from sequence import rev_complement
from fastamasta import FastaReader
from functional import partition
if __name__ == "__main__":
seq = [i for i in FastaReader("data/44.fas")][0][1]
rev_palindromes = []
for i in range(4, 13):
parts = [''.join(x) for x in partition(seq, i, list)]
for j in range(len(parts)):
if parts[j] == rev_complement(parts[j]):
rev_palindromes.append((j + 1, i))
for tup in rev_palindromes:
print tup[0], tup[1]
from fastamasta import FastaReader
from functional import partition
if __name__ == "__main__":
data = []
for datum in FastaReader("data/21.fas"):
data.append(datum[1])
shortest = ' ' * 1001
for i in data:
if len(i) < len(shortest):
shortest = i
data.remove(shortest)
print data
for i in range(2, len(shortest) + 1)[::-1]:
parts = [i for i in partition(shortest, i, str)]
for part in parts:
in_all = True
for datum in data:
if part not in datum:
in_all = False
break
if in_all:
print part
from aaiter import find_orfs
from fastamasta import FastaReader
from sequence import translate, rev_complement
if __name__ == "__main__":
reader = FastaReader("data/12.dat")
seq = reader.readnext()[1]
rcseq = rev_complement(seq)
orfs = find_orfs(seq)
rorfs = find_orfs(rcseq)
candidates = set()
for orf in orfs:
candidates.add(translate(seq[orf[0]:orf[1]]))
for rorf in rorfs:
candidates.add(translate(rcseq[rorf[0]:rorf[1]]))
for candidate in candidates:
print candidate
from fastamasta import FastaReader
from functional import frequencies
if __name__ == '__main__':
fr = FastaReader('data/6.fas')
hi_gc_content = ('', 0.0)
while True:
current = fr.readnext()
if current == None:
break
sym_count = frequencies(current[1])
curr_gc_content = float(sym_count['C'] + sym_count['G']) / float(
len(current[1]))
if curr_gc_content > hi_gc_content[1]:
hi_gc_content = (current[0], curr_gc_content)
print hi_gc_content[0]
print round(hi_gc_content[1] * 100, 6)
from Bio import pairwise2
from Bio.SubsMat.MatrixInfo import blosum62
from fastamasta import FastaReader
if __name__ == "__main__":
data = [i[1] for i in FastaReader("data/35.fas")]
for i in pairwise2.align.globalds(data[0], data[1], blosum62, -11, -1):
print int(i[2])
print i[0]
print i[1]
break
from fastamasta import FastaReader
if __name__ == "__main__":
seq = FastaReader("data/22.fas").readnext()[1]
fail_arr = [0] * len(seq)
for i in range(1, len(seq)):
j = fail_arr[i-1]
while (j > 0) and seq[i] != seq[j]:
j = fail_arr[j-1]
if (seq[i] == seq[j]):
j += 1
fail_arr[i] = j
for i in fail_arr:
print i,
from functional import partition, frequencies
from fastamasta import FastaReader
def alphabet(order, length, string='', arr=None):
if arr is None:
arr=[]
if length == 0:
arr.append(string)
else:
for char in order:
alphabet(order, length-1, string + char, arr)
return arr
if __name__ == "__main__":
with open("data/13.dat", 'r') as data_file:
reader = FastaReader('data/14.dat')
data = reader.readnext()
order, size = ['A', 'C', 'G', 'T'], 4
alph = alphabet(order, size)
fourmer_count = frequencies(partition(data[1], size, str))
output = ''
for word in alph:
output += str(fourmer_count.get(word, 0)) + ' '
print output
from fastamasta import FastaReader
from sequence import edit_dist
if __name__ == "__main__":
data = [i for i in FastaReader("data/30.fas")]
a, b = data[0][1], data[1][1]
print edit_distance(a, b)