bio-polyploid-tools 0.7.3 → 0.8.0

data/lib/bio/PolyploidTools/PrimerRegion.rb

@@ -1,6 +1,10 @@
 module Bio::PolyploidTools
   class PrimerRegion
-    attr_accessor :snp_pos, :sequence, :chromosome_specific, :almost_chromosome_specific, :crhomosome_specific_intron , :almost_crhomosome_specific_intron, :homoeologous
+    attr_accessor :snp_pos, :almost_chromosome_specific_in_mask 
+    attr_accessor :chromosome_specific_in_mask, :sequence 
+    attr_accessor :chromosome_specific, :almost_chromosome_specific
+    attr_accessor :crhomosome_specific_intron , :almost_crhomosome_specific_intron
+    attr_accessor :homoeologous, :position_in_mask_from_template
 
     def initialize
 
@@ -8,6 +12,10 @@ module Bio::PolyploidTools
       @almost_chromosome_specific = Array.new
       @crhomosome_specific_intron  = Array.new
       @almost_crhomosome_specific_intron = Array.new
+      #For deletions
+      @chromosome_specific_in_mask = Array.new
+      @almost_chromosome_specific_in_mask = Array.new
+      @position_in_mask_from_template = Hash.new
     end
 
     def tail_candidates

data/lib/bio/PolyploidTools/SNP.rb

@@ -18,7 +18,7 @@ module Bio::PolyploidTools
 
     #Format: 
     #Gene_name,Original,SNP_Pos,pos,chromosome
-    #A_comp0_c0_seq1,C,519,A
+    #A_comp0_c0_seq1,C,519,A,2A
     def self.parse(reg_str)
       reg_str.chomp!
       snp = SNP.new
@@ -35,19 +35,43 @@ module Bio::PolyploidTools
       snp
     end
 
+    def setTemplateFromFastaFile(fastaFile ,flanking_size = 100)
+      reg = Bio::DB::Fasta::Region.new
+      reg.entry = gene
+      reg.entry = @contig if @contig
+      #puts reg.entry 
+      #puts @contig
+      #puts gene
+      reg.start = position - flanking_size
+      reg.end = position + flanking_size +1
+      reg.orientation = :forward
+      entry = fastaFile.index.region_for_entry(gene)
+      reg.start = 1 if reg.start < 1
+      reg.end = entry.length if reg.end > entry.length
+      amb = Bio::NucleicAcid.to_IUAPC("#{original}#{snp}")
+      @position = @position - reg.start + 1
+      @position = 1 if @position < 1
+      self.template_sequence = fastaFile.fetch_sequence(reg)
+      template_sequence[position - 1] = amb
+    end
+
     def initialize
-      @genomes_count = 3 #TODO: if we want to use this with other polyploids, me need to set this as a variable in the main script. 
+      @genomes_count = 3 
       @primer_3_min_seq_length = 50
       @variation_free_region = 0
+      @contig = false
     end
 
-    def to_polymarker_sequence(flanking_size)
+    def to_polymarker_sequence(flanking_size, total:nil)
       out = template_sequence.clone
+      #puts "changing: #{position} #{flanking_size} len: #{total}"
       out[position-1]  = "[#{original}/#{snp}]"
-
       start = position - flanking_size - 1
+      #puts "Start: #{start}"
       start = 0 if start < 0
-      total = flanking_size * 2 + 6
+      total = flanking_size * 2 unless total
+      total += 5
+      #puts "Total: #{total}"
       out[start , total ]
     end
     
@@ -172,10 +196,6 @@ module Bio::PolyploidTools
         ret_str << "#{seq}\n"
       end
 
-      #self.exon_sequences.each do | chromosome, exon_seq | 
-      #  ex_seq = cut_sequence_to_primer_region(exon_seq)
-      #  ret_str << ">#{chromosome}\n#{ex_seq}\n"
-      #end
       self.surrounding_exon_sequences.each do |chromosome, exon_seq|
         ret_str << ">#{chromosome}\n#{exon_seq}\n"
       end
@@ -253,6 +273,8 @@ module Bio::PolyploidTools
       left = opts[:left_pos]
       right = opts[:right_pos]
       sequence =  opts[:sequence]
+      extra =  opts[:extra]
+
       orientation = "forward"
       if opts[:right_pos]
         orientation = "forward"
@@ -271,9 +293,13 @@ module Bio::PolyploidTools
 
 
       str = "SEQUENCE_ID=#{opts[:name]} #{orientation}\n"
-      str << "SEQUENCE_FORCE_LEFT_END=#{left}\n"
+      str << "SEQUENCE_FORCE_LEFT_END=#{left}\n" unless  opts[:extra_f]
       str << "SEQUENCE_FORCE_RIGHT_END=#{right}\n" if opts[:right_pos]
+      str << extra if extra
+      str << opts[:extra_f] if opts[:extra_f]
       str << "SEQUENCE_TEMPLATE=#{sequence}\n"
+      
+     
       str << "=\n"
 
 
@@ -284,8 +310,10 @@ module Bio::PolyploidTools
         orientation = "reverse"
         sequence = reverse_complement_string(sequence)
         str << "SEQUENCE_ID=#{opts[:name]} #{orientation}\n"
-        str << "SEQUENCE_FORCE_LEFT_END=#{left}\n"
+        str << "SEQUENCE_FORCE_LEFT_END=#{left}\n" unless  opts[:extra_r]
+        str << opts[:extra_r] if opts[:extra_r]
         str << "SEQUENCE_TEMPLATE=#{sequence}\n"
+        str << extra if extra
         str << "=\n"
       end
 
@@ -298,8 +326,10 @@ module Bio::PolyploidTools
       primer_3_propertes = Array.new
 
       seq_original = String.new(pr.sequence)
-      #puts seq_original.size.to_s << "-" << primer_3_min_seq_length.to_s
+      puts seq_original.size.to_s << "-" << primer_3_min_seq_length.to_s 
       return primer_3_propertes if seq_original.size < primer_3_min_seq_length
+      #puts self.inspect
+      puts pr.snp_pos.to_s << "(" << seq_original.length.to_s << ")"
       
       seq_original[pr.snp_pos] = self.original
       seq_original_reverse = reverse_complement_string(seq_original)
@@ -402,8 +432,8 @@ module Bio::PolyploidTools
         
         seq[local_pos_in_gene] = self.snp if name == self.snp_in    
         @parental_sequences [name] = seq
-        #puts name
-        #puts seq
+        puts name
+        puts seq
       end
       @parental_sequences
     end
@@ -420,8 +450,9 @@ module Bio::PolyploidTools
           seq =  bam.consensus_with_ambiguities({:region=>gene_region}).to_s
         else
           seq = container.gene_model_sequence(gene_region)
+           
            unless name == self.snp_in
-             # puts "Modiging original: #{name} #{self.original}"  
+              #puts "Modifing original: #{name} #{seq}"  
               seq[local_pos_in_gene] = self.original 
             end
         end
@@ -466,9 +497,12 @@ module Bio::PolyploidTools
     def aligned_sequences
      
       return @aligned_sequences if @aligned_sequences
+     
+      
       options = ['--maxiterate', '1000', '--localpair', '--quiet']
       mafft = Bio::MAFFT.new( "mafft" , options)
-    #  puts "Before MAFT:#{sequences_to_align.inspect}"
+      #puts "Before MAFT:#{sequences_to_align.inspect}"
+
       report = mafft.query_align(sequences_to_align)
       @aligned_sequences = report.alignment
    #   puts "MAFFT: #{report.alignment.inspect}" 
@@ -508,7 +542,11 @@ module Bio::PolyploidTools
       local_pos = 0
       started = false
 #TODO: Validate the cases when the alignment has padding on the left on all the chromosomes
-
+      #unless parental_strings[0] 
+        #puts "parental hash: #{parental_sequences}"
+        #puts "Aligned sequences: #{aligned_sequences.to_fasta}"
+       # puts "parental_strings: #{parental_strings.to_s}"
+      #end
       while i < parental_strings[0].size  do
         if local_pos_in_gene == local_pos
           pos = i
@@ -541,10 +579,11 @@ module Bio::PolyploidTools
         different = 0
         cov = 0
         from_group = 0
+        nCount = 0
         names.each do | chr |
           if aligned_sequences[chr] and aligned_sequences[chr][i]  != "-"
             cov += 1 
-
+            nCount += 1 if aligned_sequences[chr][i] == 'N' or  aligned_sequences[chr][i] == 'n' # maybe fix this to use ambiguity codes instead. 
             from_group += 1 if chr[0] == chromosome_group
             #puts "Comparing #{chromosome_group} and #{chr[0]} as chromosomes"
             if chr != chromosome 
@@ -556,6 +595,7 @@ module Bio::PolyploidTools
         end
         masked_snps[i] = "-" if different == 0
         masked_snps[i] = "-" if cov == 1
+        masked_snps[i] = "-" if nCount > 0
         masked_snps[i] = "*" if cov == 0
         expected_snps = names.size - 1
        # puts "Diferences: #{different} to expected: #{ expected_snps } [#{i}] Genome count (#{from_group} == #{genomes_count})"

data/lib/bio/PolyploidTools/SNPMutant.rb

@@ -7,7 +7,7 @@ module Bio::PolyploidTools
 
   class SNPMutant < SNPSequence
 
-    attr_accessor :library, :contig, :chr
+    attr_accessor :library, :contig, :chr, :parsed_start, :parsed_flanking, :region_size
     #Format: 
     #seqid,library,position,wt_base,mut_base
     #IWGSC_CSS_1AL_scaff_1455974,Kronos2281,127,C,T
@@ -17,9 +17,9 @@ module Bio::PolyploidTools
 
       arr = reg_str.split(",")
       
-      throw SNPSequenceException.new "Need five fields to parse, and got #{arr.size} in #{reg_str}" unless arr.size == 5
+      throw SNPSequenceException.new "Need five fields to parse, and got #{arr.size} in #{reg_str}" if arr.size < 5
       
-      snp.contig, snp.library, snp.position, snp.original, snp.snp = reg_str.split(",")
+      snp.contig, snp.library, snp.position, snp.original, snp.snp, parsed_flanking, region_size = reg_str.split(",")
       snp.position = snp.position.to_i
       snp.gene = "EMPTY"
       begin
@@ -40,6 +40,8 @@ module Bio::PolyploidTools
       
       snp.exon_list = Hash.new()
       snp.flanking_size=100
+      snp.region_size = region_size.to_i if region_size
+      snp.flanking_size = parsed_flanking.to_i if parsed_flanking
       snp
     end
     

data/lib/bio/db/blast.rb

@@ -0,0 +1,112 @@
+module Bio::DB::Blast
+
+	def self.to_sugar(line)
+		fields = line.split("\t")[0..8]
+		
+		if  fields[3] =="-1"
+			fields[3] = "-"
+			fields[2] = fields[2].to_i - 1
+		else
+			fields[3] = "+"
+			fields[1] = fields[1].to_i - 1
+		end
+		if fields[7] =="-1"
+			fields[7] = "-"
+			fields[6] = fields[6].to_i - 1
+		else
+			fields[7] = "+"
+			fields[5] = fields[5].to_i - 1
+		end
+		fields.join(" ")
+	end
+
+	def self.to_vulgar(line)
+		qseq, sseq = line.split("\t")[12..13]
+
+		len = qseq.length
+		l_status = ""
+		l_len = 0
+		str = Array.new
+		statuses = ""
+		for i in 0..len
+			if qseq[i] == "-"
+				status = "D"
+			elsif sseq[i] == "-"
+				status = "I"
+			else
+				status = "M"
+			end
+			statuses << status
+		end
+		statuses.split('').each do |e| 
+			if l_status != e
+				case l_status
+				when "M"
+					str << ["M", l_len, l_len]
+				when "I"
+					str << ["G", l_len, 0]
+				when "D"
+					str << ["G", 0, l_len]
+				end
+				l_len = 0
+			end
+			l_status = e
+			l_len += 1
+		end
+		l_len -= 1
+		case l_status
+		when "M"
+			str << ["M", l_len, l_len]
+		when "I"
+			str << ["G", l_len, 0]
+		when "D"
+			str << ["G", 0, l_len]
+		end
+
+		str.flatten!.join(" ")
+	end
+
+	def self.to_exo(line)
+		arr = Array.new
+		arr << "RESULT:"
+		arr << to_sugar(line)
+		arr << line.split("\t")[9..11]
+		arr << "."
+		arr << to_vulgar(line)
+		arr.join("\t")
+	end
+
+	def self.align(opts={})
+		target=opts[:target]
+		query=opts[:query]
+		cmdline = "blastn -query #{query} -db #{target} -outfmt '6 qseqid qstart qend qframe sseqid sstart send sframe score pident qlen slen qseq sseq'"
+
+		status, stdout, stderr = systemu cmdline
+		if status.exitstatus == 0
+			alns = Array.new unless block_given?
+			stdout.each_line do |e_l|
+				#puts e_l
+				line = to_exo(e_l)
+				#puts line
+				arr = line.split("\t")
+				aln = Bio::DB::Exonerate::Alignment.parse_custom(line) 
+				if aln
+					if block_given?
+						yield aln
+					else
+						alns << aln
+					end
+				end
+			end
+			return alns unless block_given?
+		else
+			raise BlasteException.new(), "Error running exonerate. Command line was '#{cmdline}'\n Blast STDERR was:\n#{stderr}"
+		end
+	end	
+
+	class BlasteException < RuntimeError 
+	end	
+
+end
+
+

data/lib/bio/db/exonerate.rb

@@ -16,10 +16,9 @@ module Bio::DB::Exonerate
 
     target=opts[:target]
     query=opts[:query]
- #
 
- cmdline = "exonerate --verbose 0 --showalignment no --bestn #{opts[:bestn]} --showvulgar no  --model #{opts[:model]}   --ryo '#{opts[:ryo]}' #{query} #{target}"
- status, stdout, stderr = systemu cmdline
+    cmdline = "exonerate --verbose 0 --showalignment no --bestn #{opts[:bestn]} --showvulgar no  --model #{opts[:model]}   --ryo '#{opts[:ryo]}' #{query} #{target}"
+    status, stdout, stderr = systemu cmdline
     #$stderr.puts cmdline
     if status.exitstatus == 0
       alns = Array.new unless block_given?
@@ -170,9 +169,9 @@ module Bio::DB::Exonerate
       end
 
       @vulgar_block = Array.new
-      # p "VULGAR #{vulgar_str}"
+      #p "VULGAR #{vulgar_str}"
       vulgar_str.split(/\s/).each_slice(3) do | block |
-        #    p block
+        #p block
         vulgar = Vulgar.new(block[0].to_sym, block[1].to_i, block[2].to_i, tarcurrent, target_multiply, query_current, query_multiply, self)
         query_current = vulgar.query_end
         tarcurrent = vulgar.target_end

data/lib/bio/db/primer3.rb

@@ -261,11 +261,76 @@ module Bio::DB::Primer3
       return ""
     end
 
-    def common_primer
-      return self.values[9] if self.values[9]&& self.values[9] != nil
+    def common_primer 
+      return self.values[9] if self.values[9] && self.values[9] != nil
       return ""
     end
 
+    def product_size
+      return self.values[16].to_i if self.values[16]&& self.values[16] != nil 
+      return 0
+    end
+
+    def orientation
+      puts "insideOrientation: #{self.values[11]}"
+      return self.values[11] if self.values[11]&& self.values[11] != nil 
+      return 'unknown'
+    end
+
+
+    def first_product
+      left = first_primer
+      right = common_primer
+      nlen = product_size - left.size - right.size
+      product = left + ('n' * nlen) + Primer3Record.reverse_complement_string(right)
+      #puts "orientation: #{orientation}"
+      
+      product = Primer3Record.reverse_complement_string(product)  if orientation == 'reverse'
+    
+      product
+    end
+
+     def second_product
+      left = second_primer
+      right = common_primer
+      nlen = product_size - left.size - right.size
+      product = left + ('n' * nlen) + Primer3Record.reverse_complement_string(right)
+      product = Primer3Record.reverse_complement_string(product) if orientation == 'reverse'
+      
+
+      product
+    end
+
+
+    def realigned_primers_fasta
+      ret_str = ""
+      realigned_primers.each_pair do |name, seq|
+        ret_str << ">#{self.to_s}-#{name}\n#{seq}\n" 
+      end
+      ret_str 
+    end
+
+
+    def realigned_primers
+     
+      return @realigned_primers if @realigned_primers
+      sequences_to_align = Hash.new
+      sequences_to_align["first_product"]  = first_product
+      sequences_to_align["second_product"] = second_product
+      sequences_to_align.merge!(snp_from.surrounding_exon_sequences)
+      if sequences_to_align.size == 1
+        @realigned_primers = sequences_to_align
+        return @realigned_primers
+      end
+      options = ['--maxiterate', '1000', '--localpair', '--quiet']
+      mafft = Bio::MAFFT.new( "mafft" , options)
+      #puts "Before MAFT:#{sequences_to_align.inspect}"
+      report = mafft.query_align(sequences_to_align)
+      @realigned_primers = report.alignment
+      #puts "MAFFT: #{report.alignment.inspect}" 
+      @realigned_primers
+    end 
+
     def self.parse(reg_str)
       reg_str.chomp!
       snp = SNP.new
@@ -330,14 +395,14 @@ module Bio::DB::Primer3
   class Primer3Record
     include Comparable
     attr_accessor :properties, :polymorphism
-    attr_accessor :socres
+    attr_accessor :scores
 
 
     def best_pair
       return @best_pair if @best_pair
       @best_pair = nil
       @primerPairs.each do | primer |
-        @best_pair = primer if @best_pair == nil
+        @best_pair = primer if @best_pair.nil?
         @best_pair = primer if primer.size < @best_pair.size
       end
       #@best_pair = @primerPairs.min
@@ -354,7 +419,7 @@ module Bio::DB::Primer3
       $stderr.puts "Missing #{method_name}"
       $stderr.puts @properties.inspect
       return "" #if a property is missing, return blank. 
-      #raise NoMethodError.new() 
+      raise NoMethodError.new() 
     end
 
     def find_left_tm(primer)
@@ -416,13 +481,14 @@ module Bio::DB::Primer3
         base_original = snp.original 
         base_snp = snp.snp
       elsif self.orientation == :reverse
-        base_original = reverse_complement_string(snp.original )
-        base_snp = reverse_complement_string(snp.snp)
+        #puts self.inspect
+        base_original =Primer3Record.reverse_complement_string(snp.original )
+        base_snp = Primer3Record.reverse_complement_string(snp.snp)
       else
         raise Primer3Exception.new "#{self.orientation} is not a valid orientation"
       end
 
-      # puts "#{snp.to_s} #{self.orientation} #{tmp_primer[-1] } #{base_original} #{base_snp}"
+      #puts "#{snp.to_s} #{self.orientation} #{tmp_primer[-1] } #{base_original} #{base_snp}"
       if tmp_primer[-1] == base_original
         tmp_primer[-1] = base_snp
       elsif tmp_primer[-1] == base_snp
@@ -438,19 +504,19 @@ module Bio::DB::Primer3
 
       seq = self.sequence_template
       #puts "Left coordinates: #{seq}"
-      seq = reverse_complement_string(seq) if self.orientation != other_orientation
+      seq = Primer3Record.reverse_complement_string(seq) if self.orientation != other_orientation
 
       seq[coordinates[0],coordinates[1]] 
     end
 
-    def reverse_complement_string(sequenc_str)
+    def self.reverse_complement_string(sequenc_str)
       complement = sequenc_str.tr('atgcrymkdhvbswnATGCRYMKDHVBSWN', 'tacgyrkmhdbvswnTACGYRKMHDBVSWN')
       complement.reverse!
     end
 
     def right_primer_delete
       @right_primer = self.sequence_template[right_coordinates[0],right_coordinates[1]] unless @right_primer
-      @right_primer = reverse_complement_string(@right_primer)
+      @right_primer = Primer3Record.reverse_complement_string(@right_primer)
       @right_primer
     end
     
@@ -547,9 +613,10 @@ module Bio::DB::Primer3
 
     end
 
-    def self.parse_file(filename)
+    def self.parse_file(filename, scores: nil)
       File.open(filename) do | f |
         record = Primer3Record.new
+        record.scores = scores if scores
         f.each_line do | line |
           line.chomp!
           if line == "="
@@ -557,6 +624,7 @@ module Bio::DB::Primer3
             record.parse_blocks
             yield record
             record = Primer3Record.new
+            record.scores = scores if scores
           else
             tokens = line.split("=")
             i = 0
@@ -672,7 +740,7 @@ module Bio::DB::Primer3
 
     attr_accessor :line_1, :line_2
     attr_accessor :snp_hash
-
+    attr_accessor :scores
 
     def add_snp_file(filename)
       @snp_hash=Hash.new unless @snp_hash
@@ -701,7 +769,8 @@ module Bio::DB::Primer3
     end
 
     def add_primers_file(filename)
-      Primer3Record.parse_file(filename) do | primer3record |
+      #primer3record.scores = @scores if @scores
+      Primer3Record.parse_file(filename, scores: @scores) do | primer3record |
         current_snp = @snp_hash["#{primer3record.snp.to_s}:#{primer3record.chromosome}"]
         current_snp.add_record(primer3record)
       end