exodb 0.1.0 → 0.1.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: f59876f64775ac85fda8bbb7db9a06e253ab39b8
-  data.tar.gz: 978e13f8048b2cabea0cfe4fc96a9da6e42b97fe
+  metadata.gz: 5d6b52be6bba76e973d002e6dbd4ad4ed82defce
+  data.tar.gz: 35f0cbe4f0d05380ca24710125e5dee20ecfb141
 SHA512:
-  metadata.gz: ceca94da8429c39dee7e1baa9d96f5a88f8860cbf1c185ee2439845d0c93d3a63605bc4d2e6bc7c33c3e1d5c0c424e1d37a1f7557ce8a96baa303ca692a78f55
-  data.tar.gz: 1d20bb30b30b1aea8a612abd255c02f985a2b6fdcc6dd38431f387c2fc3335e56fd5261b38adefb58655d064cb6fef074e11d725af871768269b4bef2b44e9ee
+  metadata.gz: 05822ee2e593e898c62294ab0795cf8769eace304356f9beed84f1b80fd956527a9f5bc74ec4c532ac5b5811ed56e07711d2593dbcd9b9ebb4a4a1d28049b74f
+  data.tar.gz: b2ac6f0484ad7a33315ff3c583f2b1fd25a1bfd70a21f22a087b3c9bbf0e03cb43882a8605e19fc66f81a2f1981b27532744b858756a93b080dfa664ac868ef1

data/README.md

@@ -0,0 +1,15 @@
+Installation
+============
+
+		gem install exodb
+
+Usage in irb or pry
+===================
+		require 'exodb'
+		Exodb.connect("username@servername/databasename")
+
+Example query
+=============
+1.	To query reference gene by cross reference
+
+		Exodb::Generef.where(xrefs: /BRAF/).first

data/exodb.gemspec

@@ -25,6 +25,8 @@ Gem::Specification.new do |s|
     
     s.add_dependency "mongoid", "~> 3.1"
     s.add_dependency "bio", "~> 1.4"
+#    s.add_dependency "bio-samtools", "~> 2.2"
+#    s.add_dependency "bio-vcf", "~> 0.8"
     s.add_dependency "highline", "~> 1.6"
     s.add_dependency "pry", "~> 0.10"
     

data/lib/exodb/datamodel/locationfield.rb

@@ -25,7 +25,7 @@ module Exodb
 		module ClassMethods
 			
 			def cover?(loc_str)
-				dat = loc_str.split(/(:|\.\.)/)
+				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
@@ -35,13 +35,13 @@ module Exodb
 			end
 			
 			def intersect?(loc_str)
-				dat = loc_str.split(/(:|\.\.)/)
+				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(/(:|\.\.)/)
+				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
@@ -100,13 +100,12 @@ module Exodb
 		#
 		# @param [String] gene location in format of chromosome_number:start..stop
 		def parse_location(loc_str)
-			dat = loc_str.split(/(:|\.\.)/)
+			dat = loc_str.split(/(:|\.\.|-)/)
 			if dat[4]
-				self[:location] = {chromosome: dat[0], start: dat[2].to_i, stop: dat[4].to_i}
+				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}
+				self[:location] = {'chromosome' => dat[0], 'start' => dat[2].to_i, 'stop' => dat[2].to_i}
 			end
-			
 		end
 		
 		def location_str

data/lib/exodb/datamodel/source.rb

@@ -40,6 +40,7 @@ module Exodb
 		field :preferred,			type: Boolean
 		field :paired,				type: Boolean
 		field :purity,				type: Float
+		field :labels,				type: Hash
 		
 		default_scope ->{where(preferred: true)}
 		

data/lib/exodb/datamodel/variant.rb

@@ -26,24 +26,30 @@ module Exodb
 		
 		field :oid,					type: String # chromosome:position..alternative:samplename
 		field :reference,			type: String #reference genotype
-		field :alternate,			type: Array #alternate genotype
-		field :quality,				type: String
+		field :alternaten,			type: Array #alternate genotype from tumor cell
+		field :alternatet,			type: Array #alternate genotype from normal cell
 		field :filter,				type: String
-		field :somaticStatus,		type: String #unknown, inherited, somatic
-		field :somaticScore,		type: Float #Somatic score
-		field :inheritantScore,		type: Float #Inheritant score
+		field :passfilter,			type: Boolean #, default: false
+		field :somstatus,			type: String #unknown, inherited, somatic
+		field :somscore,			type: Float #Somatic score 0-1
+		field :inhscore,			type: Float #Inheritant score 0-1
 		#field :fdr,					type: Float #False discovery rate score 
-		field :ctrlread,			type: String
-		field :inhreads,			type: String #reads from normal cell
-		field :reads,				type: String
+		field :pileupt,				type: String #pileup string from tumor cell
+		field :pileupn,				type: String #pileup string from normal cell
+		field :qualt,				type: String #pileup quality from tumor cell
+		field :qualn,				type: String #pileup quality from normal cell
 		field :predicted_damage,	type: Boolean #Temporaly field
-		field :aachange,			type: String #Temporaly field
+		field :temp,				type: Array #Temporaly field
 		
 		belongs_to :cell
 		belongs_to :aacid
 		
 		validates_uniqueness_of :oid, message: "Variant oid of experiment is not unique"
 		
+		def self.from_pileup(pileupline)
+			
+		end
+		
 		# add this variant to original cell sample
 		# 
 		# @param [String] oid
@@ -53,9 +59,9 @@ module Exodb
 			
 			if sample.exists?
 				self.cell = sample.first()
-				#output.puts "#EXODB:INFO This sample is added to #{dataset.first().name}." if _pry_
+				#output.puts "#EXODB:INFO This sample is added to #{dataset.first().name}." if $0 == 'pry'
 			else
-				#output.puts "#EXODB:ERRO Cannot find dataset by #{str}." if _pry_
+				#output.puts "#EXODB:ERRO Cannot find dataset by #{str}." if $0 == 'pry'
 			end
 			
 			self.oid = "#{self.location_str}:#{sample.first().oid}"
@@ -63,6 +69,71 @@ module Exodb
 		end
 		
 		alias_method :add_to_cell, :add_to_sample
+		
+		## overwrite default assignment of pileuplinet
+		## automatically update :reference, :alternatet, and location
+		## 
+		## @param [String] pile-up line from mpileup
+		#def pileuplinet=(pileupline)
+		#	begin
+		#		if pileupline.is_a?(Bio::DB::Pileup)
+		#			pile = pileupline
+		#		else
+		#			pile = Bio::DB::Pileup.new(pileupline.chomp)
+		#		end
+		#		
+		#		self[:reference] = pile.ref_base
+		#		self.parse_location("#{pile.ref_name}:#{pile.pos}..#{pile.pos}")
+		#		self[:alternatet] = pile.genotype_list
+		#		self[:pileuplinet] = pileupline
+		#	rescue
+		#		self[:pileuplinet] = pileupline
+		#	end
+		#end
+		#
+		## overwrite default assignment of pileuplinen
+		## automatically update :alternaten
+		## 
+		## @param [String] pile-up line from mpileup
+		#def pileuplinen=(pileupline)
+		#	begin
+		#		if pileupline.is_a?(Bio::DB::Pileup)
+		#			pile = pileupline
+		#		else
+		#			pile = Bio::DB::Pileup.new(pileupline.chomp)
+		#		end
+		#		
+		#		if self[:reference] == pile.ref_base
+		#			self.parse_location("#{pile.ref_name}:#{pile.pos}..#{pile.pos}")
+		#			self[:alternaten] = pile.genotype_list
+		#			self[:pileuplinen] = pileupline
+		#		end
+		#	rescue
+		#		self[:pileuplinen] = pileupline
+		#	end
+		#end
+		#
+		## overwrite default read of pileuplinet
+		## 
+		## @return [Bio::DB::Pileup] pile-up object of tumor sample
+		#def pileuplinet()
+		#	return Bio::DB::Pileup.new(self[:pileuplinet])
+		#end
+		#
+		## overwrite default read of pileuplinet
+		## 
+		## @return [Bio::DB::Pileup] pile-up object of normal sample
+		#def pileuplinen()
+		#	return Bio::DB::Pileup.new(self[:pileuplinen])
+		#end
+		
+		# apply filter to the variant
+		# the result is kelp in passfilter
+		# 
+		# @param [String] pile-up line from mpileup
+		def apply_filter(filter)
+			self[:filter] = filter
+		end
 	end
 	
 	class SNV < Variant

data/lib/exodb/rositza/load.rb

@@ -0,0 +1,115 @@
+ 
+# 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"
+
+# Script used in Rositza project (Naevi, Spitzoid naevi, Spitzoid melanoma)
+
+module Exodb
+	
+	module Utils
+		
+		module_function
+		
+		def load_variant_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.reference = record["ref nucleotide"].split('/')[0]
+				var.alternate = record["var nucleotide"].split('/').uniq
+				var.somaticStatus = record["Somatic Status"]
+				var.reads = 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.add_to_sample(record["cell"])
+				
+				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"],
+								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],
+								preferred: record["Preferred"] == 'Y' ? true : false,
+								paired: record["merge41final"] =~ /\Apaired\z/i ? true : false},
+								labels: {})
+				
+				sample.add_to_dataset('internal.ds:000001')
+				
+				p sample.save!
+				
+			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)
+			
+			File.open(mergefile).each do |line|
+				record = line.chomp.split("\t")
+				
+				header = record[0..15]
+				
+				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!
+					else
+						snv = Exodb::Variant.new()
+						snv.parse_location("#{header[2]}:#{header[3]}..#{header[3]}")
+						snv.reference = header[10]
+						snv.pileupt = sampledata[6]
+						snv.temp = [] if snv.temp == nil
+						snv.temp.push(header[0..6].join("\t"))
+						snv.add_to_sample(sampledata[0])
+						p snv.save!
+					end
+				end
+			end
+			
+		end
+		
+	end
+end
+
+#Exodb::Utils.load_sample_from_csv('Samples_all.txt')
+#Exodb::Utils.load_variant_from_csv('NovelSNVs_13.txt')
+#Exodb::Utils.load_variant_from_merge('gilead_ann/tumor/exome.UTR')

data/lib/exodb/rositza.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"
+
+# Script used in Rositza project (Naevi, Spitzoid naevi, Spitzoid melanoma)
+
+require 'exodb/rositza/load.rb'
+
+module Exodb
+	
+	module Utils
+		
+		module_function
+		
+	end
+end

data/lib/exodb/utils/ensemblrest.rb

@@ -0,0 +1,39 @@
+# 
+# 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 Ensembl
+		
+		module REST
+			@@url = URI.parse('http://rest.ensembl.org')
+			@@http = Net::HTTP.new(@@url.host, @@url.port)
+			
+			module_function
+			
+			def get(getpart, options)
+				request = Net::HTTP::Get.new(get_path, {'Content-Type' => 'application/json'}.merge(options))
+				response = http.request(request)
+				if response.code != "200"
+					riase InvalidResponse, "Invalid response: #{response.code}"
+				else
+					return JSON.parse(response.body)
+				end
+			end
+			
+			def fetch_variant(region, allele, species, options = {})
+				return Exodb::Ensembl::REST.get("vep/#{species}/region/#{region}/allele", options)
+			end
+			
+		end
+		
+	end
+end

data/lib/exodb/utils/upload_generef.rb

@@ -150,7 +150,7 @@ module Exodb
 						
 					end
 					
-					p gene.save!
+					puts "STATUS: #{gene.save! ? "SUCCESS" : "FAIL"}: Deposit Gene reference #{gene.xrefs[0]}"
 					
 				end
 				

data/lib/exodb/utils/upload_var.rb

@@ -9,7 +9,6 @@
 
 # raise "Please, use ruby 1.9.0 or later." if RUBY_VERSION < "1.9.0"
 
-require 'csv'
 
 module Exodb
 	
@@ -17,54 +16,15 @@ module Exodb
 		
 		module_function
 		
-		def load_variant_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.reference = record["ref nucleotide"].split('/')[0]
-				var.alternate = record["var nucleotide"].split('/').uniq
-				var.somaticStatus = record["Somatic Status"]
-				var.reads = 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.add_to_sample(record["cell"])
-				
-				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"],
-								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],
-								preferred: record["Preferred"] == 'Y' ? true : false,
-								paired: record["merge41final"] =~ /\Apaired\z/i ? true : false})
-				
-				sample.add_to_dataset('internal.ds:000001')
-				
-				p sample.save!
-				
-			end
-		end
-		
-		def load_variant_from_ann(annfile)
-			
-			File.open(annfile).each do |line|
-				record = line.chomp.split("\t")
-				p record
-			end
-			
-		end
+		#def pop_var_from_sam(bamfile, templatefasta, samplename, normalsample = false, additioninfo = {}, mpileupoptions = {})
+		#	
+		#	bam = Bio::DB::Sam.new(bam: bamfile, fasta: templatefasta)
+		#	bam.samtools
+		#end
 		
 	end
 	
 end
 
-#Exodb::Utils.load_sample_from_csv('Samples_all.txt')
-#Exodb::Utils.load_variant_from_csv('NovelSNVs_13.txt')
+
 

data/lib/exodb/utils.rb

@@ -13,6 +13,10 @@ require 'exodb/utils/upload_generef.rb'
 require 'exodb/utils/upload_var.rb'
 require 'exodb/utils/ensemblrest.rb'
 
+
+#load script specific to rosiza project
+require 'exodb/rositza.rb'
+
 module Exodb
 	
 	module Utils

data/lib/exodb/version.rb

@@ -11,5 +11,5 @@
 
 
 module Exodb
-	VERSION = "0.1.0"
+	VERSION = "0.1.1"
 end

data/lib/exodb.rb

@@ -20,6 +20,7 @@ require 'open-uri'
 require 'net/http'
 require 'uri'
 require 'json'
+require 'csv'
 
 #External library
 #require 'bio-vcf'
@@ -27,6 +28,7 @@ require 'highline/import'
 require 'mongoid'
 require 'bio'
 require 'pry'
+require 'bio-samtools'
 
 I18n.enforce_available_locales = false
 

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: exodb
 version: !ruby/object:Gem::Version
-  version: 0.1.0
+  version: 0.1.1
 platform: ruby
 authors:
 - Natapol Pornputtapong
@@ -72,6 +72,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- README.md
 - contributors.txt
 - exodb.gemspec
 - genome/process_genome_seq.rb
@@ -87,8 +88,11 @@ files:
 - lib/exodb/datamodel/xrefsfield.rb
 - lib/exodb/dbconnection.rb
 - lib/exodb/exception.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/upload_var.rb
 - lib/exodb/vcf.rb