4 ff = Bio::FlatFile.auto('bcl2.fasta')
5 ff.each_entry do |entry|
7 puts entry.entry_id # prints the identifier of the entry
8 puts entry.definition # prints the definition of the entry
9 puts entry.seq # prints the sequence data of the entry
12 # Creates a multiple sequence alignment (possibly unaligned) named
13 # 'seqs' from array 'seq_ary'.
14 seqs = Bio::Alignment.new( seq_ary )
17 seqs.each { |seq| puts seq.to_s }
22 # Writes multiple sequence alignment (possibly unaligned) 'seqs'
23 # to a file in PHYLIP format.
24 File.open('out0.phylip', 'w') do |f|
25 f.write(seqs.output(:phylip))
28 File.open('out0.fasta', 'w') do |f|
29 f.write(seqs.output(:fasta))
35 # Reads in a FASTA-formatted multiple sequence alignment (which does
36 # not have to be aligned, though) and stores its sequences in
39 fasta_seqs = Bio::Alignment::MultiFastaFormat.new(File.open('bcl2.fasta').read)
40 fasta_seqs.entries.each do |seq|
44 # Creates a multiple sequence alignment (possibly unaligned) named
45 # 'seqs' from array 'seq_ary'.
46 seqs = Bio::Alignment.new( seq_ary )
47 seqs.each { |seq| puts seq.to_s }
52 # Writes multiple sequence alignment (possibly unaligned) 'seqs'
53 # to a file in PHYLIP format.
54 File.open('out1.phylip', 'w') do |f|
55 f.write(seqs.output(:phylip))
58 File.open('out1.fasta', 'w') do |f|
59 f.write(seqs.output(:fasta))
65 #ff = Bio::FlatFile.new(Bio::FastaFormat, 'bcl2.fasta')
67 # puts "definition : " + f.definition
68 # puts "nalen : " + f.nalen.to_s
69 # puts "naseq : " + f.naseq
74 Bio::FastaFormat.open('bcl2.fasta') do | file |
76 puts entry.entry_id # Gets the identifier, e.g. 'sp|O35147|BAD_RAT'.
77 # puts entry.definition # Gets the complete fasta description line.
78 #puts entry.seq # Gets the actual sequence.
82 seqs =Bio::Alignment.new( seq_ary )
83 seqs.each { |x| puts x }
90 #seqs =Bio::Alignment.readfiles(File.open('bcl2.fasta'))
91 #seqs.entries.each do |seq|
92 # puts seq.to_biosequence
102 seqs = Bio::Alignment::MultiFastaFormat.new(File.open('bcl2.fasta').read)
103 seqs.entries.each do |seq|
104 puts seq.to_seq.output(:genbank)
109 puts seqs.entries[0].to_seq.output(:genbank)
112 puts seqs.entries[0].to_seq.output(:fasta)
115 puts seqs.entries[0].to_seq.output(:embl)
118 puts seqs.entries[0].to_seq.output(:raw)
121 puts seqs.entries[0].to_seq.output(:fasta_ncbi)
124 puts seqs.entries[0].to_seq.output(:fastq)
127 puts seqs.entries[0].to_seq.output(:fastq_sanger)
130 puts seqs.entries[0].to_seq.output(:fastq_solexa)
133 puts seqs.entries[0].to_seq.output(:fastq_illumina)
136 puts seqs.entries[0].to_seq.output(:fasta_numeric)
139 puts seqs.entries[0].to_seq.output(:qual)
144 # Reads in a ClustalW formatted multiple sequence alignment
145 # from a file named "infile_clustalw.aln" and stores it in 'report'.
146 report = Bio::ClustalW::Report.new(File.read('infile_clustalw.aln'))
148 # Accesses the actual alignment.
149 msa = report.alignment
151 # Goes through all sequences in 'msa' and prints the
152 # actual molecular sequence.
159 DEFAULT_PARSER = Bio::Alignment::MultiFastaFormat
160 puts DEFAULT_PARSER.to_s
162 #file = Bio::Alignment.readfiles('bcl2.fasta', Bio::Alignment::MultiFastaFormat)
163 #file.each do |entry|
164 # puts entry.entry_id # Gets the identifier, e.g. 'sp|O35147|BAD_RAT'.
165 # puts entry.definition # Gets the complete fasta description line.
166 # puts entry.seq # Gets the actual sequence.
167 #puts entry.aaseq.composition # Gets the amino acid composition.
172 file = Bio::FastaFormat.open('bcl2.fasta')
174 puts entry.entry_id # Gets the identifier, e.g. 'sp|O35147|BAD_RAT'.
175 puts entry.definition # Gets the complete fasta description line.
176 puts entry.seq # Gets the actual sequence.
177 # do something on each fasta sequence entry
183 # Creates a new file named "outfile.fasta" and writes
184 # multiple sequence alignment 'msa' to it in fasta format.
185 File.open('outfile.fasta', 'w') do |f|
186 f.write(msa.output(:fasta))
190 File.open('outfile.clustal', 'w') do |f|
191 f.write(msa.output(:clustal))
193 File.open('outfile.phylip', 'w') do |f|
194 f.write(msa.output(:phylip))
196 File.open('outfile.phylipnon', 'w') do |f|
197 f.write(msa.output(:phylipnon))
199 File.open('outfile.msf', 'w') do |f|
200 f.write(msa.output(:msf))
202 File.open('outfile.molphy', 'w') do |f|
203 f.write(msa.output(:molphy))
210 seq1 = Bio::Sequence.auto("gggggg")
213 puts seq1.output(:fasta)
214 #seq2 = Bio::Sequence::AA.new("ggggt")
215 #seq3 = Bio::Sequence::AA.new("ggt")
219 seqs = ['MFQIPEFEPSEQEDSSSAER',
220 'MGTPKQPSLAPAHALGLRKS',
226 options = [ '--maxiterate', '1000', '--localpair' ]
227 mafft = Bio::MAFFT.new('mafft', options )
228 report = mafft.query_align( seqs)
230 # Accesses the actual alignment
231 align = report.alignment
233 # Prints each sequence to the console.
234 align.each { |s| puts s.to_s }
241 clustalw = Bio::ClustalW.new('/home/zma/SOFTWARE/clustalw-2.1/src/clustalw2' )
242 report = clustalw.query_align( seqs)
243 #puts report.alignment.output_fasta.to_s
244 report.alignment.each { |x| puts x.to_s }
249 options = [ '-quiet', '-maxiters', '64' ]
250 muscle = Bio::Muscle.new('/home/zma/SOFTWARE/muscle3.8.31/src/muscle', options )
251 report = muscle.query_align( seqs)
252 #puts report.alignment.output_fasta.to_s
253 report.alignment.each { |x| puts x.to_s }
257 file = Bio::FastaFormat.open('bcl2.fasta')
259 puts entry.entry_id # Gets the identifier, e.g. 'sp|O35147|BAD_RAT'.
260 puts entry.definition # Gets the complete fasta description line.
261 puts entry.seq # Gets the actual sequence.
262 puts entry.aaseq.composition # Gets the amino acid composition.
267 Bio::FlatFile.auto('bcl2.fasta') do |ff|
269 puts entry.entry_id # Gets the identifier, e.g. 'sp|O35147|BAD_RAT'.
270 puts entry.definition # Gets the complete fasta description line.
271 puts entry.seq # Gets the actual sequence.
272 puts entry.aaseq.composition # Gets the amino acid composition.