def save_predotar():
genomes = ppr.get_genomes()
data = []
vals = [
u"none",
u"mitochondrial",
u"plastid",
u"er",
u"elsewhere",
u"possibly mitochondrial",
u"possibly plastid",
u"possibly er",
u"possibly elsewhere",
]
for g in genomes:
pprs = ppr.load_records(g)
if len(pprs) < 50:
continue
row = [0] * len(vals)
total = float(len(pprs))
for p in pprs:
pred = p.annotations["predotar"]
if pred not in vals:
raise ValueError("didn't expect {}".format(pred))
else:
row[vals.index(pred)] += 1
row = [float(r) / total for r in row]
data.append([short_name(g)] + row)
data.sort(key=lambda d: d[1])
utils.write_data(["genome"] + vals, data, "output/ppr_predotar.dat")
def annotate_all(genome_name='Arabidopsis_thaliana',plastid_name='NC_000932'):
pprs = [p for p in PPR.load_records(genome_name) if (len(p.features) >= 23
and p.annotations.get('localization','').upper() == 'C')]
plastid = utils.load_plastid(plastid_name)
plastid.features = [f for f in plastid.features if f.type.lower() == 'gene']
annotate_binding_domains(pprs, plastid)
ofile = os.path.join(utils.OutDir, "Binding/{}--{}.gb".format(genome_name,
plastid_name))
SeqIO.write(plastid, ofile, 'gb')
def save_predotar():
genomes = ppr.get_genomes()
data = []
vals = [
u'none',
u'mitochondrial',
u'plastid',
u'er',
u'elsewhere',
u'possibly mitochondrial',
u'possibly plastid',
u'possibly er',
u'possibly elsewhere',
]
for g in genomes:
pprs = ppr.load_records(g)
if len(pprs) < 50:
continue
row = [
0,
] * len(vals)
total = float(len(pprs))
for p in pprs:
pred = p.annotations['predotar']
if pred not in vals:
raise ValueError("didn't expect {}".format(pred))
else:
row[vals.index(pred)] += 1
row = [float(r) / total for r in row]
data.append([
short_name(g),
] + row)
data.sort(key=lambda d: d[1])
utils.write_data([
"genome",
] + vals, data, "output/ppr_predotar.dat")