def get_merge_gene(fh, header=[None]):
if header[0] is None:
header[0] = fh.readline()
line = fh.readline()
genes = []
while line and line[0] != "#":
d = DagLine(line)
genes.append(d)
line = fh.readline()
if len(genes) == 0: return None, None
l = header[0]
header_string = parse_pyheader(header[0], asstring=True)
# save the next header.
header[0] = line
# header string is joined with JS
reverse = JS + "r" + JS in header_string
a_start = min(g.a_start for g in genes)
a_end = max(g.a_end for g in genes)
b_start = min(g.b_start for g in genes)
b_end = max(g.b_end for g in genes)
if reverse: b_start, b_end = b_end, b_start
d = {'a_seqid': genes[0].a_seqid,
'b_seqid': genes[0].b_seqid,
'a_accn': 'a' + header_string,
'b_accn': 'b' + header_string,
'a_start': a_start,
'b_start': b_start,
'a_end': a_end,
'b_end': b_end,
'evalue': 1e-250}
return DagLine.from_dict(d), header_string
def get_dag_line(fh):
line = fh.readline()
if not line: return None, None
if line[0] == "#":
get_dag_line.header = parse_pyheader(line, asstring=True)
line = fh.readline()
return DagLine(line), get_dag_line.header
def matches_by_diag_id(matches):
""" take the structure returned by parse_file and return a dictionary
where the keys are the diag_ids and the values are the dag-pair."""
by_diag = collections.defaultdict(list)
for seqid_pair, accn_pair_dict in matches.iteritems():
for accn_pair_key, accn_pair in accn_pair_dict.iteritems():
assert accn_pair['diag_str'] is not None
by_diag[accn_pair['diag_str']].append(DagLine.from_pair_dict(accn_pair))
return dict(by_diag)
def matches_by_diag_id(matches):
""" take the structure returned by parse_file and return a dictionary
where the keys are the diag_ids and the values are the dag-pair."""
by_diag = collections.defaultdict(list)
for seqid_pair, accn_pair_dict in matches.iteritems():
for accn_pair_key, accn_pair in accn_pair_dict.iteritems():
assert accn_pair['diag_str'] is not None
by_diag[accn_pair['diag_str']].append(
DagLine.from_pair_dict(accn_pair))
return dict(by_diag)
def get_merge_gene(fh, header=[None]):
if header[0] is None:
header[0] = fh.readline()
line = fh.readline()
genes = []
while line and line[0] != "#":
d = DagLine(line)
genes.append(d)
line = fh.readline()
if len(genes) == 0: return None, None
l = header[0]
header_string = parse_pyheader(header[0], asstring=True)
# save the next header.
header[0] = line
# header string is joined with JS
reverse = JS + "r" + JS in header_string
a_start = min(g.a_start for g in genes)
a_end = max(g.a_end for g in genes)
b_start = min(g.b_start for g in genes)
b_end = max(g.b_end for g in genes)
if reverse: b_start, b_end = b_end, b_start
d = {
'a_seqid': genes[0].a_seqid,
'b_seqid': genes[0].b_seqid,
'a_accn': 'a' + header_string,
'b_accn': 'b' + header_string,
'a_start': a_start,
'b_start': b_start,
'a_end': a_end,
'b_end': b_end,
'evalue': 1e-250
}
return DagLine.from_dict(d), header_string
