def main():
# create a substitution matrix
sub_matrix = SubstitutionMatrix('blosum50')
# set up for alignment
aligner = NWAlign(sub_matrix)
print "Testing a simple alignment..."
seq1 = "HEAGAWGHEE"
seq2 = "PAWHEAE"
aligner.align(seq1, seq2)
align1, align2 = aligner.get_optimal_alignment()
score = aligner.get_optimal_score()
print "Alignment Score:", score
print align1.data
print align2.data
print "Testing a more complex alignment..."
test_file = "PEPCarboxylase.fasta"
print "Getting sequences from the file PEPCarboxylase.fasta..."
seq_list = []
scanner = Fasta._Scanner()
handler = FASTAHandler(seq_list)
file = open(test_file, 'r')
scanner.feed(file, handler)
scanner.feed(file, handler)
#print seq_list
print "Aligning sequences..."
aligner = NWAlign(sub_matrix)
aligner.align(seq_list[0][0:150], seq_list[1][0:150])
align1, align2 = aligner.get_optimal_alignment()
score = aligner.get_optimal_score()
print "Alignment Score:", score
line_width = 25
current_position = 0
current_position = current_position + line_width
# pretty print the alignment
while current_position < len(align1):
print ""
print align1.data[current_position - line_width:current_position]
print align2.data[current_position - line_width:current_position]
current_position = current_position + line_width
# print whatever is left
print ""
print align1.data[current_position - line_width:len(align1) - 1]
print align2.data[current_position - line_width:len(align2) - 1]
def extract_organisms(file, num_records):
scanner = Fasta._Scanner()
consumer = SpeciesExtractor()
file_to_parse = UndoHandle(open(file, "r"))
for fasta_record in range(num_records):
scanner.feed(file_to_parse, consumer)
file_to_parse.close()
return consumer.species_list
