def cog_info(candidates, sp2hits):
sp_coverages = [hits/float(len(candidates)) for hits in list(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 list(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 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_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_best_selection(cogs_selections, species):
ALL_SPECIES = set(species)
def _compare_cog_selection(cs1, cs2):
seed_1, missing_sp_allowed_1, candidates_1, sp2hits_1 = cs1
seed_2, missing_sp_allowed_2, candidates_2, sp2hits_2 = cs2
score_1, min_cov_1, max_cov_1, median_cov_1, cov_std_1, cog_cov_1 = get_cog_score(
candidates_1, sp2hits_1, median_cogs, ALL_SPECIES - set([seed_1]))
score_2, min_cov_2, max_cov_2, median_cov_2, cov_std_2, cog_cov_2 = get_cog_score(
candidates_2, sp2hits_2, median_cogs, ALL_SPECIES - set([seed_2]))
sp_represented_1 = len(sp2hits_1)
sp_represented_2 = len(sp2hits_1)
cmp_rpr = cmp(sp_represented_1, sp_represented_2)
if cmp_rpr == 1:
return 1
elif cmp_rpr == -1:
return -1
else:
cmp_score = cmp(score_1, score_2)
if cmp_score == 1:
return 1
elif cmp_score == -1:
return -1
else:
cmp_mincov = cmp(min_cov_1, min_cov_2)
if cmp_mincov == 1:
return 1
elif cmp_mincov == -1:
return -1
else:
cmp_maxcov = cmp(max_cov_1, max_cov_2)
if cmp_maxcov == 1:
return 1
elif cmp_maxcov == -1:
return -1
else:
cmp_cand = cmp(len(candidates_1), len(candidates_2))
if cmp_cand == 1:
return 1
elif cmp_cand == -1:
return -1
else:
return 0
min_score = 0.5
max_cogs = _max([len(data[2]) for data in cogs_selections])
median_cogs = _median([len(data[2]) for data in cogs_selections])
cogs_selections.sort(_compare_cog_selection)
cogs_selections.reverse()
header = [
'seed', 'missing sp allowed', 'spcs covered', '#COGs',
'mean sp coverage)', '#COGs for worst sp.', '#COGs for best sp.',
'sp. in COGS(avg)', 'SCORE'
]
print_header = True
best_cog_selection = None
cog_analysis = StringIO()
for i, cogs in enumerate(cogs_selections):
seed, missing_sp_allowed, candidates, sp2hits = cogs
sp_percent_coverages = [
(100 * sp2hits.get(sp, 0)) / float(len(candidates))
for sp in species
]
sp_coverages = [sp2hits.get(sp, 0) for sp in species]
score, min_cov, max_cov, median_cov, cov_std, cog_cov = get_cog_score(
candidates, sp2hits, median_cogs, ALL_SPECIES - set([seed]))
if best_cog_selection is None:
best_cog_selection = i
flag = "*"
else:
flag = " "
data = (candidates,
flag+"%10s" %seed, \
missing_sp_allowed, \
"%d (%0.1f%%)" %(len(set(sp2hits.keys()))+1, 100*float(len(ALL_SPECIES))/(len(sp2hits)+1)) , \
len(candidates), \
"%0.1f%% +- %0.1f" %(_mean(sp_percent_coverages), _std(sp_percent_coverages)), \
"% 3d (%0.1f%%)" %(min(sp_coverages),100*min(sp_coverages)/float(len(candidates))), \
"% 3d (%0.1f%%)" %(max(sp_coverages),100*max(sp_coverages)/float(len(candidates))), \
cog_cov,
score
)
if print_header:
print_as_table([data[1:]],
header=header,
print_header=True,
stdout=cog_analysis)
print_header = False
else:
print_as_table([data[1:]],
header=header,
print_header=False,
stdout=cog_analysis)
#raw_input("Press")
print(cog_analysis.getvalue())
#best_cog_selection = int(raw_input("choose:"))
return cogs_selections[best_cog_selection], cog_analysis
def finish(self):
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 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
all_species = self.targets | self.outgroups
# strict threshold
#min_species = len(all_species) - int(round(self.missing_factor * len(all_species)))
# Relax threshold for cog selection to ensure sames genes are always included
min_species = len(all_species) - int(round(self.missing_factor * len(GLOBALS["target_species"])))
min_species = max(min_species, (1-self.max_missing_factor) * len(all_species))
smallest_cog, largest_cog = len(all_species), 0
all_singletons = []
sp2cogs = defaultdict(int)
for cognumber, cog in enumerate(open(GLOBALS["cogs_file"])):
sp2seqs = defaultdict(list)
for sp, seqid in [list(map(str.strip, seq.split(GLOBALS["spname_delimiter"], 1))) for seq in cog.split("\t")]:
sp2seqs[sp].append(seqid)
one2one_cog = set()
for sp, seqs in six.iteritems(sp2seqs):
#if len(seqs) != 1:
# print sp, len(seqs)
if sp in all_species and len(seqs) == 1:
sp2cogs[sp] += 1
one2one_cog.add((sp, seqs[0]))
smallest_cog = min(smallest_cog, len(one2one_cog))
largest_cog = max(largest_cog, len(one2one_cog))
all_singletons.append(one2one_cog)
#if len(one2one_cog) >= min_species:
# valid_cogs.append(one2one_cog)
cognumber += 1 # sets the ammount of cogs in file
for sp, ncogs in sorted(list(sp2cogs.items()), key=lambda x: x[1], reverse=True):
log.log(28, "% 20s found in single copy in % 6d (%0.1f%%) COGs " %(sp, ncogs, 100 * ncogs/float(cognumber)))
valid_cogs = sorted([sing for sing in all_singletons if len(sing) >= min_species],
sort_cogs_by_size)
log.log(28, "Largest cog size: %s. Smallest cog size: %s" %(
largest_cog, smallest_cog))
self.cog_analysis = ""
# save original cog names hitting the hard limit
if len(valid_cogs) > self.cog_hard_limit:
log.warning("Applying hard limit number of COGs: %d out of %d available" %(self.cog_hard_limit, len(valid_cogs)))
self.raw_cogs = valid_cogs[:self.cog_hard_limit]
self.cogs = []
# Translate sequence names into the internal DB names
sp_repr = defaultdict(int)
sizes = []
for co in self.raw_cogs:
sizes.append(len(co))
for sp, seq in co:
sp_repr[sp] += 1
co_names = ["%s%s%s" %(sp, GLOBALS["spname_delimiter"], seq) for sp, seq in co]
encoded_names = db.translate_names(co_names)
if len(encoded_names) != len(co):
print(set(co) - set(encoded_names.keys()))
raise DataError("Some sequence ids could not be translated")
self.cogs.append(list(encoded_names.values()))
# ERROR! COGs selected are not the prioritary cogs sorted out before!!!
# Sort Cogs according to the md5 hash of its content. Random
# sorting but kept among runs
#map(lambda x: x.sort(), self.cogs)
#self.cogs.sort(lambda x,y: cmp(md5(','.join(x)), md5(','.join(y))))
log.log(28, "Analysis of current COG selection:")
for sp, ncogs in sorted(list(sp_repr.items()), key=lambda x:x[1], reverse=True):
log.log(28, " % 30s species present in % 6d COGs (%0.1f%%)" %(sp, ncogs, 100 * ncogs/float(len(self.cogs))))
log.log(28, " %d COGs selected with at least %d species out of %d" %(len(self.cogs), min_species, len(all_species)))
log.log(28, " Average COG size %0.1f/%0.1f +- %0.1f" %(_mean(sizes), _median(sizes), _std(sizes)))
# Some consistency checks
missing_sp = (all_species) - set(sp_repr.keys())
if missing_sp:
log.error("%d missing species or not present in single-copy in any cog:\n%s" %\
(len(missing_sp), '\n'.join(missing_sp)))
open('etebuild.valid_species_names.tmp', 'w').write('\n'.join(list(sp_repr.keys())) +'\n')
log.error("All %d valid species have been dumped into etebuild.valid_species_names.tmp."
" You can use --spfile to restrict the analysis to those species." %len(sp_repr))
raise TaskError('missing or not single-copy species under current cog selection')
CogSelectorTask.store_data(self, self.cogs, self.cog_analysis)
def get_best_selection(cogs_selections, species):
ALL_SPECIES = set(species)
def _compare_cog_selection(cs1, cs2):
seed_1, missing_sp_allowed_1, candidates_1, sp2hits_1 = cs1
seed_2, missing_sp_allowed_2, candidates_2, sp2hits_2 = cs2
score_1, min_cov_1, max_cov_1, median_cov_1, cov_std_1, cog_cov_1 = get_cog_score(candidates_1, sp2hits_1, median_cogs, ALL_SPECIES-set([seed_1]))
score_2, min_cov_2, max_cov_2, median_cov_2, cov_std_2, cog_cov_2 = get_cog_score(candidates_2, sp2hits_2, median_cogs, ALL_SPECIES-set([seed_2]))
sp_represented_1 = len(sp2hits_1)
sp_represented_2 = len(sp2hits_1)
cmp_rpr = cmp(sp_represented_1, sp_represented_2)
if cmp_rpr == 1:
return 1
elif cmp_rpr == -1:
return -1
else:
cmp_score = cmp(score_1, score_2)
if cmp_score == 1:
return 1
elif cmp_score == -1:
return -1
else:
cmp_mincov = cmp(min_cov_1, min_cov_2)
if cmp_mincov == 1:
return 1
elif cmp_mincov == -1:
return -1
else:
cmp_maxcov = cmp(max_cov_1, max_cov_2)
if cmp_maxcov == 1:
return 1
elif cmp_maxcov == -1:
return -1
else:
cmp_cand = cmp(len(candidates_1), len(candidates_2))
if cmp_cand == 1:
return 1
elif cmp_cand == -1:
return -1
else:
return 0
min_score = 0.5
max_cogs = _max([len(data[2]) for data in cogs_selections])
median_cogs = _median([len(data[2]) for data in cogs_selections])
cogs_selections.sort(_compare_cog_selection)
cogs_selections.reverse()
header = ['seed',
'missing sp allowed',
'spcs covered',
'#COGs',
'mean sp coverage)',
'#COGs for worst sp.',
'#COGs for best sp.',
'sp. in COGS(avg)',
'SCORE' ]
print_header = True
best_cog_selection = None
cog_analysis = StringIO()
for i, cogs in enumerate(cogs_selections):
seed, missing_sp_allowed, candidates, sp2hits = cogs
sp_percent_coverages = [(100*sp2hits.get(sp,0))/float(len(candidates)) for sp in species]
sp_coverages = [sp2hits.get(sp, 0) for sp in species]
score, min_cov, max_cov, median_cov, cov_std, cog_cov = get_cog_score(candidates, sp2hits, median_cogs, ALL_SPECIES-set([seed]))
if best_cog_selection is None:
best_cog_selection = i
flag = "*"
else:
flag = " "
data = (candidates,
flag+"%10s" %seed, \
missing_sp_allowed, \
"%d (%0.1f%%)" %(len(set(sp2hits.keys()))+1, 100*float(len(ALL_SPECIES))/(len(sp2hits)+1)) , \
len(candidates), \
"%0.1f%% +- %0.1f" %(_mean(sp_percent_coverages), _std(sp_percent_coverages)), \
"% 3d (%0.1f%%)" %(min(sp_coverages),100*min(sp_coverages)/float(len(candidates))), \
"% 3d (%0.1f%%)" %(max(sp_coverages),100*max(sp_coverages)/float(len(candidates))), \
cog_cov,
score
)
if print_header:
print_as_table([data[1:]], header=header, print_header=True, stdout=cog_analysis)
print_header = False
else:
print_as_table([data[1:]], header=header, print_header=False, stdout=cog_analysis)
#raw_input("Press")
print(cog_analysis.getvalue())
#best_cog_selection = int(raw_input("choose:"))
return cogs_selections[best_cog_selection], cog_analysis
def finish(self):
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 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
all_species = self.targets | self.outgroups
# strict threshold
#min_species = len(all_species) - int(round(self.missing_factor * len(all_species)))
# Relax threshold for cog selection to ensure sames genes are always included
min_species = len(all_species) - int(
round(self.missing_factor * len(GLOBALS["target_species"])))
min_species = max(min_species,
(1 - self.max_missing_factor) * len(all_species))
smallest_cog, largest_cog = len(all_species), 0
all_singletons = []
sp2cogs = defaultdict(int)
for cognumber, cog in enumerate(open(GLOBALS["cogs_file"])):
sp2seqs = defaultdict(list)
for sp, seqid in [
list(
map(str.strip, seq.split(GLOBALS["spname_delimiter"],
1)))
for seq in cog.split("\t")
]:
sp2seqs[sp].append(seqid)
one2one_cog = set()
for sp, seqs in six.iteritems(sp2seqs):
#if len(seqs) != 1:
# print sp, len(seqs)
if sp in all_species and len(seqs) == 1:
sp2cogs[sp] += 1
one2one_cog.add((sp, seqs[0]))
smallest_cog = min(smallest_cog, len(one2one_cog))
largest_cog = max(largest_cog, len(one2one_cog))
all_singletons.append(one2one_cog)
#if len(one2one_cog) >= min_species:
# valid_cogs.append(one2one_cog)
cognumber += 1 # sets the ammount of cogs in file
for sp, ncogs in sorted(list(sp2cogs.items()),
key=lambda x: x[1],
reverse=True):
log.log(
28, "% 20s found in single copy in % 6d (%0.1f%%) COGs " %
(sp, ncogs, 100 * ncogs / float(cognumber)))
valid_cogs = sorted(
[sing for sing in all_singletons if len(sing) >= min_species],
sort_cogs_by_size)
log.log(
28, "Largest cog size: %s. Smallest cog size: %s" %
(largest_cog, smallest_cog))
self.cog_analysis = ""
# save original cog names hitting the hard limit
if len(valid_cogs) > self.cog_hard_limit:
log.warning(
"Applying hard limit number of COGs: %d out of %d available" %
(self.cog_hard_limit, len(valid_cogs)))
self.raw_cogs = valid_cogs[:self.cog_hard_limit]
self.cogs = []
# Translate sequence names into the internal DB names
sp_repr = defaultdict(int)
sizes = []
for co in self.raw_cogs:
sizes.append(len(co))
for sp, seq in co:
sp_repr[sp] += 1
co_names = [
"%s%s%s" % (sp, GLOBALS["spname_delimiter"], seq)
for sp, seq in co
]
encoded_names = db.translate_names(co_names)
if len(encoded_names) != len(co):
print(set(co) - set(encoded_names.keys()))
raise DataError("Some sequence ids could not be translated")
self.cogs.append(list(encoded_names.values()))
# ERROR! COGs selected are not the prioritary cogs sorted out before!!!
# Sort Cogs according to the md5 hash of its content. Random
# sorting but kept among runs
#map(lambda x: x.sort(), self.cogs)
#self.cogs.sort(lambda x,y: cmp(md5(','.join(x)), md5(','.join(y))))
log.log(28, "Analysis of current COG selection:")
for sp, ncogs in sorted(list(sp_repr.items()),
key=lambda x: x[1],
reverse=True):
log.log(
28, " % 30s species present in % 6d COGs (%0.1f%%)" %
(sp, ncogs, 100 * ncogs / float(len(self.cogs))))
log.log(
28, " %d COGs selected with at least %d species out of %d" %
(len(self.cogs), min_species, len(all_species)))
log.log(
28, " Average COG size %0.1f/%0.1f +- %0.1f" %
(_mean(sizes), _median(sizes), _std(sizes)))
# Some consistency checks
missing_sp = (all_species) - set(sp_repr.keys())
if missing_sp:
log.error("%d missing species or not present in single-copy in any cog:\n%s" %\
(len(missing_sp), '\n'.join(missing_sp)))
open('etebuild.valid_species_names.tmp',
'w').write('\n'.join(list(sp_repr.keys())) + '\n')
log.error(
"All %d valid species have been dumped into etebuild.valid_species_names.tmp."
" You can use --spfile to restrict the analysis to those species."
% len(sp_repr))
raise TaskError(
'missing or not single-copy species under current cog selection'
)
CogSelectorTask.store_data(self, self.cogs, self.cog_analysis)