonym} #{e.message}"
|
77
|
-
end
|
78
|
-
end
|
79
|
-
|
80
|
-
end
|
81
|
-
|
82
|
-
public
|
83
|
-
attr_reader :entry
|
84
|
-
|
85
|
-
def delete
|
86
|
-
#TODO: check is references connected to this bioentry are leaf or not.
|
87
|
-
#actually I think it should be more sofisticated, check if there are
|
88
|
-
#other bioentries connected to references; if not delete 'em
|
89
|
-
@entry.references.each { |ref| ref.delete if ref.bioentries.size==1}
|
90
|
-
@entry.destroy
|
91
|
-
end
|
92
|
-
|
93
|
-
def get_seqfeature(sf)
|
94
|
-
|
95
|
-
#in seqfeature BioSQL class
|
96
|
-
locations_str = sf.locations.map{|loc| loc.to_s}.join(',')
|
97
|
-
#pp sf.locations.inspect
|
98
|
-
locations_str = "join(#{locations_str})" if sf.locations.count>1
|
99
|
-
Bio::Feature.new(sf.type_term.name, locations_str,sf.seqfeature_qualifier_values.collect{|sfqv| Bio::Feature::Qualifier.new(sfqv.term.name,sfqv.value)})
|
100
|
-
end
|
101
|
-
|
102
|
-
def length=(len)
|
103
|
-
@entry.biosequence.length=len
|
104
|
-
end
|
105
|
-
|
106
|
-
def initialize(options={})
|
107
|
-
#options.assert_valid_keys(:entry, :biodatabase,:biosequence)
|
108
|
-
return @entry = options[:entry] unless options[:entry].nil?
|
109
|
-
|
110
|
-
return to_biosql(options[:biosequence], options[:biodatabase]) unless options[:biosequence].nil? or options[:biodatabase].nil?
|
111
|
-
|
112
|
-
end
|
113
|
-
|
114
|
-
def to_biosql(bs,biodatabase)
|
115
|
-
#DELETE #Transcaction works greatly!!!
|
116
|
-
begin
|
117
|
-
#DELETE Bioentry.transaction do
|
118
|
-
@entry = biodatabase.bioentries.build({:name=>bs.entry_id})
|
119
|
-
|
120
|
-
puts "primary" if $DEBUG
|
121
|
-
self.primary_accession = bs.primary_accession
|
122
|
-
|
123
|
-
puts "def" if $DEBUG
|
124
|
-
self.definition = bs.definition unless bs.definition.nil?
|
125
|
-
|
126
|
-
puts "seqver" if $DEBUG
|
127
|
-
self.sequence_version = bs.sequence_version || 0
|
128
|
-
|
129
|
-
puts "divi" if $DEBUG
|
130
|
-
self.division = bs.division unless bs.division.nil?
|
131
|
-
|
132
|
-
puts "identifier" if $DEBUG
|
133
|
-
self.identifier = bs.other_seqids.collect{|dblink| "#{dblink.database}:#{dblink.id}"}.join(';') unless bs.other_seqids.nil?
|
134
|
-
@entry.save
|
135
|
-
puts "secacc" if $DEBUG
|
136
|
-
|
137
|
-
bs.secondary_accessions.each do |sa|
|
138
|
-
puts "#{sa}" if $DEBUG
|
139
|
-
#write as qualifier every secondary accession into the array
|
140
|
-
self.secondary_accessions = sa
|
141
|
-
end unless bs.secondary_accessions.nil?
|
142
|
-
|
143
|
-
|
144
|
-
#to create the sequence entry needs to exists
|
145
|
-
puts "seq" if $DEBUG
|
146
|
-
puts bs.seq if $DEBUG
|
147
|
-
self.seq = bs.seq unless bs.seq.nil?
|
148
|
-
puts "mol" if $DEBUG
|
149
|
-
|
150
|
-
self.molecule_type = bs.molecule_type unless bs.molecule_type.nil?
|
151
|
-
puts "dc" if $DEBUG
|
152
|
-
|
153
|
-
self.data_class = bs.data_class unless bs.data_class.nil?
|
154
|
-
puts "top" if $DEBUG
|
155
|
-
self.topology = bs.topology unless bs.topology.nil?
|
156
|
-
puts "datec" if $DEBUG
|
157
|
-
self.date_created = bs.date_created unless bs.date_created.nil?
|
158
|
-
puts "datemod" if $DEBUG
|
159
|
-
self.date_modified = bs.date_modified unless bs.date_modified.nil?
|
160
|
-
puts "key" if $DEBUG
|
161
|
-
|
162
|
-
bs.keywords.each do |kw|
|
163
|
-
#write as qualifier every secondary accessions into the array
|
164
|
-
self.keywords = kw
|
165
|
-
end unless bs.keywords.nil?
|
166
|
-
|
167
|
-
puts "spec" if $DEBUG
|
168
|
-
#self.species = bs.species unless bs.species.nil?
|
169
|
-
self.species = bs.species unless bs.species.empty?
|
170
|
-
puts "Debug: #{bs.species}" if $DEBUG
|
171
|
-
puts "Debug: feat..start" if $DEBUG
|
172
|
-
|
173
|
-
bs.features.each do |feat|
|
174
|
-
self.feature=feat
|
175
|
-
end unless bs.features.nil?
|
176
|
-
|
177
|
-
puts "Debug: feat...end" if $DEBUG
|
178
|
-
bs.references.each do |reference|
|
179
|
-
self.reference=reference
|
180
|
-
end unless bs.references.nil?
|
181
|
-
|
182
|
-
bs.comments.each do |comment|
|
183
|
-
self.comment=comment
|
184
|
-
end unless bs.comments.nil?
|
185
|
-
|
186
|
-
#DELETE end #transaction
|
187
|
-
return self
|
188
|
-
rescue Exception => e
|
189
|
-
puts "to_biosql exception: #{e}"
|
190
|
-
puts $!
|
191
|
-
end #rescue
|
192
|
-
end #to_biosql
|
193
|
-
|
194
|
-
|
195
|
-
def name
|
196
|
-
@entry.name
|
197
|
-
end
|
198
|
-
alias entry_id name
|
199
|
-
|
200
|
-
def name=(value)
|
201
|
-
@entry.name=value
|
202
|
-
end
|
203
|
-
alias entry_id= name=
|
204
|
-
|
205
|
-
def primary_accession
|
206
|
-
@entry.accession
|
207
|
-
end
|
208
|
-
|
209
|
-
def primary_accession=(value)
|
210
|
-
@entry.accession=value
|
211
|
-
end
|
212
|
-
|
213
|
-
#TODO def secondary_accession
|
214
|
-
# @entry.bioentry_qualifier_values
|
215
|
-
# end
|
216
|
-
|
217
|
-
def organism
|
218
|
-
@entry.taxon.nil? ? "" : "#{@entry.taxon.taxon_scientific_name.name}"+ (@entry.taxon.taxon_genbank_common_name ? "(#{@entry.taxon.taxon_genbank_common_name.name})" : '')
|
219
|
-
end
|
220
|
-
alias species organism
|
221
|
-
|
222
|
-
def organism=(value)
|
223
|
-
#FIX there is a shortcut
|
224
|
-
taxon_name=TaxonName.first(:conditions=>["name = ? and name_class = ?",value.gsub(/\s+\(.+\)/,''),'scientific name'])
|
225
|
-
if taxon_name.nil?
|
226
|
-
puts "Error value doesn't exists in taxon_name table with scientific name constraint."
|
227
|
-
else
|
228
|
-
@entry.taxon_id=taxon_name.taxon_id
|
229
|
-
@entry.save
|
230
|
-
end
|
231
|
-
end
|
232
|
-
alias species= organism=
|
233
|
-
|
234
|
-
def database
|
235
|
-
@entry.biodatabase.name
|
236
|
-
end
|
237
|
-
|
238
|
-
def database_desc
|
239
|
-
@entry.biodatabase.description
|
240
|
-
end
|
241
|
-
|
242
|
-
def version
|
243
|
-
@entry.version
|
244
|
-
end
|
245
|
-
alias sequence_version version
|
246
|
-
|
247
|
-
def version=(value)
|
248
|
-
@entry.version=value
|
249
|
-
end
|
250
|
-
alias sequence_version= version=
|
251
|
-
|
252
|
-
def division
|
253
|
-
@entry.division
|
254
|
-
end
|
255
|
-
|
256
|
-
def division=(value)
|
257
|
-
@entry.division=value
|
258
|
-
end
|
259
|
-
|
260
|
-
def description
|
261
|
-
@entry.description
|
262
|
-
end
|
263
|
-
alias definition description
|
264
|
-
|
265
|
-
def description=(value)
|
266
|
-
@entry.description=value
|
267
|
-
end
|
268
|
-
alias definition= description=
|
269
|
-
|
270
|
-
def identifier
|
271
|
-
@entry.identifier
|
272
|
-
end
|
273
|
-
alias other_seqids identifier
|
274
|
-
|
275
|
-
def identifier=(value)
|
276
|
-
@entry.identifier=value
|
277
|
-
end
|
278
|
-
|
279
|
-
bioentry_qualifier_anchor :data_class
|
280
|
-
bioentry_qualifier_anchor :molecule_type, :synonym=>'mol_type'
|
281
|
-
bioentry_qualifier_anchor :topology
|
282
|
-
bioentry_qualifier_anchor :date_created
|
283
|
-
bioentry_qualifier_anchor :date_modified, :synonym=>'date_changed'
|
284
|
-
bioentry_qualifier_anchor :keywords, :synonym=>'keyword'
|
285
|
-
bioentry_qualifier_anchor :secondary_accessions, :synonym=>'secondary_accession'
|
286
|
-
|
287
|
-
def features
|
288
|
-
@entry.seqfeatures.collect do |sf|
|
289
|
-
self.get_seqfeature(sf)
|
290
|
-
end
|
291
|
-
end
|
292
|
-
|
293
|
-
def feature=(feat)
|
294
|
-
#ToDo: avoid Ontology find here, probably more efficient create class variables
|
295
|
-
#DELETE type_term_ontology = Ontology.find_or_create({:name=>'SeqFeature Keys'})
|
296
|
-
puts "feature:type_term = #{feat.feature}" if $DEBUG
|
297
|
-
type_term = Term.first(:conditions=>["name = ?", feat.feature]) || Term.create({:name=>feat.feature, :ontology=>Ontology.first(:conditions=>["name = ?",'SeqFeature Keys'])})
|
298
|
-
#DELETE source_term_ontology = Ontology.find_or_create({:name=>'SeqFeature Sources'})
|
299
|
-
puts "feature:source_term" if $DEBUG
|
300
|
-
source_term = Term.first(:conditions=>["name = ?",'EMBLGenBankSwit'])
|
301
|
-
puts "feature:seqfeature" if $DEBUG
|
302
|
-
seqfeature = @entry.seqfeatures.build({:source_term=>source_term, :type_term=>type_term, :rank=>@entry.seqfeatures.count.succ, :display_name=>''})
|
303
|
-
seqfeature.save
|
304
|
-
puts "feature:location" if $DEBUG
|
305
|
-
feat.locations.each do |loc|
|
306
|
-
location = seqfeature.locations.build({:seqfeature=>seqfeature, :start_pos=>loc.from, :end_pos=>loc.to, :strand=>loc.strand, :rank=>seqfeature.locations.count.succ})
|
307
|
-
location.save
|
308
|
-
end
|
309
|
-
|
310
|
-
#DELETE qual_term_ontology = Ontology.find_or_create({:name=>'Annotation Tags'})
|
311
|
-
|
312
|
-
puts "feature:qualifier" if $DEBUG
|
313
|
-
feat.each do |qualifier|
|
314
|
-
#DELETE qual_term = Term.find_or_create({:name=>qualifier.qualifier}, {:ontology=>qual_term_ontology})
|
315
|
-
qual_term = Term.first(:conditions=>["name = ?", qualifier.qualifier]) || Term.create({:name=>qualifier.qualifier, :ontology=>Ontology.first(:conditions=>["name = ?", 'Annotation Tags'])})
|
316
|
-
qual = seqfeature.seqfeature_qualifier_values.build({:seqfeature=>seqfeature, :term=>qual_term, :value=>qualifier.value.to_s, :rank=>seqfeature.seqfeature_qualifier_values.count.succ})
|
317
|
-
qual.save
|
318
|
-
|
319
|
-
end
|
320
|
-
end
|
321
|
-
|
322
|
-
#return the seqfeature mapped from BioSQL with a type_term like 'CDS'
|
323
|
-
def cdsfeatures
|
324
|
-
@entry.cdsfeatures
|
325
|
-
end
|
326
|
-
|
327
|
-
# Returns the sequence.
|
328
|
-
# Returns a Bio::Sequence::Generic object.
|
329
|
-
|
330
|
-
def seq
|
331
|
-
s = @entry.biosequence
|
332
|
-
Bio::Sequence::Generic.new(s ? s.seq : '')
|
333
|
-
end
|
334
|
-
|
335
|
-
def seq=(value)
|
336
|
-
#TODO: revise this piece of code.
|
337
|
-
#chk which type of alphabet is, NU/NA/nil
|
338
|
-
if @entry.biosequence.nil?
|
339
|
-
#DELETE puts "intoseq1"
|
340
|
-
@entry.biosequence = Biosequence.new(:seq=>value)
|
341
|
-
# biosequence = @entry.biosequence.build({:seq=>value})
|
342
|
-
@entry.biosequence.save
|
343
|
-
# biosequence.save
|
344
|
-
else
|
345
|
-
@entry.biosequence.seq=value
|
346
|
-
end
|
347
|
-
self.length=value.length
|
348
|
-
#DELETE #@entry.biosequence.length=value.length
|
349
|
-
#DELETE #break
|
350
|
-
@entry.save
|
351
|
-
end
|
352
|
-
|
353
|
-
#report parents and exclude info with "no rank". Now I report rank == class but ... Question ? Have to be reported taxonomy with rank=="class"?
|
354
|
-
def taxonomy
|
355
|
-
tax = []
|
356
|
-
taxon = Taxon.first(:conditions=>["taxon_id = ?",@entry.taxon.parent_taxon_id])
|
357
|
-
while taxon and taxon.taxon_id != taxon.parent_taxon_id and taxon.node_rank!='no rank'
|
358
|
-
tax << taxon.taxon_scientific_name.name if taxon.node_rank!='class'
|
359
|
-
#Note: I don't like this call very much, correct with a relationship in the ref class.
|
360
|
-
taxon = Taxon.first(:conditions=>["taxon_id = ?",taxon.parent_taxon_id])
|
361
|
-
end
|
362
|
-
tax.reverse
|
363
|
-
end
|
364
|
-
|
365
|
-
def length
|
366
|
-
@entry.biosequence.length
|
367
|
-
end
|
368
|
-
|
369
|
-
def references
|
370
|
-
#return and array of hash, hash has these keys ["title", "dbxref_id", "reference_id", "authors", "crc", "location"]
|
371
|
-
#probably would be better to d a class refrence to collect these informations
|
372
|
-
@entry.bioentry_references.collect do |bio_ref|
|
373
|
-
hash = Hash.new
|
374
|
-
hash['authors'] = bio_ref.reference.authors.gsub(/\.\s/, "\.\s\|").split(/\|/) if (bio_ref.reference and bio_ref.reference.authors)
|
375
|
-
|
376
|
-
hash['sequence_position'] = "#{bio_ref.start_pos}-#{bio_ref.end_pos}" if (bio_ref.start_pos and bio_ref.end_pos)
|
377
|
-
hash['title'] = bio_ref.reference.title
|
378
|
-
hash['embl_gb_record_number'] = bio_ref.rank
|
379
|
-
#TODO: solve the problem with specific comment per reference.
|
380
|
-
#TODO: get dbxref
|
381
|
-
#take a look when location is build up in def reference=(value)
|
382
|
-
|
383
|
-
bio_ref.reference.location.split('|').each do |element|
|
384
|
-
key,value=element.split('=')
|
385
|
-
hash[key]=value
|
386
|
-
end unless bio_ref.reference.location.nil?
|
387
|
-
|
388
|
-
hash['xrefs'] = bio_ref.reference.dbxref ? "#{bio_ref.reference.dbxref.dbname}; #{bio_ref.reference.dbxref.accession}." : ''
|
389
|
-
Bio::Reference.new(hash)
|
390
|
-
end
|
391
|
-
end
|
392
|
-
|
393
|
-
def comments
|
394
|
-
@entry.comments.map do |comment|
|
395
|
-
comment.comment_text
|
396
|
-
end
|
397
|
-
end
|
398
|
-
|
399
|
-
def reference=(value)
|
400
|
-
locations=Array.new
|
401
|
-
locations << "journal=#{value.journal}" unless value.journal.empty?
|
402
|
-
locations << "volume=#{value.volume}" unless value.volume.empty?
|
403
|
-
locations << "issue=#{value.issue}" unless value.issue.empty?
|
404
|
-
locations << "pages=#{value.pages}" unless value.pages.empty?
|
405
|
-
locations << "year=#{value.year}" unless value.year.empty?
|
406
|
-
locations << "pubmed=#{value.pubmed}" unless value.pubmed.empty?
|
407
|
-
locations << "medline=#{value.medline}" unless value.medline.empty?
|
408
|
-
locations << "doi=#{value.doi}" unless value.doi.nil?
|
409
|
-
locations << "abstract=#{value.abstract}" unless value.abstract.empty?
|
410
|
-
locations << "url=#{value.url}" unless value.url.nil?
|
411
|
-
locations << "mesh=#{value.mesh}" unless value.mesh.empty?
|
412
|
-
locations << "affiliations=#{value.affiliations}" unless value.affiliations.empty?
|
413
|
-
locations << "comments=#{value.comments.join('~')}"unless value.comments.nil?
|
414
|
-
start_pos, end_pos = value.sequence_position ? value.sequence_position.gsub(/\s*/,'').split('-') : [nil,nil]
|
415
|
-
reference= Reference.first(:conditions=>["title = ?",value.title]) || Reference.create({:title=>value.title,:authors=>value.authors.join(' '), :location=>locations.join('|')})
|
416
|
-
bio_reference=@entry.bioentry_references.build({:reference=>reference,:rank=>value.embl_gb_record_number, :start_pos=>start_pos, :end_pos=>end_pos})
|
417
|
-
bio_reference.save
|
418
|
-
end
|
419
|
-
|
420
|
-
def comment=(value)
|
421
|
-
#DELETE comment=Comment.new({:bioentry=>@entry, :comment_text=>value, :rank=>@entry.comments.count.succ})
|
422
|
-
comment = @entry.comments.build({:comment_text=>value, :rank=>@entry.comments.count.succ})
|
423
|
-
comment.save
|
424
|
-
end
|
425
|
-
|
426
|
-
def save
|
427
|
-
#I should add chks for SQL errors
|
428
|
-
@entry.biosequence.save
|
429
|
-
@entry.save
|
430
|
-
end
|
431
|
-
def to_fasta
|
432
|
-
">" + accession + "\n" + seq.gsub(Regexp.new(".{1,#{60}}"), "\\0\n")
|
433
|
-
end
|
434
|
-
|
435
|
-
def to_fasta_reverse_complememt
|
436
|
-
">" + accession + "\n" + seq.reverse_complement.gsub(Regexp.new(".{1,#{60}}"), "\\0\n")
|
437
|
-
end
|
438
|
-
|
439
|
-
def to_biosequence
|
440
|
-
Bio::Sequence.adapter(self,Bio::Sequence::Adapter::BioSQL)
|
441
|
-
end
|
442
|
-
end #Sequence
|
443
|
-
end #SQL
|
444
|
-
end #Bio
|