def _calc_statistics_(pvals,exp_quantiles,exp_median=0.5,exp_pvals=None): m = analyzePhenotype._calcMedian_(pvals,exp_median) ks_res = analyzePhenotype._calcKS_(pvals,exp_pvals) s = analyzePhenotype._estLogSlope_(pvals,exp_pvals)-1.0 ks_stat = ks_res["D"] ks_pvalue = ks_res["p.value"] quantiles = analyzePhenotype._getQuantiles_(pvals, 1000) #exp_quantiles = analyzePhenotype.__getExpectedPvalueQuantiles__(1000) a = analyzePhenotype._estAreaBetweenCurves_(quantiles,exp_quantiles) return (m,a,ks_stat,ks_pvalue,s)
def _calc_statistics_(pvals,exp_quantiles,exp_median=0.5,exp_pvals=None): m = analyzePhenotype._calcMedian_(pvals,exp_median) ks_res = analyzePhenotype._calcKS_(pvals,exp_pvals) s = analyzePhenotype._estLogSlope_(pvals,exp_pvals)-1.0 ks_stat = ks_res["D"] ks_pvalue = ks_res["p.value"] quantiles = analyzePhenotype._getQuantiles_(pvals, 1000) #exp_quantiles = analyzePhenotype.__getExpectedPvalueQuantiles__(1000) a = analyzePhenotype._estAreaBetweenCurves_(quantiles,exp_quantiles) return (m,a,ks_stat,ks_pvalue,s)
def _perm_test_(all_snps,phenVals,numPerm,outputFile,filter=0.1,test_type = "KW",savePermutations=False,useSameSnps=False):
def _calc_statistics_(pvals,exp_quantiles,exp_median=0.5,exp_pvals=None):
m = analyzePhenotype._calcMedian_(pvals,exp_median)
ks_res = analyzePhenotype._calcKS_(pvals,exp_pvals)
s = analyzePhenotype._estLogSlope_(pvals,exp_pvals)-1.0
ks_stat = ks_res["D"]
ks_pvalue = ks_res["p.value"]
quantiles = analyzePhenotype._getQuantiles_(pvals, 1000)
#exp_quantiles = analyzePhenotype.__getExpectedPvalueQuantiles__(1000)
a = analyzePhenotype._estAreaBetweenCurves_(quantiles,exp_quantiles)
return (m,a,ks_stat,ks_pvalue,s)
if filter <1.0:
snps = random.sample(all_snps,int(len(all_snps)*filter))
print "Number of SNPs:",len(snps)
else:
snps = all_snps
#Calc norm stats, and est. p-value
# print "running old KW"
# t1 = time.time()
# pvals = analyzeHaplotype._run_kw_(snps,phenVals)
# t2 = time.time()
# print "Took",t2-t1,"seconds."
if test_type=="KW":
print "running KW"
t1 = time.time()
true_pvals = util.kruskal_wallis(snps,phenVals)["ps"]
t2 = time.time()
print "Took",t2-t1,"seconds."
elif test_type=="Fisher":
print "running Fisher's exact test"
t1 = time.time()
true_pvals = run_fet(snps,phenVals)
t2 = time.time()
print "Took",t2-t1,"seconds."
perm_pvalues_list = []
for i in range(0,numPerm):#For every perm
if filter <1.0:
snps = random.sample(all_snps,int(len(all_snps)*filter))
print "Number of SNPs:",len(snps)
print i
random.shuffle(phenVals) #Permute phenotype
#pvals = analyzeHaplotype._run_kw_(snps,phenVals) #Run KW
if test_type=="KW":
print "running KW"
t1 = time.time()
pvals = util.kruskal_wallis(snps,phenVals)["ps"]
t2 = time.time()
print "Took",t2-t1,"seconds."
elif test_type=="Fisher":
print "running Fisher's exact test"
t1 = time.time()
pvals = run_fet(snps,phenVals)
t2 = time.time()
print "Took",t2-t1,"seconds."
perm_pvalues_list.append(pvals)
print "Combining p-values"
quantiles = []
all_pvals = []
for pvals in perm_pvalues_list:
for pval in pvals:
all_pvals.append(pval)
print len(all_pvals),"permuted pvals in all"
quantiles = analyzePhenotype._getQuantiles_(all_pvals, 1000)
print "len(quantiles):", len(quantiles)
exp_median = (quantiles[499]+quantiles[500])/2.0
(true_m,true_a,true_ks_stat,true_ks_pvalue,true_s) = _calc_statistics_(true_pvals,quantiles,exp_median,all_pvals)
m_list = []
a_list = []
ks_stat_list = []
ks_pvalue_list = []
s_list = []
for i in range(0,numPerm):
pvals = perm_pvalues_list[i]
(m,a,ks_stat,ks_pvalue,s) = _calc_statistics_(pvals,quantiles,exp_median,all_pvals) #Calc. statistic
m_list.append(m)
a_list.append(a)
s_list.append(s)
ks_stat_list.append(ks_stat)
ks_pvalue_list.append(ks_pvalue)
del all_pvals,quantiles
if savePermutations:
permOutputFile = outputFile+".perm.pvals"
print "Writing to",permOutputFile
f = open(permOutputFile,"w")
i = 0
for pvals in perm_pvalues_list:
pvals_str = map(str,pvals)
f.write(",".join(pvals_str)+"\n")
print "Done writing to",permOutputFile
f.close()
#Output results
outputFile = outputFile+".perm.stat.txt"
f = open(outputFile,"w")
f.write("Perm_nr, median, area, ks_stat, s_stat \n")
for i in range(0,numPerm):
str_l = map(str,[i, m_list[i],a_list[i],ks_stat_list[i],s_list[i]])
f.write(", ".join(str_l)+"\n")
f.write("\n"+"Observed values: "+str((true_m,true_a,true_ks_stat,true_s))+"\n")
pvals = [0.0,0.0,0.0,0.0]
#M stat p-value (two sided)
#Assuming symm. dist.
for i in range(0,numPerm):
if abs(true_m) <= abs(m_list[i]):
pvals[0]+=1.0/numPerm
#A stat p-value (one tailed)
for i in range(0,numPerm):
if true_a <= a_list[i]:
pvals[1]+=1.0/numPerm
#KS stat p-value (one tailed)
for i in range(0,numPerm):
if true_ks_stat <= ks_stat_list[i]:
pvals[2]+=1.0/numPerm
#S stat p-value (one tailed)
for i in range(0,numPerm):
if abs(math.log(true_s+1.0)) <= abs(math.log(s_list[i]+1.0)):
pvals[3]+=1.0/numPerm
for i in range(0,len(pvals)):
if pvals[i] == 0.0:
pvals[i] = 0.5*(1.0/numPerm)
str_pvals = map(str,pvals)
f.write("\n"+"Estimated p-values: "+",".join(str_pvals)+"\n")
f.close()
#Plot results
pngFile_median = outputFile+".perm.m.png"
pngFile_area = outputFile+".perm.a.png"
pngFile_ks = outputFile+".perm.ks.png"
pngFile_s = outputFile+".perm.s.png"
def _getBinning_(n_bins,min_val,max_val):
bins = []
delta = (max_val-min_val)/n_bins
start_val = min_val-delta*0.5
for i in range(0,n_bins+2):
bins.append(start_val+delta*i)
return (bins,delta)
n_bins = 20+int(4*(math.log(numPerm)))
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
min_val = min(min(m_list),true_m)
max_val = max(max(m_list),true_m)
(bins,delta) = _getBinning_(n_bins,min_val,max_val)
print (bins,delta)
plt.figure(figsize=(10,7))
plt.hist(m_list+[true_m], bins = bins)#, range=[start_val,end_val])
plt.hist([true_m], bins = bins)#, range=[start_val,end_val])
plt.savefig(pngFile_median, format = "png")
plt.legend()
plt.clf()
min_val = min(min(a_list),true_a)
max_val = max(max(a_list),true_a)
(bins,delta) = _getBinning_(n_bins,min_val,max_val)
print (bins,delta)
plt.figure(figsize=(10,7))
plt.hist(a_list+[true_a], bins = bins)
plt.hist([true_a], bins = bins)
plt.savefig(pngFile_area, format = "png")
plt.clf()
min_val = min(min(ks_stat_list),true_ks_stat)
max_val = max(max(ks_stat_list),true_ks_stat)
(bins,delta) = _getBinning_(n_bins,min_val,max_val)
print (bins,delta)
plt.figure(figsize=(10,7))
plt.hist(ks_stat_list+[true_ks_stat], bins = bins)
plt.hist([true_ks_stat], bins = bins)
plt.savefig(pngFile_ks, format = "png")
plt.clf()
min_val = min(min(s_list),true_s)
max_val = max(max(s_list),true_s)
(bins,delta) = _getBinning_(n_bins,min_val,max_val)
print (bins,delta)
plt.figure(figsize=(10,7))
plt.hist(s_list+[true_s], bins = bins)
plt.hist([true_s], bins = bins)
plt.savefig(pngFile_s, format = "png")
plt.clf()
def _perm_test_(all_snps,phenVals,numPerm,outputFile,filter=0.1,test_type = "KW",savePermutations=False,useSameSnps=False):
def _calc_statistics_(pvals,exp_quantiles,exp_median=0.5,exp_pvals=None):
m = analyzePhenotype._calcMedian_(pvals,exp_median)
ks_res = analyzePhenotype._calcKS_(pvals,exp_pvals)
s = analyzePhenotype._estLogSlope_(pvals,exp_pvals)-1.0
ks_stat = ks_res["D"]
ks_pvalue = ks_res["p.value"]
quantiles = analyzePhenotype._getQuantiles_(pvals, 1000)
#exp_quantiles = analyzePhenotype.__getExpectedPvalueQuantiles__(1000)
a = analyzePhenotype._estAreaBetweenCurves_(quantiles,exp_quantiles)
return (m,a,ks_stat,ks_pvalue,s)
if filter <1.0:
snps = random.sample(all_snps,int(len(all_snps)*filter))
print "Number of SNPs:",len(snps)
else:
snps = all_snps
#Calc norm stats, and est. p-value
# print "running old KW"
# t1 = time.time()
# pvals = analyzeHaplotype._run_kw_(snps,phenVals)
# t2 = time.time()
# print "Took",t2-t1,"seconds."
if test_type=="KW":
print "running KW"
t1 = time.time()
true_pvals = util.kruskal_wallis(snps,phenVals)["ps"]
t2 = time.time()
print "Took",t2-t1,"seconds."
elif test_type=="Fisher":
print "running Fisher's exact test"
t1 = time.time()
true_pvals = run_fet(snps,phenVals)
t2 = time.time()
print "Took",t2-t1,"seconds."
perm_pvalues_list = []
for i in range(0,numPerm):#For every perm
if filter <1.0:
snps = random.sample(all_snps,int(len(all_snps)*filter))
print "Number of SNPs:",len(snps)
print i
random.shuffle(phenVals) #Permute phenotype
#pvals = analyzeHaplotype._run_kw_(snps,phenVals) #Run KW
if test_type=="KW":
print "running KW"
t1 = time.time()
pvals = util.kruskal_wallis(snps,phenVals)["ps"]
t2 = time.time()
print "Took",t2-t1,"seconds."
elif test_type=="Fisher":
print "running Fisher's exact test"
t1 = time.time()
pvals = run_fet(snps,phenVals)
t2 = time.time()
print "Took",t2-t1,"seconds."
perm_pvalues_list.append(pvals)
print "Combining p-values"
quantiles = []
all_pvals = []
for pvals in perm_pvalues_list:
for pval in pvals:
all_pvals.append(pval)
print len(all_pvals),"permuted pvals in all"
quantiles = analyzePhenotype._getQuantiles_(all_pvals, 1000)
print "len(quantiles):", len(quantiles)
exp_median = (quantiles[499]+quantiles[500])/2.0
(true_m,true_a,true_ks_stat,true_ks_pvalue,true_s) = _calc_statistics_(true_pvals,quantiles,exp_median,all_pvals)
m_list = []
a_list = []
ks_stat_list = []
ks_pvalue_list = []
s_list = []
for i in range(0,numPerm):
pvals = perm_pvalues_list[i]
(m,a,ks_stat,ks_pvalue,s) = _calc_statistics_(pvals,quantiles,exp_median,all_pvals) #Calc. statistic
m_list.append(m)
a_list.append(a)
s_list.append(s)
ks_stat_list.append(ks_stat)
ks_pvalue_list.append(ks_pvalue)
del all_pvals,quantiles
if savePermutations:
permOutputFile = outputFile+".perm.pvals"
print "Writing to",permOutputFile
f = open(permOutputFile,"w")
i = 0
for pvals in perm_pvalues_list:
pvals_str = map(str,pvals)
f.write(",".join(pvals_str)+"\n")
print "Done writing to",permOutputFile
f.close()
#Output results
outputFile = outputFile+".perm.stat.txt"
f = open(outputFile,"w")
f.write("Perm_nr, median, area, ks_stat, s_stat \n")
for i in range(0,numPerm):
str_l = map(str,[i, m_list[i],a_list[i],ks_stat_list[i],s_list[i]])
f.write(", ".join(str_l)+"\n")
f.write("\n"+"Observed values: "+str((true_m,true_a,true_ks_stat,true_s))+"\n")
pvals = [0.0,0.0,0.0,0.0]
#M stat p-value (two sided)
#Assuming symm. dist.
for i in range(0,numPerm):
if abs(true_m) <= abs(m_list[i]):
pvals[0]+=1.0/numPerm
#A stat p-value (one tailed)
for i in range(0,numPerm):
if true_a <= a_list[i]:
pvals[1]+=1.0/numPerm
#KS stat p-value (one tailed)
for i in range(0,numPerm):
if true_ks_stat <= ks_stat_list[i]:
pvals[2]+=1.0/numPerm
#S stat p-value (one tailed)
for i in range(0,numPerm):
if abs(math.log(true_s+1.0)) <= abs(math.log(s_list[i]+1.0)):
pvals[3]+=1.0/numPerm
for i in range(0,len(pvals)):
if pvals[i] == 0.0:
pvals[i] = 0.5*(1.0/numPerm)
str_pvals = map(str,pvals)
f.write("\n"+"Estimated p-values: "+",".join(str_pvals)+"\n")
f.close()
#Plot results
pngFile_median = outputFile+".perm.m.png"
pngFile_area = outputFile+".perm.a.png"
pngFile_ks = outputFile+".perm.ks.png"
pngFile_s = outputFile+".perm.s.png"
def _getBinning_(n_bins,min_val,max_val):
bins = []
delta = (max_val-min_val)/n_bins
start_val = min_val-delta*0.5
for i in range(0,n_bins+2):
bins.append(start_val+delta*i)
return (bins,delta)
n_bins = 20+int(4*(math.log(numPerm)))
import matplotlib
matplotlib.use('Agg')
import matplotlib.pyplot as plt
min_val = min(min(m_list),true_m)
max_val = max(max(m_list),true_m)
(bins,delta) = _getBinning_(n_bins,min_val,max_val)
print (bins,delta)
plt.figure(figsize=(10,7))
plt.hist(m_list+[true_m], bins = bins)#, range=[start_val,end_val])
plt.hist([true_m], bins = bins)#, range=[start_val,end_val])
plt.savefig(pngFile_median, format = "png")
plt.legend()
plt.clf()
min_val = min(min(a_list),true_a)
max_val = max(max(a_list),true_a)
(bins,delta) = _getBinning_(n_bins,min_val,max_val)
print (bins,delta)
plt.figure(figsize=(10,7))
plt.hist(a_list+[true_a], bins = bins)
plt.hist([true_a], bins = bins)
plt.savefig(pngFile_area, format = "png")
plt.clf()
min_val = min(min(ks_stat_list),true_ks_stat)
max_val = max(max(ks_stat_list),true_ks_stat)
(bins,delta) = _getBinning_(n_bins,min_val,max_val)
print (bins,delta)
plt.figure(figsize=(10,7))
plt.hist(ks_stat_list+[true_ks_stat], bins = bins)
plt.hist([true_ks_stat], bins = bins)
plt.savefig(pngFile_ks, format = "png")
plt.clf()
min_val = min(min(s_list),true_s)
max_val = max(max(s_list),true_s)
(bins,delta) = _getBinning_(n_bins,min_val,max_val)
print (bins,delta)
plt.figure(figsize=(10,7))
plt.hist(s_list+[true_s], bins = bins)
plt.hist([true_s], bins = bins)
plt.savefig(pngFile_s, format = "png")
plt.clf()
