bio 1.5.2 → 1.6.0.pre.20181210
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +5 -5
- data/.travis.yml +12 -11
- data/ChangeLog +14 -3106
- data/{gemfiles/Gemfile.travis-ruby2.2 → Gemfile} +0 -1
- data/KNOWN_ISSUES.rdoc +0 -5
- data/README.rdoc +11 -18
- data/RELEASE_NOTES.rdoc +34 -291
- data/Rakefile +13 -9
- data/appveyor.yml +21 -0
- data/bioruby.gemspec +7 -78
- data/bioruby.gemspec.erb +8 -27
- 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 -1
- data/gemfiles/Gemfile.travis-ruby1.8 +4 -4
- data/gemfiles/Gemfile.travis-ruby1.9 +0 -1
- data/gemfiles/prepare-gemspec.rb +4 -0
- data/lib/bio.rb +0 -10
- data/lib/bio/data/codontable.rb +99 -3
- data/lib/bio/io/togows.rb +5 -5
- data/lib/bio/version.rb +6 -8
- data/sample/test_restriction_enzyme_long.rb +1 -1
- data/test/unit/bio/data/test_codontable.rb +3 -0
- metadata +11 -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/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/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
@@ -1,444 +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
|
@@ -1,582 +0,0 @@
|
|
1
|
-
<?xml version="1.0" encoding="UTF-8"?>
|
2
|
-
<!-- -->
|
3
|
-
<!-- phyloXML -->
|
4
|
-
<!-- -->
|
5
|
-
<!-- schema in XMLSchema -->
|
6
|
-
<!-- -->
|
7
|
-
<!-- License: The phyloXML XML Schema Definition is -->
|
8
|
-
<!-- dual-licensed under the LGPL or Ruby's -->
|
9
|
-
<!-- License. -->
|
10
|
-
<!-- You can redistribute and/or modify -->
|
11
|
-
<!-- it under either the terms of the LGPL, -->
|
12
|
-
<!-- or Ruby's License. -->
|
13
|
-
<!-- see: http://www.ruby-lang.org/en/about/license.txt -->
|
14
|
-
<!-- -->
|
15
|
-
<!-- Copyright (c) 2008-2009 Christian M Zmasek -->
|
16
|
-
<!-- -->
|
17
|
-
<!-- www.phyloxml.org -->
|
18
|
-
<!-- Version: 1.10 -->
|
19
|
-
<!-- Last modified: 2009.11.17 by Christian M Zmasek -->
|
20
|
-
<!-- -->
|
21
|
-
<xs:schema xmlns:xs="http://www.w3.org/2001/XMLSchema" xmlns:phy="http://www.phyloxml.org"
|
22
|
-
targetNamespace="http://www.phyloxml.org" elementFormDefault="qualified" attributeFormDefault="unqualified">
|
23
|
-
<xs:annotation>
|
24
|
-
<xs:documentation> phyloXML is an XML language to describe evolutionary trees and associated data. Version: 1.10.
|
25
|
-
License: dual-licensed under the LGPL or Ruby's License. Copyright (c) 2008-2009 Christian M Zmasek.</xs:documentation>
|
26
|
-
</xs:annotation>
|
27
|
-
<!-- phyloxml is the root element:-->
|
28
|
-
<xs:element name="phyloxml" type="phy:Phyloxml"/>
|
29
|
-
<!-- phyloXML definition:-->
|
30
|
-
<xs:complexType name="Phyloxml">
|
31
|
-
<xs:annotation>
|
32
|
-
<xs:documentation> 'phyloxml' is the name of the root element. Phyloxml contains an arbitrary number of
|
33
|
-
'phylogeny' elements (each representing one phylogeny) possibly followed by elements from other namespaces.
|
34
|
-
</xs:documentation>
|
35
|
-
</xs:annotation>
|
36
|
-
<xs:sequence maxOccurs="unbounded">
|
37
|
-
<xs:element name="phylogeny" type="phy:Phylogeny" minOccurs="0" maxOccurs="unbounded"/>
|
38
|
-
<xs:any minOccurs="0" maxOccurs="unbounded" processContents="lax" namespace="##other"/>
|
39
|
-
</xs:sequence>
|
40
|
-
</xs:complexType>
|
41
|
-
<!-- Phylogeny:-->
|
42
|
-
<xs:complexType name="Phylogeny">
|
43
|
-
<xs:annotation>
|
44
|
-
<xs:documentation> Element Phylogeny is used to represent a phylogeny. The required attribute 'rooted' is used
|
45
|
-
to indicate whether the phylogeny is rooted or not. The attribute 'rerootable' can be used to indicate that
|
46
|
-
the phylogeny is not allowed to be rooted differently (i.e. because it is associated with root dependent
|
47
|
-
data, such as gene duplications). The attribute 'type' can be used to indicate the type of phylogeny (i.e.
|
48
|
-
'gene tree'). It is recommended to use the attribute 'branch_length_unit' if the phylogeny has branch
|
49
|
-
lengths. Element clade is used in a recursive manner to describe the topology of a phylogenetic
|
50
|
-
tree.</xs:documentation>
|
51
|
-
</xs:annotation>
|
52
|
-
<xs:sequence>
|
53
|
-
<xs:element name="name" type="xs:token" minOccurs="0"/>
|
54
|
-
<xs:element name="id" type="phy:Id" minOccurs="0"/>
|
55
|
-
<xs:element name="description" type="xs:token" minOccurs="0"/>
|
56
|
-
<xs:element name="date" type="xs:dateTime" minOccurs="0"/>
|
57
|
-
<xs:element name="confidence" type="phy:Confidence" minOccurs="0" maxOccurs="unbounded"/>
|
58
|
-
<xs:element name="clade" type="phy:Clade" minOccurs="0"/>
|
59
|
-
<xs:element name="clade_relation" type="phy:CladeRelation" minOccurs="0" maxOccurs="unbounded"/>
|
60
|
-
<xs:element name="sequence_relation" type="phy:SequenceRelation" minOccurs="0" maxOccurs="unbounded"/>
|
61
|
-
<xs:element name="property" type="phy:Property" minOccurs="0" maxOccurs="unbounded"/>
|
62
|
-
<xs:any minOccurs="0" maxOccurs="unbounded" processContents="lax" namespace="##other"/>
|
63
|
-
</xs:sequence>
|
64
|
-
<xs:attribute name="rooted" type="xs:boolean" use="required"/>
|
65
|
-
<xs:attribute name="rerootable" type="xs:boolean"/>
|
66
|
-
<xs:attribute name="branch_length_unit" type="xs:token"/>
|
67
|
-
<xs:attribute name="type" type="xs:token"/>
|
68
|
-
</xs:complexType>
|
69
|
-
<!-- Clade:-->
|
70
|
-
<xs:complexType name="Clade">
|
71
|
-
<xs:annotation>
|
72
|
-
<xs:documentation> Element Clade is used in a recursive manner to describe the topology of a phylogenetic tree.
|
73
|
-
The parent branch length of a clade can be described either with the 'branch_length' element or the
|
74
|
-
'branch_length' attribute (it is not recommended to use both at the same time, though). Usage of the
|
75
|
-
'branch_length' attribute allows for a less verbose description. Element 'confidence' is used to indicate
|
76
|
-
the support for a clade/parent branch. Element 'events' is used to describe such events as gene-duplications
|
77
|
-
at the root node/parent branch of a clade. Element 'width' is the branch width for this clade (including
|
78
|
-
parent branch). Both 'color' and 'width' elements apply for the whole clade unless overwritten in-sub
|
79
|
-
clades. Attribute 'id_source' is used to link other elements to a clade (on the xml-level).
|
80
|
-
</xs:documentation>
|
81
|
-
</xs:annotation>
|
82
|
-
<xs:sequence>
|
83
|
-
<xs:element name="name" type="xs:token" minOccurs="0"/>
|
84
|
-
<xs:element name="branch_length" type="xs:double" minOccurs="0"/>
|
85
|
-
<xs:element name="confidence" type="phy:Confidence" minOccurs="0" maxOccurs="unbounded"/>
|
86
|
-
<xs:element name="width" type="xs:double" minOccurs="0"/>
|
87
|
-
<xs:element name="color" type="phy:BranchColor" minOccurs="0"/>
|
88
|
-
<xs:element name="node_id" type="phy:Id" minOccurs="0"/>
|
89
|
-
<xs:element name="taxonomy" type="phy:Taxonomy" minOccurs="0" maxOccurs="unbounded"/>
|
90
|
-
<xs:element name="sequence" type="phy:Sequence" minOccurs="0" maxOccurs="unbounded"/>
|
91
|
-
<xs:element name="events" type="phy:Events" minOccurs="0"/>
|
92
|
-
<xs:element name="binary_characters" type="phy:BinaryCharacters" minOccurs="0"/>
|
93
|
-
<xs:element name="distribution" type="phy:Distribution" minOccurs="0" maxOccurs="unbounded"/>
|
94
|
-
<xs:element name="date" type="phy:Date" minOccurs="0"/>
|
95
|
-
<xs:element name="reference" type="phy:Reference" minOccurs="0" maxOccurs="unbounded"/>
|
96
|
-
<xs:element name="property" type="phy:Property" minOccurs="0" maxOccurs="unbounded"/>
|
97
|
-
<xs:element name="clade" type="phy:Clade" minOccurs="0" maxOccurs="unbounded"/>
|
98
|
-
<xs:any minOccurs="0" maxOccurs="unbounded" processContents="lax" namespace="##other"/>
|
99
|
-
</xs:sequence>
|
100
|
-
<xs:attribute name="branch_length" type="xs:double"/>
|
101
|
-
<xs:attribute name="id_source" type="phy:id_source"/>
|
102
|
-
</xs:complexType>
|
103
|
-
<!-- Taxonomy:-->
|
104
|
-
<xs:complexType name="Taxonomy">
|
105
|
-
<xs:annotation>
|
106
|
-
<xs:documentation> Element Taxonomy is used to describe taxonomic information for a clade. Element 'code' is
|
107
|
-
intended to store UniProt/Swiss-Prot style organism codes (e.g. 'APLCA' for the California sea hare 'Aplysia
|
108
|
-
californica') or other styles of mnemonics (e.g. 'Aca'). Element 'authority' is used to keep the authority,
|
109
|
-
such as 'J. G. Cooper, 1863', associated with the 'scientific_name'. Element 'id' is used for a unique
|
110
|
-
identifier of a taxon (for example '6500' with 'ncbi_taxonomy' as 'provider' for the California sea hare).
|
111
|
-
Attribute 'id_source' is used to link other elements to a taxonomy (on the xml-level).</xs:documentation>
|
112
|
-
</xs:annotation>
|
113
|
-
<xs:sequence>
|
114
|
-
<xs:element name="id" type="phy:Id" minOccurs="0"/>
|
115
|
-
<xs:element name="code" type="phy:TaxonomyCode" minOccurs="0"/>
|
116
|
-
<xs:element name="scientific_name" type="xs:token" minOccurs="0"/>
|
117
|
-
<xs:element name="authority" type="xs:token" minOccurs="0"/>
|
118
|
-
<xs:element name="common_name" type="xs:token" minOccurs="0" maxOccurs="unbounded"/>
|
119
|
-
<xs:element name="synonym" type="xs:token" minOccurs="0" maxOccurs="unbounded"/>
|
120
|
-
<xs:element name="rank" type="phy:Rank" minOccurs="0"/>
|
121
|
-
<xs:element name="uri" type="phy:Uri" minOccurs="0"/>
|
122
|
-
<xs:any minOccurs="0" maxOccurs="unbounded" processContents="lax" namespace="##other"/>
|
123
|
-
</xs:sequence>
|
124
|
-
<xs:attribute name="id_source" type="phy:id_source"/>
|
125
|
-
</xs:complexType>
|
126
|
-
<xs:simpleType name="TaxonomyCode">
|
127
|
-
<xs:restriction base="xs:token">
|
128
|
-
<xs:pattern value="[a-zA-Z0-9_]{2,10}"/>
|
129
|
-
</xs:restriction>
|
130
|
-
</xs:simpleType>
|
131
|
-
<xs:simpleType name="Rank">
|
132
|
-
<xs:restriction base="xs:token">
|
133
|
-
<xs:enumeration value="domain"/>
|
134
|
-
<xs:enumeration value="kingdom"/>
|
135
|
-
<xs:enumeration value="subkingdom"/>
|
136
|
-
<xs:enumeration value="branch"/>
|
137
|
-
<xs:enumeration value="infrakingdom"/>
|
138
|
-
<xs:enumeration value="superphylum"/>
|
139
|
-
<xs:enumeration value="phylum"/>
|
140
|
-
<xs:enumeration value="subphylum"/>
|
141
|
-
<xs:enumeration value="infraphylum"/>
|
142
|
-
<xs:enumeration value="microphylum"/>
|
143
|
-
<xs:enumeration value="superdivision"/>
|
144
|
-
<xs:enumeration value="division"/>
|
145
|
-
<xs:enumeration value="subdivision"/>
|
146
|
-
<xs:enumeration value="infradivision"/>
|
147
|
-
<xs:enumeration value="superclass"/>
|
148
|
-
<xs:enumeration value="class"/>
|
149
|
-
<xs:enumeration value="subclass"/>
|
150
|
-
<xs:enumeration value="infraclass"/>
|
151
|
-
<xs:enumeration value="superlegion"/>
|
152
|
-
<xs:enumeration value="legion"/>
|
153
|
-
<xs:enumeration value="sublegion"/>
|
154
|
-
<xs:enumeration value="infralegion"/>
|
155
|
-
<xs:enumeration value="supercohort"/>
|
156
|
-
<xs:enumeration value="cohort"/>
|
157
|
-
<xs:enumeration value="subcohort"/>
|
158
|
-
<xs:enumeration value="infracohort"/>
|
159
|
-
<xs:enumeration value="superorder"/>
|
160
|
-
<xs:enumeration value="order"/>
|
161
|
-
<xs:enumeration value="suborder"/>
|
162
|
-
<xs:enumeration value="superfamily"/>
|
163
|
-
<xs:enumeration value="family"/>
|
164
|
-
<xs:enumeration value="subfamily"/>
|
165
|
-
<xs:enumeration value="supertribe"/>
|
166
|
-
<xs:enumeration value="tribe"/>
|
167
|
-
<xs:enumeration value="subtribe"/>
|
168
|
-
<xs:enumeration value="infratribe"/>
|
169
|
-
<xs:enumeration value="genus"/>
|
170
|
-
<xs:enumeration value="subgenus"/>
|
171
|
-
<xs:enumeration value="superspecies"/>
|
172
|
-
<xs:enumeration value="species"/>
|
173
|
-
<xs:enumeration value="subspecies"/>
|
174
|
-
<xs:enumeration value="variety"/>
|
175
|
-
<xs:enumeration value="subvariety"/>
|
176
|
-
<xs:enumeration value="form"/>
|
177
|
-
<xs:enumeration value="subform"/>
|
178
|
-
<xs:enumeration value="cultivar"/>
|
179
|
-
<xs:enumeration value="unknown"/>
|
180
|
-
<xs:enumeration value="other"/>
|
181
|
-
</xs:restriction>
|
182
|
-
</xs:simpleType>
|
183
|
-
<!-- Sequence:-->
|
184
|
-
<xs:complexType name="Sequence">
|
185
|
-
<xs:annotation>
|
186
|
-
<xs:documentation> Element Sequence is used to represent a molecular sequence (Protein, DNA, RNA) associated
|
187
|
-
with a node. 'symbol' is a short (maximal ten characters) symbol of the sequence (e.g. 'ACTM') whereas
|
188
|
-
'name' is used for the full name (e.g. 'muscle Actin'). 'location' is used for the location of a sequence on
|
189
|
-
a genome/chromosome. The actual sequence can be stored with the 'mol_seq' element. Attribute 'type' is used
|
190
|
-
to indicate the type of sequence ('dna', 'rna', or 'protein'). One intended use for 'id_ref' is to link a
|
191
|
-
sequence to a taxonomy (via the taxonomy's 'id_source') in case of multiple sequences and taxonomies per
|
192
|
-
node. </xs:documentation>
|
193
|
-
</xs:annotation>
|
194
|
-
<xs:sequence>
|
195
|
-
<xs:element name="symbol" type="phy:SequenceSymbol" minOccurs="0"/>
|
196
|
-
<xs:element name="accession" type="phy:Accession" minOccurs="0"/>
|
197
|
-
<xs:element name="name" type="xs:token" minOccurs="0"/>
|
198
|
-
<xs:element name="location" type="xs:token" minOccurs="0"/>
|
199
|
-
<xs:element name="mol_seq" type="phy:MolSeq" minOccurs="0"/>
|
200
|
-
<xs:element name="uri" type="phy:Uri" minOccurs="0"/>
|
201
|
-
<xs:element name="annotation" type="phy:Annotation" minOccurs="0" maxOccurs="unbounded"/>
|
202
|
-
<xs:element name="domain_architecture" type="phy:DomainArchitecture" minOccurs="0"/>
|
203
|
-
<xs:any minOccurs="0" maxOccurs="unbounded" processContents="lax" namespace="##other"/>
|
204
|
-
</xs:sequence>
|
205
|
-
<xs:attribute name="type" type="phy:SequenceType"/>
|
206
|
-
<xs:attribute name="id_source" type="phy:id_source"/>
|
207
|
-
<xs:attribute name="id_ref" type="phy:id_ref"/>
|
208
|
-
</xs:complexType>
|
209
|
-
<xs:simpleType name="SequenceSymbol">
|
210
|
-
<xs:restriction base="xs:token">
|
211
|
-
<xs:pattern value="\S{1,10}"/>
|
212
|
-
</xs:restriction>
|
213
|
-
</xs:simpleType>
|
214
|
-
<xs:complexType name="MolSeq">
|
215
|
-
<xs:annotation>
|
216
|
-
<xs:documentation> Element 'mol_seq' is used to store molecular sequences. The 'is_aligned' attribute is used
|
217
|
-
to indicated that this molecular sequence is aligned with all other sequences in the same phylogeny for
|
218
|
-
which 'is aligned' is true as well (which, in most cases, means that gaps were introduced, and that all
|
219
|
-
sequences for which 'is aligned' is true must have the same length).</xs:documentation>
|
220
|
-
</xs:annotation>
|
221
|
-
<xs:simpleContent>
|
222
|
-
<xs:extension base="phy:MolSeqChars">
|
223
|
-
<xs:attribute name="is_aligned" type="xs:boolean"/>
|
224
|
-
</xs:extension>
|
225
|
-
</xs:simpleContent>
|
226
|
-
</xs:complexType>
|
227
|
-
<xs:simpleType name="MolSeqChars">
|
228
|
-
<xs:restriction base="xs:token">
|
229
|
-
<xs:pattern value="[a-zA-Z\.\-\?\*_]+"/>
|
230
|
-
</xs:restriction>
|
231
|
-
</xs:simpleType>
|
232
|
-
<xs:simpleType name="SequenceType">
|
233
|
-
<xs:restriction base="xs:token">
|
234
|
-
<xs:enumeration value="rna"/>
|
235
|
-
<xs:enumeration value="dna"/>
|
236
|
-
<xs:enumeration value="protein"/>
|
237
|
-
</xs:restriction>
|
238
|
-
</xs:simpleType>
|
239
|
-
<!-- Accession:-->
|
240
|
-
<xs:complexType name="Accession">
|
241
|
-
<xs:annotation>
|
242
|
-
<xs:documentation> Element Accession is used to capture the local part in a sequence identifier (e.g. 'P17304'
|
243
|
-
in 'UniProtKB:P17304', in which case the 'source' attribute would be 'UniProtKB'). </xs:documentation>
|
244
|
-
</xs:annotation>
|
245
|
-
<xs:simpleContent>
|
246
|
-
<xs:extension base="xs:token">
|
247
|
-
<xs:attribute name="source" type="xs:token" use="required"/>
|
248
|
-
</xs:extension>
|
249
|
-
</xs:simpleContent>
|
250
|
-
</xs:complexType>
|
251
|
-
<!-- DomainArchitecture: -->
|
252
|
-
<xs:complexType name="DomainArchitecture">
|
253
|
-
<xs:annotation>
|
254
|
-
<xs:documentation> This is used describe the domain architecture of a protein. Attribute 'length' is the total
|
255
|
-
length of the protein</xs:documentation>
|
256
|
-
</xs:annotation>
|
257
|
-
<xs:sequence>
|
258
|
-
<xs:element name="domain" type="phy:ProteinDomain" minOccurs="1" maxOccurs="unbounded"/>
|
259
|
-
</xs:sequence>
|
260
|
-
<xs:attribute name="length" type="xs:nonNegativeInteger"/>
|
261
|
-
</xs:complexType>
|
262
|
-
<xs:complexType name="ProteinDomain">
|
263
|
-
<xs:annotation>
|
264
|
-
<xs:documentation> To represent an individual domain in a domain architecture. The name/unique identifier is
|
265
|
-
described via the 'id' attribute. 'confidence' can be used to store (i.e.) E-values.</xs:documentation>
|
266
|
-
</xs:annotation>
|
267
|
-
<xs:simpleContent>
|
268
|
-
<xs:extension base="xs:token">
|
269
|
-
<xs:attribute name="from" type="xs:nonNegativeInteger" use="required"/>
|
270
|
-
<xs:attribute name="to" type="xs:nonNegativeInteger" use="required"/>
|
271
|
-
<xs:attribute name="confidence" type="xs:double"/>
|
272
|
-
<xs:attribute name="id" type="xs:token"/>
|
273
|
-
</xs:extension>
|
274
|
-
</xs:simpleContent>
|
275
|
-
</xs:complexType>
|
276
|
-
<!-- Events:-->
|
277
|
-
<xs:complexType name="Events">
|
278
|
-
<xs:annotation>
|
279
|
-
<xs:documentation> Events at the root node of a clade (e.g. one gene duplication). </xs:documentation>
|
280
|
-
</xs:annotation>
|
281
|
-
<xs:sequence>
|
282
|
-
<xs:element name="type" type="phy:EventType" minOccurs="0"/>
|
283
|
-
<xs:element name="duplications" type="xs:nonNegativeInteger" minOccurs="0"/>
|
284
|
-
<xs:element name="speciations" type="xs:nonNegativeInteger" minOccurs="0"/>
|
285
|
-
<xs:element name="losses" type="xs:nonNegativeInteger" minOccurs="0"/>
|
286
|
-
<xs:element name="confidence" type="phy:Confidence" minOccurs="0"/>
|
287
|
-
</xs:sequence>
|
288
|
-
</xs:complexType>
|
289
|
-
<xs:simpleType name="EventType">
|
290
|
-
<xs:restriction base="xs:token">
|
291
|
-
<xs:enumeration value="transfer"/>
|
292
|
-
<xs:enumeration value="fusion"/>
|
293
|
-
<xs:enumeration value="speciation_or_duplication"/>
|
294
|
-
<xs:enumeration value="other"/>
|
295
|
-
<xs:enumeration value="mixed"/>
|
296
|
-
<xs:enumeration value="unassigned"/>
|
297
|
-
</xs:restriction>
|
298
|
-
</xs:simpleType>
|
299
|
-
<!--BinaryCharacters:-->
|
300
|
-
<xs:complexType name="BinaryCharacters">
|
301
|
-
<xs:annotation>
|
302
|
-
<xs:documentation> The names and/or counts of binary characters present, gained, and lost at the root of a
|
303
|
-
clade. </xs:documentation>
|
304
|
-
</xs:annotation>
|
305
|
-
<xs:sequence>
|
306
|
-
<xs:element name="gained" type="phy:BinaryCharacterList" minOccurs="0"/>
|
307
|
-
<xs:element name="lost" type="phy:BinaryCharacterList" minOccurs="0"/>
|
308
|
-
<xs:element name="present" type="phy:BinaryCharacterList" minOccurs="0"/>
|
309
|
-
<xs:element name="absent" type="phy:BinaryCharacterList" minOccurs="0"/>
|
310
|
-
</xs:sequence>
|
311
|
-
<xs:attribute name="type" type="xs:token"/>
|
312
|
-
<xs:attribute name="gained_count" type="xs:nonNegativeInteger"/>
|
313
|
-
<xs:attribute name="lost_count" type="xs:nonNegativeInteger"/>
|
314
|
-
<xs:attribute name="present_count" type="xs:nonNegativeInteger"/>
|
315
|
-
<xs:attribute name="absent_count" type="xs:nonNegativeInteger"/>
|
316
|
-
</xs:complexType>
|
317
|
-
<xs:complexType name="BinaryCharacterList">
|
318
|
-
<xs:sequence>
|
319
|
-
<xs:element name="bc" type="xs:token" maxOccurs="unbounded"/>
|
320
|
-
</xs:sequence>
|
321
|
-
</xs:complexType>
|
322
|
-
<!-- Reference:-->
|
323
|
-
<xs:complexType name="Reference">
|
324
|
-
<xs:annotation>
|
325
|
-
<xs:documentation> A literature reference for a clade. It is recommended to use the 'doi' attribute instead of
|
326
|
-
the free text 'desc' element whenever possible. </xs:documentation>
|
327
|
-
</xs:annotation>
|
328
|
-
<xs:sequence>
|
329
|
-
<xs:element name="desc" type="xs:token" minOccurs="0"/>
|
330
|
-
</xs:sequence>
|
331
|
-
<xs:attribute name="doi" type="phy:Doi"/>
|
332
|
-
</xs:complexType>
|
333
|
-
<xs:simpleType name="Doi">
|
334
|
-
<xs:restriction base="xs:token">
|
335
|
-
<xs:pattern value="[a-zA-Z0-9_\.]+/\S+"/>
|
336
|
-
</xs:restriction>
|
337
|
-
</xs:simpleType>
|
338
|
-
<!-- Annotation:-->
|
339
|
-
<xs:complexType name="Annotation">
|
340
|
-
<xs:annotation>
|
341
|
-
<xs:documentation> The annotation of a molecular sequence. It is recommended to annotate by using the optional
|
342
|
-
'ref' attribute (some examples of acceptable values for the ref attribute: 'GO:0008270',
|
343
|
-
'KEGG:Tetrachloroethene degradation', 'EC:1.1.1.1'). Optional element 'desc' allows for a free text
|
344
|
-
description. Optional element 'confidence' is used to state the type and value of support for a annotation.
|
345
|
-
Similarly, optional attribute 'evidence' is used to describe the evidence for a annotation as free text
|
346
|
-
(e.g. 'experimental'). Optional element 'property' allows for further, typed and referenced annotations from
|
347
|
-
external resources.</xs:documentation>
|
348
|
-
</xs:annotation>
|
349
|
-
<xs:sequence>
|
350
|
-
<xs:element name="desc" type="xs:token" minOccurs="0"/>
|
351
|
-
<xs:element name="confidence" type="phy:Confidence" minOccurs="0"/>
|
352
|
-
<xs:element name="property" type="phy:Property" minOccurs="0" maxOccurs="unbounded"/>
|
353
|
-
<xs:element name="uri" type="phy:Uri" minOccurs="0"/>
|
354
|
-
</xs:sequence>
|
355
|
-
<xs:attribute name="ref" type="phy:ref"/>
|
356
|
-
<xs:attribute name="source" type="xs:token"/>
|
357
|
-
<xs:attribute name="evidence" type="xs:token"/>
|
358
|
-
<xs:attribute name="type" type="xs:token"/>
|
359
|
-
</xs:complexType>
|
360
|
-
<!-- Property:-->
|
361
|
-
<xs:complexType name="Property" mixed="true">
|
362
|
-
<xs:annotation>
|
363
|
-
<xs:documentation> Property allows for typed and referenced properties from external resources to be attached
|
364
|
-
to 'Phylogeny', 'Clade', and 'Annotation'. The value of a property is its mixed (free text) content.
|
365
|
-
Attribute 'datatype' indicates the type of a property and is limited to xsd-datatypes (e.g. 'xsd:string',
|
366
|
-
'xsd:boolean', 'xsd:integer', 'xsd:decimal', 'xsd:float', 'xsd:double', 'xsd:date', 'xsd:anyURI'). Attribute
|
367
|
-
'applies_to' indicates the item to which a property applies to (e.g. 'node' for the parent node of a clade,
|
368
|
-
'parent_branch' for the parent branch of a clade). Attribute 'id_ref' allows to attached a property
|
369
|
-
specifically to one element (on the xml-level). Optional attribute 'unit' is used to indicate the unit of
|
370
|
-
the property. An example: <property datatype="xsd:integer" ref="NOAA:depth" applies_to="clade"
|
371
|
-
unit="METRIC:m"> 200 </property> </xs:documentation>
|
372
|
-
</xs:annotation>
|
373
|
-
<xs:attribute name="ref" type="phy:ref" use="required"/>
|
374
|
-
<xs:attribute name="unit" type="phy:ref"/>
|
375
|
-
<xs:attribute name="datatype" type="phy:PropertyDataType" use="required"/>
|
376
|
-
<xs:attribute name="applies_to" type="phy:AppliesTo" use="required"/>
|
377
|
-
<xs:attribute name="id_ref" type="phy:id_ref"/>
|
378
|
-
</xs:complexType>
|
379
|
-
<xs:simpleType name="ref">
|
380
|
-
<xs:restriction base="xs:token">
|
381
|
-
<xs:pattern value="[a-zA-Z0-9_]+:[a-zA-Z0-9_\.\-\s]+"/>
|
382
|
-
</xs:restriction>
|
383
|
-
</xs:simpleType>
|
384
|
-
<xs:simpleType name="AppliesTo">
|
385
|
-
<xs:restriction base="xs:token">
|
386
|
-
<xs:enumeration value="phylogeny"/>
|
387
|
-
<xs:enumeration value="clade"/>
|
388
|
-
<xs:enumeration value="node"/>
|
389
|
-
<xs:enumeration value="annotation"/>
|
390
|
-
<xs:enumeration value="parent_branch"/>
|
391
|
-
<xs:enumeration value="other"/>
|
392
|
-
</xs:restriction>
|
393
|
-
</xs:simpleType>
|
394
|
-
<xs:simpleType name="PropertyDataType">
|
395
|
-
<xs:restriction base="xs:token">
|
396
|
-
<xs:enumeration value="xsd:string"/>
|
397
|
-
<xs:enumeration value="xsd:boolean"/>
|
398
|
-
<xs:enumeration value="xsd:decimal"/>
|
399
|
-
<xs:enumeration value="xsd:float"/>
|
400
|
-
<xs:enumeration value="xsd:double"/>
|
401
|
-
<xs:enumeration value="xsd:duration"/>
|
402
|
-
<xs:enumeration value="xsd:dateTime"/>
|
403
|
-
<xs:enumeration value="xsd:time"/>
|
404
|
-
<xs:enumeration value="xsd:date"/>
|
405
|
-
<xs:enumeration value="xsd:gYearMonth"/>
|
406
|
-
<xs:enumeration value="xsd:gYear"/>
|
407
|
-
<xs:enumeration value="xsd:gMonthDay"/>
|
408
|
-
<xs:enumeration value="xsd:gDay"/>
|
409
|
-
<xs:enumeration value="xsd:gMonth"/>
|
410
|
-
<xs:enumeration value="xsd:hexBinary"/>
|
411
|
-
<xs:enumeration value="xsd:base64Binary"/>
|
412
|
-
<xs:enumeration value="xsd:anyURI"/>
|
413
|
-
<xs:enumeration value="xsd:normalizedString"/>
|
414
|
-
<xs:enumeration value="xsd:token"/>
|
415
|
-
<xs:enumeration value="xsd:integer"/>
|
416
|
-
<xs:enumeration value="xsd:nonPositiveInteger"/>
|
417
|
-
<xs:enumeration value="xsd:negativeInteger"/>
|
418
|
-
<xs:enumeration value="xsd:long"/>
|
419
|
-
<xs:enumeration value="xsd:int"/>
|
420
|
-
<xs:enumeration value="xsd:short"/>
|
421
|
-
<xs:enumeration value="xsd:byte"/>
|
422
|
-
<xs:enumeration value="xsd:nonNegativeInteger"/>
|
423
|
-
<xs:enumeration value="xsd:unsignedLong"/>
|
424
|
-
<xs:enumeration value="xsd:unsignedInt"/>
|
425
|
-
<xs:enumeration value="xsd:unsignedShort"/>
|
426
|
-
<xs:enumeration value="xsd:unsignedByte"/>
|
427
|
-
<xs:enumeration value="xsd:positiveInteger"/>
|
428
|
-
</xs:restriction>
|
429
|
-
</xs:simpleType>
|
430
|
-
<!--Uri-->
|
431
|
-
<xs:complexType name="Uri">
|
432
|
-
<xs:annotation>
|
433
|
-
<xs:documentation> A uniform resource identifier. In general, this is expected to be an URL (for example, to
|
434
|
-
link to an image on a website, in which case the 'type' attribute might be 'image' and 'desc' might be
|
435
|
-
'image of a California sea hare'). </xs:documentation>
|
436
|
-
</xs:annotation>
|
437
|
-
<xs:simpleContent>
|
438
|
-
<xs:extension base="xs:anyURI">
|
439
|
-
<xs:attribute name="desc" type="xs:token"/>
|
440
|
-
<xs:attribute name="type" type="xs:token"/>
|
441
|
-
</xs:extension>
|
442
|
-
</xs:simpleContent>
|
443
|
-
</xs:complexType>
|
444
|
-
<!-- Confidence:-->
|
445
|
-
<xs:complexType name="Confidence">
|
446
|
-
<xs:annotation>
|
447
|
-
<xs:documentation> A general purpose confidence element. For example this can be used to express the bootstrap
|
448
|
-
support value of a clade (in which case the 'type' attribute is 'bootstrap').</xs:documentation>
|
449
|
-
</xs:annotation>
|
450
|
-
<xs:simpleContent>
|
451
|
-
<xs:extension base="xs:double">
|
452
|
-
<xs:attribute name="type" type="xs:token" use="required"/>
|
453
|
-
</xs:extension>
|
454
|
-
</xs:simpleContent>
|
455
|
-
</xs:complexType>
|
456
|
-
<!-- Identifier:-->
|
457
|
-
<xs:complexType name="Id">
|
458
|
-
<xs:annotation>
|
459
|
-
<xs:documentation> A general purpose identifier element. Allows to indicate the provider (or authority) of an
|
460
|
-
identifier. </xs:documentation>
|
461
|
-
</xs:annotation>
|
462
|
-
<xs:simpleContent>
|
463
|
-
<xs:extension base="xs:token">
|
464
|
-
<xs:attribute name="provider" type="xs:token"/>
|
465
|
-
</xs:extension>
|
466
|
-
</xs:simpleContent>
|
467
|
-
</xs:complexType>
|
468
|
-
<!-- Distribution:-->
|
469
|
-
<xs:complexType name="Distribution">
|
470
|
-
<xs:annotation>
|
471
|
-
<xs:documentation> The geographic distribution of the items of a clade (species, sequences), intended for
|
472
|
-
phylogeographic applications. The location can be described either by free text in the 'desc' element and/or
|
473
|
-
by the coordinates of one or more 'Points' (similar to the 'Point' element in Google's KML format) or by
|
474
|
-
'Polygons'. </xs:documentation>
|
475
|
-
</xs:annotation>
|
476
|
-
<xs:sequence>
|
477
|
-
<xs:element name="desc" type="xs:token" minOccurs="0"/>
|
478
|
-
<xs:element name="point" type="phy:Point" minOccurs="0" maxOccurs="unbounded"/>
|
479
|
-
<xs:element name="polygon" type="phy:Polygon" minOccurs="0" maxOccurs="unbounded"/>
|
480
|
-
</xs:sequence>
|
481
|
-
</xs:complexType>
|
482
|
-
<xs:complexType name="Point">
|
483
|
-
<xs:annotation>
|
484
|
-
<xs:documentation> The coordinates of a point with an optional altitude (used by element 'Distribution').
|
485
|
-
Required attributes are the 'geodetic_datum' used to indicate the geodetic datum (also called 'map datum',
|
486
|
-
for example Google's KML uses 'WGS84'). Attribute 'alt_unit' is the unit for the altitude (e.g. 'meter').
|
487
|
-
</xs:documentation>
|
488
|
-
</xs:annotation>
|
489
|
-
<xs:sequence>
|
490
|
-
<xs:element name="lat" type="xs:decimal"/>
|
491
|
-
<xs:element name="long" type="xs:decimal"/>
|
492
|
-
<xs:element name="alt" type="xs:decimal" minOccurs="0"/>
|
493
|
-
</xs:sequence>
|
494
|
-
<xs:attribute name="geodetic_datum" type="xs:token" use="required"/>
|
495
|
-
<xs:attribute name="alt_unit" type="xs:token"/>
|
496
|
-
</xs:complexType>
|
497
|
-
<xs:complexType name="Polygon">
|
498
|
-
<xs:annotation>
|
499
|
-
<xs:documentation> A polygon defined by a list of 'Points' (used by element 'Distribution').
|
500
|
-
</xs:documentation>
|
501
|
-
</xs:annotation>
|
502
|
-
<xs:sequence>
|
503
|
-
<xs:element name="point" type="phy:Point" minOccurs="3" maxOccurs="unbounded"/>
|
504
|
-
</xs:sequence>
|
505
|
-
</xs:complexType>
|
506
|
-
<!-- Date:-->
|
507
|
-
<xs:complexType name="Date">
|
508
|
-
<xs:annotation>
|
509
|
-
<xs:documentation> A date associated with a clade/node. Its value can be numerical by using the 'value' element
|
510
|
-
and/or free text with the 'desc' element' (e.g. 'Silurian'). If a numerical value is used, it is recommended
|
511
|
-
to employ the 'unit' attribute to indicate the type of the numerical value (e.g. 'mya' for 'million years
|
512
|
-
ago'). The elements 'minimum' and 'maximum' are used the indicate a range/confidence
|
513
|
-
interval</xs:documentation>
|
514
|
-
</xs:annotation>
|
515
|
-
<xs:sequence>
|
516
|
-
<xs:element name="desc" type="xs:token" minOccurs="0"/>
|
517
|
-
<xs:element name="value" type="xs:decimal" minOccurs="0"/>
|
518
|
-
<xs:element name="minimum" type="xs:decimal" minOccurs="0"/>
|
519
|
-
<xs:element name="maximum" type="xs:decimal" minOccurs="0"/>
|
520
|
-
</xs:sequence>
|
521
|
-
<xs:attribute name="unit" type="xs:token"/>
|
522
|
-
</xs:complexType>
|
523
|
-
<!-- BranchColor:-->
|
524
|
-
<xs:complexType name="BranchColor">
|
525
|
-
<xs:annotation>
|
526
|
-
<xs:documentation> This indicates the color of a clade when rendered (the color applies to the whole clade
|
527
|
-
unless overwritten by the color(s) of sub clades).</xs:documentation>
|
528
|
-
</xs:annotation>
|
529
|
-
<xs:sequence>
|
530
|
-
<xs:element name="red" type="xs:unsignedByte"/>
|
531
|
-
<xs:element name="green" type="xs:unsignedByte"/>
|
532
|
-
<xs:element name="blue" type="xs:unsignedByte"/>
|
533
|
-
</xs:sequence>
|
534
|
-
</xs:complexType>
|
535
|
-
<!-- SequenceRelation:-->
|
536
|
-
<xs:complexType name="SequenceRelation">
|
537
|
-
<xs:annotation>
|
538
|
-
<xs:documentation> This is used to express a typed relationship between two sequences. For example it could be
|
539
|
-
used to describe an orthology (in which case attribute 'type' is 'orthology'). </xs:documentation>
|
540
|
-
</xs:annotation>
|
541
|
-
<xs:sequence>
|
542
|
-
<xs:element name="confidence" type="phy:Confidence" minOccurs="0"/>
|
543
|
-
</xs:sequence>
|
544
|
-
<xs:attribute name="id_ref_0" type="phy:id_ref" use="required"/>
|
545
|
-
<xs:attribute name="id_ref_1" type="phy:id_ref" use="required"/>
|
546
|
-
<xs:attribute name="distance" type="xs:double"/>
|
547
|
-
<xs:attribute name="type" type="phy:SequenceRelationType" use="required"/>
|
548
|
-
</xs:complexType>
|
549
|
-
<xs:simpleType name="SequenceRelationType">
|
550
|
-
<xs:restriction base="xs:token">
|
551
|
-
<xs:enumeration value="orthology"/>
|
552
|
-
<xs:enumeration value="one_to_one_orthology"/>
|
553
|
-
<xs:enumeration value="super_orthology"/>
|
554
|
-
<xs:enumeration value="paralogy"/>
|
555
|
-
<xs:enumeration value="ultra_paralogy"/>
|
556
|
-
<xs:enumeration value="xenology"/>
|
557
|
-
<xs:enumeration value="unknown"/>
|
558
|
-
<xs:enumeration value="other"/>
|
559
|
-
</xs:restriction>
|
560
|
-
</xs:simpleType>
|
561
|
-
<!-- CladeRelation:-->
|
562
|
-
<xs:complexType name="CladeRelation">
|
563
|
-
<xs:annotation>
|
564
|
-
<xs:documentation> This is used to express a typed relationship between two clades. For example it could be
|
565
|
-
used to describe multiple parents of a clade.</xs:documentation>
|
566
|
-
</xs:annotation>
|
567
|
-
<xs:sequence>
|
568
|
-
<xs:element name="confidence" type="phy:Confidence" minOccurs="0"/>
|
569
|
-
</xs:sequence>
|
570
|
-
<xs:attribute name="id_ref_0" type="phy:id_ref" use="required"/>
|
571
|
-
<xs:attribute name="id_ref_1" type="phy:id_ref" use="required"/>
|
572
|
-
<xs:attribute name="distance" type="xs:double"/>
|
573
|
-
<xs:attribute name="type" type="xs:token" use="required"/>
|
574
|
-
</xs:complexType>
|
575
|
-
<!-- Used to link elements together on the xml level:-->
|
576
|
-
<xs:simpleType name="id_source">
|
577
|
-
<xs:restriction base="xs:ID"/>
|
578
|
-
</xs:simpleType>
|
579
|
-
<xs:simpleType name="id_ref">
|
580
|
-
<xs:restriction base="xs:IDREF"/>
|
581
|
-
</xs:simpleType>
|
582
|
-
</xs:schema>
|