def krill_open(q_min, q_percent, p64, in1, in2, pe_1, pe_2, se_1, se_2, f_1,
f_2):
'''
quality filter test for single and paired-end reads
'''
compressed = gzip_test(in1)
if compressed:
pe_1, _ = os.path.splitext(pe_1)
pe_2, _ = os.path.splitext(pe_2)
se_1, _ = os.path.splitext(se_1)
se_2, _ = os.path.splitext(se_2)
f_1, _ = os.path.splitext(f_1)
f_2, _ = os.path.splitext(f_2)
with gzip.open(in1, 'rt') as f1, gzip.open(in2, 'rt') as f2,\
open(pe_1, "w") as pe_o1,\
open(pe_2, "w") as pe_o2,\
open(se_1, "w") as se_o1,\
open(se_2, "w") as se_o2,\
open(f_1, "w") as fail_o1,\
open(f_2, "w") as fail_o2:
krill(q_min, q_percent, p64, f1, f2, pe_o1, pe_o2, se_o1, se_o2,
fail_o1, fail_o2)
else:
with open(in1) as f1, open(in2) as f2,\
open(pe_1, "w") as pe_o1,\
open(pe_2, "w") as pe_o2,\
open(se_1, "w") as se_o1,\
open(se_2, "w") as se_o2,\
open(f_1, "w") as fail_o1,\
open(f_2, "w") as fail_o2:
krill(q_min, q_percent, p64, f1, f2, pe_o1, pe_o2, se_o1, se_o2,
fail_o1, fail_o2)
def porifera_open(in1, in2, subseqs1, subseqs2, se_1, pe_1, se_2, pe_2, k,
rounds, match, min_l, tiny_ls1, tiny_ls2, tiny):
'''
open paired end files for adapter detection
'''
compressed = gzip_test(in1)
if compressed:
pe_1, _ = os.path.splitext(pe_1)
pe_2, _ = os.path.splitext(pe_2)
se_1, _ = os.path.splitext(se_1)
se_2, _ = os.path.splitext(se_2)
with gzip.open(in1, 'rt') as f1, gzip.open(in2, 'rt') as f2,\
open(pe_1, 'w') as pe_o1,\
open(pe_2, 'w') as pe_o2,\
open(se_1, 'w') as se_o1,\
open(se_2, 'w') as se_o2:
porifera(f1, f2, subseqs1, subseqs2, pe_o1, pe_o2, se_o1, se_o2, k,
rounds, match, min_l, tiny_ls1, tiny_ls2, tiny)
else:
with open(in1, 'rt') as f1, open(in2, 'rt') as f2,\
open(pe_1, 'w') as pe_o1,\
open(pe_2, 'w') as pe_o2,\
open(se_1, 'w') as se_o1,\
open(se_2, 'w') as se_o2:
porifera(f1, f2, subseqs1, subseqs2, pe_o1, pe_o2, se_o1, se_o2, k,
rounds, match, min_l, tiny_ls1, tiny_ls2, tiny)
def rotifer_open(R1_bases_ls, R2_bases_ls, in1, in2, pe_1, pe_2, se_1, se_2,
trim):
'''
parse single and paired-end reads for recognized motifs
'''
compressed = gzip_test(in1)
if compressed:
pe_1, _ = os.path.splitext(pe_1)
pe_2, _ = os.path.splitext(pe_2)
se_1, _ = os.path.splitext(se_1)
se_2, _ = os.path.splitext(se_2)
with gzip.open(in1, 'rt') as f1, gzip.open(in2, 'rt') as f2,\
open(pe_1, "w") as pe_o1,\
open(pe_2, "w") as pe_o2,\
open(se_1, "w") as se_o1,\
open(se_2, "w") as se_o2:
if trim:
rotifer_trim(R1_bases_ls, R2_bases_ls, f1, f2, pe_o1, pe_o2,
se_o1, se_o2, trim)
else:
rotifer(R1_bases_ls, R2_bases_ls, f1, f2, pe_o1, pe_o2, se_o1,
se_o2)
else:
with open(in1) as f1, open(in2) as f2,\
open(pe_1, "w") as pe_o1,\
open(pe_2, "w") as pe_o2,\
open(se_1, "w") as se_o1,\
open(se_2, "w") as se_o2:
if trim:
rotifer_trim(R1_bases_ls, R2_bases_ls, f1, f2, pe_o1, pe_o2,
se_o1, se_o2, trim)
else:
rotifer(R1_bases_ls, R2_bases_ls, f1, f2, pe_o1, pe_o2, se_o1,
se_o2)
def porifera_single_open(args):
'''
open files for adapter detection
'''
compressed = gzip_test(args.in1)
if compressed:
se_1, _ = os.path.splitext(args.se_1)
with gzip.open(args.in1, 'rt') as f, open(se_1, 'w') as o:
porifera_single(args, f, o)
else:
with open(args.in1) as f, open(args.se_1, 'w') as o:
porifera_single(args, f, o)
def krill_single_open(q_min, q_percent, p64, in1, se_1):
'''
quality filter test for single-end reads
'''
compressed = gzip_test(in1)
if compressed:
se_1, _ = os.path.splitext(se_1)
with gzip.open(in1, 'rt') as f1, open(se_1, "w") as se_o1:
krill_single(q_min, q_percent, p64, f1, se_o1)
else:
with open(in1) as f1, open(se_1, "w") as se_o1:
krill_single(q_min, q_percent, p64, f1, se_o1)
def scallop_open(in1, front_trim, end_trim, out1):
'''
test if gzipped, then open single-end files
'''
compressed = gzip_test(in1)
if compressed:
out1, _ = os.path.splitext(out1)
with gzip.open(in1, 'rt') as f, open(out1, 'w') as o:
scallop(front_trim, end_trim, f, o)
else:
with open(in1) as f, open(out1, 'w') as o:
scallop(front_trim, end_trim, f, o)
def scallop_single_end_open(in1, out1, front_trim, end_score, window, min_l):
'''
test if gzipped, then open single-end files
'''
compressed = gzip_test(in1)
if compressed:
out1, _ = os.path.splitext(out1)
with gzip.open(in1, 'rt') as f, open(out1, 'w') as o:
scallop_single_end_line(f, o, front_trim, end_score, window, min_l)
else:
with open(in1) as f, open(out1, 'w') as o:
scallop_single_end_line(f, o, front_trim, end_score, window, min_l)
def anemone_single_open(in1, out1, of1_ls, mismatch, bcs, proj, round_one,
front_trim):
'''
create IO file object based on gzipped status for se data
'''
compressed = gzip_test(in1)
if compressed:
with gzip.open(in1, 'rt') as f1:
anemone_single(f1, out1, of1_ls, mismatch, bcs, proj, round_one,
front_trim)
else:
with open(in1) as f1:
anemone_single(f1, out1, of1_ls, mismatch, bcs, proj, round_one,
front_trim)
def crinoid_open(in1, out1, out2, procs, p64):
'''
open as gzipped file object if gzipped
'''
compressed = gzip_test(in1)
if compressed:
with gzip.open(in1, 'rt') as f:
k_score = kmer_test(f)
with gzip.open(in1, 'rt') as f:
crinoid(f, out1, out2, procs, p64, k_score)
else:
with open(in1) as f:
k_score = kmer_test(f)
with open(in1) as f:
crinoid(f, out1, out2, procs, p64, k_score)
def porifera_single_open(in1, subseqs, se_1, k, rounds, match, min_l, tiny_ls,
tiny):
'''
open files for adapter detection
'''
compressed = gzip_test(in1)
if compressed:
se_1, _ = os.path.splitext(se_1)
with gzip.open(in1, 'rt') as f, open(se_1, 'w') as o:
porifera_single(f, subseqs, o, k, rounds, match, min_l, tiny_ls,
tiny)
else:
with open(in1) as f, open(se_1, 'w') as o:
porifera_single(f, subseqs, o, k, rounds, match, min_l, tiny_ls,
tiny)
def anemone_comp(in1_ls, in2_ls, mismatch, bcs_dict, curr, front_trim, in1):
'''
composer entry point to anemone
'''
if in1 in in2_ls:
return
try:
in2 = in2_ls[in1_ls.index(in1)]
out2 = os.path.basename(in2)
except (IndexError, ValueError) as e:
in2 = False
out2 = False
out1 = os.path.basename(in1)
compressed = gzip_test(in1)
if compressed:
out1 = out1[:-3] if out1.endswith('.gz') else out1
if out2:
out2 = out2[:-3] if out2.endswith('.gz') else out2
if out1 in bcs_dict.keys():
pass
elif out1 + '.gz' in bcs_dict.keys():
bcs_dict[out1] = bcs_dict.pop(out1 + '.gz')
'''
the following copies files not found in index.txt
'''
try:
bcs_file = bcs_dict[out1]
except KeyError:
shutil.copy(in1, curr)
try:
shutil.copy(in2, curr)
except TypeError:
pass
return
if in1.endswith('.fastq'):
tmp_dir = os.path.basename(in1)[:-6]
elif in1.endswith('.fastq.gz'):
tmp_dir = os.path.basename(in1)[:-9]
else:
tmp_dir = os.path.basename(in1)
subdir = os.path.join(curr, tmp_dir)
os.mkdir(subdir)
anemone_init(in1, in2, out1, out2, mismatch, bcs_file, subdir, front_trim)
def anemone_open(in1, in2, out1, out2, of1_ls, of2_ls, mismatch, bcs, proj,
round_one, front_trim):
'''
create IO file object based on gzipped status for pe data
'''
compressed = gzip_test(in1)
if compressed:
with gzip.open(in1, 'rt') as f1, gzip.open(in2, 'rt') as f2:
of1_ls, of2_ls = anemone(f1, f2, out1, out2, of1_ls, of2_ls,
mismatch, bcs, proj, round_one,
front_trim)
else:
with open(in1) as f1, open(in2) as f2:
of1_ls, of2_ls = anemone(f1, f2, out1, out2, of1_ls, of2_ls,
mismatch, bcs, proj, round_one,
front_trim)
return of1_ls, of2_ls
def rotifer_single_open(R1_bases_ls, in1, se_1, f_1, trim):
'''
parse single-end reads for recognized motifs
'''
compressed = gzip_test(in1)
if compressed:
se_1, _ = os.path.splitext(se_1)
f_1, _ = os.path.splitext(f_1)
with gzip.open(in1,
'rt') as f1, open(se_1,
"w") as se_o1, open(f_1,
"w") as fail_o1:
rotifer_single(R1_bases_ls, f1, se_o1, fail_o1)
else:
with open(in1) as f1, open(se_1, "w") as se_o1, open(f_1,
"w") as fail_o1:
rotifer_single(R1_bases_ls, f1, se_o1, fail_o1)
def fastq_test(fastq_ls):
'''
test if gzipped fastq file
'''
fastq_dt, in1_ls, in2_ls = {}, [], []
for filename in fastq_ls:
compressed = gzip_test(filename)
if compressed is None:
sys.exit('\n\n' + filename + msg.fastq_test1)
elif compressed is True:
with gzip.open(filename, 'rt') as f:
fastq_dt = fastq_structure(f, filename, fastq_dt)
else:
with open(filename) as f:
fastq_dt = fastq_structure(f, filename, fastq_dt)
for i in fastq_dt.values():
if None not in i:
in1_ls.append(i[0])
in2_ls.append(i[1])
return in1_ls, in2_ls
def porifera_open(args):
'''
open paired end files for adapter detection
'''
compressed = gzip_test(args.in1)
if compressed:
pe_1, _ = os.path.splitext(args.pe_1)
pe_2, _ = os.path.splitext(args.pe_2)
se_1, _ = os.path.splitext(args.se_1)
se_2, _ = os.path.splitext(args.se_2)
with gzip.open(args.in1, 'rt') as f1, gzip.open(args.in2, 'rt') as f2,\
open(pe_1, 'w') as pe_o1,\
open(pe_2, 'w') as pe_o2,\
open(se_1, 'w') as se_o1,\
open(se_2, 'w') as se_o2:
porifera(args, f1, f2, pe_o1, pe_o2, se_o1, se_o2)
else:
with open(args.in1, 'rt') as f1, open(args.in2, 'rt') as f2,\
open(args.pe_1, 'w') as pe_o1,\
open(args.pe_2, 'w') as pe_o2,\
open(args.se_1, 'w') as se_o1,\
open(args.se_2, 'w') as se_o2:
porifera(args, f1, f2, pe_o1, pe_o2, se_o1, se_o2)
def scallop_end_open(in1, in2, pe_1, pe_2, se_1, se_2, front_trim, end_score, window, min_l):
'''
test if gzipped, then open paired-end files
'''
compressed = gzip_test(in1)
if compressed:
pe_1, _ = os.path.splitext(pe_1)
pe_2, _ = os.path.splitext(pe_2)
se_1, _ = os.path.splitext(se_1)
se_2, _ = os.path.splitext(se_2)
with gzip.open(in1, 'rt') as f1, gzip.open(in2, 'rt') as f2,\
open(pe_1, "w") as pe_o1,\
open(pe_2, "w") as pe_o2,\
open(se_1, "w") as se_o1,\
open(se_2, "w") as se_o2:
scallop_end_line(f1, f2, pe_o1, pe_o2, se_o1, se_o2, front_trim, end_score, window, min_l)
else:
with open(in1) as f1, open(in2) as f2,\
open(pe_1, "w") as pe_o1,\
open(pe_2, "w") as pe_o2,\
open(se_1, "w") as se_o1,\
open(se_2, "w") as se_o2:
scallop_end_line(f1, f2, pe_o1, pe_o2, se_o1, se_o2, front_trim, end_score, window, min_l)
