snp-search 2.10.8 → 2.11.0

data/README.rdoc

@@ -106,13 +106,13 @@ Alternatively, you may download a SQL tool to view your database (e.g. SQLite so
 == Contact
 
 If you have any comments, questions or suggestions, please email
-  ali.al-shahib@hpa.org.uk
+  ali.al-shahib@phe.gov.uk
 or
-  anthony.underwood@hpa.org.uk
+  anthony.underwood@phe.gov.uk
 
 Have fun snp-searching!
 
 == Copyright
 
 Copyright (c) 2012 Ali Al-Shahib. See LICENSE.txt for
-further details.
+further details.

data/VERSION

@@ -1 +1 @@
-2.10.8
+2.11.0

data/bin/snp-search

@@ -3,6 +3,8 @@ require 'snp_db_connection'
 require 'snp_db_models'
 require 'snp_db_schema'
 require 'output_information_methods'
+require 'create_methods'
+require 'filter_ignore_snps_methods.rb'
 require 'activerecord-import'
 require 'slop'
 
@@ -24,7 +26,7 @@ opts = Slop.parse do
   on :r, :reference_file=, 'Reference genome file, in gbk or embl file format, Required', true
   on :v, :vcf_file=, 'variant call format (vcf) file, Required', true
   on :d, :name_of_database=, 'Name of database, Required'
-  on :A, :cuttoff_ad=, 'AD ratio cutoff (default 0.9)', :as => :int, :default => 0.9
+  on :A, :cutoff_ad=, 'AD ratio cutoff (default 0.9)', :as => :int, :default => 0.9
 
   separator ''
  
@@ -33,8 +35,8 @@ opts = Slop.parse do
   on :f, :all_or_filtered_snps, 'ignore SNPs from specified features in the database (if you do not want to ignore any SNPs, just use this option with -F/T -o)'
   on :F, :fasta, 'output fasta file format (default)'
   on :T, :tabular, 'output tabular file format'
-  on :c, :cuttoff_snp_qual=, 'SNP quality cutoff, (default = 90)', :as => :int, :default => 90
-  on :g, :cuttoff_genotype=, 'Genotype quality cutoff (default = 30)', :as => :int,  :default => 30
+  on :c, :cutoff_snp_qual=, 'SNP quality cutoff, (default = 90)', :as => :int, :default => 90
+  on :g, :cutoff_genotype=, 'Genotype quality cutoff (default = 30)', :as => :int,  :default => 30
   on :R, :remove_non_informative_snps, 'Only output informative SNPs.'
   on :e, :ignore_snps_in_range=, 'A list of position ranges to ignore e.g 10..500,2000..2500.'
   on :a, :ignore_strains=, 'A list of strains to ignore (seperate by comma e.g. S1,S4,S8 ).'
@@ -47,8 +49,8 @@ opts = Slop.parse do
   separator '-output -unique_snps -d db.sqlite3 -s strains.txt -o unique_snps.txt [options]'
   separator 'e.g. snp-search -O -u -d ecoli.sqlite3 -s strains_list_for_unique_snps.txt -o ecoli_unique_snps_strains.txt'
   on :u, :unique_snps, 'Query for unique snps in the database'  
-  on :c, :cuttoff_snp_qual=, 'SNP quality cutoff, (default = 90)', :as => :int, :default => 90
-  on :g, :cuttoff_genotype=, 'Genotype quality cutoff (default = 30)', :as => :int,  :default => 30
+  on :c, :cutoff_snp_qual=, 'SNP quality cutoff, (default = 90)', :as => :int, :default => 90
+  on :g, :cutoff_genotype=, 'Genotype quality cutoff (default = 30)', :as => :int,  :default => 30
   on :s, :strain=, 'The strains/samples you like to query (only used with -unique_snps flag)'
   on :o, :out=, 'Name of output file, Required'
 
@@ -57,8 +59,8 @@ opts = Slop.parse do
   separator '-output -info -d db.sqlite3 -o info.txt [options]'
   separator ''
   on :i, :info, 'Output various information about SNPs'
-  on :c, :cuttoff_snp_qual=, 'SNP quality cutoff, (default = 90)', :as => :int, :default => 90
-  on :g, :cuttoff_genotype=, 'Genotype quality cutoff (default = 30)', :as => :int,  :default => 30
+  on :c, :cutoff_snp_qual=, 'SNP quality cutoff, (default = 90)', :as => :int, :default => 90
+  on :g, :cutoff_genotype=, 'Genotype quality cutoff (default = 30)', :as => :int,  :default => 30
   on :o, :out=, 'Name of output file, Required'
 end
 
@@ -68,7 +70,7 @@ end
 if opts[:create] 
 
   # raise "Please provide a database file name" if opts[:reference_file].empty?
-  # puts opts[:cuttoff_snp_qual].to_i
+  # puts opts[:cutoff_snp_qual].to_i
   
     error_msg = ""
 
@@ -122,7 +124,7 @@ if opts[:create]
 
   #The populate_snps_alleles_genotypes method populates the snps, alleles and genotypes.  It uses the vcf file, and if specified, the SNP quality cutoff and genotype quality cutoff
 
-  populate_snps_alleles_genotypes(opts[:vcf_file], opts[:cuttoff_ad])
+  populate_snps_alleles_genotypes(opts[:vcf_file], opts[:cutoff_ad])
 
 ###########################################################
 
@@ -143,6 +145,7 @@ elsif opts[:output]
 
     error_msg = ""
 
+    
     error_msg += "-d: \t Name of your database\n" unless opts[:name_of_database]
     error_msg += "-o: \t name of your output file\n" unless opts[:out]
     error_msg += "-F: \t Fasta output OR\n-T: \t Tabular output" unless opts[:fasta] || opts[:tabular]
@@ -152,8 +155,8 @@ elsif opts[:output]
     error_msg_optional += "-I,\t --ignore_snps_on_annotation: The name of the feature(s) to ignore.  Features should be seperated by comma (e.g. phages,inserstion,transposons)\n" unless opts[:ignore_snps_on_annotation]
     error_msg_optional += "-a,\t --ignore_strains: A list of strains to ignore\n" unless  opts[:ignore_strains]
     error_msg_optional += "-e,\t --ignore_snps_in_range: A list of position ranges to ignore e.g 10..500,2000..2500\n" unless  opts[:ignore_snps_in_range]
-    error_msg_optional += "-c,\t --cuttoff_snp_qual: cuttoff for SNP Quality\n"  unless  opts[:cuttoff_snp_qual]
-    error_msg_optional += "-g,\t --cuttoff_genotype: cuttoff for Genotype Quality\n"  unless  opts[:cuttoff_genotype]
+    error_msg_optional += "-c,\t --cutoff_snp_qual: cutoff for SNP Quality\n"  unless  opts[:cutoff_snp_qual]
+    error_msg_optional += "-g,\t --cutoff_genotype: cutoff for Genotype Quality\n"  unless  opts[:cutoff_genotype]
     error_msg_optional += "-R,\t --remove_non_informative_snps: Only output informative SNPs\n"  unless  opts[:remove_non_informative_snps]
     error_msg_optional += "-t,\t --tree: Construct tree from output\n" unless  opts[:tree]
 
@@ -163,8 +166,8 @@ elsif opts[:output]
       puts "Optional fields:"
       puts error_msg_optional
       # Added this here as it wont appear here in error_msg_optional as its set as default.
-      puts "-c,\t --cuttoff_snp_qual: cuttoff for SNP Quality (default 90)\n"
-      puts "-g,\t --cuttoff_genotype: cuttoff for Genotype Quality (default 30)\n"
+      puts "-c,\t --cutoff_snp_qual: cutoff for SNP Quality (default 90)\n"
+      puts "-g,\t --cutoff_genotype: cutoff for Genotype Quality (default 30)\n"
       # puts opts.help unless opts.empty?
       exit
     end
@@ -173,7 +176,7 @@ elsif opts[:output]
 
     establish_connection(opts[:name_of_database])
 
-    get_snps(opts[:out], opts[:ignore_snps_on_annotation], opts[:ignore_snps_in_range], opts[:ignore_strains], opts[:remove_non_informative_snps], opts[:fasta], opts[:tabular], opts[:cuttoff_genotype], opts[:cuttoff_snp_qual], opts[:tree], opts[:fasttree_path])
+    get_snps(opts[:out], opts[:ignore_snps_on_annotation], opts[:ignore_snps_in_range], opts[:ignore_strains], opts[:remove_non_informative_snps], opts[:fasta], opts[:tabular], opts[:cutoff_genotype], opts[:cutoff_snp_qual], opts[:tree], opts[:fasttree_path])
   end
 
 ####################################################################################################
@@ -191,8 +194,8 @@ elsif opts[:output]
       puts error_msg
       puts "Optional fields:"
       # Added this here as it wont appear here in error_msg_optional as its set as default.
-      puts "-c,\t --cuttoff_snp_qual: cuttoff for SNP Quality (default 90)\n"
-      puts "-g,\t --cuttoff_genotype: cuttoff for Genotype Quality (default 30)\n"
+      puts "-c,\t --cutoff_snp_qual: cutoff for SNP Quality (default 90)\n"
+      puts "-g,\t --cutoff_genotype: cutoff for Genotype Quality (default 30)\n"
       # puts opts.help unless opts.empty?
       exit
     end
@@ -207,7 +210,7 @@ elsif opts[:output]
         strains << line.chop
       end
     # find_unique_snps defined in bin/snp-search.rb 
-    find_unqiue_snps(strains, opts[:out], opts[:cuttoff_genotype], opts[:cuttoff_snp_qual])
+    find_unqiue_snps(strains, opts[:out], opts[:cutoff_genotype], opts[:cutoff_snp_qual])
   end
   
 ##############################################################
@@ -223,8 +226,8 @@ elsif opts[:output]
       puts error_msg
       puts "Optional fields:"
       # Added this here as it wont appear here in error_msg_optional as its set as default.
-      puts "-c,\t --cuttoff_snp_qual: cuttoff for SNP Quality (default 90)\n"
-      puts "-g,\t --cuttoff_genotype: cuttoff for Genotype Quality (default 30)\n"
+      puts "-c,\t --cutoff_snp_qual: cutoff for SNP Quality (default 90)\n"
+      puts "-g,\t --cutoff_genotype: cutoff for Genotype Quality (default 30)\n"
       # puts opts.help unless opts.empty?
       exit
     end
@@ -234,7 +237,7 @@ elsif opts[:output]
     establish_connection(opts[:name_of_database])
 
     #information defined in bin/snp-search.rb
-    information(opts[:out], opts[:cuttoff_genotype], opts[:cuttoff_snp_qual])
+    information(opts[:out], opts[:cutoff_genotype], opts[:cutoff_snp_qual])
     
   end
   

data/lib/create_methods.rb

@@ -50,9 +50,10 @@ def populate_features_and_annotations(sequence_file)
 end
 
 #This method populates the rest of the information, i.e. SNP information, Alleles and Genotypes.
-def populate_snps_alleles_genotypes(vcf_file, cuttoff_ad)
+def populate_snps_alleles_genotypes(vcf_file, cutoff_ad)
 
   puts "Adding SNPs........"
+  
   # open vcf file and parse each line
   File.open(vcf_file) do |f|
     # header names
@@ -60,20 +61,23 @@ def populate_snps_alleles_genotypes(vcf_file, cuttoff_ad)
       if  line =~ /CHROM/
         line.chomp!
         column_headings = line.split("\t")
-        strain_names = column_headings[9..-1]
-        strain_names.map!{|name| name.sub(/\..*/, '')}
+        potential_strain_names = column_headings[9..-1]
+        potential_strain_names.map!{|name| name.sub(/\..*/, '')}
+        # strain_names = column_headings[9..-1]
+        # strain_names.map!{|name| name.sub(/\..*/, '')}
+        strains = Array.new
 
-        strain_names.each do |str|
-          ss = Strain.new
-          ss.name = str
-          ss.save
-        end
+        # strain_names.each do |str|
+        #   ss = Strain.new
+        #   ss.name = str
+        #   ss.save
+        # end
 
-        strains = Array.new
-        strain_names.each do |strain_name|
-          strain = Strain.find_by_name(strain_name) # equivalent to Strain.find.where("strains.name=?", strain_name).first
-          strains << strain
-        end
+        # strains = Array.new
+        # strain_names.each do |strain_name|
+        #   strain = Strain.find_by_name(strain_name) # equivalent to Strain.find.where("strains.name=?", strain_name).first
+        #   strains << strain
+        # end
 
         good_snps = 0
         # start parsing snps
@@ -86,28 +90,53 @@ def populate_snps_alleles_genotypes(vcf_file, cuttoff_ad)
           ref_base = details[3]
           snp_bases = details[4].split(",")
           snp_qual = details [5]
+          number_of_colons_in_format = details[8].count ":"
           format = details[8].split(":")
+          
           gt_array_position = format.index("GT")
           gq_array_position = format.index("GQ")
           ad_array_position = format.index("AD")
           # dp = format.index("DP")
+          # columns_after_format = details[9..-1]
+          # samples = columns_after_format.select{|column_after_format| column_after_format.count(":")  == number_of_colons_in_format}
+          # puts samples
           samples = details[9..-1]
+          if strains.empty?
+            samples.zip(potential_strain_names).each do |column_after_format, potential_strain_name|
+              if column_after_format.count(":")  == number_of_colons_in_format
+                ss = Strain.new
+                ss.name = potential_strain_name
+                ss.save
+                strains << ss
+              end
+            end
+          end
 
           gts = []
           gqs = []
           ad_ratios = []
-
           
           next if samples.any?{|sample| sample =~ /\.\/\./}  # no coverage in at least one sample
+
           samples.map do |sample|
             format_values = sample.split(":") # output (e.g.): ["0/0 ", "0,255,209", "99"]
-            gt = format_values[gt_array_position] # e.g.          
-            gt = gt.split("/")
-            next if gt.size > 1 && (gt.first != gt.last) # if its 0/1, 1/2 etc then ignore
-            next if gt.first == "." # no coverage
-            gt = gt.first.to_i
+            if gt_array_position
+              gt = format_values[gt_array_position] # e.g.          
+              gt = gt.split("/")
+              next if gt.size > 1 && (gt.first != gt.last) # if its 0/1, 1/2 etc then ignore
+              next if gt.first == "." # no coverage
+              gt = gt.first.to_i
+            else
+              puts "GT field in the FORMAT section of the vcf file is missing....snp-search requires this field to assess the SNP quality.....sorry aborting"
+              exit
+            end
 
-            gq = format_values[gq_array_position].to_f
+            if gq_array_position
+              gq = format_values[gq_array_position].to_f
+            else
+              puts "GQ field in the FORMAT section of the vcf file is missing....snp-search requires this field to assess the SNP quality.....sorry aborting"
+              exit
+            end
 
             if ad_array_position
               # If there is AD in vcf.  Typically AD is Allele specific depth. i.e. if ref is 'A' and alt is 'G' and AD is '6,9' you got 6 A reads and 9 G reads.
@@ -117,12 +146,12 @@ def populate_snps_alleles_genotypes(vcf_file, cuttoff_ad)
               sum_of_ad = ad.inject{|sum,x| sum + x }
               ad_ratios << ad[gt]/sum_of_ad.to_f
             end
-
+            
             gqs << gq
             gts << gt
           end
-
-          next if ad_ratios.any?{|ad_ratio| ad_ratio < cuttoff_ad.to_i} # exclude if any samples have a call ratio of less than a cuttoff set by user
+          
+          next if ad_ratios.any?{|ad_ratio| ad_ratio < cutoff_ad.to_i} # exclude if any samples have a call ratio of less than a cutoff set by user
           if gts.size == samples.size # if some gts have been rejected due to heterozygote or no coverage
             good_snps +=1
             
@@ -143,6 +172,7 @@ def populate_snps_alleles_genotypes(vcf_file, cuttoff_ad)
               s.reference_allele = ref_allele
               s.save
 
+              
               snp_alleles = Array.new
               gts.uniq.select{|gt| gt > 0}.each do |gt|
                 # create snp allele

data/lib/filter_ignore_snps_methods.rb

@@ -4,7 +4,7 @@
 
 require 'output_information_methods'
 
-def get_snps(out, ignore_snps_on_annotation, ignore_snps_in_range, ignore_strains, remove_non_informative_snps, fasta_output, tabular_output, cuttoff_genotype, cuttoff_snp, tree, fasttree_path)
+def get_snps(out, ignore_snps_on_annotation, ignore_snps_in_range, ignore_strains, remove_non_informative_snps, fasta_output, tabular_output, cutoff_genotype, cutoff_snp, tree, fasttree_path)
 
   strains = Strain.all
 
@@ -72,17 +72,18 @@ def get_snps(out, ignore_snps_on_annotation, ignore_snps_in_range, ignore_strain
       genotypes = snp.alleles.collect{|allele| allele.genotypes}.flatten
 
       snp_qual = Snp.find_by_sql("select qual from snps where snps.id = #{snp.id}")
-      # ignore snp if the snp qual is less than cuttoff.
-      next if snp_qual.any?{|snps_quality| snps_quality.qual < cuttoff_snp.to_i}
+      # ignore snp if the snp qual is less than cutoff.
+      next if snp_qual.any?{|snps_quality| snps_quality.qual < cutoff_snp.to_i}
       
       next if alleles.any?{|allele| allele.base.length > 1} # indel
-      next unless genotypes.all?{|genotype| genotype.geno_qual >= cuttoff_genotype} # all geno quals > cutoff
+      next unless genotypes.all?{|genotype| genotype.geno_qual >= cutoff_genotype.to_f} # all geno quals > cutoff
       # puts "#{i} SNPs processed so far" if i % 100 == 0
       strain_alleles = Hash.new
       strains.each do |strain|
         strain_genotype = genotypes.select{|genotype| genotype.strain_id == strain.id}.first
+        # next if strain_genotype == nil
+        puts strain_genotype.inspect
         strain_allele = alleles.select{|allele| allele.id == strain_genotype.allele_id}.first
-
         strain_alleles[strain.name] = strain_allele.base
      end
 
@@ -101,7 +102,7 @@ def get_snps(out, ignore_snps_on_annotation, ignore_snps_in_range, ignore_strain
 
   # If user has specified a tabular output
   if tabular_output
-    output_information_methods(snps_array, output, cuttoff_genotype, cuttoff_snp, true)
+    output_information_methods(snps_array, output, cutoff_genotype, cutoff_snp, true)
   # If user has specified a fasta output
   elsif fasta_output
     # generate FASTA file

data/lib/output_information_methods.rb

@@ -13,21 +13,21 @@ def output_information_methods(snps, outfile, cuttoff_genotype, cuttoff_snp, inf
   total_number_of_syn_snps = 0
   total_number_of_non_syn_snps = 0
   total_number_of_pseudo = 0
-  snps.each do |snp|
 
+  snps.each do |snp|
     ActiveRecord::Base.transaction do
       snp.alleles.each do |allele|
         next if snp.alleles.any?{|allele| allele.base.length > 1} # indel
         if allele.id != snp.reference_allele_id
-          
+
           # get annotation (if there is any) for each SNP
           features = Feature.joins(:snps).where("snps.id = ?", snp.id)
           
           # get snp quality for each snp
           snp_qual = Snp.find_by_sql("select qual from snps where snps.id = #{snp.id}")
-          next if snp_qual.any?{|snps_quality| snps_quality.qual < cuttoff_snp.to_i}
           # ignore snp if the snp qual is less than cuttoff.
-          # next if snp.snp_qual < cuttoff_snp.to_i
+          next if snp_qual.any?{|snps_quality| snps_quality.qual < cuttoff_snp.to_i}
+          
 
           # get all genotype qualities for each snp.
           gqs = Genotype.find_by_sql("select geno_qual from genotypes inner join alleles on alleles.id = genotypes.allele_id inner join snps on snps.id = alleles.snp_id where snps.id = #{snp.id}")
@@ -37,13 +37,12 @@ def output_information_methods(snps, outfile, cuttoff_genotype, cuttoff_snp, inf
           ref_base = Bio::Sequence.auto(Allele.find(snp.reference_allele_id).base)
           snp_base = Bio::Sequence.auto(allele.base)
           # count snps now: after you have selected the snps with gqs and snp_qual greater than the threshold.
-          snps_counter += 1
+          snps_counter += 1 
           # If the feature is empty then just output basic information about the snp.
 
           if features.empty?
             outfile.puts "#{snp.ref_pos}\t#{features.map{|feature| feature.strand == 1} ? "#{ref_base.upcase}" : "#{ref_base.reverse_complement.upcase}"}\t#{features.map{|feature| feature.strand == 1} ? "#{snp_base.upcase}" : "#{snp_base.reverse_complement.upcase}"}"
-          
-          else  
+          else 
             features.each do |feature|
               if feature.name == "CDS"
 
@@ -91,10 +90,14 @@ def output_information_methods(snps, outfile, cuttoff_genotype, cuttoff_snp, inf
                   non_small = ["I","L","M","F","Y","W","H","K","R","E","Q"]
 
                   # Get alleles for each strain
-                  alleles_array = []
+                  bases_from_alleles = []
                     strains.each do |strain|
+                      
                       allele_for_strains = Allele.joins(:genotypes => :strain).where("strains.id = ? AND alleles.snp_id = ?", strain.id, snp.id).first
-                      alleles_array << allele_for_strains.base
+                      # allele_for_strains =  Allele.find_by_sql("select * from alleles inner join genotypes on genotypes.allele_id = alleles.id inner join strains on strains.id = genotypes.strain_id where strains.id = #{strain.id} and alleles.snp_id = #{snp.id}")
+                      puts allele_for_strains.inspect
+                      # next if bases_from_alleles.empty?
+                      bases_from_alleles << allele_for_strains.base
                     end
 
                   # If no difference between the amino acids then its synonymous SNP, if different then its non-synonymous.
@@ -102,9 +105,9 @@ def output_information_methods(snps, outfile, cuttoff_genotype, cuttoff_snp, inf
                     total_number_of_syn_snps +=1
                     if mutated_seq_translated_clean =~ /\*/
                       total_number_of_pseudo +=1
-                      outfile.puts "#{snp.ref_pos}\t#{features.map{|feature| feature.strand == 1} ? "#{ref_base.upcase}" : "#{ref_base.reverse_complement.upcase}"}\t#{features.map{|feature| feature.strand == 1} ? "#{snp_base.upcase}" : "#{snp_base.reverse_complement.upcase}"}\tsynonymous\t#{annotation.value}\tYes\tN/A\tN/A\tN/A\tN/A\tN/A\t#{alleles_array.join("\t") if info}"
+                      outfile.puts "#{snp.ref_pos}\t#{features.map{|feature| feature.strand == 1} ? "#{ref_base.upcase}" : "#{ref_base.reverse_complement.upcase}"}\t#{features.map{|feature| feature.strand == 1} ? "#{snp_base.upcase}" : "#{snp_base.reverse_complement.upcase}"}\tsynonymous\t#{annotation.value}\tYes\tN/A\tN/A\tN/A\tN/A\tN/A\t#{bases_from_alleles.join("\t") if info}"
                     else
-                      outfile.puts "#{snp.ref_pos}\t#{features.map{|feature| feature.strand == 1} ? "#{ref_base.upcase}" : "#{ref_base.reverse_complement.upcase}"}\t#{features.map{|feature| feature.strand == 1} ? "#{snp_base.upcase}" : "#{snp_base.reverse_complement.upcase}"}\tsynonymous\t#{annotation.value}\tNo\tN/A\tN/A\tN/A\tN/A\tN/A\t#{alleles_array.join("\t") if info}"
+                      outfile.puts "#{snp.ref_pos}\t#{features.map{|feature| feature.strand == 1} ? "#{ref_base.upcase}" : "#{ref_base.reverse_complement.upcase}"}\t#{features.map{|feature| feature.strand == 1} ? "#{snp_base.upcase}" : "#{snp_base.reverse_complement.upcase}"}\tsynonymous\t#{annotation.value}\tNo\tN/A\tN/A\tN/A\tN/A\tN/A\t#{bases_from_alleles.join("\t") if info}"
                     end
                   else
                     total_number_of_non_syn_snps +=1
@@ -112,21 +115,21 @@ def output_information_methods(snps, outfile, cuttoff_genotype, cuttoff_snp, inf
 
                     if mutated_seq_translated_clean =~ /\*/
                       total_number_of_pseudo +=1
-                      outfile.puts "#{snp.ref_pos}\t#{features.map{|feature| feature.strand == 1} ? "#{ref_base.upcase}" : "#{ref_base.reverse_complement.upcase}"}\t#{features.map{|feature| feature.strand == 1} ? "#{snp_base.upcase}" : "#{snp_base.reverse_complement.upcase}"}\tnon-synonymous\t#{annotation.value}\tYes\t#{diffs[0][0].element}\t#{diffs[0][1].element}\t#{'Yes' if (hydrophobic.include? diffs[0][0].element) == (non_hydrophobic.include? diffs[0][1].element)}#{'No' if (hydrophobic.include? diffs[0][0].element) != (non_hydrophobic.include? diffs[0][1].element)}\t#{'Yes' if (polar.include? diffs[0][0].element) == (non_polar.include? diffs[0][1].element)}#{'No' if (polar.include? diffs[0][0].element) != (non_polar.include? diffs[0][1].element)}\t#{'Yes' if (small.include? diffs[0][0].element) == (non_small.include? diffs[0][1].element)}#{'No' if (small.include? diffs[0][0].element) != (non_small.include? diffs[0][1].element)}\t#{alleles_array.join("\t") if info}"
+                      outfile.puts "#{snp.ref_pos}\t#{features.map{|feature| feature.strand == 1} ? "#{ref_base.upcase}" : "#{ref_base.reverse_complement.upcase}"}\t#{features.map{|feature| feature.strand == 1} ? "#{snp_base.upcase}" : "#{snp_base.reverse_complement.upcase}"}\tnon-synonymous\t#{annotation.value}\tYes\t#{diffs[0][0].element}\t#{diffs[0][1].element}\t#{'Yes' if (hydrophobic.include? diffs[0][0].element) == (non_hydrophobic.include? diffs[0][1].element)}#{'No' if (hydrophobic.include? diffs[0][0].element) != (non_hydrophobic.include? diffs[0][1].element)}\t#{'Yes' if (polar.include? diffs[0][0].element) == (non_polar.include? diffs[0][1].element)}#{'No' if (polar.include? diffs[0][0].element) != (non_polar.include? diffs[0][1].element)}\t#{'Yes' if (small.include? diffs[0][0].element) == (non_small.include? diffs[0][1].element)}#{'No' if (small.include? diffs[0][0].element) != (non_small.include? diffs[0][1].element)}\t#{bases_from_alleles.join("\t") if info}"
                     else
-                      outfile.puts "#{snp.ref_pos-1}\t#{features.map{|feature| feature.strand == 1} ? "#{ref_base.upcase}" : "#{ref_base.reverse_complement.upcase}"}\t#{features.map{|feature| feature.strand == 1} ? "#{snp_base.upcase}" : "#{snp_base.reverse_complement.upcase}"}\tnon-synonymous\t#{annotation.value}\tNo\t#{diffs[0][0].element}\t#{diffs[0][1].element}\t#{'Yes' if (hydrophobic.include? diffs[0][0].element) == (non_hydrophobic.include? diffs[0][1].element)}#{'No' if (hydrophobic.include? diffs[0][0].element) != (non_hydrophobic.include? diffs[0][1].element)}\t#{'Yes' if (polar.include? diffs[0][0].element) == (non_polar.include? diffs[0][1].element)}#{'No' if (polar.include? diffs[0][0].element) != (non_polar.include? diffs[0][1].element)}\t#{'Yes' if (small.include? diffs[0][0].element) == (non_small.include? diffs[0][1].element)}#{'No' if (small.include? diffs[0][0].element) != (non_small.include? diffs[0][1].element)}\t#{alleles_array.join("\t") if info}"
+                      outfile.puts "#{snp.ref_pos-1}\t#{features.map{|feature| feature.strand == 1} ? "#{ref_base.upcase}" : "#{ref_base.reverse_complement.upcase}"}\t#{features.map{|feature| feature.strand == 1} ? "#{snp_base.upcase}" : "#{snp_base.reverse_complement.upcase}"}\tnon-synonymous\t#{annotation.value}\tNo\t#{diffs[0][0].element}\t#{diffs[0][1].element}\t#{'Yes' if (hydrophobic.include? diffs[0][0].element) == (non_hydrophobic.include? diffs[0][1].element)}#{'No' if (hydrophobic.include? diffs[0][0].element) != (non_hydrophobic.include? diffs[0][1].element)}\t#{'Yes' if (polar.include? diffs[0][0].element) == (non_polar.include? diffs[0][1].element)}#{'No' if (polar.include? diffs[0][0].element) != (non_polar.include? diffs[0][1].element)}\t#{'Yes' if (small.include? diffs[0][0].element) == (non_small.include? diffs[0][1].element)}#{'No' if (small.include? diffs[0][0].element) != (non_small.include? diffs[0][1].element)}\t#{bases_from_alleles.join("\t") if info}"
                     end
                   end
                 end
               end
             end
           end
+        puts "Total SNPs added so far: #{snps_counter}" if snps_counter % 100 == 0 
         end
       end
-      puts "Total SNPs added so far: #{snps_counter}" if snps_counter % 100 == 0 
     end
   end
-  puts "Total number of snps: #{snps_counter}"
+  puts "Total number of snps: #{snps_counter} with Genotype quality cutoff at #{cuttoff_genotype} and SNP quality cutoff at #{cuttoff_snp}"
   puts "Total number of snps in CDS region: #{cds_snps_counter}"
   puts "Total number of synonymous SNPs: #{total_number_of_syn_snps}"
   puts "Total number of non-synonymous SNPs: #{total_number_of_non_syn_snps}"

data/lib/snp-search.rb

@@ -7,7 +7,7 @@ require 'create_methods'
 require 'filter_ignore_snps_methods'
 require 'output_information_methods'
 
-def find_unqiue_snps(strain_names, out, cuttoff_genotype, cuttoff_snp)
+def find_unqiue_snps(strain_names, out, cutoff_genotype, cutoff_snp)
 
   *strain_names = strain_names
 
@@ -15,24 +15,25 @@ def find_unqiue_snps(strain_names, out, cuttoff_genotype, cuttoff_snp)
 
   outfile = File.open(out, "w")
 
-   snps = Snp.find_by_sql("SELECT snps.* from snps INNER JOIN alleles ON alleles.snp_id = snps.id INNER JOIN genotypes ON alleles.id = genotypes.allele_id INNER JOIN strains ON strains.id = genotypes.strain_id WHERE (#{where_statement}) AND alleles.id <> snps.reference_allele_id AND genotypes.geno_qual >= #{cuttoff_genotype} AND snps.qual >= #{cuttoff_snp} AND (SELECT COUNT(*) from snps AS s INNER JOIN alleles ON alleles.snp_id = snps.id INNER JOIN genotypes ON alleles.id = genotypes.allele_id WHERE alleles.id <> snps.reference_allele_id and s.id = snps.id) = #{strain_names.size} GROUP BY snps.id HAVING COUNT(*) = #{strain_names.size}")
+   snps = Snp.find_by_sql("SELECT snps.* from snps INNER JOIN alleles ON alleles.snp_id = snps.id INNER JOIN genotypes ON alleles.id = genotypes.allele_id INNER JOIN strains ON strains.id = genotypes.strain_id WHERE (#{where_statement}) AND alleles.id <> snps.reference_allele_id AND genotypes.geno_qual >= #{cutoff_genotype} AND snps.qual >= #{cutoff_snp} AND (SELECT COUNT(*) from snps AS s INNER JOIN alleles ON alleles.snp_id = snps.id INNER JOIN genotypes ON alleles.id = genotypes.allele_id WHERE alleles.id <> snps.reference_allele_id and s.id = snps.id) = #{strain_names.size} GROUP BY snps.id HAVING COUNT(*) = #{strain_names.size}")
    # puts "The number of unique snps are #{snps.size}"
 
-   output_information_methods(snps, outfile, cuttoff_genotype, cuttoff_snp, false)
+   output_information_methods(snps, outfile, cutoff_genotype, cutoff_snp, false)
 end
 
 
-def information(out, cuttoff_genotype, cuttoff_snp)
+def information(out, cutoff_genotype, cutoff_snp)
 
   puts "outputting SNP info....."
   
   strains = Strain.all
 
-  snps = Snp.find_by_sql("SELECT distinct snps.* from snps INNER JOIN alleles ON alleles.snp_id = snps.id INNER JOIN genotypes ON alleles.id = genotypes.allele_id INNER JOIN strains ON strains.id = genotypes.strain_id where alleles.id <> snps.reference_allele_id")
+  # snps = Snp.find_by_sql("SELECT distinct snps.* from snps INNER JOIN alleles ON alleles.snp_id = snps.id INNER JOIN genotypes ON alleles.id = genotypes.allele_id INNER JOIN strains ON strains.id = genotypes.strain_id where alleles.id <> snps.reference_allele_id")
 
+  snps = Snp.find_by_sql("SELECT distinct snps.* from snps INNER JOIN alleles ON alleles.snp_id = snps.id")
   outfile = File.open(out, "w")
 
-  output_information_methods(snps, outfile, cuttoff_genotype, cuttoff_snp, true)
+  output_information_methods(snps, outfile, cutoff_genotype, cutoff_snp, true)
 
 end