def check_merged_reads(merge_d, source_d):
results = {}
for idx_seq,idx in idx_lookup.items():
for r in [1,2]:
for l in range(1,9):
sources = glob('%s/*_%s_L00%s_R%s*.fastq.gz' % (source_d,idx_seq,l,r))
if len(sources) > 0:
source_sum = sum([preprocess_radtag_lane.get_read_count(f) for f in sources])
merge_f = '%s/s_%s_%s_sequence_index%s.txt.gz' % (merge_d,l,r,idx)
if os.path.exists(merge_f):
merge_sum = preprocess_radtag_lane.get_read_count(merge_f)
results[merge_f] = source_sum == merge_sum
else:
results[merge_f] = None
return results
#!/usr/bin/env python
import Seq, os,sys
from radtag_denovo import preprocess_radtag_lane
from Util import smartopen
def join_pair(r1,r2,num_n=10,qual_n='#'):
return [r1[0],r1[1]+'N'*num_n+str(Seq.Sequence(r2[1]).rc()),r1[2]+qual_n*num_n+''.join(reversed(r2[2]))]
if __name__ == "__main__":
f1,f2 = sys.argv[1:]
fh1 = smartopen(f1)
fh2 = smartopen(f2)
rc = preprocess_radtag_lane.get_read_count(f1)
for i in xrange(rc):
if i % 1000 == 0:
print >> sys.stderr, '\r%s / %s' % (i,rc),
r1 = preprocess_radtag_lane.next_read_from_fh(fh1,4)
r2 = preprocess_radtag_lane.next_read_from_fh(fh2,4)
print preprocess_radtag_lane.as_fq4_lines(*join_pair(r1,r2))
print >> sys.stderr, '\ndone'
if len(sys.argv) == 2:
fq = sys.argv[1]
boundstr = "0:"
else:
fq, boundstr = sys.argv[1:]
start,end = boundstr.split(':')
start = int(start)
lnum,baseQ,readlen = get_fastq_properties(fq)
if end == '':
end = readlen
readcount = preprocess_radtag_lane.get_read_count(fq)
qsc_n = 0
qsc_tot = numpy.zeros(readlen)
qsc_by_read = []
fh = smartopen(fq)
tickon = readcount/1000
for i in range(readcount):
if i % tickon == 0:
print >> sys.stderr, '\r%0.1f' % ((i/float(readcount)) * 100),
t,r,q = preprocess_radtag_lane.next_read_from_fh(fh,lnum)
qsc = [ord(c)-baseQ for c in q]
qsc_n += 1
qsc_tot += qsc
raise OSError
else:
if opts.check_donefiles:
if os.path.exists(donefile):
print >> sys.stderr, '.done file for bam %s found, but bam is missing; remove %s ...' % (rg_ref_bam,donefile),
ret = os.system('rm -f %s' % donefile)
if ret == 0:
print >> sys.stderr, 'DONE'
else:
raise OSError, 'FAILED'
if isinstance(readfile,tuple):
r1,r2 = readfile
readct1 = preprocess_radtag_lane.get_read_count(r1)
readct2 = preprocess_radtag_lane.get_read_count(r2)
if readct1 != readct2:
raise ValueError, 'read counts do not match, abort'
num_parts = (readct1*2)/opts.reads_per_part
if num_parts < 1: num_parts = 1
print >> sys.stderr, 'map in %s part(s)' % num_parts
samparts_by_bam[rg_ref_bam] = []
for i in xrange(1,num_parts+1):
sampart = samfbase+'_%05dof%05d.sam' % (i,num_parts)
samparts_by_bam[rg_ref_bam].append(sampart)
cmdstr = 'run_safe.py \"module load %s; stampy.py -g %s -h %s --gatkcigarworkaround --overwrite --readgroup=%s --processpart %s/%s -o %s %s -M %s %s\" %s.done' % (stampy_module,t,t,readgroup_arg,i,num_parts,sampart,stampy_argstr,r1,r2,sampart)
cmds.append(cmdstr)
cmd_by_sam[sampart] = cmdstr
#!/usr/bin/env python
'''calculate the percent of reads in a lane properly resolved by barcode
'''
import os,sys
from radtag_denovo import preprocess_radtag_lane
from glob import glob
fastq,analysis_folder = sys.argv[1:]
tot_reads = preprocess_radtag_lane.get_read_count(fastq)
indiv_barcoded = {}
fqs = glob('%s/*1_sequence.33.fq4*' % analysis_folder)
for fq in fqs:
indiv_barcoded[fq] = preprocess_radtag_lane.get_read_count(fq)
print float(sum(indiv_barcoded.values()))/tot_reads
