def moving_win(chromosome, chrlength, winlength, k):
#chro = getWhole(chromosome)
winstart = 0
winend = winlength
out = "winS winE dist AT\n"
mdict = getMito(k)
seq = 'temp'
while chrlength - winstart > winlength:
seq = k_genes.get_sequence(winstart, winend, chromosome)
N_count = seq.count('N')
#print(N_count)
kmers = kmer_distr.kmer_distr(seq, k)
#print(kmers)
dist = findDist(mdict, kmers)
toAdd = str(winstart) + " " + str(winend) + " " + str(dist) + " "
#only mito hard code because ugh
# if winstart == 640000 or winstart == 239456000 or winstart == 241904000:
#print(len(seq) - N_count)
leng = len(seq)
if leng - N_count != 0:
toAdd += str(
bpcontent.findATcontent(seq) / ((leng - N_count) * 1.0)) + '\n'
# else:
# toAdd += "NA\n"
print(toAdd)
if N_count < 100:
out += toAdd
winstart = winend
winend = winstart + winlength
return out
def getRMito(k):
source = open(GOLDEN_PATH_DIR + "Homo_sapiens.GRCh38.dna.chromosome.MT.fa",
'rU')
m = combine_second_strand.secondStrand(k_genes.get_sequence(
1, 16569, 'MT'))
#print(m)
return create_kmers(m, k, True)
def marKer(k, chrocomp):
mit = getMito(k)
LMito = []
for key in mit:
if mit[key] > 0.01:
LMito.append(key)
print(LMito)
start = 0
end = 3000
LPos = []
leng = len(getWhole(chrocomp))
while end < leng:
count = 0
seq = k_genes.get_sequence(start, end, chrocomp)
for mer in LMito:
if seq.find(mer) != -1:
count += 1
print(count)
print(start)
if count > 5:
LPos.append(start)
start += 1500
end += 1500
return LPos
def comp_mit(chromosome, chrlength, winlength, k):
winstart = 0
winend = winlength
out = "winS winE dist strand\n"
mf = getMito(k)
mr = getRMito(k)
while chrlength - winstart > winlength:
shortstep = False
seq = k_genes.get_sequence(winstart, winend, chromosome)
kmers = create_kmers(seq, k)
#print(kmers)
# if len(kmers) < 10:
# dist = -1
#else:
distF = findDist(kmers, mf)
distR = findDist(kmers, mr)
if distF <= distR:
if distF < 3:
shortstep = True
toAdd = str(winstart) + " " + str(winend) + " " + str(
distF) + " +\n"
else:
if distR < 3:
shortstep = True
toAdd = str(winstart) + " " + str(winend) + " " + str(
distR) + ' -\n'
#print(toAdd)
if seq.count('N') < 100:
out += toAdd
if shortstep == True:
winstart += winlength / 10
winend += winlength / 10
else:
winstart += winlength / 2
winend += winlength / 2
return out
def getMito(k):
source = open(GOLDEN_PATH_DIR + "Homo_sapiens.GRCh38.dna.chromosome.MT.fa",
'rU')
m = k_genes.get_sequence(1, 16569, 'MT')
return create_kmers(m, k, True)