argument_list = [["maxlen", "maxlen", int, -1, "Maximum length of reads"]]
arguments = map(CLArgument._make, argument_list)
if not len(sys.argv) > 2:
sys.exit(getHelpStr(description, arguments) + "\n")
(p_arg_map, args_remaining) = parseArgs(sys.argv[1:], arguments)
minlen = int(args_remaining[0])
files = args_remaining[1:]
if not all(map(os.path.exists, files)):
sys.exit("Not all files exist")
file_readers = starmap(fileIterator, zip(files, map(iteratorFromExtension, files)))
filt_cond = lambda record: seqlen(record) > minlen
if p_arg_map["maxlen"] > 1:
filt_cond = lambda record: seqlen(record) > minlen and seqlen(record) <= p_arg_map["maxlen"]
filtered_records = ifilter(filt_cond, chain.from_iterable(file_readers))
filtered_seqs = imap(recordToString, filtered_records)
for seq in filtered_seqs:
print seq
arguments = map(CLArgument._make, argument_list)
if not len(sys.argv) > 2:
sys.exit(getHelpStr(description, arguments) +"\n")
(p_arg_map, args_remaining) = parseArgs(sys.argv[1:], arguments)
minlen = int(args_remaining[0])
files = args_remaining[1:]
if not all(map(os.path.exists,files)):
sys.exit("Not all files exist")
file_readers = starmap(fileIterator, zip(files, map(iteratorFromExtension, files)))
filt_cond = lambda record : seqlen(record) > minlen
if p_arg_map["maxlen"] > 1:
filt_cond = lambda record: seqlen(record) > minlen and seqlen(record) <= p_arg_map["maxlen"]
filtered_records = ifilter(filt_cond, chain.from_iterable(file_readers))
filtered_seqs = imap(recordToString, filtered_records)
for seq in filtered_seqs:
print 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
iterators = map(iteratorFromExtension, imap(itemgetter(1), openers))
openfuncs = map(defdef(open), imap(itemgetter(0),openers))
input_data = chain.from_iterable(starmap(fileIterator,
zip(in_files, iterators, openfuncs)))
total_reads = 0
dnum = 0
fnum = 0
fh = None
readidx_fh = open("ReadIndex.txt", "w")
recordString = recordToString if p_arg_map["samefmt"] else fastaRecordToString
for record in input_data:
if seqlen(record) < p_arg_map["minlen"]:
continue
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")
clean_name = str(record.name).split()[0]
clean_record = record._replace(name=clean_name)
