def reassign_reads(readsf, priors, mates, constraints, soft_assign, initial_seed):
k = len(priors)
if use_priors:
priors = update_priors(priors, readsf, mates, constraints, soft_assign)
(likelihood, read_probs) = get_read_probs(priors, mates, constraints, soft_assign)
# open files
read_files = []
build_files = []
for i in range(k):
read_files.append(open('cluster-%d.tmp' % i,'w'))
if soft_assign:
build_files.append(open('cluster-%d.build.fa' % i, 'w'))
if initial_seed:
myk = 1
else:
myk = k
rsments = 0
for c in range(myk):
# reassign
for line in open('cluster-%d.fa' % c):
if line[0] == '>':
r = line[1:].strip() # remove front spaces
if not read_probs.has_key(r):
print 'ERROR: missing read %s scores' % r
exit()
elif constraints.has_key(r):
if constraints[r] != c:
print 'Found a constrained read in the wrong cluster'
max_icm = constraints[r]
else:
(max_prob, max_icm) = util.max_i(read_probs[r])
# count reassignments
if max_icm != c:
rsments += 1
# print line to files
read_files[max_icm].write(line)
if soft_assign:
for i in range(k):
if read_probs[r][i] > soft_assign_t:
if line[0] == '>':
build_files[i].write('>%f;%s' % (read_probs[r][i],line[1:]))
else:
build_files[i].write(line)
# close files
for i in range(k):
read_files[i].close()
if soft_assign:
build_files[i].close()
# move tmp
for i in range(k):
os.rename('cluster-%d.tmp'%i, 'cluster-%d.fa'%i)
return (rsments,likelihood,priors)
def init_clusters(readsf, soft_assign):
# load_mates
mates = {}
#if matesf: ... just in case I need this later ...
# for line in open(options.mates_file):
# (lr,rr) = line.split()
# mates[lr] = rr
# mates[rr] = lr
read_likes = {}
for line in open('sample.fa.binning.allprobs'):
a = line.split('\t')
r = a[0].strip()
read_likes[r] = [float(x) for x in a[1:]]
k = len(a[1:])
# Note that I'm assuming here that the cluster priors
# are incorporated into the printed likelihoods. I can't
# be sure but I'd rather be wrong and have used a uniform
# prior than reestimate the priors myself and be wrong and
# double count them. However, this means I am double
# counting the prior for mated reads.
# assign to clusters
hard_clusters = {}
soft_clusters = {}
for r in read_likes:
if not hard_clusters.has_key(r): # mate may have been done
# if mated, combine likelihood with
if mates.has_key(r):
m = mates[r]
clust_likes = [read_likes[r][i] + read_likes[m][i] for i in range(k)]
else:
m = r # it works
clust_likes = read_likes[r]
# hard assignment
(like_max, clust) = util.max_i(clust_likes)
hard_clusters[r] = clust
hard_clusters[m] = clust
# soft assignment
if soft_assign:
sum_score = clust_likes[0]
for i in range(1,k):
sum_score = imm_cluster.log_add(sum_score, clust_likes[i])
soft_clusters[r] = []
for i in range(k):
prob = math.exp(clust_likes[i] - sum_score)
if r != m:
soft_clusters[m] = []
if prob > imm_cluster.soft_assign_t:
soft_clusters[r].append((i,prob))
if r != m:
soft_clusters[m].append((i,prob))
chunk_size = 50
chunk_i = 0
while chunk_i*chunk_size < k:
# open files
init_files = {}
build_files = {}
for c in range(chunk_i*chunk_size, min(k, (chunk_i+1)*chunk_size)):
init_files[c] = open('cluster-%d.fa' % c, 'w')
if soft_assign:
build_files[c] = open('cluster-%d.build.fa' % c, 'w')
# read fasta to cluster-*.fa
for line in open(readsf):
if line[0] == '>':
r = line[1:].strip() # front spaces are removed by LikelyBin
if hard_clusters.has_key(r):
hc = hard_clusters[r]
if init_files.has_key(hc):
init_files[hc].write(line)
if soft_assign:
for (sc,p) in soft_clusters[r]:
build_files[sc].write('>%f;%s' % (p,line[1:]))
else:
hc = -1
elif hc != -1:
if init_files.has_key(hc):
init_files[hc].write(line)
if soft_assign:
for (sc,p) in soft_clusters[r]:
build_files[sc].write(line)
# close files
for c in init_files:
init_files[c].close()
if soft_assign:
build_files[c].close()
# increment
chunk_i += 1
def init_clusters(readsf, soft_assign):
# load_mates
mates = {}
#if matesf: ... just in case I need this later ...
# for line in open(options.mates_file):
# (lr,rr) = line.split()
# mates[lr] = rr
# mates[rr] = lr
read_likes = {}
for line in open('sample.fa.binning.allprobs'):
a = line.split('\t')
r = a[0].strip()
read_likes[r] = [float(x) for x in a[1:]]
k = len(a[1:])
# Note that I'm assuming here that the cluster priors
# are incorporated into the printed likelihoods. I can't
# be sure but I'd rather be wrong and have used a uniform
# prior than reestimate the priors myself and be wrong and
# double count them. However, this means I am double
# counting the prior for mated reads.
# assign to clusters
hard_clusters = {}
soft_clusters = {}
for r in read_likes:
if not hard_clusters.has_key(r): # mate may have been done
# if mated, combine likelihood with
if mates.has_key(r):
m = mates[r]
clust_likes = [read_likes[r][i] + read_likes[m][i] for i in range(k)]
else:
m = r # it works
clust_likes = read_likes[r]
# hard assignment
(like_max, clust) = util.max_i(clust_likes)
hard_clusters[r] = clust
hard_clusters[m] = clust
# soft assignment
if soft_assign:
sum_score = clust_likes[0]
for i in range(1,k):
sum_score = imm_cluster.log_add(sum_score, clust_likes[i])
soft_clusters[r] = []
for i in range(k):
prob = math.exp(clust_likes[i] - sum_score)
if r != m:
soft_clusters[m] = []
if prob > imm_cluster.soft_assign_t:
soft_clusters[r].append((i,prob))
if r != m:
soft_clusters[m].append((i,prob))
chunk_size = 50
chunk_i = 0
while chunk_i*chunk_size < k:
# open files
init_files = {}
build_files = {}
for c in range(chunk_i*chunk_size, min(k, (chunk_i+1)*chunk_size)):
init_files[c] = open('cluster-%d.fa' % c, 'w')
if soft_assign:
build_files[c] = open('cluster-%d.build.fa' % c, 'w')
# read fasta to cluster-*.fa
for line in open(readsf):
if line[0] == '>':
r = line[1:].strip() # front spaces are removed by LikelyBin
if hard_clusters.has_key(r):
hc = hard_clusters[r]
if init_files.has_key(hc):
init_files[hc].write(line)
if soft_assign:
for (sc,p) in soft_clusters[r]:
build_files[sc].write('>%f;%s' % (p,line[1:]))
else:
hc = -1
elif hc != -1:
if init_files.has_key(hc):
init_files[hc].write(line)
if soft_assign:
for (sc,p) in soft_clusters[r]:
build_files[sc].write(line)
# close files
for c in init_files:
init_files[c].close()
if soft_assign:
build_files[c].close()
# increment
chunk_i += 1
