def main():
data = readFASTA(sys.argv[1])
dna_len = len(data[0][1])
profile = [{'A' : 0, 'C' : 0, 'G' : 0, 'T' : 0}]*dna_len
for i in range(dna_len):
count = {'A' : 0, 'C' : 0, 'G' : 0, 'T' : 0}
for j in range(0, len(data)):
dna = data[j][1]
count[dna[i]] += 1
profile[i] = count
dna = str()
for pair in profile:
dna += getMaxProb(pair)
print dna
for nuc in 'ACGT':
line = nuc + ':'
for pair in profile:
line += ' ' + str(pair[nuc])
print line
def main():
data = readFASTA(sys.argv[1])
dna_len = len(data[0][1])
profile = [{'A': 0, 'C': 0, 'G': 0, 'T': 0}] * dna_len
for i in range(dna_len):
count = {'A': 0, 'C': 0, 'G': 0, 'T': 0}
for j in range(0, len(data)):
dna = data[j][1]
count[dna[i]] += 1
profile[i] = count
dna = str()
for pair in profile:
dna += getMaxProb(pair)
print dna
for nuc in 'ACGT':
line = nuc + ':'
for pair in profile:
line += ' ' + str(pair[nuc])
print line
def main():
data = readFASTA(sys.argv[1])
dna = list()
for fasta in data:
dna.append(fasta[1])
longest = long_substr(dna)
print longest
def main():
data = readFASTA(sys.argv[1])
dna = data[0].dna
for i in range(1, len(data)):
dna = dna.replace(data[i].dna, '')
prot = DNA_to_PROT(dna)
print prot
def main():
data = readFASTA(sys.argv[1])
dna = data[0].dna
for i in range(1, len(data)):
dna = dna.replace(data[i].dna, '')
prot = DNA_to_PROT(dna)
print prot
def main():
data = readFASTA(sys.argv[1])
dna = data.dna
n = len(dna)
revc = revcomp_DNA(dna)
locations = list()
for l in range(4, 13):
for i in range(n - l + 1):
if dna[i:i + l] == revc[i:i + l]:
locations.append(str(i + 1) + ' ' + str(l))
print '\n'.join(locations)
def main():
data = readFASTA(sys.argv[1])
s, q = [d.dna for d in data]
transitions = transversions = 0
for i in range(len(q)):
if (s[i] != q[i]):
if (is_transition(s[i], q[i])):
transitions += 1
else:
transversions += 1
print 1. * transitions / transversions
def main():
data = readFASTA(sys.argv[1])
s, q = [d.dna for d in data]
i = 0
res = list()
for c in q:
idx = s.find(c, i)
res.append(idx + 1)
i = idx + 1
print ' '.join(list(map(str, res)))
def main():
data = readFASTA(sys.argv[1])
s, q = [d.dna for d in data]
i = 0
res = list()
for c in q:
idx = s.find(c, i)
res.append(idx + 1)
i = idx + 1
print ' '.join(list(map(str, res)))
def main():
data = readFASTA(sys.argv[1])
s, q = [d.dna for d in data]
transitions = transversions = 0
for i in range(len(q)):
if(s[i] != q[i]):
if(is_transition(s[i], q[i])):
transitions += 1
else:
transversions += 1
print 1.*transitions/transversions
def main():
data = readFASTA(sys.argv[1])
dna = data.dna
n = len(dna)
revc = revcomp_DNA(dna)
locations = list()
for l in range(4, 13):
for i in range(n - l + 1):
if dna[i:i + l] == revc[i:i + l]:
locations.append(str(i + 1) + ' ' + str(l))
print '\n'.join(locations)
def main():
data = readFASTA(sys.argv[1])
matrix = zeros((len(data), len(data)))
for i in range(len(data)):
for j in range(i + 1, len(data)):
matrix[i][j] = p_distance(data[i][1], data[j][1])
matrix[j][i] = matrix[i][
j] # this matrix is mirrored by main diag, so we can compute only part of matrix
for i in range(len(data)):
line = ' '.join(map(str, matrix[i]))
print line
def main():
data = readFASTA(sys.argv[1])
dna = data.dna
fail = [0]*len(dna)
fail[0] = 0
for i in range(1, len(dna)):
j = fail[i-1]
while(j > 0 and dna[i] != dna[j]):
j = fail[j - 1]
if(dna[i] == dna[j]):
j += 1
fail[i] = j
with open('output/kmp.txt', 'w') as output:
output.write(' '.join(list(map(str, fail))))
help="Input FASTA")
parser.add_argument('-o',
'--output',
required=False,
type=argparse.FileType('w'),
default=stdout,
help="Output")
parser.add_argument('-a',
'--alpha',
required=False,
type=float,
default=float('inf'),
help="Gamma distribution alpha parameter")
args = parser.parse_args()
return args.input, args.output, args.alpha
# main code execution
infile, outfile, alpha = parseArgs()
seqs = readFASTA(infile)
infile.close()
keys = list(seqs.keys())
L = None
for k in keys:
if L is None:
L = len(seqs[k])
assert L == len(seqs[k]), "All sequences must be of equal length"
for i in range(len(keys) - 1):
for j in range(i + 1, len(keys)):
outfile.write('%f\n' % jc69(seqs[keys[i]], seqs[keys[j]], alpha))
'''
Convert names of FASTA file to random safe names.
Sequences are output to STDOUT.
Dictionary of name mappings is output to STDERR.
'''
from common import ran_str, readFASTA
K = 20 # safenames will be length 20
ALPHABET = 'ABCDEFGHIJKLMNOPQRSTUVWXYZ'
from sys import stdin, stderr
import argparse
parser = argparse.ArgumentParser(
description=__doc__,
formatter_class=argparse.ArgumentDefaultsHelpFormatter)
parser.add_argument('-i',
'--input',
required=False,
type=argparse.FileType('r'),
default=stdin,
help="Input FASTA")
args = parser.parse_args()
seqs = readFASTA(args.input)
map = {}
for key in seqs:
safe = ran_str(ALPHABET, K)
while safe in map:
safe = ran_str(ALPHABET, K)
map[safe] = key
print('>%s\n%s\n' % (safe, seqs[key]))
print(str(map), file=stderr)