def main_toBed(args):
def proc_func_toBed(hchr, hstr, hpos, hend, mchr, mstr, mpos, mend, m, s,
t, data):
htoken = '%s:%d_%d:%s' % (hchr, hpos, hend, hstr)
mtoken = '%s:%d_%d:%s' % (mchr, mpos, mend, mstr)
hp = []
mp = []
gaps = []
hp1 = 0
mp1 = 0
hgenome, mgenome = data
if hgenome:
hseq = hgenome.fetch_sequence(hchr, hpos, hend, uppercase=True)
if hstr == '-':
hseq = reverse_complement(hseq)
if mgenome:
mseq = mgenome.fetch_sequence(mchr, mpos, mend, uppercase=True)
if mstr == '-':
mseq = reverse_complement(mseq)
for i, m1 in enumerate(m):
wprint('\t'.join(
map(str, [
hchr, hpos + hp1 if hstr == '+' else hend - hp1 - m1,
hpos + hp1 + m1 if hstr == '+' else hend - hp1, htoken,
mchr, mpos + mp1 if mstr == '+' else hend - mp1 - m1,
mpos + mp1 + m1 if mstr == '+' else mend - mp1, mtoken
])))
if hseq and mseq:
hs = []
ms = []
for j in xrange(m1):
hb = hseq[hp1 + j]
mb = mseq[mp1 + j]
if hb == mb:
hs.append(MCHC + hb + ENDC)
ms.append(MCHC + mb + ENDC)
else:
hs.append(MISC + hb + ENDC)
ms.append(MISC + mb + ENDC)
wprint(''.join(hs))
wprint(''.join(ms))
hp1 += m1
mp1 += m1
if i != len(m) - 1:
hp1 += s[i]
mp1 += t[i]
import faidx
h_genome = faidx.RefGenome(args.g1) if args.g1 else None
m_genome = faidx.RefGenome(args.g2) if args.g2 else None
slice_chains(args.i, proc_func_toBed, (h_genome, m_genome))
def main(args):
ref = faidx.RefGenome(args.ref)
prev_chrm = None
prev_beg = None
prev_end = None
for line in args.bed:
fields = line.strip().split('\t')
chrm = fields[0]
beg = int(fields[1])
end = int(fields[2])
val = float(fields[3])
if chrm != prev_chrm or beg != prev_beg or end != prev_end:
if not prev_end is None:
print '\t'.join(map(str, [prev_chrm, prev_beg-1, prev_end, tval]))
tval = 0.0
if chrm != prev_chrm:
if not prev_end is None:
print '\t'.join(map(str, [prev_chrm, prev_end, ref.chrm2len(prev_chrm), 0]))
print '\t'.join(map(str, [chrm, 0, beg-1, 0]))
elif prev_end != beg-1:
print '\t'.join(map(str, [chrm, prev_end, beg-1, 0]))
if args.op == 'sum':
tval += val
prev_chrm = chrm
prev_beg = beg
prev_end = end
if prev_chrm is not None:
print '\t'.join(map(str, [prev_chrm, prev_beg-1, prev_end, tval]))
def __init__(self, window_queue, result_queue, winlen, vcf_path,
reference_path):
multiprocessing.Process.__init__(self)
self.window_queue = window_queue
self.result_queue = result_queue
self.reference = faidx.RefGenome(reference_path)
self.vcf = pysam.Tabixfile(vcf_path)
self.winlen = winlen
def main_CpH(args):
# processes = multiprocessing.cpu_count() - 2
num_processes = 25
if args.chrm:
chrms = [args.chrm]
else:
chrms = [
'chr1', 'chr2', 'chr3', 'chr4', 'chr5', 'chr6', 'chr7', 'chr8',
'chr9', 'chr10', 'chr11', 'chr12', 'chr13', 'chr14', 'chr15',
'chr16', 'chr17', 'chr18', 'chr19', 'chr20', 'chr21', 'chr22',
'chrX', 'chrY', 'chrM'
]
windows = multiprocessing.JoinableQueue()
results = multiprocessing.Queue()
consumers = []
for i in xrange(num_processes):
c = Consumer(windows, results, args.winlen, args.vcf, args.ref)
c.start()
consumers.append(c)
writer = Writer(results)
writer.start()
# create windows
r = faidx.RefGenome(args.ref)
for chrm in chrms:
chrmlen = r.faidx[chrm][0]
step = args.winlen
# start from the second base, since we are looking at binucleotides
for winbeg in xrange(2, chrmlen - args.winlen, step):
windows.put((chrm, winbeg))
# put poison pills
for i in xrange(num_processes):
windows.put(None)
# print 'before joining'
windows.join()
# print 'windows joined'
# consumers need to be joined so that
# the items put on the queue got flushed
for c in consumers:
c.join()
results.put(None)
writer.join()
# print 'writer joined'
return
def main_runningcomp(args):
""" export local composition at every base """
def compute_comp(seq):
return (seq.count('C'), seq.count('G'), len(seq) - seq.count('N'),
seq.count('CG'))
import faidx
genome = faidx.RefGenome(args.i)
out = open(args.o, 'w') if args.o is not None else sys.stdout
for chrm in genome.faidx:
if args.v:
err_print(chrm)
gseq = genome.fetch_chrmseq(chrm).upper()
if len(gseq) <= args.k * 2:
continue
c, g, n, cg = compute_comp(gseq[:args.k * 2])
for i in range(len(gseq) - args.k * 2):
b1 = gseq[i]
b2 = gseq[i + args.k * 2]
if b1 == 'N':
pass
elif b1 == 'C':
n -= 1
c -= 1
if gseq[i + 1] == 'G':
cg -= 1
elif b1 == 'G':
n -= 1
g -= 1
elif b1 == 'A' or b1 == 'T':
n -= 1
else:
raise Exception("Unknown base: %s" % b1)
if b2 == 'N':
pass
elif b2 == 'C':
n += 1
c += 1
elif b2 == 'G':
n += 1
g += 1
if gseq[i + args.k * 2 - 1] == 'C':
cg += 1
elif b2 == 'A' or b2 == 'T':
n += 1
else:
raise Exception('Unknown base: %s' % b2)
if i % args.s == 0:
out.write("%s\t%d\t%d\t%d\t%d\t%d\t%d\n" %
(chrm, i + args.k - 1, i + args.k, c, g, cg, n))
def main_comp(args):
import faidx, re
genome = faidx.RefGenome(args.i)
m = re.match(r'([^:]*):(\d+)-(\d+)', args.g)
chrm = m.group(1)
beg = int(m.group(2))
end = int(m.group(3))
seq = genome.fetch_sequence(chrm, beg, end, uppercase=True)
print('n:%d' % (end - beg))
print('C:%d' % seq.count('C'))
print('G:%d' % seq.count('G'))
print('CG:%d' % seq.count('CG'))
def load_te_and_seqs(
rmskbed='/Users/wandingzhou/projects/pj-mm/2015-04-23-alu/rmsk.bed.gz',
load_seq=False,
tetype=None,
tetype2=None,
tetype3=None):
refgenome = faidx.RefGenome('/Users/wandingzhou/references/hg19/hg19.fa')
tes = {}
wzcore.err_print_sig()
for i, line in enumerate(wzcore.opengz(rmskbed)):
if i % 100000 == 0:
wzcore.err_print_m(' %d' % i)
fields = line.strip().split('\t')
te = TE()
te.chrm = fields[0]
if te.chrm.find('_') > 0:
continue
te.beg = int(fields[1])
te.end = int(fields[2])
te.rmskbed = rmskbed
te.strand = fields[3]
te.tetype = fields[4]
te.tetype2 = fields[5]
te.tetype3 = fields[6]
if tetype is not None and te.tetype != tetype:
continue
if tetype2 is not None and te.tetype2 != tetype2:
continue
if tetype3 is not None and te.tetype3 != tetype3:
continue
if load_seq:
try:
_te_load_seqs(refgenome, te)
except IndexError: # TE at chromosome boundaries, ignore
# te.seq == None
pass
tes[(te.chrm, te.beg, te.end)] = te
wzcore.err_print_m('\n')
wzcore.err_print('Loaded %d TEs' % len(tes))
return tes
def main_icc(args):
""" incomplete conversion """
ref = faidx.RefGenome(args.ref)
refseq = ref.fetch_chrmseq('chrM')
bam = pysam.Samfile(args.bam)
n_inc = 0
n_com = 0
for x in bam.fetch(reference='chrM'):
# only consider primary alignment
if x.is_secondary:
continue
strand_tag = dict(x.tags)['ZS']
(nG2A, nC2T, nG2G, nC2C) = count_read_retention(x, refseq, args.m)
if strand_tag == '++' or strand_tag == '+-':
n_inc += nC2C
n_com += nC2T
else: # -+ or --
n_inc += nG2G
n_com += nG2A
if args.v:
if strand_tag in ['++', '+-'] and nC2C > 0:
print '\t'.join(
map(str, [
nC2C, (nC2C + nC2T),
float(nC2C) / (nC2C + nC2T), strand_tag, nC2C, nC2T,
nG2G, nG2A, x.qname, x.pos, x.tid, x.flag
]))
elif strand_tag in ['-+', '--'] and nG2G > 0:
print '\t'.join(
map(str, [
nG2G, (nG2G + nG2A),
float(nG2G) / (nG2G + nG2A), strand_tag, nC2C, nC2T,
nG2G, nG2A, x.qname, x.pos, x.tid, x.flag
]))
if not args.v:
print '\t'.join(
map(str,
[n_inc, n_com, float(n_inc) / (n_inc + n_com)]))
def te_load_seqs(tes):
refgenome = faidx.RefGenome('/Users/wandingzhou/references/hg19/hg19.fa')
tes2 = {}
if isinstance(tes, dict):
it = tes.itervalues()
else:
it = iter(tes)
for te in it:
try:
_te_load_seqs(refgenome, te)
except IndexError: # TE at chromosome boundaries, ignore
continue
tes2[(te.chrm, te.beg, te.end)] = te
return tes2
def main_getfasta(args):
import faidx
genome = faidx.RefGenome(args.f)
out = open(args.o, 'w') if args.o is not None else sys.stdout
for line in args.i:
fields = line.strip().split('\t')
# print(fields[0])
chrm = fields[0]
beg = int(fields[1])
end = int(fields[2])
try:
seq = genome.fetch_sequence(chrm, beg + 1, end)
except IndexError:
seq = "OVERFLOW"
out.write('%s\t%s\n' % (line.strip(), seq))
def load_cgi_and_seqs():
cgis = []
refgenome = faidx.RefGenome('/Users/wandingzhou/references/hg19/hg19.fa')
for line in wzcore.opengz(
'/Users/wandingzhou/projects/hs-tcga/data/2015_03_24_cpg_island/TakaiJones/takai.jones.strict.bed.gz'
):
fields = line.strip().split('\t')
cgi = CGI()
cgi.chrm = fields[0]
cgi.beg = int(fields[1])
cgi.end = int(fields[2])
cgi.cgitype = fields[3]
cgi.seq = refgenome.fetch_sequence(cgi.chrm, cgi.seq_beg(),
cgi.seq_end()).upper()
cgis.append(cgi)
wzcore.err_print('Loaded %d CGIs' % len(cgis))
return cgis
def tss_load_cpgdensity(tss_table):
d_upstream = 2500
d_downstream = 2500
poses = range(-d_upstream, d_downstream + 1)
import faidx
import numpy as np
import pandas as pd
refgenome = faidx.RefGenome('/Users/wandingzhou/references/hg19/hg19.fa')
_CpG_density = []
j = 0
for k, f in tss_table.iterrows():
chrm = f[0]
tss = f[1]
strand = f[2]
j += 1
# if j%1000 ==0:
# print j
if strand == "+":
d1 = d_upstream
d2 = d_downstream
else:
d1 = d_downstream
d2 = d_upstream
_cg = [np.nan] * (d1 + d2 + 1)
genome_seq = refgenome.fetch_sequence(chrm, tss - d1 - 200,
tss + d2 + 200).upper()
for i in xrange(d1 + d2 + 1):
seq = genome_seq[200 + i - 50:200 + i + 50]
if strand == '+':
_cg[i] = seq.count('CG')
else:
_cg[d1 + d2 - i] = seq.count('CG')
_CpG_density.append(_cg)
CpG_density = pd.DataFrame(_CpG_density,
index=tss_table.index,
columns=poses)
return CpG_density
def main_orphan(args):
import faidx
genome = faidx.RefGenome(args.i)
out = open(args.o, 'w') if args.o is not None else sys.stdout
for c in genome.faidx:
if args.v:
err_print(c)
gseq = genome.fetch_chrmseq(c)
prev = None
prev_is_good_left = True
for i in range(len(gseq) - 2):
if gseq[i] == 'C' and gseq[i + 1] == 'G':
if prev and prev_is_good_left and i - prev >= args.l:
tprint([c, prev, prev + 2, '+'], out)
if prev:
prev_is_good_left = i - prev >= args.l
prev = i
if prev_is_good_left and prev is not None:
tprint([c, prev, prev + 2, '+'], out)
def main_printc(args):
import faidx
genome = faidx.RefGenome(args.i)
out = open(args.o, 'w') if args.o is not None else sys.stdout
for c in genome.faidx:
if args.v:
err_print(c)
gseq = genome.fetch_chrmseq(c)
for i in range(len(gseq) - 2):
# for CG (symmetric), print the position of CG (2-bases)
if gseq[i] == 'C' and gseq[i + 1] == 'G':
tprint([c, i, i + 2, 'CG', '+', 'CG'], out)
# CHGs are assymetric
# for example, CCG is a CHG but its reverse complement CGG is not a CHG
if gseq[i] == 'C' and gseq[i + 1] != 'G' and gseq[i + 2] == 'G':
if gseq[i + 1] != 'N':
tprint([c, i, i + 1, 'CHG', '+', gseq[i:i + 3]], out)
if gseq[i] == 'C' and gseq[i + 1] != 'C' and gseq[i + 2] == 'G':
if gseq[i + 1] != 'N':
tprint([
c, i + 2, i + 3, 'CHG', '-',
reverse_complement(gseq[i:i + 3])
], out)
# for CHH, print the position of C
if gseq[i] == 'C' and gseq[i + 1] != 'G' and gseq[i + 2] != 'G':
if gseq[i + 1] != 'N' and gseq[i + 2] != 'N':
tprint([c, i, i + 1, 'CHH', '+', gseq[i:i + 3]], out)
if gseq[i] != 'C' and gseq[i + 1] != 'C' and gseq[i + 2] == 'G':
if gseq[i] != 'N' and gseq[i + 1] != 'N':
tprint([
c, i + 2, i + 3, 'CHH', '-',
reverse_complement(gseq[i:i + 3])
], out)
def main_one(args):
samrec = args.sam
ref = faidx.RefGenome(args.ref)
samfields = samrec.split()
# print samfields
chrm = samfields[2]
read = Read
read.pos = int(samfields[3]) - 1 # the raw sequence is 1-based, shift back
read.seq = samfields[9]
read.cigar = parse_cigar(samfields[5])
read.qname = samfields[0]
read.flag = int(samfields[1])
read.is_read1 = read.flag & 0x40
read.is_read2 = read.flag & 0x80
read.is_reverse = read.flag & 0x10
read.qual = samfields[10]
read.tags3 = [_tagstr.split(':') for _tagstr in samfields[11:]]
read.tags = [(_[0], _[2]) for _ in read.tags3]
print read.tags
refbeg = read.pos - 100 if read.pos > 100 else 1
refend = read.pos + len(read.seq) + 100
refseq = ref.fetch_sequence(chrm, refbeg, refend).upper()
rpos = read.pos - refbeg + 1
qpos = 0
flen = flank_len
if flen > rpos:
flen = rpos
op, oplen = read.cigar[0]
if op == 4:
pr_beg = rpos - flen - oplen
else:
pr_beg = rpos - flen
pp = pr = pq = pqual = ''
pp += " " * (rpos - pr_beg)
pr += rprint(refseq[pr_beg:rpos])
pq += ' ' * flen
pqual += ' ' * flen
pbis = ' ' * flen
for i, (op, clen) in enumerate(read.cigar):
if op == 0:
if pp.isspace():
pp += "|{}:{}".format(chrm, rpos + refbeg - 1)
pr += rprint(refseq[rpos:rpos + clen])
pq += qprint(read, qpos, qpos + clen, refseq, rpos)
pqual += qualprint(read, qpos, qpos + clen)
pbis += bsprint(read, qpos, qpos + clen, refseq, rpos)
rpos += clen
qpos += clen
elif op == 1:
pr += GAPC + '*' * clen + ENDC
pq += qprint(read, qpos, qpos + clen, refseq, rpos)
pqual += qualprint(read, qpos, qpos + clen)
pbis += bsprint(read, qpos, qpos + clen, refseq, rpos)
qpos += clen
elif op == 2:
pr += rprint(refseq[rpos:rpos + clen])
pq += GAPC + '*' * clen + ENDC
pqual += '*' * clen
pbis += '*' * clen
rpos += clen
elif op == 4:
pq += qprint(read, qpos, qpos + clen, refseq, rpos, UNDERLINE)
pqual += qualprint(read, qpos, qpos + clen)
pbis += bsprint(read, qpos, qpos + clen, refseq, rpos)
qpos += clen
else:
raise Exception("unknown cigar: %d" % op)
pr += rprint(refseq[rpos:rpos + flen])
print "\n" + "=" * 5 + read.qname + "=" * 5
print pp # position
print pr # reference
print pq # query sequence
print pbis # bisulfite mode
print pqual # quality
def main_bis(args):
samfile = pysam.Samfile(args.bam)
ref = faidx.RefGenome(args.ref)
read1seen = read2seen = False
for read in samfile.fetch(region=args.reg):
if read.qname != args.qname:
continue
chrm = samfile.getrname(read.tid)
refbeg = read.pos - 100 if read.pos > 100 else 1
refend = read.pos + len(read.seq) + 100
refseq = ref.fetch_sequence(chrm, refbeg, refend).upper()
rpos = read.pos - refbeg + 1
qpos = 0
flen = flank_len
if flen > rpos:
flen = rpos
op, oplen = read.cigar[0]
if op == 4:
pr_beg = rpos - flen - oplen
else:
pr_beg = rpos - flen
pp = pr = pq = pqual = ''
pp += " " * (rpos - pr_beg)
pr += rprint(refseq[pr_beg:rpos])
pq += ' ' * flen
pqual += ' ' * flen
if args.pbis: pbis = ' ' * flen
for i, (op, clen) in enumerate(read.cigar):
if op == 0:
if pp.isspace():
pp += "|{}:{}".format(chrm, rpos + refbeg - 1)
pr += rprint(refseq[rpos:rpos + clen])
pq += qprint(read, qpos, qpos + clen, refseq, rpos)
pqual += qualprint(read, qpos, qpos + clen)
if args.pbis:
pbis += bsprint(read, qpos, qpos + clen, refseq, rpos)
rpos += clen
qpos += clen
elif op == 1:
pr += GAPC + '*' * clen + ENDC
pq += qprint(read, qpos, qpos + clen, refseq, rpos)
pqual += qualprint(read, qpos, qpos + clen)
if args.pbis:
pbis += bsprint(read, qpos, qpos + clen, refseq, rpos)
qpos += clen
elif op == 2:
pr += rprint(refseq[rpos:rpos + clen])
pq += GAPC + '*' * clen + ENDC
pqual += '*' * clen
if args.pbis: pbis += '*' * clen
rpos += clen
elif op == 4:
pq += qprint(read, qpos, qpos + clen, refseq, rpos, UNDERLINE)
pqual += qualprint(read, qpos, qpos + clen)
if args.pbis:
pbis += bsprint(read, qpos, qpos + clen, refseq, rpos)
qpos += clen
else:
raise Exception("unknown cigar: %d" % op)
pr += rprint(refseq[rpos:rpos + flen])
print "\n" + "=" * 5 + read.qname + "=" * 5
print pp
print pr
print pq
print pqual
if args.pbis: print pbis
if args.pread:
print str(read)
if read.is_read1: read1seen = True
if read.is_read2: read2seen = True
if args.pair == '12' and read1seen and read2seen:
break
elif args.pair == '1' and read1seen:
break
elif args.pair == '2' and read2seen:
break
elif args.pair == '0':
break
def __init__(self,
genome, # faidx.RefGenome
cytoband=None,
angle_beg=0, angle_end=360,
angle_chrm_space=0.05, inner_radius=98, outer_radius=101,
angle_inc=0.01, # when plotting an arc, this is the increment
bezier_anchor = 15.0, # higher the number the higher the peak
track_height = 10,
track_space = 1,
fontname = 'Arial',
):
if angle_end - angle_beg == 360:
self.full_circle = True
else:
self.full_circle = False
genome_path = genome
if isinstance(genome, str):
genome = faidx.RefGenome(genome)
if isinstance(genome, list):
chrms = genome
else:
chrms = getsortedchrms(genome)
if cytoband:
# if re.search('mm10', genome_path) is not None:
# self.cytoband_table = pd.read_table(
# cytoband, header=None,
# names=['_','chrm','band','band2','beg','end','bandtype'])[['chrm','beg','end','bandtype']]
# elif re.search('hg38', genome_path) is not None:
self.cytoband_table = pd.read_table(
cytoband, header=None,
names=['chrm','beg','end','band','bandtype'])[['chrm','beg','end','bandtype']]
else:
self.cytoband_table = None
self.chrms = [_[0] for _ in chrms]
self.chrms_plot = self.chrms[:] # plot all by default
self.chrm2len = dict(chrms)
self.chrm2angles = {}
## plot parameters
self.angle_beg = angle_beg / 180.0 * np.pi
self.angle_end = angle_end / 180.0 * np.pi
self.angle_chrm_space = angle_chrm_space # space between chromosomes
self.inner_radius = inner_radius
self.outer_radius = outer_radius
self.angle_inc = angle_inc
self.bezier_anchor = bezier_anchor
self.ax = None
self.fontname = fontname
self.track_height = track_height
self.track_space = track_space
## derived parameters
self.connect_radius = inner_radius*0.95
# self.ax_radius = self.outer_radius*1.05
self.inner_track_outer_radius = self.inner_radius - self.track_space
self.inner_track_inner_radius = self.inner_track_outer_radius - self.track_height
self.outer_track_inner_radius = self.outer_radius + self.track_space
self.outer_track_outer_radius = self.outer_track_inner_radius + self.track_height
self.tracks = []
return
def main_mutation(args):
""" generate genome with mutation from a mutation list """
genome = faidx.RefGenome(args.genome)
fmut = open(args.prefix + '/mutations.tsv', 'w')
for chrm in genome.faidx.keys(): # process each chromosome
print(chrm)
chrmseq = list(genome.fetch_chrmseq(chrm))
original = range(len(chrmseq))
deletion = [False] * len(chrmseq)
insertion = [''] * len(chrmseq)
# sample SNP
nmut = int(args.m * len(chrmseq))
print("sampling %d SNPs" % nmut)
i = 0
for coord in random.sample(original, 2 * nmut):
if i >= nmut:
break
source = chrmseq[coord]
if source == 'N':
continue
target = random.choice(
[_ for _ in ['A', 'C', 'G', 'T'] if _ != chrmseq[coord]])
fmut.write('%s\t%d\t%d\t%s\t%s\tSNP\n' %
(chrm, coord, coord + 1, source, target))
chrmseq[coord] = target
i += 1
# sample insertion
nIns = int(args.i * len(chrmseq) / 2)
print("sampling %d insertion" % nIns)
lambdaIns = 1
lenIns = numpy.random.poisson(lambdaIns, nIns) + 1
i = 0
for coord in random.sample(original, 2 * nIns):
if i >= nIns:
break
if insertion[coord] != '': # already have insertion
continue
source = chrmseq[coord]
if source == 'N':
continue
insertion[coord] = ''.join(
numpy.random.choice(['A', 'T', 'C', 'G'], lenIns[i]))
fmut.write(
'%s\t%d\t%d\t%s\t%s\tINS\n' %
(chrm, coord, coord + 1, source, source + insertion[coord]))
i += 1
# sample deletion
nDel = int(args.i * len(chrmseq) / 2)
print("sampling %d deletions" % nDel)
lambdaDel = 1
lenDel = numpy.random.poisson(lambdaDel, nDel) + 1
i = 0
for coord in random.sample(original, 2 * nDel):
if i >= nDel:
break
source = chrmseq[coord]
if source == 'N':
continue
toDelete = True
for j in xrange(lenDel[i]):
if insertion[coord + j] != '' or deletion[
coord + j]: # avoid mixing insertion with deletion
toDelete = False
if not toDelete:
continue
delSeq = ''.join(
[chrmseq[coord + j + 1] for j in xrange(lenDel[i])])
for j in xrange(lenDel[i]):
deletion[coord + j + 1] = True
fmut.write(
'%s\t%d\t%d\t%s\t%s\tDEL\n' %
(chrm, coord, coord + lenDel[i] + 1, source + delSeq, source))
i += 1
chrmseq1 = ''.join([(b + insertion[i]) if insertion[i] != '' else b
for i, b in enumerate(chrmseq) if not deletion[i]])
coords = []
for i, b in enumerate(chrmseq):
if not deletion[i]:
coords.append(i)
if insertion[i] != '':
coords.extend([-1] * len(insertion[i]))
# the original coordinates
dump(coords, open(args.prefix + '/' + chrm + '.coords.pkl', 'w'))
# chromseq
# chrmseq0 = ''.join(chrmseq)
dump(chrmseq1, open(args.prefix + '/' + chrm + '.chrmseq.pkl', 'w'))
fmut.close()
import wzcore
import faidx
refgenomehg19 = faidx.RefGenome('/Users/zhouw3/references/hg19/hg19.fa')
class GeneticElement(object):
def __init__(self, flank=1000, flank1=None, flank2=None):
self.flank1 = flank # upstream (gene order)
self.flank2 = flank # downstream (gene order)
if flank1:
self.flank1 = flank1
if flank2:
self.flank2 = flank2
def __len__(self):
return self.end - self.beg
def __repr__(self):
return '<Element: %s:%d-%d>' % (self.chrm, self.beg, self.end)
def rep_coord(self):
return '%s:%d-%d' % (self.chrm, self.beg, self.end)
def seq_beg(self):
""" note that beg, end, seq_beg(), seq_end() are all in reference coordinates """
if self.strand == '+':
return self.beg - self.flank1
else: