def parse_m5_record(r_m5_record):
if r_m5_record['tStrand'] != '+':
raise NotImplementedError, (
'Mapping indicates negative strand reference mapping.')
if r_m5_record['qStrand'] == "+":
alignVals = zip(r_m5_record['qAlignedSeq'], r_m5_record['tAlignedSeq'])
else:
alignVals = zip(nh.rev_comp(r_m5_record['qAlignedSeq']),
nh.rev_comp(r_m5_record['tAlignedSeq']))
alignVals, start_clipped_bases, end_clipped_bases, genome_loc \
= clip_m5_alignment(
alignVals, int(r_m5_record['tStart']),
r_m5_record['qStrand'], r_m5_record['tName'])
return (alignVals, genome_loc, start_clipped_bases, end_clipped_bases)
def align_to_genome(basecalls, genome_filename, graphmap_path):
## align to genome
read_fp = NamedTemporaryFile(delete=False, suffix='.fasta')
read_fp.write(">" + ''.join(basecalls[:5]) + '\n' + ''.join(basecalls) +
'\n')
read_fp.close()
out_fp = NamedTemporaryFile(delete=False)
try:
# suppress output from graphmap with devnull sink
with open(os.devnull, 'w') as FNULL:
exitStatus = call([
graphmap_path, 'align', '-r', genome_filename, '-d',
read_fp.name, '-o', out_fp.name, '-L', 'm5'
],
stdout=FNULL,
stderr=STDOUT)
alignment = dict(zip(GRAPHMAP_FIELDS, out_fp.readline().split()))
out_fp.close()
except:
raise OSError, ('Problem running/parsing graphmap. Ensure ' +
'you have a compatible version installed.')
## flip read and genome to match raw signal if neg strand mapped
if len(alignment) != len(GRAPHMAP_FIELDS):
raise NotImplementedError, ('Graphmap did not produce alignment.')
if alignment['tStrand'] != '+':
raise NotImplementedError, (
'Graphmap indicates negative strand reference mapping.')
if alignment['qStrand'] == "+":
alignVals = zip(alignment['qAlignedSeq'], alignment['tAlignedSeq'])
else:
alignVals = zip(rev_comp(alignment['qAlignedSeq']),
rev_comp(alignment['tAlignedSeq']))
return alignVals, genomeLoc(int(alignment['tStart']), alignment['qStrand'],
alignment['tName'])
def write_most_signif(files1, files2, num_regions, qval_thresh,
corrected_group, basecall_subgroups, seqs_fn, num_bases,
test_type, obs_filter, min_test_vals, stats_fn, fasta_fn,
fishers_method_offset):
calc_stats = stats_fn is None or not os.path.isfile(stats_fn)
if not calc_stats:
if VERBOSE: sys.stderr.write('Loading statistics from file.\n')
all_stats = ns.parse_stats(stats_fn)
if calc_stats or fasta_fn is None:
if VERBOSE: sys.stderr.write('Parsing files.\n')
raw_read_coverage1 = nh.parse_fast5s(files1, corrected_group,
basecall_subgroups)
raw_read_coverage2 = nh.parse_fast5s(files2, corrected_group,
basecall_subgroups)
raw_read_coverage1 = nh.filter_reads(raw_read_coverage1, obs_filter)
raw_read_coverage2 = nh.filter_reads(raw_read_coverage2, obs_filter)
if calc_stats:
if VERBOSE: sys.stderr.write('Calculating statistics.\n')
all_stats = ns.get_all_significance(raw_read_coverage1,
raw_read_coverage2, test_type,
min_test_vals, stats_fn,
fishers_method_offset)
plot_intervals = ns.get_most_signif_regions(all_stats, num_bases,
num_regions, qval_thresh)
if fasta_fn is None:
reg_seqs = get_region_sequences(plot_intervals, raw_read_coverage1,
raw_read_coverage2, num_bases,
corrected_group)
else:
fasta_records = nh.parse_fasta(fasta_fn)
reg_seqs = [(p_int, fasta_records[chrm][start:start + num_bases])
for p_int, (chrm, start, strand,
reg_name) in plot_intervals
if chrm in fasta_records]
# get reads overlapping each region
if VERBOSE: sys.stderr.write('Outputting region seqeuences.\n')
with open(seqs_fn, 'w') as seqs_fp:
for reg_i, reg_seq in reg_seqs:
chrm, start, strand, stat = next(
p_int for p_reg_i, p_int in plot_intervals if p_reg_i == reg_i)
if strand == '-':
reg_seq = nh.rev_comp(reg_seq)
seqs_fp.write('>{0}::{1:d}::{2} {3}\n{4}\n'.format(
chrm, start, strand, stat, ''.join(reg_seq)))
return
def parse_sam_record(r_sam_record, genome_index):
# parse cigar string
cigar = [(int(reg_len), reg_type)
for reg_len, reg_type in CIGAR_PAT.findall(r_sam_record['cigar'])]
if len(cigar) < 1:
raise RuntimeError, 'Invalid cigar string produced.'
strand = '-' if int(r_sam_record['flag']) & 0x10 else '+'
if strand == '-':
cigar = cigar[::-1]
# record clipped bases and remove from query seq as well as cigar
qSeq = r_sam_record['seq'] if strand == '+' else nh.rev_comp(
r_sam_record['seq'])
start_clipped_bases = 0
end_clipped_bases = 0
# handle clipping elements (H and S)
if cigar[0][1] == 'H':
start_clipped_bases += cigar[0][0]
cigar = cigar[1:]
if cigar[-1][1] == 'H':
end_clipped_bases += cigar[-1][0]
cigar = cigar[:-1]
if cigar[0][1] == 'S':
start_clipped_bases += cigar[0][0]
qSeq = qSeq[cigar[0][0]:]
cigar = cigar[1:]
if cigar[-1][1] == 'S':
end_clipped_bases += cigar[-1][0]
qSeq = qSeq[:-cigar[-1][0]]
cigar = cigar[:-1]
tLen = sum([reg_len for reg_len, reg_type in cigar if reg_type in 'MDN=X'])
tSeq = genome_index[r_sam_record['rName']][int(r_sam_record['pos']) -
1:int(r_sam_record['pos']) +
tLen - 1]
if strand == '-': tSeq = nh.rev_comp(tSeq)
# check that cigar starts and ends with matched bases
while cigar[0][1] not in 'M=X':
if cigar[0][1] in 'IP':
tSeq = tSeq[cigar[0][0]:]
else:
qSeq = qSeq[cigar[0][0]:]
start_clipped_bases += cigar[0][0]
cigar = cigar[1:]
while cigar[-1][1] not in 'M=X':
if cigar[-1][1] in 'IP':
tSeq = tSeq[:-cigar[-1][0]]
else:
qSeq = qSeq[:-cigar[-1][0]]
end_clipped_bases += cigar[0][0]
cigar = cigar[:-1]
qLen = sum([reg_len for reg_len, reg_type in cigar if reg_type in 'MIP=X'])
assert len(qSeq) == qLen, 'Read sequence from SAM and ' + \
'cooresponding cigar string do not agree.'
# create pairwise alignment via zipped pairs
alignVals = []
for reg_len, reg_type in cigar:
if reg_type in 'M=X':
alignVals.extend(zip(qSeq[:reg_len], tSeq[:reg_len]))
qSeq = qSeq[reg_len:]
tSeq = tSeq[reg_len:]
elif reg_type in 'IP':
alignVals.extend(zip(qSeq[:reg_len], repeat('-')))
qSeq = qSeq[reg_len:]
else:
alignVals.extend(zip(repeat('-'), tSeq[:reg_len]))
tSeq = tSeq[reg_len:]
return (alignVals,
genomeLoc(
int(r_sam_record['pos']) - 1, strand,
r_sam_record['rName']), start_clipped_bases, end_clipped_bases)