dna_sequence_aligner 0.0.2

data/older/align_all.rb

@@ -0,0 +1,160 @@
+#!/usr/bin/ruby
+
+require 'bio'
+require 'optparse'
+
+def printv(*args)
+  if $VERBOSE
+    print(*args) ; $stdout.flush
+  end
+end
+
+def putsv(*args)
+  if $VERBOSE
+    puts(*args) ; $stdout.flush
+  end
+end
+
+
+def print_align(io, sequences, labels, opts={})
+  opts = {:cutoff => 100, :start => 0, :chars => 20}.merge(opts)
+  (start, length, chars) = opts.values_at(:start, :cutoff, :chars)
+
+  loop do
+    fin = false
+    sequences.zip(labels) do |string, label|
+      fin = (start >= string.length )
+      break if fin
+      io.puts "#{label.exactly_chars(chars)} : #{string[start,length]}"
+    end
+    io.puts " "
+    break if fin
+    start += length
+  end
+end
+
+class String
+
+  # returns [% same chars, % same letters (template), % same letters self]
+  def percent_similar_to(template)
+    num_same = 0
+    num_same_letters = 0
+    num_letters_in_template = 0
+    num_letters_in_self = 0
+    (0...(template.size)).each do |i|
+      if letters = (self[i,1] =~ /[A-Za-z]/)
+        num_letters_in_self += 1 
+      end
+      if template[i,1] =~ /[A-Za-z]/
+        num_letters_in_template += 1
+      end
+      if self[i] == template[i]
+        num_same += 1 
+        if letters
+          num_same_letters += 1
+        end
+      end
+    end
+    [[num_same, template.size], [num_same_letters, num_letters_in_template], [num_same_letters, num_letters_in_self]].map {|a,b| (a.to_f / b) * 100 }
+  end
+
+  def exactly_chars(n)
+    at_least = "%#{n}s" % self
+    at_least[0,n]
+  end
+
+end
+
+def seqs_and_defs(file)
+  ff = Bio::FlatFile.auto(file)
+  na_seq_objs = []
+  definitions = []
+  ff.each_entry do |entry|
+    definitions << entry.definition
+    na_seq_objs << Bio::Sequence::NA.new(entry.seq.to_s)
+  end
+  [na_seq_objs, definitions]
+end
+
+opt = {
+  :min => 80,
+}
+
+$VERBOSE = 3
+opts = OptionParser.new do |op|
+  op.banner = "usage: #{File.basename(__FILE__)} <many_seqs>.fasta <one_template>.fasta"
+  op.separator "output: <many_seqs>__<one_template>.<Threshold>.aligned"
+  op.separator " "
+  op.separator "description: goes through and does pairwise matching between all sequences and template,"
+  op.separator "then does a multiple alignment on all those with the template."
+  op.separator " "
+  op.on("-t", "--threshold-pct <#{opt[:min]}>", Float, "minimum % match of given sequence") {|v| opt[:min] = v }
+  op.on("-q", "--quiet", "don't give any info while running") {|v| $VERBOSE = false }
+end
+opts.parse!
+
+
+if ARGV.size != 2
+  puts opts
+  exit
+end
+
+(all_fasta_file, template) = ARGV
+
+(file_base, template_base) = ARGV.map do |file|
+  File.basename(file, ".*")
+end
+
+outfile = [[file_base, template_base].join("__"), opt[:min], 'aligned'].join('.')
+
+
+(seqs, definitions) = seqs_and_defs(all_fasta_file)
+
+(template_seq, template_def) = seqs_and_defs(template).map(&:first)
+
+#seqs = seqs[184,10]
+#definitions = definitions[184,10]
+
+#PSIM = %w(%chars_to_template %letters_to_template %letters_to_self)
+
+factory = Bio::ClustalW.new
+
+pass_threshold = []
+
+printv "performing pairwise alignments [on #{seqs.size} seqs]: "
+seqs.zip(definitions) do |seq, df|
+  if seq.to_s !~ /[^N]/i
+    printv '- '
+    next
+  end
+  align = Bio::Alignment.new([template_seq, seq])
+  result = align.do_align(factory)
+  (template_s, seq_s) = result.map do |seq|
+    seq.to_s
+  end
+  psimilar = seq_s.percent_similar_to(template_s)
+  printv( ("%.0f" % psimilar.last) + ' ')
+  if psimilar.last > opt[:min]
+    pass_threshold << [df, seq]
+    #printv '*'
+  else
+    #printv '.'
+  end
+end
+putsv "Done!"
+
+abort "none found above threshold! #{opt[:min]}" if pass_threshold.size == 0
+putsv "Found #{pass_threshold.size} sequence(s) above #{opt[:min]}% identical"
+
+pass_threshold << [template_def, template_seq]
+
+multi_align = Bio::Alignment.new( pass_threshold.map {|pair| pair.last } )
+m_result = multi_align.do_align(factory).strip
+
+labels = pass_threshold.map {|pair| pair.first }
+aligned_seqs = m_result.map {|seq| seq.to_s }
+
+File.open(outfile, 'w') do |out|
+  print_align(out, aligned_seqs, labels)
+end
+

data/older/align_to_template.rb

@@ -0,0 +1,143 @@
+#!/usr/bin/ruby
+
+require 'bio'
+require 'optparse'
+
+def printv(*args)
+  if $VERBOSE
+    print(*args) ; $stdout.flush
+  end
+end
+
+def putsv(*args)
+  if $VERBOSE
+    puts(*args) ; $stdout.flush
+  end
+end
+
+
+def print_align(io, sequences, labels, opts={})
+  opts = {:cutoff => 100, :start => 0, :chars => 20}.merge(opts)
+  (start, length, chars) = opts.values_at(:start, :cutoff, :chars)
+
+  loop do
+    fin = false
+    sequences.zip(labels) do |string, label|
+      fin = (start >= string.length )
+      break if fin
+      io.puts "#{label.exactly_chars(chars)} : #{string[start,length]}"
+    end
+    io.puts " "
+    break if fin
+    start += length
+  end
+end
+
+class String
+
+  # returns [% same chars, % same letters (template), % same letters self]
+  def percent_similar_to(template)
+    num_same = 0
+    num_same_letters = 0
+    num_letters_in_template = 0
+    num_letters_in_self = 0
+    (0...(template.size)).each do |i|
+      if letters = (self[i,1] =~ /[A-Za-z]/)
+        num_letters_in_self += 1 
+      end
+      if template[i,1] =~ /[A-Za-z]/
+        num_letters_in_template += 1
+      end
+      if self[i] == template[i]
+        num_same += 1 
+        if letters
+          num_same_letters += 1
+        end
+      end
+    end
+    [[num_same, template.size], [num_same_letters, num_letters_in_template], [num_same_letters, num_letters_in_self]].map {|a,b| (a.to_f / b) * 100 }
+  end
+
+  def exactly_chars(n)
+    at_least = "%#{n}s" % self
+    at_least[0,n]
+  end
+
+end
+
+def seqs_and_defs(file)
+  ff = Bio::FlatFile.auto(file)
+  na_seq_objs = []
+  definitions = []
+  ff.each_entry do |entry|
+    definitions << entry.definition
+    na_seq_objs << Bio::Sequence::NA.new(entry.seq.to_s)
+  end
+  [na_seq_objs, definitions]
+end
+
+outfile = "aligned.txt"
+
+$VERBOSE = 3
+opts = OptionParser.new do |op|
+  op.banner = "usage: #{File.basename(__FILE__)} template.fasta"
+  op.separator "output: aligned.txt"
+  op.separator "if template.ANNOTATED.fasta, then strips leading '#' lines and writes template.fasta"
+  op.separator " "
+end
+opts.parse!
+
+
+if ARGV.size != 2
+  puts opts
+  exit
+end
+
+template = ARGV.shift
+
+#seqs = seqs[184,10]
+#definitions = definitions[184,10]
+
+#PSIM = %w(%chars_to_template %letters_to_template %letters_to_self)
+
+factory = Bio::ClustalW.new
+
+pass_threshold = []
+
+printv "performing pairwise alignments [on #{seqs.size} seqs]: "
+seqs.zip(definitions) do |seq, df|
+  if seq.to_s !~ /[^N]/i
+    printv '- '
+    next
+  end
+  align = Bio::Alignment.new([template_seq, seq])
+  result = align.do_align(factory)
+  (template_s, seq_s) = result.map do |seq|
+    seq.to_s
+  end
+  psimilar = seq_s.percent_similar_to(template_s)
+  printv( ("%.0f" % psimilar.last) + ' ')
+  if psimilar.last > opt[:min]
+    pass_threshold << [df, seq]
+    #printv '*'
+  else
+    #printv '.'
+  end
+end
+putsv "Done!"
+
+abort "none found above threshold! #{opt[:min]}" if pass_threshold.size == 0
+putsv "Found #{pass_threshold.size} sequence(s) above #{opt[:min]}% identical"
+
+pass_threshold << [template_def, template_seq]
+
+multi_align = Bio::Alignment.new( pass_threshold.map {|pair| pair.last } )
+m_result = multi_align.do_align(factory).strip
+
+labels = pass_threshold.map {|pair| pair.first }
+aligned_seqs = m_result.map {|seq| seq.to_s }
+
+File.open(outfile, 'w') do |out|
+  print_align(out, aligned_seqs, labels)
+end
+

data/reference/clustalw_opts.txt

@@ -0,0 +1,73 @@
+# http://align.genome.jp/clustalw/clustalw_help.html
+
+ >>HELP 8 <<      Help for command line parameters
+
+                DATA (sequences)
+
+-INFILE=file.ext                             :input sequences.
+
+
+
+                VERBS (do things)
+
+-OPTIONS	    :list the command line parameters
+-HELP  or -CHECK    :outline the command line params.
+-ALIGN              :do full multiple alignment 
+-TREE               :calculate NJ tree.
+-BOOTSTRAP(=n)      :bootstrap a NJ tree (n= number of bootstraps; def. = 1000).
+-CONVERT            :output the input sequences in a different file format.
+
+
+                PARAMETERS (set things)
+
+***General settings:****
+-INTERACTIVE :read command line, then enter normal interactive menus
+-QUICKTREE   :use FAST algorithm for the alignment guide tree
+-TYPE=       :PROTEIN or DNA sequences
+-NEGATIVE    :protein alignment with negative values in matrix
+-OUTFILE=    :sequence alignment file name
+-OUTPUT=     :GCG, GDE, PHYLIP, PIR or NEXUS
+-OUTORDER=   :INPUT or ALIGNED
+-CASE        :LOWER or UPPER (for GDE output only)
+-SEQNOS=     :OFF or ON (for Clustal output only)
+-SEQNO_RANGE=:OFF or ON (NEW: for all output formats) 
+-RANGE=m,n   :sequence range to write starting m to m+n. 
+
+***Fast Pairwise Alignments:***
+-KTUPLE=n    :word size
+-TOPDIAGS=n  :number of best diags.
+-WINDOW=n    :window around best diags.
+-PAIRGAP=n   :gap penalty
+-SCORE       :PERCENT or ABSOLUTE
+
+
+***Slow Pairwise Alignments:***
+-PWMATRIX=    :Protein weight matrix=BLOSUM, PAM, GONNET, ID or filename
+-PWDNAMATRIX= :DNA weight matrix=IUB, CLUSTALW or filename
+-PWGAPOPEN=f  :gap opening penalty        
+-PWGAPEXT=f   :gap opening penalty
+
+
+***Multiple Alignments:***
+-NEWTREE=      :file for new guide tree
+-USETREE=      :file for old guide tree
+-MATRIX=       :Protein weight matrix=BLOSUM, PAM, GONNET, ID or filename
+-DNAMATRIX=    :DNA weight matrix=IUB, CLUSTALW or filename
+-GAPOPEN=f     :gap opening penalty        
+-GAPEXT=f      :gap extension penalty
+-ENDGAPS       :no end gap separation pen. 
+-GAPDIST=n     :gap separation pen. range
+-NOPGAP        :residue-specific gaps off  
+-NOHGAP        :hydrophilic gaps off
+-HGAPRESIDUES= :list hydrophilic res.    
+-MAXDIV=n      :% ident. for delay
+-TYPE=         :PROTEIN or DNA
+-TRANSWEIGHT=f :transitions weighting
+
+
+***Trees:***
+-OUTPUTTREE=nj OR phylip OR dist OR nexus
+-SEED=n        :seed number for bootstraps.
+-KIMURA        :use Kimura's correction.   
+-TOSSGAPS      :ignore positions with gaps.
+-BOOTLABELS=node OR branch :position of bootstrap values in tree display

data/script/fasta_compile_annotated.rb

@@ -0,0 +1,19 @@
+#!/usr/bin/ruby
+
+outfile = "ANALYZE.FASTA"
+
+if ARGV.size == 0
+  puts "usage: #{File.basename(__FILE__)} <file>.fasta ..."
+  puts "comments (starting with '#') are ok"
+  puts "outputs: #{outfile}"
+  exit
+end
+
+all_text = ARGV.map do |file|
+  IO.read(file).split("\n").reject {|line| line =~ /^\#/ }.join("\n")
+end.join("\n")
+
+File.open(outfile, 'w') do |out|
+  out.print all_text
+end
+

data/spec/align_spec.rb

@@ -0,0 +1,67 @@
+
+require File.dirname(__FILE__) + '/spec_helper'
+require 'bio/alignment/dna_sequence'
+
+DNAReads = Bio::Alignment::DNASequenceReads
+
+describe 'aligning' do
+
+  before do
+    @string = 'AAAATTTTGGGGGCCCCCC'
+    @conc = '--A?A-AT?TTGGGGGCCCAAC?C---'
+    @testcase = "testcase.fasta"
+
+    @pa = [ ["--ABCDEFGHIJKLMNOP", 
+             "-----DEFGHIJK-MN--"], 
+            ["--ABCDEFGHIJKLM-NOP", 
+             "--ABCDE---IJKLMZNOP"],
+            ["--ABCDEFGHIJKLMNOP", 
+             "-------------LMNOP"],
+            ["--ABCDEFGHIJKLMNOP", 
+             "--ABCDEFGHIJKLMN--"],
+            ["--ABCDEFGHIJKLMNOP", 
+             "--ABC------JKLM--P"],
+            ["--ABC--DEFGHIJKLMNOP", 
+              "--ABCZZDEFGHIJKLMNOP"],
+    ]
+    @template = "--ABC--DEFGHIJKLM-NO"
+    @aligned = ["-------DEFGHIJK-M-N-", 
+                "--ABC--DE---IJKLMZNO", 
+                "---------------LM-NO", 
+                "--ABC--DEFGHIJKLM-N-",
+                "--ABC--------JKLM---", 
+                "--ABCZZDEFGHIJKLM-NO"
+                ] 
+
+    @labels = %w(one two three four five six)
+
+  end
+
+  it 'removes bad ends' do
+    (start, len) = DNAReads.find_good_section(@conc, 4)
+    @conc[start, len].is "TTGGGGGCCCAAC"
+  end
+
+  it 'aligns pairwise' do
+    (template, others) = DNAReads.merge_pairwise(@pa)
+    template.is @template
+    @aligned.enums others
+  end
+
+  it 'can create a good consensus string' do
+    (string, stats) = DNAReads.consensus_string_and_stats([@template, *@aligned])
+    string.is "  ===^^==========^=="
+    stats.enums [2, 3, 15, 0, 0, 0]
+    (string, stats) = DNAReads.consensus_string_and_stats([@template, "-------DEFGHIJK-M-N-"])
+    string.is "  ...  ========.= =."
+    stats.enums [5, 0, 10, 5, 0, 0]
+  end
+
+  xit 'prints useful printout' do
+    st = StringIO.new
+    DNAReads.print_align(st, @aligned, @labels, :template => @template, :template_label => "template", :chars => 8)
+    puts " "
+    puts st.string
+    1.is 1
+  end
+end