def test_distance(self):
dist = ncd.Distance(self.pep_records)
matrix = distmatrix.create(self.pep_records.id_list, dist)
exp = [
" 4", "seq1 0.0000000 0.2698413 0.3809524 0.5238095",
"seq2 0.2698413 0.0000000 0.2950820 0.4666667",
"seq3 0.3809524 0.2950820 0.0000000 0.4754098",
"seq4 0.5238095 0.4666667 0.4754098 0.0000000"
]
self.assertEqual(matrix.format(), "\n".join(exp))
def calc_distances(seqs):
seq_records = seqrecords.SeqRecords()
for seq in seqs:
seq_records.add(seq.name, "".join(seq.sequence))
dist = ncd.Distance(seq_records)
matrix = distmatrix.create(seq_records.id_list, dist)
return matrix.data
def main():
parser = get_parser()
args = validate_args(parser)
seq_records = seqrecords.read_fasta(args.fasta)
dist = ncd.Distance(seq_records)
matrix = distmatrix.create(seq_records.id_list, dist)
if args.out:
oh = open(args.out, 'w')
matrix.write_to_file(oh, args.outfmt)
oh.close()
else:
matrix.display(args.outfmt)
outfile = sys.argv[3]
input_file = open(infile, 'r')
seq_records = seqrecords.read_fasta(input_file)
input_file.close()
#choose one method to compute distance matrix
if method == "bbc":
alphabet = seqcontent.get_alphabet('protein')
vector = bbc.create_vectors(seq_records, 10, alphabet)
dist = bbc.Distance(vector)
matrix = distmatrix.create(seq_records.id_list, dist)
matrix.display()
elif method == "ncd":
dist = ncd.Distance(seq_records)
matrix = distmatrix.create(seq_records.id_list, dist)
matrix.display()
elif method == "wmetric":
matrix = subsmat.get('blosum62')
dist = wmetric.Distance(seq_records, matrix)
matrix = distmatrix.create(seq_records.id_list, dist)
matrix.display()
elif method == "d2":
patterns = []
for i in range(1, 5 + 1):
p = word_pattern.create(seq_records.seq_list, i)
patterns.append(p)
def test_complexities(self):
dist = ncd.Distance(self.pep_records)
exp = [((0, ), 63.0), ((0, 1), 77.0), ((0, 2), 85.0), ((0, 3), 70.0),
((1, ), 60.0), ((1, 2), 78.0), ((1, 3), 65.0), ((2, ), 61.0),
((2, 3), 66.0), ((3, ), 37.0)]
self.assertEqual(exp, sorted(dist._complexity.items()))