opt = dict()
with open(conf) as handle:
for line in handle.readlines():
if not line.startswith("//") and line.rstrip() is not "":
val = line.split("=")
opt[val[0]] = val[1].rstrip()
# filename intermediates
saileft = opt[base] + ".left.sai"
sairight = opt[base] + ".right.sai"
samfile = opt[base] + ".sam"
bamclean = opt[base] + ".clean.bam"
bamfile = opt[base] + ".bam"
bamindex = opt[base] + ".bai"
''' create objects from utility libraries '''
seq_obj = seq_util.SplitFile(opt[numseq])
bwa_obj = align_util.BWA(opt[prefix])
st_obj = samtool_util.Use()
''' split large fastq file into multiple smaller fastq files '''
left_files = seq_obj.split_fastq(opt[seqleft])
right_files = seq_obj.split_fastq(opt[seqright])
''' do alignments '''
rg = "@RG\tID:" + opt[rgid] + "\tSM:" + opt[rgsm] + "\tLB:" + opt[
rglb] + "\tPL:" + opt[rgpl] + "\tPU:" + opt[rgpu]
samfiles = bwa_obj.multifastq_call(left_files, right_files, rg, opt[base])
''' groom sam files () '''
cmd = "groom_sam.py"
bamfiles = list()
jobids = list()
for eachfile in samfiles:
#!/usr/bin/env python import seq_util import sys try: fastq = sys.argv[1] num_seq = sys.argv[2] except IOError as (errno,strerror): print "usage: break_fastq.py fastq_file number_of_seqs_per_file" seq_obj = seq_util.SplitFile(num_seq) files = seq_obj.split_fastq(fastq) for produce in files: print produce
import seq_util
import sys
lineperseq = 4
try:
fastq = sys.argv[1]
num_seq = sys.argv[2]
# buffer length, default 100Mb
try:
buff_len = int(sys.argv[3])
except:
buff_len = 100000000
# option to clobber file or leave there and skip
try:
noclobber = bool(sys.argv[4]) # if defined, translates to true
except:
noclobber = False
except IOError as (errno, strerror):
print "usage: break_fastq.py fastq_file number_of_seqs_per_file buffer_length_bytes clobber_file (optional) "
seq_obj = seq_util.SplitFile(num_seq, lineperseq)
files = seq_obj.split_fastq_buffer(fastq, buff_len, noclobber)
for produce in files:
print produce