exodb 0.1.2 → 0.1.3

data/lib/exodb/rositza/load.rb

@@ -17,28 +17,68 @@ module Exodb
 		
 		module_function
 		
-		def load_variant_from_csv(csvfile)
+		def load_snv_from_csv(csvfile)
 			
 			CSV.read(csvfile, col_sep: "\t", headers: true).each do |record|
 				
-				var = SNV.new()
-				var.parse_location("#{record["chromosome"]}:#{record["start position"]}")
+				var = Exodb::Variant.new()
+				var.location=("chr#{record["chromosome"]}:#{record["start position"]}")
 				var.reference = record["ref nucleotide"].split('/')[0]
-				var.alternate = record["var nucleotide"].split('/').uniq
-				var.somaticStatus = record["Somatic Status"]
-				var.reads = record["Reads"]
+				var.alternatet = record["var nucleotide"].split('/').uniq
+				var.somstatus = record["Somatic Status"].downcase
+				var.passfilter = true
+				var.pileupt = record["Reads"]
 				var.predicted_damage = record["PolyPhen"] =~ /probably_damaging/ || record["SIFT"] =~ /deleterious/i || record["PROVEAN"] =~ /deleterious/i ? true : false
-				var.aachange = record["AA Change"]
+				var.temp = {} if var.temp.blank?
+				var.temp['aachange'] = "#{record["symbol"]}:#{record["AA Change"]}"
 				var.add_to_sample(record["cell"])
 				
 				p var.save!
 			end
 		end
 		
+		def load_splice_from_csv(csvfile)
+			
+			CSV.read(csvfile, col_sep: "\t", headers: true).each do |record|
+				
+				var = Exodb::Variant.new()
+				var.location=("chr#{record["chr"]}:#{record["Position"]}")
+				var.reference = record["Reference Genotype"]
+				var.alternatet = ['N']
+				var.somstatus = 'somatic'
+				var.passfilter = true
+				#var.pileupt = record["Reads"]
+				var.predicted_damage = true
+				var.temp = {} if var.temp.blank?
+				var.temp['aachange'] = "#{record["Gene Symbol"]}:SpV"
+				var.add_to_sample(record["Sample"])
+				p var.save!
+			end
+		end
+		
+		def load_indel_from_csv(csvfile)
+			
+			CSV.read(csvfile, col_sep: "\t", headers: true).each do |record|
+				
+				var = Exodb::Variant.new()
+				var.location=("#{record["chr"]}:#{record["pos"]}")
+				#var.reference = record["Reference Genotype"]
+				var.alternatet = ['-2N']
+				var.somstatus = record["Somatic Status"].downcase
+				var.passfilter = true
+				#var.pileupt = record["Reads"]
+				var.predicted_damage = true
+				var.temp = {} if var.temp.blank?
+				var.temp['aachange'] = "#{record["symbol"]}:InDel"
+				var.add_to_sample(record["cell lines"])
+				p var.save!
+			end
+		end
+		
 		def load_sample_from_csv(csvfile)
 			CSV.read(csvfile, col_sep: "\t", headers: true).each do |record|
 				
-				sample = Tumor.new({oid: record["SampleFinal"],
+				sample = Cell.new({oid: record["SampleFinal"],
 								type: record["Type"].downcase,
 								typeid: "urn:miriam:bioportal.meddra:#{record["Type"] =~ /^spitz /i ? '10041632' : record["Type"] =~ /^spitzoid /i ? '10072450' : '10028679'}",
 								patient: record["SampleFinal"].split('T')[0],
@@ -53,29 +93,7 @@ module Exodb
 			end
 		end
 		
-		def load_variant_from_ann(annfile)
-			
-			File.open(annfile).each do |line|
-				record = line.chomp.split("\t")
-				p record
-			end
-			
-		end
-		
-		def load_indel_from_merge(mergefile)
-			
-			File.open(mergefile).each do |line|
-				record = line.chomp.split("\t")
-				p record[0..21]
-				#others = record[22..-1]
-				#until others.empty?
-				#	p others.shift(11)
-				#end
-			end
-			
-		end
-		
-		def load_variant_from_merge(mergefile)
+		def load_variant_from_merge(mergefile, normal = false, assembly = Exodb::DEFAULTASSEMBLY)
 			
 			File.open(mergefile).each do |line|
 				record = line.chomp.split("\t")
@@ -85,20 +103,16 @@ module Exodb
 				list = record[16..-1]
 				
 				until list.empty?
-					
-					sampledata = list.shift(7)
-					snvq = Exodb::Variant.where(oid: "#{header[2]}:#{header[3]}:#{sampledata[0]}")
-					if snvq.exists?
-						snv = snvq.first
-						snv.temp.push(header[0..6].join("\t"))
-						p snv.save!
+					if normal
+						snv = Exodb::Variant.where(oid: "#{header[2]}:#{header[3]}:#{assembly}:#{sampledata[0]}").first
+						snv.pileupn = sampledata[6] if snv != nil
 					else
+						sampledata = list.shift(7)
 						snv = Exodb::Variant.new()
-						snv.parse_location("#{header[2]}:#{header[3]}..#{header[3]}")
+						snv.location=("#{header[2]}:#{header[3]}:#{assembly}")
 						snv.reference = header[10]
 						snv.pileupt = sampledata[6]
-						snv.temp = [] if snv.temp == nil
-						snv.temp.push(header[0..6].join("\t"))
+						snv.temp = {} if snv.temp.blank?
 						snv.add_to_sample(sampledata[0])
 						p snv.save!
 					end
@@ -111,5 +125,5 @@ module Exodb
 end
 
 #Exodb::Utils.load_sample_from_csv('Samples_all.txt')
-#Exodb::Utils.load_variant_from_csv('NovelSNVs_13.txt')
+#Exodb::Utils.load_snv_from_csv('NovelSNVs_13.txt')
 #Exodb::Utils.load_variant_from_merge('gilead_ann/tumor/exome.UTR')

data/lib/exodb/utils.rb

@@ -9,10 +9,9 @@
 
 # raise "Please, use ruby 1.9.0 or later." if RUBY_VERSION < "1.9.0"
 
-require 'exodb/utils/upload_generef.rb'
 require 'exodb/utils/upload_var.rb'
 require 'exodb/utils/ensemblrest.rb'
-
+require 'exodb/utils/miriamrest.rb'
 
 #load script specific to rosiza project
 require 'exodb/rositza.rb'

data/lib/exodb/utils/ensemblrest.rb

@@ -19,9 +19,9 @@ module Exodb
 			
 			module_function
 			
-			def get(getpart, options)
+			def get(get_path, options)
 				request = Net::HTTP::Get.new(get_path, {'Content-Type' => 'application/json'}.merge(options))
-				response = http.request(request)
+				response = @@http.request(request)
 				if response.code != "200"
 					riase InvalidResponse, "Invalid response: #{response.code}"
 				else
@@ -29,10 +29,38 @@ module Exodb
 				end
 			end
 			
-			def fetch_variant(region, allele, species, options = {})
+			
+			# http://rest.ensembl.org/documentation/info/vep_region_get
+			def vep_region_get(region, allele, species, options = {})
 				return Exodb::Ensembl::REST.get("vep/#{species}/region/#{region}/allele", options)
 			end
 			
+			# http://rest.ensembl.org/documentation/info/vep_hgvs_get
+			def vep_hgvs_get(hgvs, species, options = {})
+				return Exodb::Ensembl::REST.get("vep/#{species}/hgvs/#{region}/allele", options)
+			end
+			
+			# Converse coordinate from one asembly to another
+			# from http://rest.ensembl.org/documentation/info/assembly_map
+			#
+			# @param [String] location string in chromosome:start..stop format
+			# @param [String] target assembly or asm_two
+			# @param [String] original assembly default: exodb::DEFAULTASSEMBLY
+			# @param [String] species of genome
+			# @param [Hash] option 
+			def assembly_map(region, asm_two, asm_one = Exodb::DEFAULTASSEMBLY, species = 'human', options = {})
+				return Exodb::Ensembl::REST.get("map/#{species.gsub(/\s+/, '_')}/#{Exodb::ASSEMBLY[asm_one.downcase]}/#{region}/#{Exodb::ASSEMBLY[asm_two.downcase]}", options)
+			end
+			
+			# Returns the genomic sequence of the specified region of the given species.
+			# from http://rest.ensembl.org/documentation/info/sequence_region
+			#
+			# @param [String] location string in chromosome:start..stop format
+			# @param [String] species of genome
+			# @param [Fasta] Return sequence 
+			def sequence_region(region, species, options = {})
+				return Exodb::Ensembl::REST.get("sequence/region/#{species}/#{region}", {'Content-Type' => 'text/x-fasta', 'coord_system_version' => Exodb::DEFAULTASSEMBLY}.merge(options))
+			end
 		end
 		
 	end

data/lib/exodb/utils/miriamrest.rb

@@ -0,0 +1,23 @@
+# 
+# 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 Miriam
+		
+		module REST
+		
+		
+		end
+		
+	end
+	
+end

data/lib/exodb/version.rb

@@ -11,5 +11,5 @@
 
 
 module Exodb
-	VERSION = "0.1.2"
+	VERSION = "0.1.3"
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: exodb
 version: !ruby/object:Gem::Version
-  version: 0.1.2
+  version: 0.1.3
 platform: ruby
 authors:
 - Natapol Pornputtapong
@@ -79,21 +79,28 @@ files:
 - lib/exodb.rb
 - lib/exodb/addon.rb
 - lib/exodb/addon/string.rb
+- lib/exodb/constant.rb
 - lib/exodb/datamodel.rb
-- lib/exodb/datamodel/locationfield.rb
+- lib/exodb/datamodel/genelocfield.rb
+- lib/exodb/datamodel/generef.rb
+- lib/exodb/datamodel/isoform.rb
 - lib/exodb/datamodel/reference.rb
 - lib/exodb/datamodel/region.rb
 - lib/exodb/datamodel/source.rb
 - lib/exodb/datamodel/variant.rb
+- lib/exodb/datamodel/varlocfield.rb
 - lib/exodb/datamodel/xrefsfield.rb
 - lib/exodb/dbconnection.rb
 - lib/exodb/exception.rb
+- lib/exodb/extra.rb
+- lib/exodb/extra/upload.rb
+- lib/exodb/extra/upload_generef.rb
 - lib/exodb/rositza.rb
 - lib/exodb/rositza/load.rb
 - lib/exodb/usermanage.rb
 - lib/exodb/utils.rb
 - lib/exodb/utils/ensemblrest.rb
-- lib/exodb/utils/upload_generef.rb
+- lib/exodb/utils/miriamrest.rb
 - lib/exodb/utils/upload_var.rb
 - lib/exodb/vcf.rb
 - lib/exodb/version.rb

data/lib/exodb/datamodel/locationfield.rb

@@ -1,116 +0,0 @@
-# 
-# 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 GenomeLocationField
-		
-		extend ActiveSupport::Concern
-		
-		included do
-			field :location,		type: Hash #{chromosome: '', start: x, stop: x}
-			field :strand,			type: String
-
-			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
-		
-		# get the start position of gene rely on the genome
-		#
-		# @return [Integer] start position of gene
-		def begin
-			self[:strand] == '+' ? self[:location]['start'] : self[:location]['stop']
-		end
-		
-		# get the start position of gene rely on the genome
-		#
-		# @return [Integer] start position of gene
-		def end
-			self[:strand] == '+' ? self[:location]['stop'] : self[:location]['start']
-		end
-		
-		# 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