def parse_psl(psl_file, min_id=0.90, cover_thres=0.96):
"""
Calculate a truth table by considering the accumulated coverage of query sequences onto
the references. The coverage is treated as a binary mask and the total extent a contig
covers each reference determines the degree of ownership.
Writes out a full truth table to user specified output path.
Note: ideally the PSL file should be sorted for descending alignment score.
:param psl_file:
:param min_id: ignore alignments whose identity is less than this threshold
:param cover_thres: query mean coverage threshold required for assignment to a ref be accepted.
:return: None -- this method presently breaks the logical flow of this script.
"""
with open(psl_file, 'r') as h_in:
all_hits = 0
rejected = 0
aln_masks = {}
# traverse alignment file, build up the masks for each query to reference[s] assocs.
for aln in Psl.parse(h_in):
all_hits += 1
if aln.percent_id < min_id:
rejected += 1
continue
if aln.q_name not in aln_masks:
aln_masks[aln.q_name] = {}
if aln.t_name not in aln_masks[aln.q_name]:
aln_masks[aln.q_name][aln.t_name] = np.zeros(int(aln.q_size))
per_id = aln.percent_id
mask_slice = aln_masks[aln.q_name][aln.t_name][aln.q_start:aln.q_end+1]
mask_slice[np.where(mask_slice < per_id)] = per_id
# build dictionary of assignments and weights
truth = {}
weights = {}
for n, ti in enumerate(aln_masks):
masks = np.vstack(aln_masks[ti].values())
names = np.array(aln_masks[ti].keys())
covers = np.mean(masks, 1)
idx = np.where(covers > cover_thres)
if idx[0].shape[0] > 0:
truth[ti] = {}
for i in np.nditer(idx):
truth[ti][str(names[i])] = float(covers[i])
weights[ti] = masks.shape[1]
# initialize truthtable
ttable = tt.TruthTable()
ttable.update(truth, weights)
return ttable
def parse_psl(psl_file):
"""
Parse a PSL converted from MAF
:param psl_file: PSL format alignment file
:return: dictionary of Alignment objects
"""
all_hits = 0
rejected = 0
alignment_repo = OrderedDict()
with open(psl_file, 'r') as h_in:
for aln in Psl.parse(h_in):
all_hits += 1
# ignore alignment records which fall below mincov or minid
# wrt the length of the alignment vs query sequence.
if aln.coverage < args.mincov or aln.percent_id < args.minid:
rejected += 1
continue
ai = Alignment(aln.q_name, aln.t_name, aln.length, aln.q_size, aln.percent_id)
if ai in alignment_repo:
alignment_repo[ai].add_bases(aln.length)
else:
alignment_repo[ai] = ai
print 'Rejected {0}/{1} alignments due to constraints on ID {2} and Coverage {3}'.format(
rejected, all_hits, args.minid, args.mincov)
return alignment_repo
def parse_psl(psl_file):
"""
Parse a PSL converted from MAF
:param psl_file: PSL format alignment file
:return: dictionary of Alignment objects
"""
all_hits = 0
rejected = 0
alignment_repo = OrderedDict()
with open(psl_file, 'r') as h_in:
for aln in Psl.parse(h_in):
all_hits += 1
# ignore alignment records which fall below mincov or minid
# wrt the length of the alignment vs query sequence.
if aln.coverage < args.mincov or aln.percent_id < args.minid:
rejected += 1
continue
ai = Alignment(aln.q_name, aln.t_name, aln.length, aln.q_size,
aln.percent_id)
if ai in alignment_repo:
alignment_repo[ai].add_bases(aln.length)
else:
alignment_repo[ai] = ai
print 'Rejected {0}/{1} alignments due to constraints on ID {2} and Coverage {3}'.format(
rejected, all_hits, args.minid, args.mincov)
return alignment_repo
def parse_psl2(psl_file):
"""
Calculate a truth table by considering the accumulated coverage of query sequences onto
the references. The coverage is treated as a binary mask and the total extent a contig
covers each reference determines the degree of ownership.
Writes out a full truth table to user specified output path.
Note: ideally the PSL file should be sorted for descending alignment score.
:param psl_file:
:return: None -- this method presently breaks the logical flow of this script.
"""
with open(psl_file, 'r') as h_in:
all_hits = 0
rejected = 0
aln_masks = {}
for aln in Psl.parse(h_in):
all_hits += 1
if aln.percent_id < 90:
rejected += 1
continue
if aln.q_name not in aln_masks:
aln_masks[aln.q_name] = {}
if aln.t_name not in aln_masks[aln.q_name]:
aln_masks[aln.q_name][aln.t_name] = np.zeros(int(aln.q_size))
per_id = 0.01 * aln.percent_id
mask_slice = aln_masks[aln.q_name][aln.t_name][
aln.q_start:aln.q_end + 1] #= aln.percent_id/100.
mask_slice[np.where(mask_slice < per_id)] = per_id
truth = {}
weights = {}
for n, ti in enumerate(aln_masks):
masks = np.vstack(aln_masks[ti].values())
names = np.array(aln_masks[ti].keys())
covers = np.mean(masks, 1)
idx = np.where(covers > 0.96)
if idx[0].shape[0] > 0:
truth[ti] = {}
for i in np.nditer(idx):
truth[ti][str(names[i])] = float(covers[i])
weights[ti] = masks.shape[1]
t = tt.TruthTable()
t.update(truth, weights)
t.write(args.output_file[0])
def parse_psl2(psl_file):
"""
Calculate a truth table by considering the accumulated coverage of query sequences onto
the references. The coverage is treated as a binary mask and the total extent a contig
covers each reference determines the degree of ownership.
Writes out a full truth table to user specified output path.
Note: ideally the PSL file should be sorted for descending alignment score.
:param psl_file:
:return: None -- this method presently breaks the logical flow of this script.
"""
with open(psl_file, 'r') as h_in:
all_hits = 0
rejected = 0
aln_masks = {}
for aln in Psl.parse(h_in):
all_hits += 1
if aln.percent_id < 90:
rejected += 1
continue
if aln.q_name not in aln_masks:
aln_masks[aln.q_name] = {}
if aln.t_name not in aln_masks[aln.q_name]:
aln_masks[aln.q_name][aln.t_name] = np.zeros(int(aln.q_size))
per_id = 0.01 * aln.percent_id
mask_slice = aln_masks[aln.q_name][aln.t_name][aln.q_start:aln.q_end+1] #= aln.percent_id/100.
mask_slice[np.where(mask_slice < per_id)] = per_id
truth = {}
weights = {}
for n, ti in enumerate(aln_masks):
masks = np.vstack(aln_masks[ti].values())
names = np.array(aln_masks[ti].keys())
covers = np.mean(masks, 1)
idx = np.where(covers > 0.96)
if idx[0].shape[0] > 0:
truth[ti] = {}
for i in np.nditer(idx):
truth[ti][str(names[i])] = float(covers[i])
weights[ti] = masks.shape[1]
t = tt.TruthTable()
t.update(truth, weights)
t.write(args.output_file[0])
