f2 = os.popen('samtools faidx ' + refname + ' ' + rname + ':' +
str(pos) + '-' + str(pos + len(aligned_read) - 1))
aligned_ref = ''.join([line2.rstrip('\n') for line2 in f2][1:])
f2.close()
positions = range(pos, pos + len(aligned_ref))
# reverse complement
if reverse_flag:
aligned_read = str(Seq(aligned_read).reverse_complement())
aligned_ref = str(Seq(aligned_ref).reverse_complement())
aligned_quality = aligned_quality[::-1]
positions = positions[::-1]
hs_all, hd_all = homodist(aligned_ref)
# index into the read to get this position
siteindex = positions.index(i)
ref = aligned_ref[siteindex]
if not true and not reverse_flag:
true = ref
call = aligned_read[siteindex]
hs = hs_all[siteindex]
hd = hd_all[siteindex]
q = aligned_quality[siteindex]
# q = ord(aligned_quality[siteindex]) - 33
if call == '-':
continue
#!/bin/python
# generates homopolymer pickle based on reference fasta (presumably from a single amplicon)
# this script generates the homopolymer data corresponding to a fasta (only one region ">" line)
import sys, pickle, re
from covariatefuncs import homodist
fasta = sys.argv[1]
homoout = sys.argv[2]
lines = open(fasta, 'r').readlines()
chr, start, end = re.split('[> : -]', lines[0][1:])
fullfasta = ''.join(lines[1:]).replace('\n', '')
outdict = {}
keys = [chr+':'+str(x) for x in range(int(start), int(end) + 1)]
for pos in range(len(fullfasta)):
outdict[keys[pos]] = {'forward':homodist(fullfasta)[pos], 'reverse':homodist(fullfasta[::-1])[-pos-1]}
pickle.dump(outdict, open(homoout, 'w'))
#!/bin/python
# generates homopolymer pickle based on reference fasta (presumably from a single amplicon)
# this script generates the homopolymer data corresponding to a fasta (only one region ">" line)
import sys, pickle, re
from covariatefuncs import homodist
fasta = sys.argv[1]
homoout = sys.argv[2]
lines = open(fasta, 'r').readlines()
chr, start, end = re.split('[> : -]', lines[0][1:])
fullfasta = ''.join(lines[1:]).replace('\n', '')
outdict = {}
keys = [chr + ':' + str(x) for x in range(int(start), int(end) + 1)]
for pos in range(len(fullfasta)):
outdict[keys[pos]] = {
'forward': homodist(fullfasta)[pos],
'reverse': homodist(fullfasta[::-1])[-pos - 1]
}
pickle.dump(outdict, open(homoout, 'w'))
aligned_ref = ''.join([line.rstrip('\n') for line in f][1:])
f.close()
# reverse complement
if reverse_flag:
aligned_read = Seq(aligned_read).reverse_complement();
aligned_ref = Seq(aligned_ref).reverse_complement();
aligned_quality = aligned_quality[::-1];
# ignore deletions from ref (insertions were removed by cigar2align)
# dels = aligned_read ~= '-';
# aligned_read = aligned_read(dels);
# aligned_ref = aligned_ref(dels);
# aligned_quality = aligned_quality(dels);
# pos = pos(dels);
# compute the error pattern variables
GC = (aligned_ref.count('G') + aligned_ref.count('C'))/float(len(aligned_ref))
hs, hd = homodist(str(aligned_ref))
readlen = len(seq)
for i in range(len(aligned_read)):
if aligned_read[i] == '-': continue
#region = rname[3:]+':'+str(pos[i])+'-'+str(pos[i])
#f = os.popen('/ifs/scratch/c2b2/ngs_lab/sz2317/bin/src/tabix-0.2.5/tabix /ifs/scratch/c2b2/ngs_lab/ngs/Projects/IonTorrent/will/xunhai/covariate_table/dbSNP132b37.vcf.gz '+region)
#if f.readline() == '':
out.write('\t'.join(map(str,[rname, pos[i], aligned_ref[i], aligned_read[i], readlen, int(reverse_flag), aligned_quality[i], pos[i], hs[i], hd[i], GC]))+'\n')
#f.close()
out.close()
aligned_read, aligned_quality = aligned_data[regionindex].split()
f2 = os.popen('samtools faidx '+refname+' '+rname+':'+str(pos)+'-'+str(pos + len(aligned_read) - 1))
aligned_ref = ''.join([line2.rstrip('\n') for line2 in f2][1:])
f2.close()
positions = range(pos, pos + len(aligned_ref))
# reverse complement
if reverse_flag:
aligned_read = str(Seq(aligned_read).reverse_complement());
aligned_ref = str(Seq(aligned_ref).reverse_complement());
aligned_quality = aligned_quality[::-1];
positions = positions[::-1]
hs_all, hd_all = homodist(aligned_ref)
# index into the read to get this position
siteindex = positions.index(i)
ref = aligned_ref[siteindex]
if not true and not reverse_flag:
true = ref
call = aligned_read[siteindex]
hs = hs_all[siteindex]
hd = hd_all[siteindex]
q = aligned_quality[siteindex]
# q = ord(aligned_quality[siteindex]) - 33
if call == '-':
continue