set1[e] = set1[e][:17] + set1[e]
set2[e] = set2[e][:17] + set2[e]
e = e + 1
#compute softmax scores for sequences in dataset
scrs1 = MGlib.esfmax_score_seqs(set1, pssm, rpssm)
scrs2 = MGlib.esfmax_score_seqs(set2, pssm, rpssm)
if verbose: print "varied"
if verbose:
for s in scrs1:
print s[0]
if verbose: print "loners"
if verbose:
for s in scrs2:
print s[0]
#get log-likelihoods for sequences in dataset
llrs1 = MGlib.ll_ratios(scrs1, n_g, n_m, alpha)
llrs2 = MGlib.ll_ratios(scrs2, n_g, n_m, alpha)
#get overall posterior for the sequences in dataset
fposts1 = MGlib.PostP(llrs1, PPR, 0)
fposts2 = MGlib.PostP(llrs2, PPR, 0)
#write results to file
out_file.write(str(fposts1))
out_file.write(',')
out_file.write(str(fposts2))
out_file.write('\n')
out_file.close()
def main():
###############################################################################
#set default parameters
motif_filename = "CsoR.txt" #input file
out_filename = "cog_exp_sym2_c" #prefix for output
verbose = 0 #verbose mode
alpha = 1.0 / 300.0 #mixing ratio for regulated model
rproms = 3.0 #number of regulated promoters [prior]
tproms = 1811.0 #total number of promoters in genome [prior]
# control number of cogs and number of permutations
num_cogs = 10000
neg_cutoff = 9900 # Cog #'s less than this are negative
num_perms = 100
cog_sample_size = 1000
#verbose
if verbose: print "Using: ", motif_filename, " as input"
if verbose: print "Writing to (suffix): ", "[void]" if out_filename==""\
else out_filename
#open file for ouput
try:
out_file = open(
out_filename + str(num_cogs) + "_s" + str(cog_sample_size) + "_p" +
str(num_perms) + ".csv", "w")
except (IOError, OSError) as file_open_exception:
print "*** Something went wrong while opening the output file"
print "*** Error: ", file_open_exception.errno, " - ",\
file_open_exception.strerror
sys.exit()
#compute priors
PR = rproms / tproms #prior probability of regulation
PB = 1.0 - PR #prior probability of non-regulation
PPR = PB / PR #prior probability ratio
# read motif and assign 0.25 pseudocounts to PSWM
# also assign background uniform distribution for the PSSM (default)
mot = MGlib.read_motif(motif_filename)
mot.pseudocounts = 1
mot.background = None
# save the pssm for the motif and the reverse complement
#(so that they are not recalculated everytime we invoke motif.pssm)
pssm = mot.pssm
rpssm = pssm.reverse_complement()
# Save the motif itself as a list of strings for later permuting
motif_sites = []
num_motif_sites = len(mot.instances)
for i in range(num_motif_sites):
motif_sites.append(str(mot.instances[i]))
random.seed(None)
# Create the COGS
all_cogs = []
the_neg_seqs = []
neg_cog_nums = [i for i in range(0, neg_cutoff)]
ran_neg_cog_nums = sample(cog_sample_size, neg_cog_nums, replace=False)
cog_file = open(
"seqs_sym2_" + str(num_cogs) + "_s" + str(cog_sample_size) + "_p" +
str(num_perms) + ".csv", "w")
for i in range(0, num_cogs):
label = get_cog_type(i, neg_cutoff)
#print "Create cog #", i, label
cur_cog = create_COG(label, mot)
all_cogs.append(cur_cog)
if i in ran_neg_cog_nums:
# A negatively regulated cog
for s in cur_cog:
the_neg_seqs.append(s)
cog_file.write("%d,%s\n" % (i, s))
else:
for s in cur_cog:
cog_file.write("%d,%s\n" % (i, s))
cog_file.close()
# compute softmax scores for sampled background sequences
gscr = MGlib.esfmax_score_seqs(the_neg_seqs, pssm, rpssm)
# compute softmax scores for motif sequences
mscr = MGlib.esfmax_score_seqs(mot.instances, pssm, rpssm)
# get normal distributions for background and motif
mean_gscr = mean(gscr)
std_gscr = std(gscr)
n_g = norm(mean_gscr, std_gscr)
mean_mscr = mean(mscr)
std_mscr = std(mscr)
n_m = norm(mean(mscr), std(mscr))
smeans_file = open(
"smeans_stds_sym2_" + str(num_cogs) + "_s" + str(cog_sample_size) +
"_p" + str(num_perms) + ".csv", "w")
smeans_file.write("PSSM n_g,%13.10f,%13.10f\n" % (mean_gscr, std_gscr))
smeans_file.write("PSSM n_m,%13.10f,%13.10f\n" % (mean_mscr, std_mscr))
# Create the permuted pssm and n_m and n_g for the permutation tests
new_pssm_list = []
rnew_pssm_list = []
n_m_perms = []
n_g_perms = []
for j in range(0, num_perms):
#print "\n***************** Create permutation #", j
# permute the columns of the motif
new_mot = sym_permute_motif(motif_sites)
new_pssm = new_mot.pssm #
rnew_pssm = new_pssm.reverse_complement()
new_pssm_list.append(new_pssm)
rnew_pssm_list.append(rnew_pssm)
# compute score for the negative sequences
gscr = MGlib.esfmax_score_seqs(the_neg_seqs, new_pssm, rnew_pssm)
mean_gscr = mean(gscr)
std_gscr = std(gscr)
# compute softmax scores for new motif sequences
mscr = MGlib.esfmax_score_seqs(new_mot.instances, new_pssm, rnew_pssm)
mean_mscr = mean(mscr)
std_mscr = std(mscr)
smeans_file.write("PermPSSM n_g,%13.10f,%13.10f\n" %
(mean_gscr, std_gscr))
smeans_file.write("PermPSSM n_m,%13.10f,%13.10f\n" %
(mean_mscr, std_mscr))
# get normal distributions for background and motif
n_g_temp = norm(mean_gscr, std_gscr)
n_g_perms.append(n_g_temp)
n_m_temp = norm(mean_mscr, std_mscr)
n_m_perms.append(n_m_temp)
smeans_file.close()
# write csv header
out_file.write(
'COG Num,Pos/Neg Regulated,Posterior,LogLikelihood,True Model LL,LL Pval\n'
)
# For each cog, do the posterior calculation and the permutation tests
for i in range(0, num_cogs):
label = get_cog_type(i, neg_cutoff)
#print "Test Cog:", i,label
# The original posterior computation
#compute softmax scores for sequences in dataset
scrs = MGlib.esfmax_score_seqs(all_cogs[i], pssm, rpssm)
#print np.min(scrs[0]), np.max(scrs[0])
# Compute posterior
# get log-likelihoods for sequences in dataset
llrs = MGlib.ll_ratios(scrs, n_g, n_m, alpha)
# get per-sequence posterior for the sequences in dataset
fpost = MGlib.PostP(llrs, PPR, 0)
true_model_ll = compute_log_l(scrs, n_g, n_m, alpha)
#####################################
# Permutation test
log_ls = []
for j in range(0, num_perms):
#print " ... perm test", j
# Compute score and log likelihood for each permutation.
scrs = MGlib.esfmax_score_seqs(all_cogs[i], new_pssm_list[j],
rnew_pssm_list[j])
log_l = compute_log_l(scrs, n_g_perms[j], n_m_perms[j], alpha)
log_ls.append(log_l)
rev_pval = compute_p_val(log_ls, true_model_ll)
pval = 1.0 - rev_pval
out_file.write("%d,%s,%10.7f,%10.7f,%10.7f,%10.7f\n" %
(i, label, fpost, rev_pval, true_model_ll, pval))
out_file.close()
n_g = norm(mean(gscr), std(gscr))
n_m = norm(mean(mscr), std(mscr))
#create motif instances
pmot1 = MGlib.sample_motif(mot, 100)
#insert sites in sequences
e = 0
while (e < len(set1)):
set1[e] = pmot1[e] + set1[e]
e = e + 1
#compute softmax scores for sequences in dataset
scrs = MGlib.esfmax_score_seqs(set1, pssm, rpssm)
#get log-likelihoods for sequences in dataset
llrs = MGlib.ll_ratios(scrs, n_g, n_m, alpha)
#get per-sequence posterior for the sequences in dataset
fposts = MGlib.PostP(llrs, PPR, 1)
#write results to file
e = 0
while (e < len(set1)):
out_file.write(str(scrs[e][0]))
out_file.write(',')
out_file.write(str(fposts[e]))
out_file.write('\n')
e = e + 1
out_file.close()
def main():
###############################################################################
# set default parameters
motif_filename = "CsoR.txt" # input file
out_filename = "cog_exp_sym2_c" # prefix for output
verbose = 0 # verbose mode
alpha = 1.0 / 300.0 # mixing ratio for regulated model
rproms = 3.0 # number of regulated promoters [prior]
tproms = 1811.0 # total number of promoters in genome [prior]
# control number of cogs and number of permutations
num_cogs = 10000
neg_cutoff = 9900 # Cog #'s less than this are negative
num_perms = 100
cog_sample_size = 1000
# verbose
if verbose:
print "Using: ", motif_filename, " as input"
if verbose:
print "Writing to (suffix): ", "[void]" if out_filename == "" else out_filename
# open file for ouput
try:
out_file = open(
out_filename + str(num_cogs) + "_s" + str(cog_sample_size) + "_p" + str(num_perms) + ".csv", "w"
)
except (IOError, OSError) as file_open_exception:
print "*** Something went wrong while opening the output file"
print "*** Error: ", file_open_exception.errno, " - ", file_open_exception.strerror
sys.exit()
# compute priors
PR = rproms / tproms # prior probability of regulation
PB = 1.0 - PR # prior probability of non-regulation
PPR = PB / PR # prior probability ratio
# read motif and assign 0.25 pseudocounts to PSWM
# also assign background uniform distribution for the PSSM (default)
mot = MGlib.read_motif(motif_filename)
mot.pseudocounts = 1
mot.background = None
# save the pssm for the motif and the reverse complement
# (so that they are not recalculated everytime we invoke motif.pssm)
pssm = mot.pssm
rpssm = pssm.reverse_complement()
# Save the motif itself as a list of strings for later permuting
motif_sites = []
num_motif_sites = len(mot.instances)
for i in range(num_motif_sites):
motif_sites.append(str(mot.instances[i]))
random.seed(None)
# Create the COGS
all_cogs = []
the_neg_seqs = []
neg_cog_nums = [i for i in range(0, neg_cutoff)]
ran_neg_cog_nums = sample(cog_sample_size, neg_cog_nums, replace=False)
cog_file = open("seqs_sym2_" + str(num_cogs) + "_s" + str(cog_sample_size) + "_p" + str(num_perms) + ".csv", "w")
for i in range(0, num_cogs):
label = get_cog_type(i, neg_cutoff)
# print "Create cog #", i, label
cur_cog = create_COG(label, mot)
all_cogs.append(cur_cog)
if i in ran_neg_cog_nums:
# A negatively regulated cog
for s in cur_cog:
the_neg_seqs.append(s)
cog_file.write("%d,%s\n" % (i, s))
else:
for s in cur_cog:
cog_file.write("%d,%s\n" % (i, s))
cog_file.close()
# compute softmax scores for sampled background sequences
gscr = MGlib.esfmax_score_seqs(the_neg_seqs, pssm, rpssm)
# compute softmax scores for motif sequences
mscr = MGlib.esfmax_score_seqs(mot.instances, pssm, rpssm)
# get normal distributions for background and motif
mean_gscr = mean(gscr)
std_gscr = std(gscr)
n_g = norm(mean_gscr, std_gscr)
mean_mscr = mean(mscr)
std_mscr = std(mscr)
n_m = norm(mean(mscr), std(mscr))
smeans_file = open(
"smeans_stds_sym2_" + str(num_cogs) + "_s" + str(cog_sample_size) + "_p" + str(num_perms) + ".csv", "w"
)
smeans_file.write("PSSM n_g,%13.10f,%13.10f\n" % (mean_gscr, std_gscr))
smeans_file.write("PSSM n_m,%13.10f,%13.10f\n" % (mean_mscr, std_mscr))
# Create the permuted pssm and n_m and n_g for the permutation tests
new_pssm_list = []
rnew_pssm_list = []
n_m_perms = []
n_g_perms = []
for j in range(0, num_perms):
# print "\n***************** Create permutation #", j
# permute the columns of the motif
new_mot = sym_permute_motif(motif_sites)
new_pssm = new_mot.pssm #
rnew_pssm = new_pssm.reverse_complement()
new_pssm_list.append(new_pssm)
rnew_pssm_list.append(rnew_pssm)
# compute score for the negative sequences
gscr = MGlib.esfmax_score_seqs(the_neg_seqs, new_pssm, rnew_pssm)
mean_gscr = mean(gscr)
std_gscr = std(gscr)
# compute softmax scores for new motif sequences
mscr = MGlib.esfmax_score_seqs(new_mot.instances, new_pssm, rnew_pssm)
mean_mscr = mean(mscr)
std_mscr = std(mscr)
smeans_file.write("PermPSSM n_g,%13.10f,%13.10f\n" % (mean_gscr, std_gscr))
smeans_file.write("PermPSSM n_m,%13.10f,%13.10f\n" % (mean_mscr, std_mscr))
# get normal distributions for background and motif
n_g_temp = norm(mean_gscr, std_gscr)
n_g_perms.append(n_g_temp)
n_m_temp = norm(mean_mscr, std_mscr)
n_m_perms.append(n_m_temp)
smeans_file.close()
# write csv header
out_file.write("COG Num,Pos/Neg Regulated,Posterior,LogLikelihood,True Model LL,LL Pval\n")
# For each cog, do the posterior calculation and the permutation tests
for i in range(0, num_cogs):
label = get_cog_type(i, neg_cutoff)
# print "Test Cog:", i,label
# The original posterior computation
# compute softmax scores for sequences in dataset
scrs = MGlib.esfmax_score_seqs(all_cogs[i], pssm, rpssm)
# print np.min(scrs[0]), np.max(scrs[0])
# Compute posterior
# get log-likelihoods for sequences in dataset
llrs = MGlib.ll_ratios(scrs, n_g, n_m, alpha)
# get per-sequence posterior for the sequences in dataset
fpost = MGlib.PostP(llrs, PPR, 0)
true_model_ll = compute_log_l(scrs, n_g, n_m, alpha)
#####################################
# Permutation test
log_ls = []
for j in range(0, num_perms):
# print " ... perm test", j
# Compute score and log likelihood for each permutation.
scrs = MGlib.esfmax_score_seqs(all_cogs[i], new_pssm_list[j], rnew_pssm_list[j])
log_l = compute_log_l(scrs, n_g_perms[j], n_m_perms[j], alpha)
log_ls.append(log_l)
rev_pval = compute_p_val(log_ls, true_model_ll)
pval = 1.0 - rev_pval
out_file.write("%d,%s,%10.7f,%10.7f,%10.7f,%10.7f\n" % (i, label, fpost, rev_pval, true_model_ll, pval))
out_file.close()
n_g=norm(mean(gscr), std(gscr))
n_m=norm(mean(mscr), std(mscr))
#create motif instances
pmot1 = MGlib.sample_motif(mot,100)
#insert sites in sequences
e=0
while (e<len(set1)):
set1[e] = pmot1[e] + set1[e]
e = e+1
#compute softmax scores for sequences in dataset
scrs=MGlib.esfmax_score_seqs(set1,pssm,rpssm)
#get log-likelihoods for sequences in dataset
llrs=MGlib.ll_ratios(scrs,n_g,n_m,alpha)
#get per-sequence posterior for the sequences in dataset
fposts=MGlib.PostP(llrs,PPR,1)
#write results to file
e=0
while (e<len(set1)):
out_file.write(str(scrs[e][0]))
out_file.write(',')
out_file.write(str(fposts[e]))
out_file.write('\n')
e=e+1
out_file.close()
sz=3
elif (cnt2==1):
sz=6
elif (cnt2==2):
sz=9
elif (cnt2==3):
sz=12
elif (cnt2==4):
sz=15
else:
sz=18
#create mixed dataset score
curr_scores=scrs1[0:sz]+scrs2[sz:len(scrs1)]
#get log-likelihoods for sequences in dataset
llrs1=MGlib.ll_ratios(curr_scores,n_g,n_m,alpha)
#get overall normalized posterior for the sequences in dataset
posts1=MGlib.PostP(llrs1,PPR)
if verbose: print sz, " - ", posts1
#write results to file
out_file.write(str(sz))
out_file.write(',')
out_file.write(str(posts1))
out_file.write('\n')
out_file.close()
if (cnt2 == 0):
sz = 3
elif (cnt2 == 1):
sz = 6
elif (cnt2 == 2):
sz = 9
elif (cnt2 == 3):
sz = 12
elif (cnt2 == 4):
sz = 15
else:
sz = 18
#create mixed dataset score
curr_scores = scrs1[0:sz] + scrs2[sz:len(scrs1)]
#get log-likelihoods for sequences in dataset
llrs1 = MGlib.ll_ratios(curr_scores, n_g, n_m, alpha)
#get overall normalized posterior for the sequences in dataset
posts1 = MGlib.PostP(llrs1, PPR)
if verbose: print sz, " - ", posts1
#write results to file
out_file.write(str(sz))
out_file.write(',')
out_file.write(str(posts1))
out_file.write('\n')
out_file.close()
#compute revised priors (assuming 300 bp average length)
aPR, aPB = MGlib.NormPriors(th, n_g, n_m, alpha, rproms,\
tproms, promlen=300.0)
#get revised prior ratio
aPPR = aPB/aPR
#FILTER sequences not matching theta
#get list of sequences with min score > th
Nscrs1 = [x for x in scrs1 if max(x)>=th]
if verbose: print "Length of post-theta bckg seqs: ", len(Nscrs1)
#get log-likelihoods for sequences in dataset
Nllrs1=MGlib.ll_ratios(Nscrs1,n_g,n_m,alpha)
#get normalization factors
Nnormfs1=MGlib.lNormFactor(Nscrs1, th, n_g, n_m, alpha)
#get overall normalized posterior for the sequences in dataset
Nposts1=MGlib.NormPostP(Nllrs1,aPPR,Nnormfs1,0)
if verbose: print theta, " - ", sz, " - ", Nposts1, " - ", \
len(Nscrs1), 1/(1+aPPR)
#write results to file
out_file.write(str(theta))
out_file.write(',')
out_file.write(str(sz))
out_file.write(',')
out_file.write(str(Nposts1))
def main():
"""Gets a motif from file and reads it. It then generates synthetic data
to represent a set of promoters (100) mapping to a particular eggNOG/COG,
inserts into these sequences pseudosites (generated from the
distribution implicit in the PSSM). It then calls the PSSM evaluation
function to score the sites using the softmax function and then the
different functions to compute the likelihoods and the posterior
probabilities.
Usage:
MG_synth -M <Motif file> -O <out file prefix> -E <experiment> \
-A <alpha mix ratio> -P <Regulation prior> -T <theta> \
-V <verbose mode>
Note: motifs are assumed to be in FASTA or 1-per-line text format
"""
#set default parameters
motif_filename="CsoR.txt" #input file
out_filename="_o" #o prefix for output
verbose=0 #verbose mode
alpha=1.0/300.0 #mixing ratio for regulated model
rproms=3.0 #number of regulated promoters [prior]
tproms=1811.0 #total number of promoters in genome [prior]
experiment=2 #the experiment number
#get cmd parameters
try:
opts, args=getopt.getopt(sys.argv[1:],"I:O:V")
except getopt.GetoptError:
print 'MG_synth -M <Motif file> -O <out file prefix> -E <experiment> \
-A <alpha mix ratio> -P <Regulation prior> -T <theta> \
-V <verbose mode>'
sys.exit(2)
#assign parameters
for opt, arg in opts:
if opt == '-M':
motif_filename=arg
elif opt == '-O':
out_filename=arg
elif opt == '-E':
experiment=int(arg)
elif opt == '-A':
alpha=float(arg)
elif opt == '-P':
PR=float(arg)
elif opt == '-T':
theta=float(arg)
elif opt == '-V':
verbose=arg
elif opt == '-askme':
motif_filename = raw_input('Enter the motif file name\n')
out_filename = raw_input('Enter the output file name prefix\n')
experiment = raw_input('Enter the experiment number\n')
alpha = raw_input('Enter the alpha mixing ratio\n')
PR = raw_input('Enter the prior probability for regulation\n')
theta = raw_input('Enter the theta sensitivity threshold\n')
verbose = raw_input('Enter verbose mode (1/0)\n')
out_filename=motif_filename.split(".")[0] + out_filename + str(experiment)
#verbose
if verbose: print "Using: ", motif_filename, " as input"
if verbose: print "Writing to (suffix): ", "[void]" if out_filename==""\
else out_filename
#open files for ouput
try:
out_file = open(out_filename + ".csv","w")
except (IOError, OSError) as file_open_exception:
print "*** Something went wrong while opening the output file"
print "*** Error: ", file_open_exception.errno, " - ",\
file_open_exception.strerror
sys.exit()
#open file for error recording
try:
err_file = open(out_filename+".err","w")
except (IOError, OSError) as file_open_exception:
print "Something went wrong while opening the error file"
sys.exit()
#compute priors
PR=rproms/tproms #prior probability of regulation
PB=1.0-PR #prior probability of non-regulation
PPR=PB/PR #prior probability ratio
#read motif and assing 0.25 pseudocounts to PSWM
#also assign background uniform distribution for the PSSM (default)
mot = MGlib.read_motif(motif_filename)
mot.pseudocounts=0.25
mot.background=None
#save the pssm for the motif and the reverse complement
#(so that they are not recalculated everytime we invoke motif.pssm)
pssm = mot.pssm
rpssm = pssm.reverse_complement()
if (experiment==0):
#-------------------------------------------------------------------------
#Experiment 0:
#10000 sequences, with 100% on average having random pseudo-sites inserted
#all sites are inserted at the first position of the sequence
#get individual sequence posteriors and write them together with the
#score of the site inserted
random.seed(None)
#create background sequence set: 100 seqs 283 bp long
set1 = MGlib.random_DNA(283,{'A': 0.3,'C': 0.2,'G': 0.2,'T': 0.3},10000)
#compute softmax scores for background sequences in dataset
gscr = MGlib.sfmax_score_seqs(set1,pssm,rpssm)
#get normal distributions for background and motif
n_g=norm(mean(gscr), std(gscr))
n_m=norm(pssm.mean(), pssm.std())
#create motif instances
pmot1 = MGlib.sample_motif(mot,1000)
#insert sites in sequences
e=0
while (e<len(set1)):
r = random.random()
#determine if site is to be inserted and insert random site
if (r<1):
set1[e] = random.choice(pmot1) + set1[e]
#otherwise insert random sequence from own sequence start
else :
set1[e] = set1[e][:17] + set1[e]
e = e+1
#compute softmax scores for sequences in dataset
scrs=MGlib.sfmax_score_seqs(set1,pssm,rpssm)
#get log-likelihoods for sequences in dataset
llrs=MGlib.ll_ratios(scrs,n_g,n_m,alpha)
#get per-sequence posterior for the sequences in dataset
fposts=MGlib.PostP(llrs,PPR,1)
#write results to file
e=0
while (e<len(set1)):
out_file.write(str(scrs[e][0]))
out_file.write(',')
out_file.write(str(fposts[e]))
out_file.write('\n')
e=e+1
out_file.close()
return 0
elif (experiment==1):
#-------------------------------------------------------------------------
#Experiment 1:
#2x100 sequences, with the first 10 having random pseudo-sites inserted
#all sites are inserted at the first position of the sequence
#get individual sequence posteriors and write them together with the
#score of the site inserted
#first sequence set includes randomly distributed sites
#second sequence set includes only one site
#experiment is repeated 100 times
random.seed(None)
for cnt in range(0,100):
#create background sequence set: 100 seqs 283 bp long
set1 = MGlib.random_DNA(283,{'A': 0.3,'C': 0.2,'G': 0.2,'T': 0.3},100)
set2 = set1[:]
#compute softmax scores for background sequences in dataset
gscr = MGlib.sfmax_score_seqs(set1,pssm,rpssm)
#get normal distributions for background and motif
n_g=norm(mean(gscr), std(gscr))
n_m=norm(pssm.mean(), pssm.std())
#create motif instances
pmot1 = MGlib.sample_motif(mot,100)
pmot2 = MGlib.sample_motif(mot,1)
print cnt
#insert sites in sequences
e=0
while (e<len(set1)):
r = random.random()
#insert random site in first 10 sequences
if (e<11):
set1[e] = random.choice(pmot1) + set1[e]
set2[e] = random.choice(pmot2) + set2[e]
#otherwise insert random sequence from own sequence start
else :
set1[e] = set1[e][:17] + set1[e]
set2[e] = set2[e][:17] + set2[e]
e = e+1
#compute softmax scores for sequences in dataset
scrs1=MGlib.sfmax_score_seqs(set1,pssm,rpssm)
scrs2=MGlib.sfmax_score_seqs(set2,pssm,rpssm)
if verbose: print "varied"
if verbose:
for s in scrs1: print s[0]
if verbose: print "loners"
if verbose:
for s in scrs2: print s[0]
#get log-likelihoods for sequences in dataset
llrs1=MGlib.ll_ratios(scrs1,n_g,n_m,alpha)
llrs2=MGlib.ll_ratios(scrs2,n_g,n_m,alpha)
#get overall posterior for the sequences in dataset
fposts1=MGlib.PostP(llrs1,PPR,0)
fposts2=MGlib.PostP(llrs2,PPR,0)
#write results to file
out_file.write(str(fposts1))
out_file.write(',')
out_file.write(str(fposts2))
out_file.write('\n')
out_file.close()
return 0
else :
set1[e] = set1[e][:17] + set1[e]
set2[e] = set2[e][:17] + set2[e]
e = e+1
#compute softmax scores for sequences in dataset
scrs1=MGlib.esfmax_score_seqs(set1,pssm,rpssm)
scrs2=MGlib.esfmax_score_seqs(set2,pssm,rpssm)
if verbose: print "varied"
if verbose:
for s in scrs1: print s[0]
if verbose: print "loners"
if verbose:
for s in scrs2: print s[0]
#get log-likelihoods for sequences in dataset
llrs1=MGlib.ll_ratios(scrs1,n_g,n_m,alpha)
llrs2=MGlib.ll_ratios(scrs2,n_g,n_m,alpha)
#get overall posterior for the sequences in dataset
fposts1=MGlib.PostP(llrs1,PPR,0)
fposts2=MGlib.PostP(llrs2,PPR,0)
#write results to file
out_file.write(str(fposts1))
out_file.write(',')
out_file.write(str(fposts2))
out_file.write('\n')
out_file.close()