def execute_tpr(args):
''' estimate true positive rate for region detection '''
model = args.model
regionlen = args.regionlen
thresshold = args.thresshold
cutoff = args.cutoff
numReps = args.nrep
pop = args.simpop
suffix = args.suffix
writedir = args.writedir
takeScore = args.score
all_scores = []
all_percentages = []
#if args.saveLog is not None:
# writefilename = args.saveLog
# if os.path.isfile(writefilename):
# print(writefilename + " already exists; aborting.")
# sys.exit(0)
#per seldaf
dafbins = [['0.10', '0.20', '0.30', '0.40', '0.50', '0.60', '0.70', '0.80', '0.90'], ['0.10', '0.20', '0.30'], ['0.40', '0.50', '0.60'], ['0.70', '0.80', '0.90'], ['0.90']]
daflabels = ['all', 'lo', 'mid', 'hi','highest']
for ibin in [3]:#[1, 2, 3, 4]:#range(1):
thesebins, thislabel = dafbins[ibin], daflabels[ibin]
allrepfilenames = []
for selbin in thesebins:
for irep in range(1, numReps + 1):
repfilename = get_sel_repfile_name(model, irep, pop, selbin, normed=True, suffix=suffix, basedir=writedir)
if (irep==1):
print(repfilename)
if os.path.isfile(repfilename):
allrepfilenames.append(repfilename)
print('loaded ' + str(len(allrepfilenames)) + " replicates...")
#numToTake = min(500, len(allrepfilenames))
#chosen = np.random.choice(allrepfilenames, numToTake, replace=False) #take random sample
chosen = allrepfilenames #this was just to expedite, no?
for repfilename in chosen:
physpos, genpos, seldaf, ihs_normed, delihh_normed, nsl_normed, xpehh_normed, fst, deldaf, cms_unnormed, cms_normed = read_cms_repfile(repfilename)
#physpos, genpos, ihs_normed, delihh_normed, nsl_normed, xpehh_normed, fst, deldaf, cms_unnormed, cms_normed = read_cms_repfile(repfilename)
these_scores = eval(takeScore)
if len(these_scores) > 0:
all_scores.append(these_scores)
rep_percentages = check_rep_windows(physpos, these_scores, regionlen, cutoff = cutoff)
all_percentages.append(rep_percentages)
print('loaded ' + str(len(all_scores)) + " replicates populations for model " + model + "...")
tpr = calc_pr(all_percentages, thresshold)
print('true positive rate: ' + str(tpr) + "\n")
if args.saveLog is not None:
writefilename = args.saveLog +"_" + thislabel
writefile = open(writefilename, 'w')
writefile.write(str(tpr)+'\n')
writefile.write(model + "\t" + str(regionlen) + "\t" + str(thresshold) + '\t' + str(cutoff) + '\n')
writefile.close()
print('wrote to : ' + str(writefilename))
return
def execute_cdf(args):
""" visualize power to localize variants: estimate p(causal variant captured | signif thresshold includes x top SNPs) from simulates. plot as cumulative density function"""
reps = args.nrep
savefilename = args.savefilename
writedir = args.writedir
scenars = ['0.70', '0.80', '0.90']#'0.10', '0.20', '0.30', '0.40', '0.50', '0.60', '0.70', '0.80', '0.90']
model = args.model
causalPos = args.selPos
suffix = args.suffix
#causal_ranks_all = []
causal_ranks_1, causal_ranks_2, causal_ranks_3, causal_ranks_4 = [], [], [], []
for pop in [1, 2, 3, 4]:
for scenar in scenars:
for irep in range(1, reps+1):
cmsfilename = get_sel_repfile_name(model, irep, pop, scenar, normed = False, basedir=writedir, suffix=suffix)
if os.path.isfile(cmsfilename):
physpos, genpos, seldaf, ihs_normed, delihh_normed, nsl_normed, xpehh_normed, fst, deldaf, cms_unnormed, cms_normed = read_cms_repfile(cmsfilename)
if causalPos in physpos:
causal_index = physpos.index(causalPos)
causal_unnormed = cms_unnormed[causal_index]
causal_rank = get_causal_rank(cms_unnormed, causal_unnormed)
#print(cmsfilename)
#print('causal rank: ' + str(causal_rank))
#causal_ranks.append(causal_rank)
this_array = eval('causal_ranks_' + str(pop))
if not np.isnan(causal_rank):
this_array.append(causal_rank)
else:
print("missing; " + cmsfilename)
print("for pop 1, loaded " + str(len(causal_ranks_1)) + " replicates.")
print("for pop 2, loaded " + str(len(causal_ranks_2)) + " replicates.")
print("for pop 3, loaded " + str(len(causal_ranks_3)) + " replicates.")
print("for pop 4, loaded " + str(len(causal_ranks_4)) + " replicates.")
cdf_fig, cdf_ax = plt.subplots()
if len(causal_ranks_1) > 0:
cdf_bins1, cdf1 = get_cdf_from_causal_ranks(causal_ranks_1)
cdf_ax.plot(cdf_bins1[1:], cdf1, color="yellow")
if len(causal_ranks_2) > 0:
cdf_bins2, cdf2 = get_cdf_from_causal_ranks(causal_ranks_2)
cdf_ax.plot(cdf_bins2[1:], cdf2, color="blue")
if len(causal_ranks_3) > 0:
cdf_bins3, cdf3 = get_cdf_from_causal_ranks(causal_ranks_3)
cdf_ax.plot(cdf_bins3[1:], cdf3, color="green")
if len(causal_ranks_4) > 0:
cdf_bins4, cdf4 = get_cdf_from_causal_ranks(causal_ranks_4)
cdf_ax.plot(cdf_bins4[1:], cdf4, color="purple")
cdf_ax.set_xlim([0, 50])
plt.title(model) #+ ", " + str(len(causal_ranks)) + " selection replicates")
plt.ylabel('probability that the causal variant is captured')
plt.xlabel('significance thresshold (i.e., examining the top x variants)')
plt.savefig(savefilename)
plt.close()
print('plotted to ' + savefilename)
return
def execute_normsims_genomewide(args):
""" given output from composite_sims, normalize all replicates to neutral parameters """
sel_freq_bins = [
'0.10', '0.20', '0.30', '0.40', '0.50', '0.60', '0.70', '0.80', '0.90'
]
model = args.model
selpop = args.simpop
numPerBin_sel = args.nrep_sel
numPerBin_neut = args.nrep_neut
writedir = args.writedir
suffix = args.runSuffix
values = []
##############################
## LOAD STATS FROM NEUT SIMS #
##############################
for irep in range(1, numPerBin_neut + 1):
outfile = get_neut_repfile_name(model,
irep,
selpop,
suffix=suffix,
normed=False,
basedir=writedir)
if os.path.isfile(outfile):
openfile = open(outfile, 'r')
header = openfile.readline()
for line in openfile:
entries = line.split()
rawscore = np.log(float(entries[-1]))
values.append(rawscore)
openfile.close()
else:
print('missing: ' + outfile)
print('loaded ' + str(len(values)) + ' values from neutral sims...')
#check for nans
values = np.array(values)
values = values[~np.isnan(values)]
values = list(values)
#check for infs
values = np.array(values)
values = values[~np.isinf(values)]
values = list(values)
mean = np.mean(values)
var = np.var(values)
sd = np.sqrt(var)
print("max: " + str(max(values)))
print("min: " + str(min(values)))
print("mean: " + str(np.mean(values)))
print("var: " + str(np.var(values)))
############################
## NORMALIZE NEUTRAL SIMS ##
############################
for irep in range(1, numPerBin_neut + 1):
outfile = get_neut_repfile_name(model,
irep,
selpop,
suffix=suffix,
normed=False,
basedir=writedir)
if os.path.isfile(outfile):
normedfile = outfile + ".norm" #.z"
if True:
#if not os.path.isfile(normedfile): #CHANGE FOR --checkOverwrite
openfile = open(outfile, 'r')
writefile = open(normedfile, 'w')
header = openfile.readline()
writefile.write(header)
for line in openfile:
entries = line.split()
rawscore = np.log(float(entries[-1]))
normalized = normalize(rawscore, mean, sd)
writeline = line.strip('\n') + "\t" + str(
normalized) + "\n"
writefile.write(writeline)
openfile.close()
writefile.close()
print("wrote to eg: " + normedfile)
########################
## NORMALIZE SEL SIMS ##
########################
for sel_freq_bin in sel_freq_bins:
for irep in range(1, numPerBin_sel + 1):
rawfile = get_sel_repfile_name(model,
irep,
selpop,
sel_freq_bin,
suffix=suffix,
normed=False,
basedir=writedir)
#print(rawfile)
if os.path.isfile(rawfile):
normedfile = rawfile + ".norm" #.z"
if True:
#if not os.path.isfile(normedfile):
openfile = open(rawfile, 'r')
writefile = open(normedfile, 'w')
header = openfile.readline()
writefile.write(header)
for line in openfile:
entries = line.split()
rawscore = np.log(float(entries[-1]))
normalized = normalize(rawscore, mean, sd)
writeline = line.strip('\n') + "\t" + str(
normalized) + "\n"
writefile.write(writeline)
openfile.close()
writefile.close()
print("wrote to eg: " + normedfile)
return