def lcsq():
recs = rosalind_utils.read_fasta("rosalind_lcsq.txt")
seqa, seqb = recs[0][1], recs[1][1]
# return the set of all longest common subsesquences
C = rosalind_utils.lcsq(seqa, seqb)
print rosalind_utils.lcsq_len(C)
print rosalind_utils.lcsq_backtrack(C, seqa, seqb, len(seqa), len(seqb))
def kmer():
seq = rosalind_utils.read_fasta("rosalind_kmer.txt")[0][1]
rev_comp = rosalind_utils.reverse_complement(seq)
for mer in itertools.product("ACGT", repeat=4):
s = ''.join(mer)
print overlapping_count(seq, s, 0),
print ""
def lcsq():
recs = rosalind_utils.read_fasta("rosalind_lcsq.txt")
seqa, seqb = recs[0][1], recs[1][1]
# return the set of all longest common subsesquences
C = rosalind_utils.lcsq(seqa, seqb)
print rosalind_utils.lcsq_len(C)
print rosalind_utils.lcsq_backtrack(C, seqa, seqb, len(seqa), len(seqb))
def gc():
records = rosalind_utils.read_fasta("rosalind_gc.txt")
gc_contents = [(desc, rosalind_utils.gc_content(seq))
for desc, seq in records]
max_gc_content = max(gc_contents, key=lambda x: x[1])
print max_gc_content[0]
print max_gc_content[1] * 100
def kmer():
seq = rosalind_utils.read_fasta("rosalind_kmer.txt")[0][1]
rev_comp = rosalind_utils.reverse_complement(seq)
for mer in itertools.product("ACGT", repeat=4):
s = ''.join(mer)
print overlapping_count(seq, s, 0),
print ""
def pmch():
seq = rosalind_utils.read_fasta("rosalind_pmch.txt")[0][1]
#seq = "AGCUAGUCAU"
num_a = seq.count('A')
num_g = seq.count('G')
#print num_possible_matchings(num_a)
#print num_possible_matchings(num_g)
return num_possible_matchings(num_a) * num_possible_matchings(num_g)
def grph():
k = 3
recs = rosalind_utils.read_fasta("rosalind_grph.txt")
for ena in recs:
for enb in recs:
if ena == enb: continue
if ena[1][-k:] == enb[1][:k]:
print ena[0], enb[0]
def pmch():
seq = rosalind_utils.read_fasta("rosalind_pmch.txt")[0][1]
#seq = "AGCUAGUCAU"
num_a = seq.count('A')
num_g = seq.count('G')
#print num_possible_matchings(num_a)
#print num_possible_matchings(num_g)
return num_possible_matchings(num_a) * num_possible_matchings(num_g)
def grph():
k = 3
recs = rosalind_utils.read_fasta("rosalind_grph.txt")
for ena in recs:
for enb in recs:
if ena == enb: continue
if ena[1][-k:] == enb[1][:k]:
print ena[0], enb[0]
def revp():
# get the sequence of the only entry
seq = rosalind_utils.read_fasta("rosalind_revp.txt")[0][1]
for l in xrange(4, 13):
# find all reverse palindromes of length l
for i in range(len(seq) - l + 1):
# if reverse palindrome, report the position and length
if seq[i:i + l] == rosalind_utils.reverse_complement(seq[i:i + l]):
print i + 1, l
def sseq():
recs = rosalind_utils.read_fasta("rosalind_sseq.txt")
s = recs[0][1]
t = recs[1][1]
last_index = 0
# assuming t is a substring of s (not necessarily contiguously)
for tlet in t:
idx = s[last_index:].find(tlet)
print last_index + idx + 1,
last_index += idx + 1
print ""
def splc():
recs = rosalind_utils.read_fasta("rosalind_splc.txt")
seqs = [rec[1] for rec in recs]
exon = seqs[0]
introns = sorted(seqs[1:], key=lambda (s): len(s), reverse=True)
#print introns
for intron in introns:
exon = exon.replace(intron, "", 1)
prot = rosalind_utils.translate(rosalind_utils.transcribe(exon))
return prot[:-1]
def splc():
recs = rosalind_utils.read_fasta("rosalind_splc.txt")
seqs = [rec[1] for rec in recs]
exon = seqs[0]
introns = sorted(seqs[1:], key=lambda(s): len(s), reverse=True)
#print introns
for intron in introns:
exon = exon.replace(intron, "", 1)
prot = rosalind_utils.translate(rosalind_utils.transcribe(exon))
return prot[:-1]
def long():
# recs contain the list of tuples (desc, sequence)
recs = rosalind_utils.read_fasta("rosalind_long.txt")
next = {}
for reca in recs:
for recb in recs:
if reca == recb: continue
min_overlap_req = min(len(seq(reca)), len(seq(recb)))
if overlap(seq(reca), seq(recb)) > min_overlap_req / 2:
next[reca] = recb
# find the starting string (the one that has not in next.values())
sub = head([rec for rec in recs if rec not in next.values()])
merged = seq(sub)
while sub in next:
overlap_len = overlap(seq(sub), seq(next[sub]))
merged += seq(next[sub])[overlap_len:]
sub = next[sub]
print merged
def cons():
# read sequences
recs = rosalind_utils.read_fasta("rosalind_cons.txt")
seqs = [rec[1] for rec in recs]
matrix = []
for i in xrange(len(seqs[0])):
d = {'A': 0, 'C': 0, 'G': 0, 'T': 0}
for seq in seqs:
d[seq[i]] += 1
matrix.append(d)
# print consensus
consensus = ''.join(
max(col.iteritems(), key=operator.itemgetter(1))[0] for col in matrix)
print consensus
# print matrix
print 'A:', ' '.join(str(col['A']) for col in matrix)
print 'C:', ' '.join(str(col['C']) for col in matrix)
print 'G:', ' '.join(str(col['G']) for col in matrix)
print 'T:', ' '.join(str(col['T']) for col in matrix)
def cons():
# read sequences
recs = rosalind_utils.read_fasta("rosalind_cons.txt")
seqs = [rec[1] for rec in recs]
matrix = []
for i in xrange(len(seqs[0])):
d = {'A':0, 'C':0, 'G':0, 'T':0}
for seq in seqs:
d[seq[i]] += 1
matrix.append(d)
# print consensus
consensus = ''.join(max(col.iteritems(), key=operator.itemgetter(1))[0]
for col in matrix)
print consensus
# print matrix
print 'A:', ' '.join(str(col['A']) for col in matrix)
print 'C:', ' '.join(str(col['C']) for col in matrix)
print 'G:', ' '.join(str(col['G']) for col in matrix)
print 'T:', ' '.join(str(col['T']) for col in matrix)
def tran():
recs = rosalind_utils.read_fasta("rosalind_tran.txt")
seqs = [rec[1] for rec in recs]
purines = "AG"
pyrimidines = "CT"
transition = 0
transversion = 0
for a,b in zip(seqs[0], seqs[1]):
if a==b:
continue
elif ((a in purines and b in purines) or
(a in pyrimidines and b in pyrimidines)):
transition += 1
else:
transversion += 1
return float(transition) / transversion
def tran():
recs = rosalind_utils.read_fasta("rosalind_tran.txt")
seqs = [rec[1] for rec in recs]
purines = "AG"
pyrimidines = "CT"
transition = 0
transversion = 0
for a, b in zip(seqs[0], seqs[1]):
if a == b:
continue
elif ((a in purines and b in purines)
or (a in pyrimidines and b in pyrimidines)):
transition += 1
else:
transversion += 1
return float(transition) / transversion
def gc():
records = rosalind_utils.read_fasta("rosalind_gc.txt")
gc_contents = [(desc, rosalind_utils.gc_content(seq)) for desc,seq in records]
max_gc_content = max(gc_contents, key=lambda x: x[1])
print max_gc_content[0]
print max_gc_content[1]*100
def pdst():
recs = rosalind_utils.read_fasta("rosalind_pdst.txt")
for reca in recs:
for recb in recs:
print p_distance(reca[1], recb[1]),
print ""
def pdst():
recs = rosalind_utils.read_fasta("rosalind_pdst.txt")
for reca in recs:
for recb in recs:
print p_distance(reca[1], recb[1]),
print ""