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 main():
genomes = ppr.get_genomes()
hist = []
numbers = []
locale = []
family = []
for g in genomes:
print g
pprs = list(ppr.load_pprs(g))
numbers.append((short_name(g), ) + get_numbers(pprs))
hist.append(length_hist(pprs))
locale.append((short_name(g), ) + get_localization(pprs))
family.append((short_name(g), ) + get_family(pprs))
numbers.sort(key=lambda n: n[1])
family.sort(key=lambda f: sum(f[1:]))
hist = fmt_hist(hist)
utils.write_data(('genome', ) + get_numbers_hdr(), numbers,
"output/ppr_numbers.dat")
utils.write_data([
'length',
] + [short_name(g) for g in genomes], hist, "output/ppr_lengths.dat")
utils.write_data(('genome', ) + get_localization_hdr(), locale,
"output/ppr_localization.dat")
utils.write_data(('genome', ) + get_family_hdr(), family,
"output/ppr_families.dat")
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 main():
genomes = ppr.get_genomes()
hist = []
numbers = []
locale = []
family = []
for g in genomes:
print g
pprs = list(ppr.load_pprs(g))
numbers.append((short_name(g),) + get_numbers(pprs))
hist.append(length_hist(pprs))
locale.append((short_name(g),) + get_localization(pprs))
family.append((short_name(g),) + get_family(pprs))
numbers.sort(key=lambda n: n[1])
family.sort(key=lambda f: sum(f[1:]))
hist = fmt_hist(hist)
utils.write_data(("genome",) + get_numbers_hdr(), numbers, "output/ppr_numbers.dat")
utils.write_data(["length"] + [short_name(g) for g in genomes], hist, "output/ppr_lengths.dat")
utils.write_data(("genome",) + get_localization_hdr(), locale, "output/ppr_localization.dat")
utils.write_data(("genome",) + get_family_hdr(), family, "output/ppr_families.dat")