def write_output(sam_reader, outf, reftag, outfmt, flank_size, logger=None):
logger = logger or NullLogger()
hit_processor = SnpHitProcessor(reftag, outf, outfmt, flank_size, logger)
hit_processor.write_header()
for i, m in enumerate(sam_reader):
hit_processor.process(m)
hit_processor.dump_current_hits() # last pair
return i + 1
def write_output(db_snp_reader, outf, mask_size, logger=None):
logger = logger or NullLogger()
bad_count = 0
for rs_label, lflank, alleles, rflank in db_snp_reader:
alleles = alleles.split("/")
if 2 <= len(alleles) <= 4 and set(alleles) <= POSSIBLE_ALLELES:
mask = build_mask(lflank, alleles, rflank, mask_size)
outf.write("%s\t%s\t%s\n" % (rs_label, rs_label, mask))
else:
logger.warn("%r: bad alleles %r, skipping" % (rs_label, alleles))
bad_count += 1
return bad_count
def write_output(reader, outf, logger=None):
logger = logger or NullLogger()
seq_count = 0
name_serializer = SeqNameSerializer()
for r in reader:
fastq_records = build_fastq_records(r['label'],
r['mask'],
name_serializer,
logger=logger)
seq_count += len(fastq_records)
for r in fastq_records:
outf.write("%s\n" % "\n".join(r))
return seq_count
def __init__(self,
ref_tag,
outf,
outfmt=DEFAULT_OUTPUT_FORMAT,
flank_size=DEFAULT_FLANK_SIZE,
logger=None):
self.logger = logger or NullLogger()
self.ref_tag = ref_tag
self.outf = outf
self.outfmt = outfmt
self.flank_size = flank_size
self.current_id = None
self.current_hits = []
self.serializer = SeqNameSerializer()
def build_fastq_records(label, mask, name_serializer, logger=None):
logger = logger or NullLogger()
records = []
try:
lflank, alleles, rflank = split_mask(mask)
except ValueError:
status = "no mask" if mask == "None" else "bad mask format"
logger.warn("%r: %s, skipping" % (label, status))
else:
snp_offset = len(lflank)
for a, c in izip(alleles, ALLELE_CODES):
seq = "%s%s%s" % (lflank, a, rflank)
seq_id = name_serializer.serialize(label, c, snp_offset, alleles)
r = ('@%s' % seq_id, seq, '+%s' % seq_id, '~' * len(seq))
records.append(r)
return records
def write_output(reader, outf, logger=None):
logger = logger or NullLogger()
bad_count = 0
for r in reader:
label = r['Probe Set ID']
if r['dbSNP RS ID'].startswith('rs'):
rs_label = r['dbSNP RS ID']
else:
rs_label = 'None'
mask = r['Flank']
problem = check_mask(mask)
if problem:
mask = 'None'
logger.warn("%r: %s, setting mask to 'None'" % (label, problem))
bad_count += 1
outf.write("%s\t%s\t%s\t%s\t%s\n" %
(label, rs_label, mask, r['Allele A'], r['Allele B']))
return bad_count
def write_output(reader, outf, logger=None):
logger = logger or NullLogger()
bad_count = 0
for r in reader:
label = r['IlmnID']
if r['Name'].startswith('rs'):
rs_label = r['Name']
else:
rs_label = 'None'
mask = r['TopGenomicSeq']
# alleles are the same as those extracted from the mask if strand
# is TOP; if strand is BOT they are their complement (NOT reversed)
allele_a, allele_b = r['SNP'].strip("[]").split("/")
problem = check_mask(mask)
if problem:
mask = 'None'
logger.warn("%r: %s, setting mask to 'None'" % (label, problem))
bad_count += 1
outf.write("%s\t%s\t%s\t%s\t%s\n" %
(label, rs_label, mask, allele_a, allele_b))
return bad_count