def _merge_sorts(self):
iterators = []
for i in range(1, self.batch_number):
extra = "_batch" + str(i)
new_path = brenninc_utils.create_new_file(self.fastq_file, extra,
outputdir=self.outputdir,
gzipped=False)
iterable = wrap_sequence(new_path)
iterators.append(iterable)
big = heapq.merge(*iterators)
extra = "_sorted"
new_path = brenninc_utils.create_new_file(self.fastq_file, extra,
outputdir=self.outputdir,
gzipped=False)
print "writing to", new_path
with open(new_path, 'w') as sorted_file:
for wrapper in big:
wrapper.sequence.write_to_fastq_file(sorted_file)
print "done"
for i in range(1, self.batch_number):
extra = "_batch" + str(i)
new_path = brenninc_utils.create_new_file(self.fastq_file, extra,
outputdir=self.outputdir,
gzipped=False)
os.remove(new_path)
def count_reads_using_features(sam_filename, features, counts, samtype, order,
stranded, overlap_mode, quiet, minaqual, samout,
directory):
if samtype is None:
samtype = detect_sam_type(sam_filename)
with open_sam(sam_filename, samtype) as (pe_mode, read_seq):
with get_write_to_samout(samout, pe_mode) as write_to_samout:
if stranded in ["yes", "no", "both"]:
if samout == "auto":
samout = brenninc_utils.create_new_file(
sam_filename,
"_forward_annotated",
outputdir=directory,
extension="sam",
gzipped=False)
forward_counter = iv_counter_factory(features, counts,
write_to_samout,
overlap_mode)
else:
forward_counter = None
if stranded in ["reverse", "both"]:
if samout == "auto":
samout = brenninc_utils.create_new_file(
sam_filename,
"_reverse_annotated",
outputdir=directory,
extension="sam",
gzipped=False)
reverse_counter = iv_counter_factory(features, counts,
write_to_samout,
overlap_mode)
else:
reverse_counter = None
if pe_mode:
pass
#count_reads_paired(read_seq, forward_counter, reverse_counter, order,
# quiet, minaqual, write_to_samout )
else:
count_reads_single(read_seq, forward_counter, order, quiet,
minaqual)
if forward_counter is not None:
output = brenninc_utils.create_new_file(sam_filename,
"_forward_count",
outputdir=directory,
extension="txt",
gzipped=False)
print "forward written to", output
with open(output, "w") as output_file:
forward_counter.results(output_file)
if reverse_counter is not None:
output = brenninc_utils.create_new_file(sam_filename,
"_reverse_count",
outputdir=directory,
extension="txt",
gzipped=False)
print "reverse written to", output
with open(output, "w") as output_file:
reverse_counter.results(output_file)
def count_reads_using_features(sam_filename, features, counts, samtype, order, stranded,
overlap_mode, quiet, minaqual, samout, directory ):
if samtype is None:
samtype = detect_sam_type(sam_filename)
with open_sam(sam_filename, samtype) as (pe_mode, read_seq):
with get_write_to_samout(samout, pe_mode) as write_to_samout:
if stranded in ["yes", "no", "both"]:
if samout == "auto":
samout = brenninc_utils.create_new_file(sam_filename,
"_forward_annotated",
outputdir=directory,
extension="sam",
gzipped=False)
forward_counter = iv_counter_factory(features,
counts,
write_to_samout,
overlap_mode)
else:
forward_counter = None
if stranded in ["reverse", "both"]:
if samout == "auto":
samout = brenninc_utils.create_new_file(sam_filename,
"_reverse_annotated",
outputdir=directory,
extension="sam",
gzipped=False)
reverse_counter = iv_counter_factory(features,
counts,
write_to_samout,
overlap_mode)
else:
reverse_counter = None
if pe_mode:
pass
#count_reads_paired(read_seq, forward_counter, reverse_counter, order,
# quiet, minaqual, write_to_samout )
else:
count_reads_single(read_seq, forward_counter, order,
quiet, minaqual)
if forward_counter is not None:
output = brenninc_utils.create_new_file(sam_filename,
"_forward_count",
outputdir=directory,
extension="txt",
gzipped=False)
print "forward written to", output
with open(output,"w") as output_file:
forward_counter.results(output_file)
if reverse_counter is not None:
output = brenninc_utils.create_new_file(sam_filename,
"_reverse_count",
outputdir=directory,
extension="txt",
gzipped=False)
print "reverse written to", output
with open(output,"w") as output_file:
reverse_counter.results(output_file)
def count_reads_in_features(sam_filename, gff_filename, samtype, order,
stranded, overlap_mode, feature_type, id_attribute,
quiet, minaqual, samout, directory):
forward = stranded in ["yes", "both"]
reverse = stranded in ["reverse", "both"]
is_stranded = stranded != "NO"
if samout != "" and stranded == "both":
raise Exception("Output SAM alignment records not supported "
"for stranded 'both'")
if samtype == "bam":
extensions = [".bam"]
elif samtype == "sam":
extensions = [".sam", ".sam.gz"]
else:
extensions = [".bam", ".sam", ".sam.gz"]
files = brenninc_utils.find_files(sam_filename,
extensions=extensions,
recursive=True)
features, counts = get_features(gff_filename, is_stranded, feature_type,
id_attribute, quiet)
for a_file in files:
if samout == "auto":
samout_file = brenninc_utils.create_new_file(sam_filename,
"_annotated",
outputdir=directory,
extension="sam",
gzipped=False)
else:
samout_file = samout
print "counting", a_file
count_reads(a_file, features, counts, samtype, order, forward, reverse,
overlap_mode, quiet, minaqual, samout_file, directory)
def count_reads_in_features(sam_filename, gff_filename, samtype, order,
stranded, overlap_mode, feature_type,
id_attribute, quiet, minaqual, samout, directory):
forward = stranded in ["yes", "both"]
reverse = stranded in ["reverse", "both"]
is_stranded = stranded != "NO"
if samout != "" and stranded == "both":
raise Exception("Output SAM alignment records not supported "
"for stranded 'both'")
if samtype == "bam":
extensions = [".bam"]
elif samtype == "sam":
extensions = [".sam", ".sam.gz"]
else:
extensions = [".bam", ".sam", ".sam.gz"]
files = brenninc_utils.find_files(sam_filename, extensions=extensions,
recursive=True)
features, counts = get_features(gff_filename, is_stranded, feature_type,
id_attribute, quiet)
for a_file in files:
if samout == "auto":
samout_file = brenninc_utils.create_new_file(sam_filename,
"_annotated",
outputdir=directory,
extension="sam",
gzipped=False)
else:
samout_file = samout
print "counting", a_file
count_reads(a_file, features, counts, samtype, order, forward, reverse,
overlap_mode, quiet, minaqual, samout_file, directory)
def head(path, sequences=100, outputdir=None,
qual_scale=_default_qual_scale):
extra = "_head" + str(sequences)
new_path = brenninc_utils.create_new_file(path, extra, outputdir=outputdir,
gzipped=False)
fastq_iterator = HTSeq.FastqReader(path, qual_scale)
with open(new_path, 'w') as headFile:
for sequence in itertools.islice(fastq_iterator, sequences):
sequence.write_to_fastq_file(headFile)
def head(path, sequences=100, outputdir=None, qual_scale=_default_qual_scale):
extra = "_head" + str(sequences)
new_path = brenninc_utils.create_new_file(path,
extra,
outputdir=outputdir,
gzipped=False)
fastq_iterator = HTSeq.FastqReader(path, qual_scale)
with open(new_path, 'w') as headFile:
for sequence in itertools.islice(fastq_iterator, sequences):
sequence.write_to_fastq_file(headFile)
def write_output(counter, original_filename, direction, directory):
if counter is None:
return
output = brenninc_utils.create_new_file(original_filename,
"_" + direction + "_count",
outputdir=directory,
extension="txt",
gzipped=False)
print direction, "written to", output
with open(output, "w") as output_file:
counter.results(output_file)
def write_output(counter, original_filename, direction, directory):
if counter is None:
return
output = brenninc_utils.create_new_file(original_filename,
"_" + direction + "_count",
outputdir=directory,
extension="txt",
gzipped=False)
print direction, "written to", output
with open(output, "w") as output_file:
counter.results(output_file)
def compare(original_fastq, trimmed_fastq, unpaired_fastq,
outputdir=os.getcwd(), qual_scale=_default_qual_scale):
shorter_path = brenninc_utils.create_new_file(original_fastq, "_shorter",
outputdir=outputdir,
gzipped=False)
dropped_path = brenninc_utils.create_new_file(original_fastq, "_dropped",
outputdir=outputdir,
gzipped=False)
short_count_path = brenninc_utils.create_new_file(original_fastq,
"_short_count",
outputdir=outputdir,
gzipped=False)
with open(shorter_path, "w") as shorter_file:
with open(dropped_path, "w") as dropped_file:
comparer = Comparer(original_fastq, trimmed_fastq, unpaired_fastq,
shorter_file, dropped_file,
outputdir=outputdir, qual_scale=qual_scale)
comparer.do_compare()
comparer.print_shorter(short_count_path)
def _sort_and_save(self, sequences):
print "sorting", len(sequences)
sequences.sort(key=lambda sequence: sequence.name)
if self.batch_number == 0:
extra = "_sorted"
else:
extra = "_batch" + str(self.batch_number)
new_path = brenninc_utils.create_new_file(self.fastq_file, extra,
outputdir=self.outputdir,
gzipped=False)
print "writing to", new_path,
with open(new_path, 'w') as sorted_file:
for sequence in sequences:
sequence.write_to_fastq_file(sorted_file)
print "done"
def count_reads(sam_filename, features, counts, samtype, order, forward,
reverse, overlap_mode, quiet, minaqual, samout, directory):
def write_to_samout(r, assignment):
if samoutfile is None:
return
if not pe_mode:
r = (r, )
for read in r:
if read is not None:
samoutfile.write(read.original_sam_line.rstrip() + "\tXF:Z:" +
assignment + "\n")
if samout != "":
samoutfile = open(samout, "w")
else:
samoutfile = None
if samtype is None:
samtype = detect_sam_type(sam_filename)
if samtype == "sam":
SAM_or_BAM_Reader = HTSeq.SAM_Reader
elif samtype == "bam":
SAM_or_BAM_Reader = HTSeq.BAM_Reader
else:
raise ValueError("Unknown input format %s specified." % samtype)
try:
if sam_filename != "-":
read_seq_file = SAM_or_BAM_Reader(sam_filename)
read_seq = read_seq_file
first_read = iter(read_seq).next()
else:
read_seq_file = SAM_or_BAM_Reader(sys.stdin)
read_seq_iter = iter(read_seq_file)
first_read = read_seq_iter.next()
read_seq = itertools.chain([first_read], read_seq_iter)
pe_mode = first_read.paired_end
except:
sys.stderr.write("Error occured when reading beginning "
"of SAM/BAM file.\n")
raise
try:
if pe_mode:
if order == "name":
read_seq = HTSeq.pair_SAM_alignments(read_seq)
elif order == "pos":
read_seq = HTSeq.pair_SAM_alignments_with_buffer(read_seq)
else:
raise ValueError("Illegal order specified.")
if forward:
empty_forward = 0
ambiguous_forward = 0
counts_forward = copy.copy(counts)
if reverse:
empty_reverse = 0
ambiguous_reverse = 0
counts_reverse = copy.copy(counts)
notaligned = 0
lowqual = 0
nonunique = 0
i = 0
for r in read_seq:
if i > 0 and i % 100000 == 0 and not quiet:
sys.stderr.write("%d SAM alignment record%s processed.\n" %
(i, "s" if not pe_mode else " pairs"))
i += 1
if not pe_mode:
if not r.aligned:
notaligned += 1
write_to_samout(r, "__not_aligned")
continue
try:
if r.optional_field("NH") > 1:
nonunique += 1
write_to_samout(r, "__alignment_not_unique")
continue
except KeyError:
pass
if r.aQual < minaqual:
lowqual += 1
write_to_samout(r, "__too_low_aQual")
continue
if forward:
iv_seq_for = (co.ref_iv for co in r.cigar
if co.type == "M" and co.size > 0)
if reverse:
iv_seq_rev = (invert_strand(co.ref_iv) for co in r.cigar
if co.type == "M" and co.size > 0)
else:
if r[0] is not None and r[0].aligned:
if forward:
iv_seq_for = (co.ref_iv for co in r[0].cigar
if co.type == "M" and co.size > 0)
if reverse:
iv_seq_rev = (invert_strand(co.ref_iv)
for co in r[0].cigar
if co.type == "M" and co.size > 0)
else:
iv_seq_rev = tuple()
iv_seq_for = tuple()
if r[1] is not None and r[1].aligned:
if forward:
iv_seq_for = (itertools.chain(
iv_seq_for, (invert_strand(co.ref_iv)
for co in r[1].cigar
if co.type == "M" and co.size > 0)))
if reverse:
iv_seq_rev = itertools.chain(
iv_seq_rev, (co.ref_iv for co in r[1].cigar
if co.type == "M" and co.size > 0))
else:
if (r[0] is None) or not (r[0].aligned):
write_to_samout(r, "__not_aligned")
notaligned += 1
continue
try:
if ((r[0] is not None and r[0].optional_field("NH") > 1) or
(r[1] is not None and r[1].optional_field("NH") > 1)):
nonunique += 1
write_to_samout(r, "__alignment_not_unique")
continue
except KeyError:
pass
if ((r[0] and r[0].aQual < minaqual)
or (r[1] and r[1].aQual < minaqual)):
lowqual += 1
write_to_samout(r, "__too_low_aQual")
continue
try:
if overlap_mode == "union":
if forward:
fs_for = set()
for iv in iv_seq_for:
if iv.chrom not in features.chrom_vectors:
raise UnknownChrom
for iv2, fs2 in features[iv].steps():
fs_for = fs_for.union(fs2)
if reverse:
fs_rev = set()
for iv in iv_seq_rev:
if iv.chrom not in features.chrom_vectors:
raise UnknownChrom
for iv2, fs2 in features[iv].steps():
fs_rev = fs_rev.union(fs2)
elif (overlap_mode == "intersection-strict"
or overlap_mode == "intersection-nonempty"):
if forward:
fs_for = None
for iv in iv_seq_for:
if iv.chrom not in features.chrom_vectors:
raise UnknownChrom
for iv2, fs2 in features[iv].steps():
if len(fs2) > 0 or \
overlap_mode == "intersection-strict":
if fs_for is None:
fs_for = fs2.copy()
else:
fs_for = fs_for.intersection(fs2)
if reverse:
fs_reverse = None
for iv in iv_seq_rev:
if iv.chrom not in features.chrom_vectors:
raise UnknownChrom
for iv2, fs2 in features[iv].steps():
if len(fs2) > 0 or \
overlap_mode == "intersection-strict":
if fs_rev is None:
fs_rev = fs2.copy()
else:
fs_rev = fs_rev.intersection(fs2)
else:
sys.exit("Illegal overlap mode.")
if forward:
if fs_for is None or len(fs_for) == 0:
write_to_samout(r, "__no_feature")
empty_forward += 1
elif len(fs_for) > 1:
write_to_samout(
r, "__ambiguous[" + '+'.join(fs_for) + "]")
ambiguous_forward += 1
else:
write_to_samout(r, list(fs_for)[0])
counts_forward[list(fs_for)[0]] += 1
if reverse:
if fs_reverse is None or len(fs_rev) == 0:
write_to_samout(r, "__no_feature")
empty_reverse += 1
elif len(fs_reverse) > 1:
write_to_samout(
r, "__ambiguous[" + '+'.join(fs_rev) + "]")
ambiguous_reverse += 1
else:
write_to_samout(r, list(fs_rev)[0])
counts_reverse[list(fs_rev)[0]] += 1
except UnknownChrom:
write_to_samout(r, "__no_feature")
empty_forward += 1
empty_reverse += 1
except:
sys.stderr.write("Error occured when processing SAM input (%s):\n" %
read_seq_file.get_line_number_string())
raise
if not quiet:
sys.stderr.write(
"%d SAM %s processed.\n" %
(i, "alignments " if not pe_mode else "alignment pairs"))
if samoutfile is not None:
samoutfile.close()
if forward:
output = brenninc_utils.create_new_file(sam_filename,
"_forward_count",
outputdir=directory,
extension="txt",
gzipped=False)
used_features_count = 0
used_features_sum = 0
print "Forward written to", output
with open(output, "w") as output_file:
for fn in sorted(counts_forward.keys()):
output_file.write("%s\t%d\n" % (fn, counts_forward[fn]))
used_features_count += 1
used_features_sum += counts_forward[fn]
output_file.write("__no_feature\t%d\n" % empty_forward)
output_file.write("__ambiguous\t%d\n" % ambiguous_forward)
output_file.write("__too_low_aQual\t%d\n" % lowqual)
output_file.write("__not_aligned\t%d\n" % notaligned)
output_file.write("__alignment_not_unique\t%d\n" % nonunique)
print "Forward features with alignment\t%d" % used_features_count
print "Forward alignments asigned to feature\t%d" % used_features_sum
print "__forward_no_feature\t%d" % empty_forward
print "__forward_ambiguous\t%d" % ambiguous_forward
if reverse:
output = brenninc_utils.create_new_file(sam_filename,
"_reverse_count",
outputdir=directory,
extension="txt",
gzipped=False)
used_features_count = 0
used_features_sum = 0
print "Reverse written to", output
with open(output, "w") as output_file:
for fn in sorted(counts_reverse.keys()):
output.write("%s\t%d\n" % (fn, counts_reverse[fn]))
used_features_count += 1
used_features_sum += counts_reverse[fn]
output_file.write("__no_feature\t%d\n" % empty_reverse)
output_file.write("__ambiguous\t%d\n" % ambiguous_reverse)
output_file.write("__too_low_aQual\t%d\n" % lowqual)
output_file.write("__not_aligned\t%d\n" % notaligned)
output_file.write("__alignment_not_unique\t%d\n" % nonunique)
print "Reverse features with alignment\t%d" % used_features_count
print "Reverse alignments asigned to feature\t%d" % used_features_sum
print "__reverse_no_feature\t%d" % empty_reverse
print "__reverse_ambiguous\t%d" % ambiguous_reverse
print "__too_low_aQual\t%d" % lowqual
print "__not_aligned\t%d" % notaligned
print "__alignment_not_unique\t%d" % nonunique
def count_reads(sam_filename, features, counts, samtype, order, forward,
reverse, overlap_mode, quiet, minaqual, samout, directory):
def write_to_samout(r, assignment):
if samoutfile is None:
return
if not pe_mode:
r = (r,)
for read in r:
if read is not None:
samoutfile.write(read.original_sam_line.rstrip() +
"\tXF:Z:" + assignment + "\n")
if samout != "":
samoutfile = open(samout, "w")
else:
samoutfile = None
if samtype is None:
samtype = detect_sam_type(sam_filename)
if samtype == "sam":
SAM_or_BAM_Reader = HTSeq.SAM_Reader
elif samtype == "bam":
SAM_or_BAM_Reader = HTSeq.BAM_Reader
else:
raise ValueError("Unknown input format %s specified." % samtype)
try:
if sam_filename != "-":
read_seq_file = SAM_or_BAM_Reader(sam_filename)
read_seq = read_seq_file
first_read = iter(read_seq).next()
else:
read_seq_file = SAM_or_BAM_Reader(sys.stdin)
read_seq_iter = iter(read_seq_file)
first_read = read_seq_iter.next()
read_seq = itertools.chain([first_read], read_seq_iter)
pe_mode = first_read.paired_end
except:
sys.stderr.write("Error occured when reading beginning "
"of SAM/BAM file.\n")
raise
try:
if pe_mode:
if order == "name":
read_seq = HTSeq.pair_SAM_alignments(read_seq)
elif order == "pos":
read_seq = HTSeq.pair_SAM_alignments_with_buffer(read_seq)
else:
raise ValueError("Illegal order specified.")
if forward:
empty_forward = 0
ambiguous_forward = 0
counts_forward = copy.copy(counts)
if reverse:
empty_reverse = 0
ambiguous_reverse = 0
counts_reverse = copy.copy(counts)
notaligned = 0
lowqual = 0
nonunique = 0
i = 0
for r in read_seq:
if i > 0 and i % 100000 == 0 and not quiet:
sys.stderr.write("%d SAM alignment record%s processed.\n" %
(i, "s" if not pe_mode else " pairs"))
i += 1
if not pe_mode:
if not r.aligned:
notaligned += 1
write_to_samout(r, "__not_aligned")
continue
try:
if r.optional_field("NH") > 1:
nonunique += 1
write_to_samout(r, "__alignment_not_unique")
continue
except KeyError:
pass
if r.aQual < minaqual:
lowqual += 1
write_to_samout(r, "__too_low_aQual")
continue
if forward:
iv_seq_for = (co.ref_iv for co in r.cigar
if co.type == "M" and co.size > 0)
if reverse:
iv_seq_rev = (invert_strand(co.ref_iv) for co in r.cigar
if co.type == "M" and co.size > 0)
else:
if r[0] is not None and r[0].aligned:
if forward:
iv_seq_for = (co.ref_iv for co in r[0].cigar
if co.type == "M" and co.size > 0)
if reverse:
iv_seq_rev = (invert_strand(co.ref_iv) for co in
r[0].cigar if co.type == "M"
and co.size > 0)
else:
iv_seq_rev = tuple()
iv_seq_for = tuple()
if r[1] is not None and r[1].aligned:
if forward:
iv_seq_for = (itertools.chain(iv_seq_for,
(invert_strand(co.ref_iv)
for co in r[1].cigar if co.type == "M"
and co.size > 0)))
if reverse:
iv_seq_rev = itertools.chain(iv_seq_rev, (co.ref_iv
for co in r[1].cigar
if co.type == "M"
and co.size > 0))
else:
if (r[0] is None) or not (r[0].aligned):
write_to_samout(r, "__not_aligned")
notaligned += 1
continue
try:
if ((r[0] is not None and r[0].optional_field("NH") > 1)
or (r[1] is not None and
r[1].optional_field("NH") > 1)):
nonunique += 1
write_to_samout(r, "__alignment_not_unique")
continue
except KeyError:
pass
if ((r[0] and r[0].aQual < minaqual) or
(r[1] and r[1].aQual < minaqual)):
lowqual += 1
write_to_samout(r, "__too_low_aQual")
continue
try:
if overlap_mode == "union":
if forward:
fs_for = set()
for iv in iv_seq_for:
if iv.chrom not in features.chrom_vectors:
raise UnknownChrom
for iv2, fs2 in features[iv].steps():
fs_for = fs_for.union(fs2)
if reverse:
fs_rev = set()
for iv in iv_seq_rev:
if iv.chrom not in features.chrom_vectors:
raise UnknownChrom
for iv2, fs2 in features[iv].steps():
fs_rev = fs_rev.union(fs2)
elif (overlap_mode == "intersection-strict" or
overlap_mode == "intersection-nonempty"):
if forward:
fs_for = None
for iv in iv_seq_for:
if iv.chrom not in features.chrom_vectors:
raise UnknownChrom
for iv2, fs2 in features[iv].steps():
if len(fs2) > 0 or \
overlap_mode == "intersection-strict":
if fs_for is None:
fs_for = fs2.copy()
else:
fs_for = fs_for.intersection(fs2)
if reverse:
fs_reverse = None
for iv in iv_seq_rev:
if iv.chrom not in features.chrom_vectors:
raise UnknownChrom
for iv2, fs2 in features[iv].steps():
if len(fs2) > 0 or \
overlap_mode == "intersection-strict":
if fs_rev is None:
fs_rev = fs2.copy()
else:
fs_rev = fs_rev.intersection(fs2)
else:
sys.exit("Illegal overlap mode.")
if forward:
if fs_for is None or len(fs_for) == 0:
write_to_samout(r, "__no_feature")
empty_forward += 1
elif len(fs_for) > 1:
write_to_samout(r, "__ambiguous[" +
'+'.join(fs_for) + "]")
ambiguous_forward += 1
else:
write_to_samout(r, list(fs_for)[0])
counts_forward[list(fs_for)[0]] += 1
if reverse:
if fs_reverse is None or len(fs_rev) == 0:
write_to_samout(r, "__no_feature")
empty_reverse += 1
elif len(fs_reverse) > 1:
write_to_samout(r, "__ambiguous[" +
'+'.join(fs_rev) + "]")
ambiguous_reverse += 1
else:
write_to_samout(r, list(fs_rev)[0])
counts_reverse[list(fs_rev)[0]] += 1
except UnknownChrom:
write_to_samout(r, "__no_feature")
empty_forward += 1
empty_reverse += 1
except:
sys.stderr.write("Error occured when processing SAM input (%s):\n" %
read_seq_file.get_line_number_string())
raise
if not quiet:
sys.stderr.write("%d SAM %s processed.\n" %
(i, "alignments "
if not pe_mode else "alignment pairs"))
if samoutfile is not None:
samoutfile.close()
if forward:
output = brenninc_utils.create_new_file(sam_filename,
"_forward_count",
outputdir=directory,
extension="txt",
gzipped=False)
used_features_count = 0
used_features_sum = 0
print "Forward written to", output
with open(output, "w") as output_file:
for fn in sorted(counts_forward.keys()):
output_file.write("%s\t%d\n" % (fn, counts_forward[fn]))
used_features_count += 1
used_features_sum += counts_forward[fn]
output_file.write("__no_feature\t%d\n" % empty_forward)
output_file.write("__ambiguous\t%d\n" % ambiguous_forward)
output_file.write("__too_low_aQual\t%d\n" % lowqual)
output_file.write("__not_aligned\t%d\n" % notaligned)
output_file.write("__alignment_not_unique\t%d\n" % nonunique)
print "Forward features with alignment\t%d" % used_features_count
print "Forward alignments asigned to feature\t%d" % used_features_sum
print "__forward_no_feature\t%d" % empty_forward
print "__forward_ambiguous\t%d" % ambiguous_forward
if reverse:
output = brenninc_utils.create_new_file(sam_filename,
"_reverse_count",
outputdir=directory,
extension="txt",
gzipped=False)
used_features_count = 0
used_features_sum = 0
print "Reverse written to", output
with open(output, "w") as output_file:
for fn in sorted(counts_reverse.keys()):
output.write("%s\t%d\n" % (fn, counts_reverse[fn]))
used_features_count += 1
used_features_sum += counts_reverse[fn]
output_file.write("__no_feature\t%d\n" % empty_reverse)
output_file.write("__ambiguous\t%d\n" % ambiguous_reverse)
output_file.write("__too_low_aQual\t%d\n" % lowqual)
output_file.write("__not_aligned\t%d\n" % notaligned)
output_file.write("__alignment_not_unique\t%d\n" % nonunique)
print "Reverse features with alignment\t%d" % used_features_count
print "Reverse alignments asigned to feature\t%d" % used_features_sum
print "__reverse_no_feature\t%d" % empty_reverse
print "__reverse_ambiguous\t%d" % ambiguous_reverse
print "__too_low_aQual\t%d" % lowqual
print "__not_aligned\t%d" % notaligned
print "__alignment_not_unique\t%d" % nonunique
