exodb 0.0.2

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: bd0cec2b7ef4791ab9686827bf8d31409152af2a
+  data.tar.gz: 117c7eb770d5473a76909af778017f2557288982
+SHA512:
+  metadata.gz: 6b7cd7602e7bda8da25c1799e5fbc0fd3221e04397b52a54cb4c1b5b2691b6cfea96d1e114bfc1f218529d747614544876da7eb78d8258ef3ee41a082d22eee2
+  data.tar.gz: 5699679e8fb8834af7c4e7f42ca2f399c549c015b1fa07781240a9a9f76d01a56951ba72af04645254232d588a6c1c9424034f23ec03791098bd57a0e3d5bf3c

data/contributors.txt

@@ -0,0 +1 @@
+Natapol Pornputtapong

data/exodb.gemspec

@@ -0,0 +1,35 @@
+# -*- encoding: utf-8 -*-
+$:.push File.expand_path("../lib", __FILE__)
+require "exodb/version"
+
+Gem::Specification.new do |s|
+    s.name          = 'exodb'
+    s.version       = Exodb::VERSION
+    s.date          = '2014-10-31'
+    s.platform      = Gem::Platform::RUBY
+    
+    s.summary       = "A library for exome sequencing data management development"
+    s.description   = "A library for exome sequencing data management"
+    s.authors       = ["Natapol Pornputtapong"]
+    s.email         = 'natapol.por@gmail.com'
+
+    s.homepage      = 'http://rubygems.org/gems/dactyls'
+    s.license       = 'GPL'
+    
+#    s.rubyforge_project = "neography"
+    
+    s.files         = `git ls-files`.split("\n")
+    s.test_files    = `git ls-files -- {test,spec,features}/*`.split("\n")
+    s.executables   = `git ls-files -- bin/*`.split("\n").map{ |f| File.basename(f) }
+    s.require_paths = ["lib"]
+    
+    s.add_dependency "mongoid", "~> 3.1"
+    s.add_dependency "bio", "~> 1.4"
+    s.add_dependency "highline", "~> 1.6"
+    s.add_dependency "pry", "~> 0.10"
+    
+    
+#    s.add_development_dependency "rspec", ">= 2.11"
+#    s.add_dependency "httpclient", ">= 2.3.3"
+
+end

data/genome/process_genome_seq.rb

@@ -0,0 +1,22 @@
+# 
+# Exodus
+# Copyright (C) 2014
+#
+# author: Natapol Pornputtapong <natapol.por@gmail.com>
+#
+# Documentation: Natapol Pornputtapong (RDoc'd and embellished by William Webber)
+#
+
+# raise "Please, use ruby 1.9.0 or later." if RUBY_VERSION < "1.9.0"
+
+require 'bio'
+
+
+Dir.glob('hs_ref_GRCh37*.fa').each do |file|
+	flatfile = Bio::FlatFile.open(Bio::FastaFormat, file)
+	flatfile.each do |e|
+		outfile = File.open("#{e.acc_version}.fa", 'w')
+		outfile.write(e.to_s)
+		outfile.close()
+	end
+end

data/lib/exodb/addon/string.rb

@@ -0,0 +1,26 @@
+# 
+# Exodus
+# Copyright (C) 2014
+#
+# author: Natapol Pornputtapong <natapol.por@gmail.com>
+#
+# Documentation: Natapol Pornputtapong (RDoc'd and embellished by William Webber)
+#
+
+# raise "Please, use ruby 1.9.0 or later." if RUBY_VERSION < "1.9.0"
+
+class String
+	
+	def is_miriam?
+		return self =~ /^urn:miriam:/
+	end
+	
+	def id
+		return self.is_miriam? ? self.split(':', 4)[-1] : ''
+	end
+	
+	def namespace
+		return self.is_miriam? ? self.split(':', 4)[2] : ''
+	end
+	
+end

data/lib/exodb/addon.rb

@@ -0,0 +1,13 @@
+# 
+# Exodus
+# Copyright (C) 2014
+#
+# author: Natapol Pornputtapong <natapol.por@gmail.com>
+#
+# Documentation: Natapol Pornputtapong (RDoc'd and embellished by William Webber)
+#
+
+# raise "Please, use ruby 1.9.0 or later." if RUBY_VERSION < "1.9.0"
+
+require 'exodb/addon/string.rb'
+

data/lib/exodb/datamodel/locationfield.rb

@@ -0,0 +1,103 @@
+# 
+# Exodb
+# Copyright (C) 2014
+#
+# author: Natapol Pornputtapong <natapol.por@gmail.com>
+#
+# Documentation: Natapol Pornputtapong (RDoc'd and embellished by William Webber)
+#
+
+# raise "Please, use ruby 1.9.0 or later." if RUBY_VERSION < "1.9.0"
+
+module Exodb
+    
+	module LocationField
+		
+		extend ActiveSupport::Concern
+		
+		included do
+			field :location,		type: Hash #{chromosome: '', start: x, stop: x}
+			index({location: 1}, background: true)
+		end
+		
+		module ClassMethods
+			
+			def cover?(loc_str)
+				dat = loc_str.split(/(:|\.\.)/)
+				if dat[4]
+					querystr = {:'location.chromosome' => dat[0], :'location.start'.lte => dat[2].to_i, :'location.stop'.gte => dat[4].to_i}
+				else
+					querystr = {:'location.chromosome' => dat[0], :'location.start'.lte => dat[2].to_i, :'location.stop'.gte => dat[2].to_i}
+				end
+				return self.where(querystr)
+			end
+			
+			def intersect?(loc_str)
+				dat = loc_str.split(/(:|\.\.)/)
+				querystr = {:'$or' => [{:'location.chromosome' => dat[0], :'location.start'.lte => dat[2].to_i, :'location.stop'.gte => dat[2].to_i}, {:'location.chromosome' => dat[0], :'location.start'.lte => dat[4].to_i, :'location.stop'.gte => dat[4].to_i}]}
+				return self.where(querystr)
+			end
+			
+			def in?(loc_str)
+				dat = loc_str.split(/(:|\.\.)/)
+				querystr = {:'location.chromosome' => dat[0], :'location.start'.gte => dat[2].to_i, :'location.stop'.lte => dat[4].to_i}
+				return self.where(querystr)
+			end
+			
+			#def converse
+			#	self.where({}).each do |e|
+			#		if e[:location][:coordinates]
+			#			oldlocation = e[:location]
+			#			if oldlocation[:coordinates][0].is_a?(Array)
+			#				e[:location] = {chromosome: oldlocation[:coordinates][0][0], start: oldlocation[:coordinates][0][1], stop: oldlocation[:coordinates][1][1]}
+			#			else
+			#				e[:location] = {chromosome: oldlocation[:coordinates][0], start: oldlocation[:coordinates][1], stop: oldlocation[:coordinates][1]}
+			#			end
+			#			p e.save!
+			#		end
+			#	end
+			#end
+		end
+		
+		# get the start position of gene rely on the genome
+		#
+		# @return [Integer] start position of gene
+		def start
+			self[:location]['start']
+		end
+		
+		# get the end position of gene rely on the genome
+		#
+		# @return [Integer] end position of gene
+		def stop
+			self[:location]['stop']
+		end
+		
+		alias_method :end, :stop
+		
+		# get the chromosome
+		#
+		# @return [Integer] chromosome
+		def chromosome
+			self[:location]['chromosome']
+		end
+		
+		# Assign gene location in format of chromosome_number:start..stop
+		#
+		# @param [String] gene location in format of chromosome_number:start..stop
+		def parse_location(loc_str)
+			dat = loc_str.split(/(:|\.\.)/)
+			if dat[4]
+				self[:location] = {chromosome: dat[0], start: dat[2].to_i, stop: dat[4].to_i}
+			else
+				self[:location] = {chromosome: dat[0], start: dat[2].to_i, stop: dat[2].to_i}
+			end
+			
+		end
+		
+		def location_str
+			return "#{self.chromosome}:#{[self.start, self.stop].uniq.join('..')}"
+		end
+	end
+    
+end

data/lib/exodb/datamodel/reference.rb

@@ -0,0 +1,387 @@
+# 
+# Exodb
+# Copyright (C) 2014
+#
+# author: Natapol Pornputtapong <natapol.por@gmail.com>
+#
+# Documentation: Natapol Pornputtapong (RDoc'd and embellished by William Webber)
+#
+
+# raise "Please, use ruby 1.9.0 or later." if RUBY_VERSION < "1.9.0"
+
+module Exodb
+	
+	class Reference
+		
+		include Mongoid::Document
+		include Mongoid::Versioning
+		include Mongoid::Timestamps
+		
+		include Exodb::XrefsField
+		
+		field :oid,					type: String
+		
+	end
+	
+	class Variantref < Reference
+		
+		PATTERN = /(?<gene>[A-Z0-9]+)-?(?<position>[0-9,]*|[is]?)(?<to>[A-Z=]*)/
+		SILENTSIGN = '='
+		
+		include Exodb::LocationField
+		
+		field :reference,			type: String
+		field :alternate,			type: String
+		
+	end
+	
+	class Incidence
+		
+		include Mongoid::Document
+		
+		field :cancertype,			type: String
+		field :position,			type: String # refseq id of chromomose
+		field :occur,				type: Array
+		field :casenumber,			type: Integer
+		
+		embedded_in :generef
+		
+	end
+	
+	class Generef < Reference
+		
+		include Exodb::LocationField
+		
+		field :sequence,			type: String
+		field :chrrefseq,			type: String # refseq id of chromomose
+		field :strand,				type: String
+		field :psuedo,				type: Boolean
+		field :genomeref,			type: String
+		
+		index({sequence: 'text'}, background: true)
+		
+		has_many :genes
+		embeds_many :splices
+		embeds_many :incidences
+		
+		validates_format_of :chrrefseq, with: /\A(urn:miriam:refseq)/
+		
+		
+		# Download sequence from web service please use by caution. NCBI will block scamming sequest
+		#
+		def dl_seq!
+			
+			case self.chrrefseq
+			when /\Aurn:miriam:refseq:/
+				self.sequence = Bio::FastaFormat.new(Bio::NCBI::REST.efetch(self.chrrefseq.split(':', 4), {"db"=>"nucleotide", "rettype"=>"fasta", "retmode"=>"text", "seq_start"=>self.start, "seq_stop"=>self.end})).seq
+			end
+			
+			self.save!
+			
+		end
+		
+		# Download gene symbol from HGNC service
+		#
+		def dl_symbol!
+			
+			baseuri = "http://rest.genenames.org/search"
+			
+			
+			query = ""
+			
+			if self.get_xref('urn:miriam:refseq')
+				query = "#{baseuri}/refseq_accession/#{self.chrrefseq.id.split('.')[0]}"
+			elsif self.get_xref('urn:miriam:ncbigene')
+				query = ""
+			end
+			
+			if !query.empty?
+				response = JSON.parse(open(query, 'Accept' => 'application/json').read)['response']
+				if !response['docs'].empty?
+					
+					response['docs'].each do |e|
+						self.add_to_set(:xrefs, "urn:miriam:hgnc:#{e["hgnc_id"]}")
+						self.add_to_set(:xrefs, "urn:miriam:hgnc.symbol:#{e["symbol"]}")
+					end
+					
+					self.save!
+					
+				end
+				
+			end
+			
+		end
+		
+		# Download incident data from TCGA
+		#
+		def dl_incidence!
+			
+			if self.get_xref('urn:miriam:hgnc.symbol')
+				
+				cancerstudies = []
+				
+				open("http://www.cbioportal.org/public-portal/webservice.do?cmd=getCancerStudies") {|f|
+					f.each_line {|line| cancerstudies.push(line.chomp.split("\t")[0])}
+				}
+				
+				incidents = {}
+				totalcase = {}
+				
+				cancerstudies.each do |study|
+					
+					totalcase[study] = 0 if !totalcase.has_key?(study)
+					
+					open("http://www.cbioportal.org/public-portal/webservice.do?cmd=getCaseLists&cancer_study_id=#{study}") do |f|
+						f.each_line do |line|
+							totalcase[study] += line.chomp.split(/\t/)[4].split(' ').length if line =~ /\tSequenced Tumors\t/
+						end
+					end
+					
+					incidents[study] = {} if !incidents.has_key?(study)
+					
+					open("http://www.cbioportal.org/public-portal/webservice.do?cmd=getMutationData&genetic_profile_id=#{study}_mutations&gene_list=#{self.get_xref('urn:miriam:hgnc.symbol').id}") do |f|
+						f.each_line do |line|
+							dat = line.chomp.split(/\t/)
+							
+							if dat[5] == 'Missense_Mutation'
+								
+								incidents[study][dat[7].split(/(\d+)/)[1]] = [] if !incidents[study].has_key?(dat[7].split(/(\d+)/)[1])
+								incidents[study][dat[7].split(/(\d+)/)[1]].push(dat[2])
+								
+							end
+							
+						end
+						
+						
+					end
+				end
+				
+				self.incidences.clear if self.incidences
+				
+				incidents.each_pair do |cancertype, v|
+					v.each_pair do |position, occur|
+						self.incidences << Incidence.new({cancertype: cancertype, position: position, occur: occur.uniq.sort, casenumber: totalcase[cancertype]})
+					end
+				end
+				
+				self.save!
+				
+			end
+			
+		end
+		
+		# return sequence as Bio::Sequence object
+		#
+		# @return [Bio::Sequence] the contents reversed lexically
+		def to_seq
+			return self.sequence ? Bio::Sequence.auto(self.sequence) : Bio::Sequence.auto("")
+		end
+		
+		# return longest splice of this gene
+		def longest_splice()
+			length = 0
+			longest = nil
+			self.splices.each do |e|
+				
+				if e.prot_len > length
+					length = e.prot_len
+					longest = e
+				end
+				
+			end
+			
+			return longest
+		end
+		
+		# Check that this gene has any splice variant
+		#
+		# @return [Boolean] true if has any splices
+		def has_splices?
+			return self.splices.exists?
+		end
+		
+		# Check if Generef has sequence
+		#
+		# @return [Boolean] Return true if there is a sequence
+		def has_sequence?()
+			return self[:sequence] ? true : false
+		end
+		
+		# Check if Generef can translate
+		#
+		# @return [Boolean] Return true if this can be translate
+		def can_translated?()
+			return self.has_sequence? && self.has_splices? && self.longest_splice != nil ? true : false
+		end
+		
+		# Get gene symbol
+		#
+		# @return [String] Return gene symbol or any id from xrefs or 'nosymbol'
+		def symbol
+			
+			if self.get_xref('urn:miriam:hgnc.symbol')
+				return self.get_xref('urn:miriam:hgnc.symbol').id
+			elsif self.xrefs && !self.xrefs.empty?
+				return self.xrefs.sort[0].id
+			else
+				return 'nosymbol'
+			end
+			
+		end
+		
+	end
+	
+	class Splice
+		
+		include Mongoid::Document
+		
+		include Exodb::XrefsField
+		
+		field :exon,				type: Array
+		field :cds,					type: Array
+		
+		embedded_in :generef
+		
+		# join exon or cds position into a string
+		#
+		# @param [Array] input array exon or cds
+		# @param [Interger] Position to stop positive value for forward read negative value for complement
+		#
+		# @return [String] a string in start..end,start..end,...
+		def get_join_str(arr, position = 0)
+			
+			reducer = self.generef.start - 1
+			tmparr = []
+			found = false
+			
+			if position > 0
+				add = true
+				arr.each do |e|
+					
+					if e[0] <= position && position <= e[1]
+						tmparr.push([e[0], position])
+						add = false
+						found = true
+					else
+						tmparr.push(e) if add
+					end
+					
+				end
+			elsif position < 0
+				position = position.abs
+				add = false
+				arr.each do |e|
+					
+					if e[0] <= position && position <= e[1]
+						tmparr.push([position, e[1]])
+						add = true
+						found = true
+					else
+						tmparr.push(e) if add
+					end
+					
+				end
+			else
+				tmparr = arr
+			end
+			
+			tmparr = [] if !found && position != 0
+			str = []
+			
+			tmparr.each do |e|
+				str.push("#{e[0] - reducer}..#{e[1] - reducer}")
+			end
+			return str.join(',')
+			
+		end
+		
+		def get_exon_join(position = 0)
+			get_join_str(self[:exon], position)
+		end
+		
+		def get_cds_join(position = 0)
+			get_join_str(self[:cds], position)
+		end
+		
+		# Get spliced DNA sequence
+		#
+		# @return [Bio::Sequence] an DNA sequence
+		def get_dna_seq
+			parent =  self.generef
+			return parent.strand == '+' ? parent.to_seq.splicing("join(#{self.get_exon_join})") : parent.to_seq.splicing("complement(join(#{self.get_exon_join}))")
+		end
+		
+		# Get spliced RNA sequence
+		#
+		# @return [Bio::Sequence] an RNA sequence
+		def get_mrna_seq
+			parent =  self.generef
+			return parent.strand == '+' ? parent.to_seq.splicing("join(#{self.get_exon_join})").rna : parent.to_seq.splicing("complement(join(#{self.get_exon_join}))").rna
+		end
+		
+		# Get spliced coding region sequence
+		#
+		# @param [Integer] end position to get sequence
+		#
+		# @return [Bio::Sequence] an coding region sequence
+		def get_cds_seq(position = 0)
+			
+			parent =  self.generef
+			if parent.strand == '+'
+				join = self.get_cds_join(position)
+				return !join.empty? ? parent.to_seq.splicing("join(#{join})") : ""
+			else
+				join = self.get_cds_join(-position)
+				return !join.empty? ? parent.to_seq.splicing("join(#{join})") : ""
+			end
+			
+		end
+		
+		# Get spliced protein sequence
+		#
+		# @return [Bio::Sequence] an protein sequence
+		def get_prot_seq
+			parent =  self.generef
+			return parent.strand == '+' ? parent.to_seq.splicing("join(#{self.get_cds_join})").translate : parent.to_seq.splicing("complement(join(#{self.get_cds_join}))").translate
+		end
+		
+		# get length of spliced RNA
+		#
+		# @return [Integer] length of spliced RNA
+		def rna_len
+			return self.get_mrna_seq.length
+		end
+		
+		# get length of protein product
+		#
+		# @return [Integer] length of protein product
+		def prot_len
+			return self.get_prot_seq.length
+		end
+		
+		# Get the codon sequence at the giving position base on position of amino acid
+		#
+		# @param [Integer] codon position
+		# @return [Bio::Sequence] the codon at given position
+		def get_codon(codon_pos)
+			return self.get_cds_seq().subseq(((codon_pos - 1) * 3) + 1 , ((codon_pos - 1) * 3) + 3)
+		end
+		
+		# convert genomic position to codon position
+		#
+		# @param [Integer] genomic position
+		# @return [Array] Return all information of codon at given position
+		def get_prot_pos(pos)
+			
+			seqlen = self.get_cds_seq(pos).length
+			if seqlen != 0
+				return [(seqlen - 1) / 3, (seqlen - 1) % 3]
+			else
+				return []
+			end
+			
+		end
+		
+	end
+	
+end

data/lib/exodb/datamodel/region.rb

@@ -0,0 +1,51 @@
+# 
+# Exodb
+# Copyright (C) 2014
+#
+# author: Natapol Pornputtapong <natapol.por@gmail.com>
+#
+# Documentation: Natapol Pornputtapong (RDoc'd and embellished by William Webber)
+#
+
+# raise "Please, use ruby 1.9.0 or later." if RUBY_VERSION < "1.9.0"
+
+
+module Exodb
+	
+	class Region
+		
+		include Mongoid::Document
+		include Mongoid::Timestamps
+		
+	end
+	
+	class Gene < Region
+		
+		include Mongoid::Versioning
+		include Exodb::LocationField
+		
+		field :symbol,				type: String
+		field :loh,					type: Boolean
+		
+		embeds_many :aacids
+		belongs_to :generef
+		belongs_to :cell
+		
+		index({'symbol' => 1, 'aacids.position' => 1}, background: true)
+	end
+	
+	class Aacid < Region
+		
+		field :position,			type: Integer # position referenced to the first codon from the longest splice variant
+		field :refcodon,			type: String
+		field :refaa,				type: String
+		field :altcodon,			type: Hash
+		field :inhcodon,			type: Hash
+		field :isoform,				type: Array
+		
+		embedded_in :gene
+		has_many :variants
+		
+	end
+	
+end