[BioRuby-cvs] bioruby/lib/bio/db/kegg keggtab.rb,1.8,1.9
Katayama Toshiaki
k at dev.open-bio.org
Tue Sep 19 05:54:32 UTC 2006
Update of /home/repository/bioruby/bioruby/lib/bio/db/kegg
In directory dev.open-bio.org:/tmp/cvs-serv31897/lib/bio/db/kegg
Modified Files:
keggtab.rb
Log Message:
* document is changed to RDoc
Index: keggtab.rb
===================================================================
RCS file: /home/repository/bioruby/bioruby/lib/bio/db/kegg/keggtab.rb,v
retrieving revision 1.8
retrieving revision 1.9
diff -C2 -d -r1.8 -r1.9
*** keggtab.rb 8 May 2006 14:26:35 -0000 1.8
--- keggtab.rb 19 Sep 2006 05:54:29 -0000 1.9
***************
*** 2,8 ****
# = bio/db/kegg/keggtab.rb - KEGG keggtab class
#
! # Copyright:: Copyright (C) 2001 Mitsuteru C. Nakao <n at bioruby.org>
! # Copyright (C) 2003, 2006 KATAYAMA Toshiaki <k at bioruby.org>
! # License:: Ruby's
#
# $Id$
--- 2,8 ----
# = bio/db/kegg/keggtab.rb - KEGG keggtab class
#
! # Copyright:: Copyright (C) 2001 Mitsuteru C. Nakao <n at bioruby.org>
! # Copyright (C) 2003, 2006 Toshiaki Katayama <k at bioruby.org>
! # License:: Ruby's
#
# $Id$
***************
*** 12,23 ****
class KEGG
# Parse 'keggtab' KEGG database definition file which also includes
! # Taxonomic category of the KEGG organisms. The 'keggtab' file can
! # be found in
#
! # * ((<URL:ftp://ftp.genome.jp/pub/kegg/tarfiles/genes.tar.gz>))
#
class Keggtab
def initialize(file_path, bioroot = nil)
@bioroot = ENV['BIOROOT'] || bioroot
--- 12,55 ----
class KEGG
+ # == Description
+ #
# Parse 'keggtab' KEGG database definition file which also includes
! # Taxonomic category of the KEGG organisms.
#
! # == References
! #
! # The 'keggtab' file is included in
! #
! # * ftp://ftp.genome.jp/pub/kegg/tarfiles/genes.tar.gz
! # * ftp://ftp.genome.jp/pub/kegg/tarfiles/genes.weekly.last.tar.Z
! #
! # == Format
! #
! # File format is something like
! #
! # # KEGGTAB
! # #
! # # name type directory abbreviation
! # #
! # enzyme enzyme $BIOROOT/db/ideas/ligand ec
! # ec alias enzyme
! # (snip)
! # # Human
! # h.sapiens genes $BIOROOT/db/kegg/genes hsa
! # H.sapiens alias h.sapiens
! # hsa alias h.sapiens
! # (snip)
! # #
! # # Taxonomy
! # #
! # (snip)
! # animals alias hsa+mmu+rno+dre+dme+cel
! # eukaryotes alias animals+plants+protists+fungi
! # genes alias eubacteria+archaea+eukaryotes
#
class Keggtab
+ # Path for keggtab file and optionally set bioroot top directory.
+ # Environmental variable BIOROOT overrides bioroot.
def initialize(file_path, bioroot = nil)
@bioroot = ENV['BIOROOT'] || bioroot
***************
*** 29,33 ****
end
end
! attr_reader :bioroot, :db_names
--- 61,68 ----
end
end
!
! # Returns a string of the BIOROOT path prefix.
! attr_reader :bioroot
! attr_reader :db_names
***************
*** 35,38 ****
--- 70,74 ----
class DB
+ # Create a container object for database definitions.
def initialize(db_name, db_type, db_path, db_abbrev)
@name = db_name
***************
*** 42,46 ****
@aliases = Array.new
end
! attr_reader :name, :type, :path, :abbrev, :aliases
alias korg abbrev
alias keggorg abbrev
--- 78,94 ----
@aliases = Array.new
end
! # Database name. (e.g. 'enzyme', 'h.sapies', 'e.coli', ...)
! attr_reader :name
! # Definition type. (e.g. 'enzyme', 'alias', 'genes', ...)
! attr_reader :type
! # Database flat file path. (e.g. '$BIOROOT/db/kegg/genes', ...)
! attr_reader :path
! # Short name for the database. (e.g. 'ec', 'hsa', 'eco', ...)
! # korg and keggorg are alias for abbrev method.
! attr_reader :abbrev
! # Array containing all alias names for the database.
! # (e.g. ["H.sapiens", "hsa"], ["E.coli", "eco"], ...)
! attr_reader :aliases
!
alias korg abbrev
alias keggorg abbrev
***************
*** 50,53 ****
--- 98,103 ----
# DB section
+ # Returns a hash containing DB definition section of the keggtab file.
+ # If database name is given as an argument, returns a Keggtab::DB object.
def database(db_abbrev = nil)
if db_abbrev
***************
*** 58,61 ****
--- 108,113 ----
end
+ # Returns an Array containing all alias names for the database.
+ # (e.g. 'hsa' -> ["H.sapiens", "hsa"], 'hpj' -> ["H.pylori_J99", "hpj"])
def aliases(db_abbrev)
if @database[db_abbrev]
***************
*** 64,67 ****
--- 116,121 ----
end
+ # Returns a canonical database name for the abbreviation.
+ # (e.g. 'ec' -> 'enzyme', 'hsa' -> 'h.sapies', ...)
def name(db_abbrev)
if @database[db_abbrev]
***************
*** 70,73 ****
--- 124,129 ----
end
+ # Returns an absolute path for the flat file database.
+ # (e.g. '/bio/db/kegg/genes', ...)
def path(db_abbrev)
if @database[db_abbrev]
***************
*** 82,85 ****
--- 138,142 ----
+ # deprecated
def alias_list(db_name)
if @db_names[db_name]
***************
*** 88,91 ****
--- 145,149 ----
end
+ # deprecated
def db_path(db_name)
if @bioroot
***************
*** 96,99 ****
--- 154,158 ----
end
+ # deprecated
def db_by_abbrev(db_abbrev)
@db_names.each do |k, db|
***************
*** 103,110 ****
--- 162,171 ----
end
+ # deprecated
def name_by_abbrev(db_abbrev)
db_by_abbrev(db_abbrev).name
end
+ # deprecated
def db_path_by_abbrev(db_abbrev)
db_name = name_by_abbrev(db_abbrev)
***************
*** 115,118 ****
--- 176,183 ----
# Taxonomy section
+ # Returns a hash containing Taxonomy section of the keggtab file.
+ # If argument is given, returns a List of all child nodes belongs
+ # to the label node.
+ # (e.g. "eukaryotes" -> ["animals", "plants", "protists", "fungi"], ...)
def taxonomy(node = nil)
if node
***************
*** 123,126 ****
--- 188,193 ----
end
+ # List of all node labels from Taxonomy section.
+ # (e.g. ["actinobacteria", "animals", "archaea", "bacillales", ...)
def taxa_list
@taxonomy.keys.sort
***************
*** 131,134 ****
--- 198,204 ----
end
+ # Returns an array of organism names included in the specified taxon
+ # label. (e.g. 'proteobeta' -> ["nme", "nma", "rso"])
+ # This method has taxo2keggorgs, taxon2korgs, and taxon2keggorgs aliases.
def taxo2korgs(node = 'genes')
if node.length == 3
***************
*** 150,153 ****
--- 220,226 ----
alias taxon2keggorgs taxo2korgs
+ # Returns an array of taxonomy names the organism belongs.
+ # (e.g. 'eco' -> ['proteogamma','proteobacteria','eubacteria','genes'])
+ # This method has aliases as keggorg2taxo, korg2taxonomy, keggorg2taxonomy.
def korg2taxo(keggorg)
tmp = Array.new
***************
*** 283,413 ****
-
- =begin
-
- The keggtab file is included in
-
- * ((URL:ftp://ftp.genome.jp/pub/kegg/tarfiles/genes.weekly.last.tar.Z>))
-
- File format is something like
-
- # KEGGTAB
- #
- # name type directory abbreviation
- #
- enzyme enzyme $BIOROOT/db/ideas/ligand ec
- ec alias enzyme
- (snip)
- # Human
- h.sapiens genes $BIOROOT/db/kegg/genes hsa
- H.sapiens alias h.sapiens
- hsa alias h.sapiens
- (snip)
- #
- # Taxonomy
- #
- (snip)
- animals alias hsa+mmu+rno+dre+dme+cel
- eukaryotes alias animals+plants+protists+fungi
- genes alias eubacteria+archaea+eukaryotes
-
- = Bio::KEGG::Keggtab
-
- --- Bio::KEGG::Keggtab.new(file_path, bioroot = nil)
-
- Path for keggtab file and optionally set bioroot top directory.
- Environmental variable BIOROOT overrides bioroot.
-
- --- Bio::KEGG::Keggtab#database -> Hash
-
- Returns a hash containing DB definition section of the keggtab file.
-
- --- Bio::KEGG::Keggtab#database(db_abbrev) -> Keggtab::DB
-
- Returns a Keggtab::DB object.
-
- --- Bio::KEGG::Keggtab#taxonomy -> Hash
-
- Returns a hash containing Taxonomy section of the keggtab file.
-
- --- Bio::KEGG::Keggtab#taxonomy(node) -> Array
-
- Returns a List of all child nodes belongs to the label node.
- (e.g. "eukaryotes" -> ["animals", "plants", "protists", "fungi"], ...)
-
- --- Bio::KEGG::Keggtab#bioroot -> String
-
- Returns a string of the BIOROOT path prefix.
-
- --- Bio::KEGG::Keggtab#name(db_abbrev) -> String
-
- Returns a canonical database name for the abbreviation.
- (e.g. 'ec' -> 'enzyme', 'hsa' -> 'h.sapies', ...)
-
- --- Bio::KEGG::Keggtab#aliases(db_abbrev) -> Array
-
- Returns an Array containing all alias names for the database.
- (e.g. 'hsa' -> ["H.sapiens", "hsa"], 'hpj' -> ["H.pylori_J99", "hpj"])
-
- --- Bio::KEGG::Keggtab#path(db_abbrev) -> String
-
- Returns an absolute path for the flat file database.
- (e.g. '/bio/db/kegg/genes', ...)
-
- --- Bio::KEGG::Keggtab#taxa_list -> Array
-
- List of all node labels from Taxonomy section.
- (e.g. ["actinobacteria", "animals", "archaea", "bacillales", ...)
-
- --- Bio::KEGG::Keggtab#taxo2korgs(taxon) -> Array
-
- Returns an array of organism names included in the specified taxon
- label. (e.g. 'proteobeta' -> ["nme", "nma", "rso"])
- This method has taxo2keggorgs, taxon2korgs, and taxon2keggorgs aliases.
-
- --- Bio::KEGG::Keggtab#korg2taxo(keggorg) -> Array
-
- Returns an array of taxonomy names the organism belongs.
- (e.g. 'eco' -> ['proteogamma','proteobacteria','eubacteria','genes'])
- This method has aliases as keggorg2taxo, korg2taxonomy, keggorg2taxonomy.
-
- * following methods are deprecated
-
- --- Bio::KEGG::Keggtab#db_names[db_name] -> Keggtab::DB
- --- Bio::KEGG::Keggtab#db_by_abbrev(db_abbrev) -> Keggtab::DB
- --- Bio::KEGG::Keggtab#alias_list(db_name) -> Array
- --- Bio::KEGG::Keggtab#name_by_abbrev(db_abbrev) -> String
- --- Bio::KEGG::Keggtab#db_path(db_name) -> String
- --- Bio::KEGG::Keggtab#db_path_by_abbrev(keggorg) -> String
-
-
- == Bio::KEGG::Keggtab::DB
-
- --- Bio::KEGG::Keggtab::DB.new(db_name, db_type, db_path, db_abbrev)
-
- Create a container object for database definitions.
-
- --- Bio::KEGG::Keggtab::DB#name -> String
-
- Database name. (e.g. 'enzyme', 'h.sapies', 'e.coli', ...)
-
- --- Bio::KEGG::Keggtab::DB#type -> String
-
- Definition type. (e.g. 'enzyme', 'alias', 'genes', ...)
-
- --- Bio::KEGG::Keggtab::DB#path -> String
-
- Database flat file path. (e.g. '$BIOROOT/db/kegg/genes', ...)
-
- --- Bio::KEGG::Keggtab::DB#abbrev -> String
-
- Short name for the database. (e.g. 'ec', 'hsa', 'eco', ...)
- korg and keggorg are alias for abbrev method.
-
- --- Bio::KEGG::Keggtab::DB#aliases -> Array
-
- Array containing all alias names for the database.
- (e.g. ["H.sapiens", "hsa"], ["E.coli", "eco"], ...)
-
- =end
-
--- 356,357 ----
More information about the bioruby-cvs
mailing list