#!/usr/bin/python
import dnaseq
import bm_preproc
import kmer_index
human_chromosome = dnaseq.read_genome("chr1.GRCh38.excerpt.fasta")
def approximate_matches(p, t, index):
n = 2
matches = set()
total_hits = 0
for i in range(0, 24, 8):
pi = p[i:i+8]
hits = index.query(pi);
total_hits += len(hits)
for hit in hits:
if hit < i or hit - i + len(p) > len(t):
continue
missmatches = 0
for j in range(0, i):
if p[j] != t[hit - i + j]:
missmatches += 1
if missmatches > n:
break
for j in range(i + len(pi), len(p)):
if p[j] != t[hit - i + j]:
missmatches += 1
if missmatches > n:
break
if missmatches <= n:
#!/usr/bin/python
import dnaseq
import bm_preproc
import kmer_index
human_chromosome = dnaseq.read_genome("chr1.GRCh38.excerpt.fasta")
def approximate_matches(p, t, index):
n = 2
matches = set()
total_hits = 0
for i in range(0, 24, 8):
pi = p[i:i + 8]
hits = index.query(pi)
total_hits += len(hits)
for hit in hits:
if hit < i or hit - i + len(p) > len(t):
continue
missmatches = 0
for j in range(0, i):
if p[j] != t[hit - i + j]:
missmatches += 1
if missmatches > n:
break
for j in range(i + len(pi), len(p)):
if p[j] != t[hit - i + j]:
missmatches += 1
if missmatches > n:
break
#!/usr/bin/python
import dnaseq
lambda_virus = dnaseq.read_genome("lambda_virus.fa")
def question_01():
occurrences = dnaseq.naive_with_rc(lambda_virus, "AGGT")
print "question_01: %i" % len(occurrences)
def question_02():
occurrences = dnaseq.naive_with_rc(lambda_virus, "TTAA")
print "question_02: %i" % len(occurrences)
def question_03():
occurrences = dnaseq.naive_with_rc(lambda_virus, "ACTAAGT")
print "question_03: %i" % occurrences[0]
def question_04():
occurrences = dnaseq.naive_with_rc(lambda_virus, "AGTCGA")
print "question_04: %i" % occurrences[0]
def question_05():
occurrences = dnaseq.naive_approximate(lambda_virus, "TTCAAGCC", 2)
print "question_05: %i" % len(occurrences)
def question_06():
occurrences = dnaseq.naive_approximate(lambda_virus, "AGGAGGTT", 2)
print "question_06: %i" % occurrences[0]
def question_07():