Skip to content

Commit

Permalink
* 2001/06/21
Browse files Browse the repository at this point in the history 
* completely rewrited to use db.rb
  * rename/add/delete some methods to satisfy the API of db.rb
  • Loading branch information
@ktym
ktym committed Jun 21, 2001
1 parent d5f08e5 commit 75a041e
Showing 1 changed file with 68 additions and 166 deletions.
234 changes: 68 additions & 166 deletions lib/bio/db/kegg/genes.rb
View file
@@ -1,7 +1,7 @@
#
# bio/db/genes.rb - KEGG/GENES database class
# bio/db/kegg/genes.rb - KEGG/GENES database class
#
# Copyright (C) 2000, 2001 KATAYAMA Toshiaki <k@bioruby.org>
# Copyright (C) 2001 KATAYAMA Toshiaki <k@bioruby.org>
#
# This library is free software; you can redistribute it and/or
# modify it under the terms of the GNU Library General Public
Expand All @@ -13,238 +13,140 @@
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
# Library General Public License for more details.
#
# $Id: genes.rb,v 0.7 2001/06/21 02:39:23 katayama Exp $
#

require 'bio/sequence'
require 'bio/db'

class GENES
class GENES < KEGGDB

DELIMITER = "\n///\n"
TAGSIZE = 12
DELIMITER = RS = "\n///\n"
TAGSIZE = 12

def initialize(entry)
@orig = {} # Hash of the original entry
@data = {} # Hash of the parsed entry

tag = '' # temporal key
@orig[tag] = ''

entry.each_line do |line|
next if line =~ /^$/

if line =~ /^\w/
tag = tag_get(line)
@orig[tag] = '' unless @orig[tag] # String
end
@orig[tag] << line
end
super(entry, TAGSIZE)
end


### general method to return block of the tag and contens as is
def get(tag)
@orig[tag] # returns nil when not found
end


### general method to return contens without tag and extra white spaces
def fetch(tag)
if get(tag)
str = ''
get(tag).each_line do |line|
str << tag_cut(line)
end
return truncate(str)
else
return nil # compatible with get()
end
end


def entry(key = nil)
unless @data['ENTRY']
@data['ENTRY'] = {}

if @orig['ENTRY']
@data['ENTRY']['id'] = @orig['ENTRY'][12..29].strip
@data['ENTRY']['type'] = @orig['ENTRY'][30..39].strip
@data['ENTRY']['species'] = @orig['ENTRY'][40..80].strip
hash = {}
if @orig['ENTRY'].length > 30
hash['id'] = @orig['ENTRY'][12..29].strip
hash['division'] = @orig['ENTRY'][30..39].strip
hash['organism'] = @orig['ENTRY'][40..80].strip
end
@data['ENTRY'] = hash
end

if key
@data['ENTRY'][key]
elsif block_given?
if block_given?
@data['ENTRY'].each do |k, v|
yield(k, v)
yield(k, v) # each contents of ENTRY
end
elsif key
@data['ENTRY'][key] # contents of key's ENTRY
else
@data['ENTRY']
@data['ENTRY'] # Hash of ENTRY
end
end
alias each_entry entry

def id
entry('id')
entry('id') # ENTRY ID
end
def division
entry('division') # CDS, tRNA etc.
end
def organism
entry('organism') # H.sapiens etc.
end

def name
@data['NAME'] = fetch('NAME') unless @data['NAME']
@data['NAME']
field_fetch('NAME')
end
def gene
name.split(', ')
end

def definition
@data['DEFINITION'] = fetch('DEFINITION') unless @data['DEFINITION']
@data['DEFINITION']
field_fetch('DEFINITION')
end

def class
@data['CLASS'] = fetch('CLASS') unless @data['CLASS']
@data['CLASS']
def keggclass
field_fetch('CLASS')
end

def position
@data['POSITION'] = fetch('POSITION') unless @data['POSITION']
@data['POSITION'].gsub!(/\s+/, '') if @data['POSITION']
unless @data['POSITION']
@data['POSITION'] = field_fetch('POSITION').gsub(/\s/, '')
end
@data['POSITION']
end

def dblinks(key = nil)
def dblinks(db = nil)
unless @data['DBLINKS']
@data['DBLINKS'] = {}
if @orig['DBLINKS']
@orig['DBLINKS'].scan(/(\S+):\s+(\S+)\n/).each do |k, v|
@data['DBLINKS'][k] = v
end
hash = {}
@orig['DBLINKS'].scan(/(\S+):\s*(\S+)\n/).each do |k, v|
hash[k] = v
end
@data['DBLINKS'] = hash
end

if key
@data['DBLINKS'][key]
elsif block_given?
if block_given?
@data['DBLINKS'].each do |k, v|
yield(k, v)
yield(k, v) # each DB:ID pair in DBLINKS
end
elsif db
@data['DBLINKS'][db] # ID of the DB
else
@data['DBLINKS']
@data['DBLINKS'] # Hash of DB:ID in DBLINKS (default)
end
end
alias each_link dblinks

def codon_usage(codon = nil)
unless @data['CODON_USAGE']
return @data['CODON_USAGE'] unless @orig['CODON_USAGE'] # nil

@data['CODON_USAGE'] = [] # data in Array

@orig['CODON_USAGE'].sub(/.*/,'').each_line do |l| # cut 1st line
l.chomp.sub(/^.{11}/, '').scan(/.{4}/) do |x|
@data['CODON_USAGE'].push(x.to_i)
ary = []
@orig['CODON_USAGE'].sub(/.*/,'').each_line do |line| # cut 1st line
line.scan(/\d+/).each do |cu|
ary.push(cu.to_i)
end
end
@data['CODON_USAGE'] = ary
end

h = { 't' => 0, 'c' => 1, 'a' => 2, 'g' => 3 }

if codon
codon.downcase!
key = h[codon[0].chr] * 16 + h[codon[1].chr] * 4 + h[codon[2].chr]
@data['CODON_USAGE'][key]
elsif block_given?
@data['CODON_USAGE'].each do |x|
yield(x)
if block_given?
@data['CODON_USAGE'].each do |cu|
yield(cu) # each CODON_USAGE
end
elsif codon
h = { 't' => 0, 'c' => 1, 'a' => 2, 'g' => 3 }
x, y, z = codon.downcase.scan(/\w/)
codon_num = h[x] * 16 + h[y] * 4 + h[z]
@data['CODON_USAGE'][codon_num] # CODON_USAGE of the codon
else
return @data['CODON_USAGE']
return @data['CODON_USAGE'] # Array of CODON_USAGE (default)
end
end
alias cu codon_usage

def aaseq
unless @data['AASEQ']
if @orig['AASEQ']
@data['AASEQ'] = fetch('AASEQ').gsub(/[\s\d\/]+/, '')
else
@data['AASEQ'] = ''
end
@data['AASEQ'] = AAseq.new(field_fetch('AASEQ').gsub(/[\s\d\/]+/, ''))
end
return AAseq.new(@data['AASEQ'])
@data['AASEQ']
end
alias aa aaseq

def aalen
unless @data['AALEN']
if @orig['AASEQ']
@data['AALEN'] = tag_cut(@orig['AASEQ'][/.*/]).to_i
else
@data['AALEN'] = 0
end
end
@data['AALEN']
@data['AALEN'] = aaseq.length
end

def ntseq
unless @data['NTSEQ']
if @orig['NTSEQ']
@data['NTSEQ'] = fetch('NTSEQ').gsub(/[\s\d\/]+/, '')
else
@data['NTSEQ'] = ''
end
@data['NTSEQ'] = NAseq.new(field_fetch('NTSEQ').gsub(/[\s\d\/]+/, ''))
end
return NAseq.new(@data['NTSEQ'])
@data['NTSEQ']
end
alias na ntseq
alias naseq ntseq

def ntlen
unless @data['NTLEN']
if @orig['NTSEQ']
@data['NTLEN'] = tag_cut(@orig['NTSEQ'][/.*/]).to_i
else
@data['NTLEN'] = 0
end
end
@data['NTLEN']
@data['NTLEN'] = ntseq.length
end
alias nalen ntlen


### change the default to private method below the line
private

# remove extra white spaces
def truncate(str)
return str.gsub(/\s+/, ' ').strip
end

def truncate!(str)
# do not chain these lines to avoid performing on nil
str.gsub!(/\s+/, ' ')
str.strip!
return str
end


# remove tag field from the line
def tag_cut(str)
if str.length > TAGSIZE
return str[TAGSIZE..str.length]
else
return '' # to avoid returning nil
end
end

def tag_cut!(str)
str[0,tag_size] = ''
return str
end


# get tag field of the line
def tag_get(str)
if str.length > TAGSIZE
return str[0,TAGSIZE].strip
else
return '' # to avoid returning nil
end
end

end

0 comments on commit 75a041e

Please sign in to comment.