def parse_description(s):
"""
Returns a dictionary based on the FASTA header, assuming JCVI data
"""
s = "".join(s.split()[1:]).replace("/", ";")
a = parse_qs(s)
return a
def make_attributes(s, gff3=True):
"""
In GFF3, the last column is typically:
ID=cds00002;Parent=mRNA00002;
In GFF2, the last column is typically:
Gene 22240.t000374; Note "Carbonic anhydrase"
"""
if gff3:
d = parse_qs(s)
else:
attributes = s.split("; ")
d = DefaultOrderedDict(list)
for a in attributes:
key, val = a.strip().split(' ', 1)
val = val.replace('"', '')
d[key].append(val)
for key, val in d.items():
d[key] = list(flatten([v.split(",") for v in val]))
return d