[BioRuby-cvs] bioruby/lib/bio sequence.rb,0.58.2.11,0.58.2.12

Naohisa Goto ngoto at dev.open-bio.org
Tue Jun 17 15:25:24 UTC 2008


Update of /home/repository/bioruby/bioruby/lib/bio
In directory dev.open-bio.org:/tmp/cvs-serv20823/lib/bio

Modified Files:
      Tag: BRANCH-biohackathon2008
	sequence.rb 
Log Message:
* Some attributes are added: strandedness (strand information), 
  release_created, release_modified (release information),
  entry_version (version of the entry numbered by database administrator),
  organelle (organelle information), other_seqids (sequence IDs other than
  accessions), and id_namespace (namespace of accessions).
  Most of them are added because corresponding tags are defined in the
  INSDSeq XML v1.4 ( http://www.insdc.org/files/documents/INSD_V1.4.dtd ).
  The "id_namespace" will be used to output NCBI style fasta format.
* The "taxonomy" attribute is changed to be an alias of the "classification"
  attribute.
* The "date" attribute is removed.
* RDoc documents of attributes are updated.


Index: sequence.rb
===================================================================
RCS file: /home/repository/bioruby/bioruby/lib/bio/sequence.rb,v
retrieving revision 0.58.2.11
retrieving revision 0.58.2.12
diff -C2 -d -r0.58.2.11 -r0.58.2.12
*** sequence.rb	24 Apr 2008 14:28:25 -0000	0.58.2.11
--- sequence.rb	17 Jun 2008 15:25:22 -0000	0.58.2.12
***************
*** 118,149 ****
    end
    
!   # The sequence identifier.  For example, for a sequence
!   # of Genbank origin, this is the accession number.
    attr_accessor :entry_id
    
!   # A String with a description of the sequence
    attr_accessor :definition
    
!   # An Array of Bio::Feature objects
    attr_accessor :features
    
!   # An Array of Bio::Reference objects
    attr_accessor :references
    
!   # A comment String
    attr_accessor :comments
    
!   # Date from sequence source. Often date of deposition.
!   attr_accessor :date
!   
!   # An Array of Strings
    attr_accessor :keywords
    
!   # An Array of Strings; links to other database entries.
    attr_accessor :dblinks
!   
!   # A taxonomy String
!   attr_accessor :taxonomy
!   
    # Bio::Sequence::NA/AA
    attr_accessor :moltype
--- 118,145 ----
    end
    
!   # The sequence identifier (String).  For example, for a sequence
!   # of Genbank origin, this is the locus name.
!   # For a sequence of EMBL origin, this is the primary accession number.
    attr_accessor :entry_id
    
!   # A String with a description of the sequence (String)
    attr_accessor :definition
    
!   # Features (An Array of Bio::Feature objects)
    attr_accessor :features
    
!   # References (An Array of Bio::Reference objects)
    attr_accessor :references
    
!   # Comments (String or an Array of String)
    attr_accessor :comments
    
!   # Keywords (An Array of String)
    attr_accessor :keywords
    
!   # Links to other database entries.
!   # (An Array of Bio::Sequence::DBLink objects)
    attr_accessor :dblinks
! 
    # Bio::Sequence::NA/AA
    attr_accessor :moltype
***************
*** 157,166 ****
    #+++
    
!   # Version number of the sequence (String).
    attr_accessor :sequence_version
  
!   # Topology (String). "circular" or "linear".
    attr_accessor :topology
  
    # molecular type (String). "DNA" or "RNA" for nucleotide sequence.
    attr_accessor :molecule_type
--- 153,170 ----
    #+++
    
!   # Version number of the sequence (String or Integer).
!   # Unlike <tt>entry_version</tt>, <tt>sequence_version</tt> will be changed
!   # when the submitter of the sequence updates the entry.
!   # Normally, the same entry taken from different databases (EMBL, GenBank,
!   # and DDBJ) may have the same sequence_version.
    attr_accessor :sequence_version
  
!   # Topology (String). "circular", "linear", or nil.
    attr_accessor :topology
  
+   # Strandedness (String). "single" (single-stranded),
+   # "double" (double-stranded), "mixed" (mixed-stranded), or nil.
+   attr_accessor :strandedness
+ 
    # molecular type (String). "DNA" or "RNA" for nucleotide sequence.
    attr_accessor :molecule_type
***************
*** 180,189 ****
    attr_accessor :secondary_accessions
  
!   # Created date of the sequence entry (String)
    attr_accessor :date_created
  
!   # Last modified date of the sequence entry (String)
    attr_accessor :date_modified
  
    # Organism species (String). For example, "Escherichia coli".
    attr_accessor :species
--- 184,208 ----
    attr_accessor :secondary_accessions
  
!   # Created date of the sequence entry (Date, DateTime, Time, or String)
    attr_accessor :date_created
  
!   # Last modified date of the sequence entry (Date, DateTime, Time, or String)
    attr_accessor :date_modified
  
+   # Release information when created (String)
+   attr_accessor :release_created
+ 
+   # Release information when last-modified (String)
+   attr_accessor :release_modified
+ 
+   # Version of the entry (String or Integer).
+   # Unlike <tt>sequence_version</tt>, <tt>entry_version</tt> is a database
+   # maintainer's internal version number.
+   # The version number will be changed when the database maintainer
+   # modifies the entry.
+   # The same enrty in EMBL, GenBank, and DDBJ may have different
+   # entry_version.
+   attr_accessor :entry_version
+ 
    # Organism species (String). For example, "Escherichia coli".
    attr_accessor :species
***************
*** 192,195 ****
--- 211,231 ----
    # (Array of String)
    attr_accessor :classification
+   alias taxonomy classification
+ 
+   # (not well supported) Organelle information (String).
+   attr_accessor :organelle
+ 
+   # Namespace of the sequence IDs described in entry_id, primary_accession,
+   # and secondary_accessions methods (String).
+   # For example, 'EMBL', 'GenBank', 'DDBJ', 'RefSeq'.
+   attr_accessor :id_namespace
+ 
+   # Sequence identifiers which are not described in entry_id,
+   # primary_accession,and secondary_accessions methods
+   # (Array of Bio::Sequence::DBLink objects).
+   # For example, NCBI GI number can be stored.
+   # Note that only identifiers of the entry itself should be stored.
+   # For database cross references, <tt>dblinks</tt> should be used.
+   attr_accessor :other_seqids
  
    # Guess the type of sequence, Amino Acid or Nucleic Acid, and create a 




More information about the bioruby-cvs mailing list