#!/usr/bin/env
import sys
from seqio import iteratorFromExtension
from nucio import fileIterator
if not len(sys.argv) == 2:
sys.exit("sequencToLine.py in.{fa.fq}\n")
it = iteratorFromExtension(sys.argv[1])
for record in fileIterator(sys.argv[1], it):
if hasattr(record, "desc"):
print "\t".join([record.name, record.seq, record.desc, record.qual])
else:
print "\t".join([record.name, record.seq])
#!/usr/bin/env python
import sys
from seqio import iteratorFromExtension, recordToString
from nucio import fileIterator
from misc import reverse_complement
if not len(sys.argv) == 2:
sys.exit("reverseComplement.py in.{fa,fq}")
f = sys.argv[1]
for record in fileIterator(f,iteratorFromExtension(f)):
print recordToString(record._replace(seq=reverse_complement(record.seq)))
#Downsample a library
import sys
from nucio import typeify, fileIterator
from seqio import iteratorFromExtension, recordToString, seqlen
if not len(sys.argv) == 5:
sys.exit("Usage: downsample.py genome_size desired_cov input.{fa,fq} output.{fa,fq}\n")
types = [int, float, str, str]
sysins = sys.argv[1:len(types)+1]
(genome_size, target_cov, infn, outfn) = typeify(sysins,types)
max_bases = genome_size * target_cov
total_bases = 0
with open(outfn, "w") as of:
for record in fileIterator(infn,iteratorFromExtension(infn)):
length = seqlen(record)
if "N" in record.seq:
continue
if total_bases > max_bases:
break
of.write(recordToString(record))
of.write("\n")
total_bases += length
#!/usr/bin/env python
import sys
from itertools import imap
from seqio import iteratorFromExtension
from nucio import fileIterator
##Create Kmers
if not len(sys.argv) == 3:
sys.exit("Usage: kmer.py k-size in.fa\n")
fn = sys.argv[2]
ksize = int(sys.argv[1])
for record in fileIterator(fn, iteratorFromExtension(fn)):
seq = record.seq
starts = range(len(seq)-ksize+1)
kmers = imap(lambda start: seq[start:start+ksize], starts)
for kmer in kmers:
print kmer
