returns comment text in the comments (CC) line.
CC Line; comments of notes (>=0)
# File lib/bio/db/embl/embl.rb, line 327 def cc get('CC').to_s.gsub(/^CC /, '') end
# File lib/bio/db/embl/embl.rb, line 130 def data_class id_line('DATA_CLASS') end
created date. Returns Date object, String or nil.
# File lib/bio/db/embl/embl.rb, line 387 def date_created parse_date(self.dt['created']) end
modified date. Returns Date object, String or nil.
# File lib/bio/db/embl/embl.rb, line 382 def date_modified parse_date(self.dt['updated']) end
database references (DR). Returns an array of Bio::Sequence::DBLink objects.
# File lib/bio/db/embl/embl.rb, line 437 def dblinks get('DR').split(/\n/).collect { |x| Bio::Sequence::DBLink.parse_embl_DR_line(x) } end
returns DIVISION in the ID line.
# File lib/bio/db/embl/embl.rb, line 140 def division id_line('DIVISION') end
returns contents in the date (DT) line.
Bio::EMBL#dt -> <DT Hash>
where <DT Hash> is:
{}
keys: ‘created’ and ‘updated’
DT Line; date (2/entry)
# File lib/bio/db/embl/embl.rb, line 182 def dt(key=nil) unless @data['DT'] tmp = Hash.new dt_line = self.get('DT').split(/\n/) tmp['created'] = dt_line[0].sub(/\w{2} /,'').strip tmp['updated'] = dt_line[1].sub(/\w{2} /,'').strip @data['DT'] = tmp end if key @data['DT'][key] else @data['DT'] end end
iterates on CDS features in the FT lines.
# File lib/bio/db/embl/embl.rb, line 306 def each_cds ft.each do |cds_feature| if cds_feature.feature == 'CDS' yield cds_feature end end end
iterates on gene features in the FT lines.
# File lib/bio/db/embl/embl.rb, line 315 def each_gene ft.each do |gene_feature| if gene_feature.feature == 'gene' yield gene_feature end end end
returns ENTRY_NAME in the ID line.
# File lib/bio/db/embl/embl.rb, line 117 def entry id_line('ENTRY_NAME') end
entry version number numbered by EMBL
# File lib/bio/db/embl/embl.rb, line 402 def entry_version parse_release_version(self.dt['updated'])[1] end
returns feature table header (String) in the feature header (FH) line.
FH Line; feature table header (0 or 2)
# File lib/bio/db/embl/embl.rb, line 251 def fh fetch('FH') end
returns contents in the feature table (FT) lines.
Bio::EMBL#ft {} -> {|Bio::Feature| }
same as features method in bio/db/genbank.rb
FT Line; feature table data (>=0)
# File lib/bio/db/embl/embl.rb, line 262 def ft unless @data['FT'] ary = Array.new in_quote = false @orig['FT'].each_line do |line| next if line =~ /^FEATURES/ head = line[0,20].strip # feature key (source, CDS, ...) body = line[20,60].chomp # feature value (position, /qualifier=) if line =~ /^FT {3}(\S+)/ ary.push([ $1, body ]) # [ feature, position, /q="data", ... ] elsif body =~ /^ \// and not in_quote ary.last.push(body) # /q="data..., /q=data, /q if body =~ /=" / and body !~ /"$/ in_quote = true end else ary.last.last << body # ...data..., ...data..." if body =~ /"$/ in_quote = false end end end ary.map! do |subary| parse_qualifiers(subary) end @data['FT'] = ary.extend(Bio::Features::BackwardCompatibility) end if block_given? @data['FT'].each do |feature| yield feature end else @data['FT'] end end
returns contents in the ID line.
Bio::EMBL#id_line -> <ID Hash>
where <ID Hash> is:
{'ENTRY_NAME' => String, 'MOLECULE_TYPE' => String, 'DIVISION' => String,
'SEQUENCE_LENGTH' => Int, 'SEQUENCE_VERSION' => Int}
ID Line
"ID ENTRY_NAME DATA_CLASS; MOLECULE_TYPE; DIVISION; SEQUENCE_LENGTH BP."
DATA_CLASS = [‘standard’]
MOLECULE_TYPE: DNA RNA XXX
Code ( DIVISION )
EST (ESTs) PHG (Bacteriophage) FUN (Fungi) GSS (Genome survey) HTC (High Throughput cDNAs) HTG (HTGs) HUM (Human) INV (Invertebrates) ORG (Organelles) MAM (Other Mammals) VRT (Other Vertebrates) PLN (Plants) PRO (Prokaryotes) ROD (Rodents) SYN (Synthetic) STS (STSs) UNC (Unclassified) VRL (Viruses)
Rel 89- ID CD789012; SV 4; linear; genomic DNA; HTG; MAM; 500 BP. ID <1>; SV <2>; <3>; <4>; <5>; <6>; <7> BP.
Primary accession number
Sequence version number
Topology: ‘circular’ or ‘linear’
Molecule type (see note 1 below)
Data class (see section 3.1)
Taxonomic division (see section 3.2)
Sequence length (see note 2 below)
# File lib/bio/db/embl/embl.rb, line 89 def id_line(key=nil) unless @data['ID'] tmp = Hash.new idline = fetch('ID').split(/; +/) tmp['ENTRY_NAME'], tmp['DATA_CLASS'] = idline.shift.split(/ +/) if idline.first =~ /^SV/ tmp['SEQUENCE_VERSION'] = idline.shift.split(' ').last tmp['TOPOLOGY'] = idline.shift tmp['MOLECULE_TYPE'] = idline.shift tmp['DATA_CLASS'] = idline.shift else tmp['MOLECULE_TYPE'] = idline.shift end tmp['DIVISION'] = idline.shift tmp['SEQUENCE_LENGTH'] = idline.shift.strip.split(' ').first.to_i @data['ID'] = tmp end if key @data['ID'][key] else @data['ID'] end end
returns MOLECULE_TYPE in the ID line.
# File lib/bio/db/embl/embl.rb, line 125 def molecule id_line('MOLECULE_TYPE') end
release number when created
# File lib/bio/db/embl/embl.rb, line 397 def release_created parse_release_version(self.dt['created'])[0] end
release number when last updated
# File lib/bio/db/embl/embl.rb, line 392 def release_modified parse_release_version(self.dt['updated'])[0] end
returns the nucleotie sequence in this entry.
@orig as sequence bb Line; (blanks) sequence data (>=1)
# File lib/bio/db/embl/embl.rb, line 371 def seq Bio::Sequence::NA.new( fetch('').gsub(/ /,'').gsub(/\d+/,'') ) end
returns SEQUENCE_LENGTH in the ID line.
Bio::EMBL#sequencelength -> String
# File lib/bio/db/embl/embl.rb, line 146 def sequence_length id_line('SEQUENCE_LENGTH') end
species
# File lib/bio/db/embl/embl.rb, line 444 def species self.fetch('OS') end
returns sequence header information in the sequence header (SQ) line.
Bio::EMBL#sq -> <SQ Hash>
where <SQ Hash> is:
{'ntlen' => Int, 'other' => Int,
'a' => Int, 'c' => Int, 'g' => Int, 't' => Int}
Bio::EMBL#sq(base) -> <base content in Int>
Bio::EMBL#sq -> <base content in Int>
SQ Line; sequence header (1/entry)
SQ Sequence 1859 BP; 609 A; 314 C; 355 G; 581 T; 0 other;
# File lib/bio/db/embl/embl.rb, line 348 def sq(base = nil) unless @data['SQ'] fetch('SQ') =~ /(\d+) BP\; (\d+) A; (\d+) C; (\d+) G; (\d+) T; (\d+) other;/ @data['SQ'] = {'ntlen' => $1.to_i, 'other' => $6.to_i, 'a' => $2.to_i, 'c' => $3.to_i , 'g' => $4.to_i, 't' => $5.to_i} else @data['SQ'] end if base @data['SQ'][base.downcase] else @data['SQ'] end end
returns the version information in the sequence version (SV) line.
Bio::EMBL#sv -> Accession.Version in String
Bio::EMBL#version -> accession in Int
SV Line; sequence version (1/entry)
SV Accession.Version
# File lib/bio/db/embl/embl.rb, line 162 def sv if (v = field_fetch('SV').sub(/;/,'')) == "" [id_line['ENTRY_NAME'], id_line['SEQUENCE_VERSION']].join('.') else v end end
converts the entry to Bio::Sequence object
Arguments |
|
Returns |
Bio::Sequence object |
# File lib/bio/db/embl/embl.rb, line 456 def to_biosequence Bio::Sequence.adapter(self, Bio::Sequence::Adapter::EMBL) end
Generated with the Darkfish Rdoc Generator 2.