X-Git-Url: http://source.jalview.org/gitweb/?a=blobdiff_plain;f=forester%2Fruby%2Fscripts%2Fbioruby_examples%2Fmsa_1.rb;h=ed5d4733613ee407eb457083612283befa1bae32;hb=65cab4a8dc67e82e562572ed5e0f5fa44df6f622;hp=dca6106b34fc9321f7e80ce200a990764bc79d15;hpb=a1086647aff9dc4f73d6ed539e8243d184e9d43d;p=jalview.git

diff --git a/forester/ruby/scripts/bioruby_examples/msa_1.rb b/forester/ruby/scripts/bioruby_examples/msa_1.rb
index dca6106..ed5d473 100644
--- a/forester/ruby/scripts/bioruby_examples/msa_1.rb
+++ b/forester/ruby/scripts/bioruby_examples/msa_1.rb
@@ -1,34 +1,88 @@
 require 'rubygems'
 require 'bio'
  
-# creating a Bio::Sequence::NA object containing ambiguous alphabets
-#as = Bio::Sequence::NA.new("atgcyrwskmbdhvn")
+#############
 
-#print as.to_s
+# Reads in a ClustalW formatted multiple sequence alignment
+# from a file named "infile_clustalw.aln" and stores it in 'report'.
+report = Bio::ClustalW::Report.new(File.read('infile_clustalw.aln'))
 
-#print "\n"
+# Accesses the actual alignment.
+align = report.alignment
 
+# Goes through all sequences in 'align' and prints the
+# actual molecular sequence.
+align.each do |entry|
+  puts entry.seq
+end
 
-#seq1 = Bio::Sequence::AA.new("gggggg")
+##############
+
+DEFAULT_PARSER = Bio::Alignment::MultiFastaFormat
+puts DEFAULT_PARSER.to_s
+
+#file = Bio::Alignment.readfiles('bcl2.fasta', Bio::Alignment::MultiFastaFormat)
+#file.each do |entry|
+#  puts entry.entry_id           # Gets the identifier, e.g. 'sp|O35147|BAD_RAT'.
+#  puts entry.definition         # Gets the complete fasta description line.
+#  puts entry.seq                # Gets the actual sequence.
+  #puts entry.aaseq.composition  # Gets the amino acid composition.
+#end
+#puts 'OK'
+#puts
+
+file = Bio::FastaFormat.open('bcl2.fasta')
+file.each do |entry|
+   puts entry.entry_id           # Gets the identifier, e.g. 'sp|O35147|BAD_RAT'.
+  puts entry.definition         # Gets the complete fasta description line.
+  puts entry.seq                # Gets the actual sequence.
+  # do something on each fasta sequence entry
+end
+
+##############
+
+# Creates a new file named "outfile.fasta" and writes
+# multiple sequence alignment 'align' to it in fasta format.
+File.open('outfile.fasta', 'w') do |f|
+  f.write(align.output(:fasta))
+end
+
+# Creates a new file named "outfile.aln" and writes
+# multiple sequence alignment 'align' to it in clustal format.
+File.open('outfile.aln', 'w') do |f|
+  f.write(align.output(:clustal))
+end
+
+#############
+
+seq1 = Bio::Sequence.auto("gggggg")
+
+
+puts seq1.output(:fasta)
 #seq2 = Bio::Sequence::AA.new("ggggt")
 #seq3 = Bio::Sequence::AA.new("ggt")
 
 
 
-seq1 = "KMLFGVVFFFGG"
-seq2 ="LMGGHHF"
-seq3 = "GKKKKGHHHGHRRRGR"
-seq4 = "KKKGHHHGHRERGR"
-seqs = [ seq1, seq2, seq3, seq4 ] 
+seqs = [ "MFQIPEFEPSEQEDSSSAER",
+         "MGTPKQPSLAPAHALGLRKS",
+         "PKQPSLAPAHALGLRKS",
+         "MCSTSGCDLE" ] 
 
 
 # MAFFT
 options = [ '--maxiterate', '1000', '--localpair' ]
 mafft = Bio::MAFFT.new('/home/zma/SOFTWARE/mafft-6.847-without-extensions/scripts/mafft', options )
 report = mafft.query_align( seqs)
-#puts report.alignment.output_fasta
-report.alignment.each { |x| puts x.to_s }
-puts 'OK'
+
+# Accesses the actual alignment
+align = report.alignment
+
+# Prints each sequence to the console.
+align.each { |s| puts s.to_s }
+
+
+puts 'MAFFT OK'
 puts
 
 #clustalw
@@ -46,4 +100,31 @@ report = muscle.query_align( seqs)
 #puts report.alignment.output_fasta.to_s
 report.alignment.each { |x| puts x.to_s }
 puts 'OK'
-puts
\ No newline at end of file
+puts
+
+file = Bio::FastaFormat.open('bcl2.fasta')
+file.each do |entry|
+  puts entry.entry_id           # Gets the identifier, e.g. 'sp|O35147|BAD_RAT'.
+  puts entry.definition         # Gets the complete fasta description line.
+  puts entry.seq                # Gets the actual sequence.
+  puts entry.aaseq.composition  # Gets the amino acid composition. 
+end
+puts 'OK'
+puts
+
+Bio::FlatFile.auto('bcl2.fasta') do |ff|
+  ff.each do |entry|
+    puts entry.entry_id           # Gets the identifier, e.g. 'sp|O35147|BAD_RAT'.
+    puts entry.definition         # Gets the complete fasta description line.
+    puts entry.seq                # Gets the actual sequence.
+    puts entry.aaseq.composition  # Gets the amino acid composition.
+  end
+end
+puts 'OK'
+puts
+
+
+
+
+
+