out.append(copy.deepcopy(ranges[i]))
return out
rfh = open(sys.argv[1])
sfh = open(sys.argv[2])
afh = open(sys.argv[3])
pout = open(sys.argv[6] +".cor.pileup", "w")
corout = open(sys.argv[6] +".cor.fa", "w")
alignment_it = lineRecordIterator(afh, NucRecord, NucRecordTypes)
snp_it = lineRecordIterator(sfh, NucSNPRecord, NucSNPRecordTypes)
reads = dict(map(lambda r : (str(r.name), str(r.seq)), fastaIterator(rfh)))
alignments = dict(map(lambda (n,a): (n,list(a)),
groupby(alignment_it, lambda x: x.sname)))
for pbname, snp_entries in groupby(snp_it, lambda x: x.sname):
warnings = []
pblen = len(reads[pbname])
##no alignments for this pb read
if pbname not in alignments:
continue
##create ranges of accepted alignments
accept_alignment_ranges = [None] * pblen
#alignments[pbname].sort(key=lambda a: (a.send-a.sstart) * pow(a.pctid/100.0,2))
alignments[pbname].sort(key=lambda a: (a.send-a.sstart))
for alignment in alignments[pbname]:
out.append(copy.deepcopy(ranges[i]))
return out
rfh = open(sys.argv[1])
sfh = open(sys.argv[2])
afh = open(sys.argv[3])
pout = open(sys.argv[6] +".cor.pileup", "w")
corout = open(sys.argv[6] +".cor.fa", "w")
alignment_it = lineRecordIterator(afh, NucRecord, NucRecordTypes)
snp_it = lineRecordIterator(sfh, NucSNPRecord, NucSNPRecordTypes)
reads = dict(map(lambda r : (str(r.name), str(r.seq)), fastaIterator(rfh)))
alignments = dict(map(lambda (n,a): (n,list(a)),
groupby(alignment_it, lambda x: x.sname)))
for pbname, snp_entries in groupby(snp_it, lambda x: x.sname):
warnings = []
pblen = len(reads[pbname])
##no alignments for this pb read
if pbname not in alignments:
continue
##create ranges of accepted alignments
accept_alignment_ranges = [None] * pblen
#alignments[pbname].sort(key=lambda a: (a.send-a.sstart) * pow(a.pctid/100.0,2))
alignments[pbname].sort(key=lambda a: (a.send-a.sstart))
for alignment in alignments[pbname]:
print "partition.py <reads_per_file (int)> <files_per_dir (int)> <input.fa>"
sys.exit(1)
def pstr(num):
return "%04d" % num
rpf = int(sys.argv[1])
fpd = int(sys.argv[2])
fa_fh = open(sys.argv[3])
total_reads = 0
dnum = 0
fnum = 0
fh = None
readidx_fh = open("ReadIndex.txt", "w")
for record in fastaIterator(fa_fh):
if total_reads % rpf == 0:
if total_reads % (rpf * fpd) == 0:
dnum += 1
fnum = 0
os.mkdir(pstr(dnum))
fnum += 1
if fh:
fh.close()
current_file ="%s/p%s" % (pstr(dnum),pstr(fnum))
fh = open(current_file, "w")
readidx_fh.write(str(record.name) +"\t" + current_file + "\n")
fh.write(">"+str(record.name)+"\n")
fh.write(str(record.seq)+"\n")
GC_WINDOW_SIZE = 300
GC_THRESHOLD = 0.7
MIN_COV_GAP = 100
if not len(sys.argv) == 4:
print "gc_count.py reads.fa alignments.sc outprefix"
sys.exit(1)
rfh = open(sys.argv[1])
afh = open(sys.argv[2])
ofh = open(sys.argv[3]+".uncov.gc.bases","w")
reads = {}
for entry in fastaIterator(rfh):
reads[str(entry.name)] = str(entry.seq)
sys.stderr.write("Loaded reads\n")
alignmentIt = getNucmerAlignmentIterator(afh)
sys.stderr.write("Loaded Alignments\n");
counter = 0
for name,group in groupby(alignmentIt, lambda x: x.sname):
#build coverage vector
cov = getCoverageFromNucAlignments(group)
#mark the regions with 0 (no) coverage as 1 and change
#everything else to 0
#!/usr/bin/env python
import sys
from seqio import fastaIterator
if not len(sys.argv) == 2:
print "qualgen.py read.fa"
sys.exit(1)
reads = sys.argv[1]
with open(reads) as rfh:
for record in fastaIterator(rfh):
print ">"+str(record.name)
print " ".join(["60"]*len(record.seq))
#!/usr/bin/env python
import sys
from seqio import fastaIterator
if not len(sys.argv) == 2:
print "qualgen.py read.fa"
sys.exit(1)
reads = sys.argv[1]
with open(reads) as rfh:
for record in fastaIterator(rfh):
print ">" + str(record.name)
print " ".join(["60"] * len(record.seq))
#read.lens is just a file with a list of read lengths
if not len(sys.argv) == 5:
print "pb_sim.py genome.fa read.lens error_rate out_prefix"
sys.exit(1)
Chromosome = namedtuple("Chromosome", ["name","seq"])
gfh = open(sys.argv[1])
lfh = open(sys.argv[2])
erate = float(sys.argv[3])
rout = open(sys.argv[4]+".sim.fa", "w")
#read genome into mem
chromosomes = map(lambda r: Chromosome._make((str(r.name),str(r.seq))), fastaIterator(gfh))
chrom_lengths = map(lambda c: len(c.seq), chromosomes)
genome_length = sum(chrom_lengths)
chrom_lengths_ivtf = map(misc.accumulator(0), map(lambda x: float(x)/genome_length , chrom_lengths))
count = 0
for l in lfh:
#length of read to simulate
readlen = int(l.strip())
while True:
#choose a chromosome
U_c = random.random()
chr_idx = misc.first_idx(lambda x : x > U_c, chrom_lengths_ivtf)
chromosome = chromosomes[chr_idx]
chromosome_len = chrom_lengths[chr_idx]
GC_WINDOW_SIZE = 300
GC_THRESHOLD = 0.7
MIN_COV_GAP = 100
if not len(sys.argv) == 4:
print "gc_count.py reads.fa alignments.sc outprefix"
sys.exit(1)
rfh = open(sys.argv[1])
afh = open(sys.argv[2])
ofh = open(sys.argv[3] + ".uncov.gc.bases", "w")
reads = {}
for entry in fastaIterator(rfh):
reads[str(entry.name)] = str(entry.seq)
sys.stderr.write("Loaded reads\n")
alignmentIt = getNucmerAlignmentIterator(afh)
sys.stderr.write("Loaded Alignments\n")
counter = 0
for name, group in groupby(alignmentIt, lambda x: x.sname):
#build coverage vector
cov = getCoverageFromNucAlignments(group)
#mark the regions with 0 (no) coverage as 1 and change
#everything else to 0
