def cog_info(candidates, sp2hits):
sp_coverages = [hits / float(len(candidates)) for hits in sp2hits.values()]
species_covered = len(set(sp2hits.keys())) + 1
min_cov = _min(sp_coverages)
max_cov = _min(sp_coverages)
median_cov = _median(sp_coverages)
return min_cov, max_cov, median_cov
def cog_info(candidates, sp2hits):
sp_coverages = [hits/float(len(candidates)) for hits in sp2hits.values()]
species_covered = len(set(sp2hits.keys()))+1
min_cov = _min(sp_coverages)
max_cov = _min(sp_coverages)
median_cov = _median(sp_coverages)
return min_cov, max_cov, median_cov
def sort_cogs_by_sp_repr(c1, c2):
c1_repr = _min([sp2cogs[_sp] for _sp, _seq in c1])
c2_repr = _min([sp2cogs[_sp] for _sp, _seq in c2])
r = cmp(c1_repr, c2_repr)
if r == 0:
r = -1 * cmp(len(c1), len(c2))
if r == 0:
return cmp(sorted(c1), sorted(c2))
else:
return r
else:
return r
def _sort_cogs(cogs1, cogs2):
cogs1 = cogs1[1] # discard seed info
cogs2 = cogs2[1] # discard seed info
cog_sizes1 = [len(cog) for cog in cogs1]
cog_sizes2 = [len(cog) for cog in cogs2]
mx1, mn1, avg1 = _max(cog_sizes1), _min(cog_sizes1), round(_mean(cog_sizes1))
mx2, mn2, avg2 = _max(cog_sizes2), _min(cog_sizes2), round(_mean(cog_sizes2))
# we want to maximize all these values in the following order:
for i, j in ((mx1, mx2), (avg1, avg2), (len(cogs1), len(cogs2))):
v = -1 * cmp(i, j)
if v != 0:
break
return v
def _sort_cogs(cogs1, cogs2):
cogs1 = cogs1[1] # discard seed info
cogs2 = cogs2[1] # discard seed info
cog_sizes1 = [len(cog) for cog in cogs1]
cog_sizes2 = [len(cog) for cog in cogs2]
mx1, mn1, avg1 = _max(cog_sizes1), _min(cog_sizes1), round(
_mean(cog_sizes1))
mx2, mn2, avg2 = _max(cog_sizes2), _min(cog_sizes2), round(
_mean(cog_sizes2))
# we want to maximize all these values in the following order:
for i, j in ((mx1, mx2), (avg1, avg2), (len(cogs1), len(cogs2))):
v = -1 * cmp(i, j)
if v != 0:
break
return v
def get_cog_score(candidates, sp2hits, max_cogs, all_species):
cog_cov = _mean([len(cogs) for cogs in candidates])/float(len(sp2hits)+1)
cog_mean_cov = _mean([len(cogs)/float(len(sp2hits)) for cogs in candidates]) # numero medio de especies en cada cog
cog_min_sp = _min([len(cogs) for cogs in candidates])
sp_coverages = [sp2hits.get(sp, 0)/float(len(candidates)) for sp in all_species]
species_covered = len(set(sp2hits.keys()))+1
nfactor = len(candidates)/float(max_cogs) # Numero de cogs
min_cov = _min(sp_coverages) # el coverage de la peor especie
max_cov = _min(sp_coverages)
median_cov = _median(sp_coverages)
cov_std = _std(sp_coverages)
score = _min([nfactor, cog_mean_cov, min_cov])
return score, min_cov, max_cov, median_cov, cov_std, cog_cov
def sort_cogs_by_size(c1, c2):
'''
sort cogs by descending size. If two cogs are the same size, sort
them keeping first the one with the less represented
species. Otherwise sort by sequence name sp_seqid.'''
r = -1 * cmp(len(c1), len(c2))
if r == 0:
# finds the cog including the less represented species
c1_repr = _min([sp2cogs[_sp] for _sp, _seq in c1])
c2_repr = _min([sp2cogs[_sp] for _sp, _seq in c2])
r = cmp(c1_repr, c2_repr)
if r == 0:
return cmp(sorted(c1), sorted(c2))
else:
return r
else:
return r
def get_identity(fname):
s = SeqGroup(fname)
seqlen = len(s.id2seq.itervalues().next())
ident = list()
for i in xrange(seqlen):
states = defaultdict(int)
for seq in s.id2seq.itervalues():
if seq[i] != "-":
states[seq[i]] += 1
values = states.values()
if values:
ident.append(float(max(values)) / sum(values))
return (_max(ident), _min(ident), _mean(ident), _std(ident))
def get_cog_score(candidates, sp2hits, max_cogs, all_species):
cog_cov = _mean([len(cogs)
for cogs in candidates]) / float(len(sp2hits) + 1)
cog_mean_cov = _mean([
len(cogs) / float(len(sp2hits)) for cogs in candidates
]) # numero medio de especies en cada cog
cog_min_sp = _min([len(cogs) for cogs in candidates])
sp_coverages = [
sp2hits.get(sp, 0) / float(len(candidates)) for sp in all_species
]
species_covered = len(set(sp2hits.keys())) + 1
nfactor = len(candidates) / float(max_cogs) # Numero de cogs
min_cov = _min(sp_coverages) # el coverage de la peor especie
max_cov = _min(sp_coverages)
median_cov = _median(sp_coverages)
cov_std = _std(sp_coverages)
score = _min([nfactor, cog_mean_cov, min_cov])
return score, min_cov, max_cov, median_cov, cov_std, cog_cov
def get_seqs_identity(alg, seqs):
""" Returns alg statistics regarding a set of sequences"""
seqlen = len(alg.get_seq(seqs[0]))
ident = list()
for i in xrange(seqlen):
states = defaultdict(int)
for seq_id in seqs:
seq = alg.get_seq(seq_id)
if seq[i] != "-":
states[seq[i]] += 1
values = states.values()
if values:
ident.append(float(max(values)) / sum(values))
return (_max(ident), _min(ident), _mean(ident), _std(ident))
