def _get192Ecotypes_():
resdir = "/Network/Data/250k/tmp-bvilhjal/phenotype_analyzis/"
phenotypeFile = "/Network/Data/250k/dataFreeze_011209/phenotypes_all_raw_012509.tsv"
print "Loading phenotype data"
phed = phenotypeData.readPhenotypeFile(phenotypeFile, delimiter = '\t')
phenotypeIndices = phenotypeData.categories_2_phenotypes[1]+phenotypeData.categories_2_phenotypes[2]+phenotypeData.categories_2_phenotypes[3]+phenotypeData.categories_2_phenotypes[4]
total_accessions = set()
for p_i in phenotypeIndices:
if not p_i in [5,6,7]:
accessions = phed.getAccessionsWithValues(p_i)
total_accessions = total_accessions.union(accessions)
ecotypes_192 = phenotypeData._getFirst192Ecotypes_()
ecotypes_192 = [str(e) for e in ecotypes_192]
print "len(ecotypes_192):",len(ecotypes_192)
#print ecotypes_192
phed.filterAccessions(ecotypes_192)
for p_i in [5,6,7]:
accessions = phed.getAccessionsWithValues(p_i)
total_accessions = total_accessions.union(accessions)
total_accessions = list(total_accessions)
print len(total_accessions)
total_accessions.sort()
print total_accessions
ecotype_info_dict = phenotypeData._getEcotypeIdInfoDict_()
ets = []
i = 0
for et in total_accessions:
et = int(et)
if ecotype_info_dict.has_key(et):
print str(et)+", "+str(ecotype_info_dict[et][0])+", "+str(ecotype_info_dict[et][1])
i += 1
ets.append(et)
else:
print et,"is missing in genotype data."
print i
return ets
def _run_():
if len(sys.argv) == 1:
print __doc__
sys.exit(2)
long_options_list = [
"rFile=",
"chr=",
"delim=",
"missingval=",
"BoundaryStart=",
"removeOutliers=",
"addConstant=",
"logTransform",
"BoundaryEnd=",
"phenotypeFileType=",
"help",
"parallel=",
"parallelAll",
"LRT",
"minMAF=",
"kinshipDatafile=",
"phenotypeRanks",
"onlyMissing",
"onlyOriginal96",
"onlyOriginal192",
"onlyBelowLatidue=",
"complement",
"negate",
"srInput=",
"sr",
"srOutput=",
"srPar=",
"srSkipFirstRun",
"testRobustness",
"permutationFilter=",
"useLinearRegress",
"regressionCofactors=",
"FriLerAsCofactor",
"FriColAsCofactor",
"memReq=",
"walltimeReq=",
]
try:
opts, args = getopt.getopt(sys.argv[1:], "o:c:d:m:h",
long_options_list)
except:
traceback.print_exc()
print sys.exc_info()
print __doc__
sys.exit(2)
phenotypeRanks = False
removeOutliers = None
addConstant = -1
phenotypeFileType = 1
rFile = None
delim = ","
missingVal = "NA"
help = 0
minMAF = 0.0
boundaries = [-1, -1]
chr = None
parallel = None
logTransform = False
negate = False
parallelAll = False
lrt = False
kinshipDatafile = None
onlyMissing = False
onlyOriginal96 = False
onlyOriginal192 = False
onlyBelowLatidue = None
complement = False
sr = False
srOutput = False
srInput = False
srSkipFirstRun = False
srTopQuantile = 0.95
srWindowSize = 30000
testRobustness = False
permutationFilter = 0.002
useLinearRegress = False
regressionCofactors = None
FriLerAsCofactor = False
FriColAsCofactor = False
memReq = "5g"
walltimeReq = "150:00:00"
for opt, arg in opts:
if opt in ("-h", "--help"):
help = 1
print __doc__
elif opt in ("-o", "--rFile"):
rFile = arg
elif opt in ("--phenotypeFileType"):
phenotypeFileType = int(arg)
elif opt in ("--BoundaryStart"):
boundaries[0] = int(arg)
elif opt in ("--BoundaryEnd"):
boundaries[1] = int(arg)
elif opt in ("--addConstant"):
addConstant = float(arg)
elif opt in ("--parallel"):
parallel = arg
elif opt in ("--minMAF"):
minMAF = float(arg)
elif opt in ("--parallelAll"):
parallelAll = True
elif opt in ("--onlyMissing"):
onlyMissing = True
elif opt in ("--onlyOriginal96"):
onlyOriginal96 = True
elif opt in ("--onlyOriginal192"):
onlyOriginal192 = True
elif opt in ("--onlyBelowLatidue"):
onlyBelowLatidue = float(arg)
elif opt in ("--complement"):
complement = True
elif opt in ("--logTransform"):
logTransform = True
elif opt in ("--negate"):
negate = True
elif opt in ("--removeOutliers"):
removeOutliers = float(arg)
elif opt in ("--LRT"):
lrt = True
elif opt in ("-c", "--chr"):
chr = int(arg)
elif opt in ("-d", "--delim"):
delim = arg
elif opt in ("-m", "--missingval"):
missingVal = arg
elif opt in ("--kinshipDatafile"):
kinshipDatafile = arg
elif opt in ("--phenotypeRanks"):
phenotypeRanks = True
elif opt in ("--sr"):
sr = True
elif opt in ("--srSkipFirstRun"):
srSkipFirstRun = True
elif opt in ("--srInput"):
srInput = arg
elif opt in ("--srOutput"):
srOutput = arg
elif opt in ("--srPar"):
vals = arg.split(",")
srTopQuantile = float(vals[0])
srWindowSize = int(vals[1])
elif opt in ("--testRobustness"):
testRobustness = True
elif opt in ("--permutationFilter"):
permutationFilter = float(arg)
elif opt in ("--FriLerAsCofactor"):
FriLerAsCofactor = True
elif opt in ("--FriColAsCofactor"):
FriColAsCofactor = True
elif opt in ("--useLinearRegress"):
useLinearRegress = True
elif opt in ("--regressionCofactors"):
regressionCofactors = arg
elif opt in ("--memReq"):
memReq = arg
elif opt in ("--walltimeReq"):
walltimeReq = arg
else:
if help == 0:
print "Unkown option!!\n"
print __doc__
sys.exit(2)
if len(args) < 3 and not parallel:
if help == 0:
print "Arguments are missing!!\n"
print __doc__
sys.exit(2)
print "Emma is being set up with the following parameters:"
print "output:", rFile
print "phenotypeRanks:", phenotypeRanks
print "phenotypeFileType:", phenotypeFileType
print "parallel:", parallel
print "parallelAll:", parallelAll
print "minMAF:", minMAF
print "LRT:", lrt
print "delim:", delim
print "missingval:", missingVal
print "kinshipDatafile:", kinshipDatafile
print "chr:", chr
print "boundaries:", boundaries
print "onlyMissing:", onlyMissing
print "onlyOriginal96:", onlyOriginal96
print "onlyOriginal192:", onlyOriginal192
print "onlyBelowLatidue:", onlyBelowLatidue
print "complement:", complement
print "negate:", negate
print "logTransform:", logTransform
print "addConstant:", addConstant
print "removeOutliers:", removeOutliers
print "sr:", sr
print "srSkipFirstRun:", srSkipFirstRun
print "srInput:", srInput
print "srOutput:", srOutput
print "srTopQuantile:", srTopQuantile
print "srWindowSize:", srWindowSize
print "testRobustness:", testRobustness
print "permutationFilter:", permutationFilter
print "useLinearRegress:", useLinearRegress
print "regressionCofactors:", regressionCofactors
print "FriLerAsCofactor:", FriLerAsCofactor
print "FriColAsCofactor:", FriColAsCofactor
print "walltimeReq:", walltimeReq
print "memReq:", memReq
def runParallel(phenotypeIndex, phed):
#Cluster specific parameters
print phenotypeIndex
phenName = phed.getPhenotypeName(phenotypeIndex)
outFileName = resultDir + "Emma_" + parallel + "_" + phenName
shstr = "#!/bin/csh\n"
shstr += "#PBS -l walltime=" + walltimeReq + "\n"
shstr += "#PBS -l mem=" + memReq + "\n"
shstr += "#PBS -q cmb\n"
shstr += "#PBS -N E" + phenName + "_" + parallel + "\n"
shstr += "set phenotypeName=" + parallel + "\n"
shstr += "set phenotype=" + str(phenotypeIndex) + "\n"
if useLinearRegress:
outFileName = resultDir + "LR_" + parallel + "_" + phenName
shstr += "(python " + emmadir + "Emma.py -o " + outFileName + " "
if useLinearRegress:
shstr += " --useLinearRegress "
if regressionCofactors:
shstr += " --regressionCofactors=" + str(regressionCofactors) + " "
if FriLerAsCofactor:
shstr += " --FriLerAsCofactor "
if FriColAsCofactor:
shstr += " --FriColAsCofactor "
if onlyOriginal96:
shstr += " --onlyOriginal96 "
elif onlyOriginal192:
shstr += " --onlyOriginal192 "
if onlyBelowLatidue:
shstr += " --onlyBelowLatidue=" + str(onlyBelowLatidue) + " "
if logTransform:
shstr += " --logTransform "
if negate:
shstr += " --negate "
if removeOutliers:
shstr += " --removeOutliers=" + str(removeOutliers) + " "
if phenotypeRanks:
shstr += " --phenotypeRanks "
if testRobustness:
shstr += " --testRobustness "
shstr += " --permutationFilter=" + str(permutationFilter) + " "
if sr:
shstr += " --sr "
if not srOutput:
output = resultDir + "Emma_" + parallel + "_" + phenName + ".sr.pvals"
shstr += " --srOutput=" + str(output) + " "
if srSkipFirstRun:
if not srInput:
output = resultDir + "Emma_" + parallel + "_" + phenName + ".pvals"
shstr += " --srInput=" + str(output) + " "
shstr += " --srSkipFirstRun "
shstr += " --srPar=" + str(srTopQuantile) + "," + str(
srWindowSize) + " "
if kinshipDatafile:
shstr += " --kinshipDatafile=" + str(kinshipDatafile) + " "
shstr += " --addConstant=" + str(addConstant) + " "
shstr += snpsDataFile + " " + phenotypeDataFile + " " + str(
phenotypeIndex) + " "
shstr += "> " + outFileName + "_job" + ".out) >& " + outFileName + "_job" + ".err\n"
f = open(parallel + ".sh", 'w')
f.write(shstr)
f.close()
#Execute qsub script
os.system("qsub " + parallel + ".sh ")
snpsDataFile = args[0]
phenotypeDataFile = args[1]
if parallel: #Running on the cluster..
phed = phenotypeData.readPhenotypeFile(
phenotypeDataFile, delimiter='\t') #Get Phenotype data
if parallelAll:
for phenotypeIndex in phed.phenIds:
if onlyMissing:
phenName = phed.getPhenotypeName(phenotypeIndex)
pvalFile = resultDir + "Emma_" + parallel + "_" + phenName + ".pvals"
res = None
try:
res = os.stat(pvalFile)
except Exception:
print "File", pvalFile, "does not exist."
if res and res.st_size > 0:
print "File", pvalFile, "already exists, and is non-empty."
if sr:
srInput = resultDir + "Emma_" + parallel + "_" + phenName + ".sr.pvals"
srRes = None
try:
srRes = os.stat(srInput)
except Exception:
print "File", srInput, "does not exist."
if srRes and srRes.st_size > 0:
print "File", srInput, "already exists, and is non-empty."
else:
runParallel(phenotypeIndex, phed)
else:
print "Setting up the run."
runParallel(phenotypeIndex, phed)
else:
runParallel(phenotypeIndex, phed)
else:
phenotypeIndex = int(args[2])
runParallel(phenotypeIndex, phed)
return
else:
phenotypeIndex = int(args[2])
print "phenotypeIndex:", phenotypeIndex
print "\nStarting program now!\n"
snpsds = dataParsers.parseCSVData(snpsDataFile,
format=1,
deliminator=delim,
missingVal=missingVal)
#Load phenotype file
phed = phenotypeData.readPhenotypeFile(phenotypeDataFile,
delimiter='\t') #Get Phenotype data
numAcc = len(snpsds[0].accessions)
#Removing outliers
if removeOutliers:
print "Remoing outliers"
phed.naOutliers(phenotypeIndex, removeOutliers)
#If onlyOriginal96, then remove all other phenotypes..
if onlyOriginal96:
print "Filtering for the first 96 accessions"
original_96_ecotypes = phenotypeData._getFirst96Ecotypes_()
original_96_ecotypes = map(str, original_96_ecotypes)
keepEcotypes = []
if complement:
for acc in phed.accessions:
if not acc in original_96_ecotypes:
keepEcotypes.append(acc)
else:
keepEcotypes = original_96_ecotypes
phed.filterAccessions(keepEcotypes)
print "len(phed.accessions)", len(phed.accessions)
if onlyOriginal192:
print "Filtering for the first 192 accessions"
original_192_ecotypes = phenotypeData._getFirst192Ecotypes_()
original_192_ecotypes = map(str, original_192_ecotypes)
keepEcotypes = []
if complement:
for acc in phed.accessions:
if not acc in original_192_ecotypes:
keepEcotypes.append(acc)
else:
keepEcotypes = original_192_ecotypes
phed.filterAccessions(keepEcotypes)
print "len(phed.accessions)", len(phed.accessions)
if onlyBelowLatidue:
print "Filtering for the accessions which orginate below latitude", onlyBelowLatidue
eiDict = phenotypeData._getEcotypeIdInfoDict_()
print eiDict
keepEcotypes = []
for acc in phed.accessions:
acc = int(acc)
if eiDict.has_key(acc) and eiDict[acc][
2] and eiDict[acc][2] < onlyBelowLatidue:
keepEcotypes.append(str(acc))
elif eiDict.has_key(acc) and eiDict[acc][2] == None:
keepEcotypes.append(str(acc))
phed.filterAccessions(keepEcotypes)
print "len(phed.accessions)", len(phed.accessions)
sys.stdout.write("Finished prefiltering phenotype accessions.\n")
sys.stdout.flush()
phenotype = phed.getPhenIndex(phenotypeIndex)
accIndicesToKeep = []
phenAccIndicesToKeep = []
#Checking which accessions to keep and which to remove .
for i in range(0, len(snpsds[0].accessions)):
acc1 = snpsds[0].accessions[i]
for j in range(0, len(phed.accessions)):
acc2 = phed.accessions[j]
if acc1 == acc2 and phed.phenotypeValues[j][phenotype] != 'NA':
accIndicesToKeep.append(i)
phenAccIndicesToKeep.append(j)
break
print "\nFiltering accessions in genotype data:"
#Filter accessions which do not have the phenotype value (from the genotype data).
for snpsd in snpsds:
sys.stdout.write(".")
sys.stdout.flush()
snpsd.removeAccessionIndices(accIndicesToKeep)
print ""
print numAcc - len(
accIndicesToKeep
), "accessions removed from genotype data, leaving", len(
accIndicesToKeep), "accessions in all."
print "\nNow filtering accessions in phenotype data:"
phed.removeAccessions(
phenAccIndicesToKeep
) #Removing accessions that don't have genotypes or phenotype values
print "Verifying number of accessions: len(phed.accessions)==len(snpsds[0].accessions) is", len(
phed.accessions) == len(snpsds[0].accessions)
if len(phed.accessions) != len(snpsds[0].accessions):
raise Exception
#Filtering monomorphic
print "Filtering monomorphic SNPs"
for snpsd in snpsds:
print "Removed", str(snpsd.filterMonoMorphicSnps()), "Snps"
#Remove minor allele frequencies
if minMAF != 0:
sys.stdout.write("Filterting SNPs with MAF<" + str(minMAF) + ".")
for snpsd in snpsds:
sys.stdout.write(".")
sys.stdout.flush()
snpsd.filterMinMAF(minMAF)
#Removing SNPs which are outside of boundaries.
if chr:
print "\nRemoving SNPs which are outside of boundaries."
snpsds[chr - 1].filterRegion(boundaries[0], boundaries[1])
snpsds = [snpsds[chr - 1]]
#Ordering accessions in genotype data to fit phenotype data.
print "Ordering genotype data accessions."
accessionMapping = []
i = 0
for acc in phed.accessions:
if acc in snpsds[0].accessions:
accessionMapping.append((snpsds[0].accessions.index(acc), i))
i += 1
#print zip(accessionMapping,snpsds[0].accessions)
print "len(snpsds[0].snps)", len(snpsds[0].snps)
for snpsd in snpsds:
sys.stdout.write(".")
sys.stdout.flush()
snpsd.orderAccessions(accessionMapping)
print "\nGenotype data has been ordered."
#Converting format to 01
newSnpsds = []
sys.stdout.write("Converting data format")
for snpsd in snpsds:
sys.stdout.write(".")
sys.stdout.flush()
newSnpsds.append(snpsd.getSnpsData(missingVal=missingVal))
print ""
print "Checking kinshipfile:", kinshipDatafile
if kinshipDatafile: #Is there a special kinship file?
kinshipSnpsds = dataParsers.parseCSVData(kinshipDatafile,
format=1,
deliminator=delim,
missingVal=missingVal)
accIndicesToKeep = []
#Checking which accessions to keep and which to remove (genotype data).
sys.stdout.write(
"Removing accessions which do not have a phenotype value for " +
phed.phenotypeNames[phenotype] + ".")
sys.stdout.flush()
for i in range(0, len(kinshipSnpsds[0].accessions)):
acc1 = kinshipSnpsds[0].accessions[i]
for j in range(0, len(phed.accessions)):
acc2 = phed.accessions[j]
if acc1 == acc2 and phed.phenotypeValues[j][phenotype] != 'NA':
accIndicesToKeep.append(i)
break
print accIndicesToKeep
for snpsd in kinshipSnpsds:
sys.stdout.write(".")
sys.stdout.flush()
snpsd.removeAccessionIndices(accIndicesToKeep)
print ""
print numAcc - len(
accIndicesToKeep
), "accessions removed from kinship genotype data, leaving", len(
accIndicesToKeep), "accessions in all."
print "Ordering kinship data accessions."
accessionMapping = []
i = 0
for acc in snpsds[0].accessions:
if acc in kinshipSnpsds[0].accessions:
accessionMapping.append(
(kinshipSnpsds[0].accessions.index(acc), i))
i += 1
print zip(accessionMapping, snpsds[0].accessions)
print "len(snpsds[0].snps)", len(snpsds[0].snps)
for snpsd in kinshipSnpsds:
sys.stdout.write(".")
sys.stdout.flush()
snpsd.orderAccessions(accessionMapping)
print "Kinship genotype data has been ordered."
newKinshipSnpsds = []
sys.stdout.write("Converting data format")
for snpsd in kinshipSnpsds:
sys.stdout.write(".")
sys.stdout.flush()
newKinshipSnpsds.append(snpsd.getSnpsData(
missingVal=missingVal)) #This data might have NAs
print ""
kinshipSnpsds = newKinshipSnpsds
else:
kinshipSnpsds = newSnpsds
print "Found kinship data."
#Ordering accessions according to the order of accessions in the genotype file
# accessionMapping = []
# i = 0
# for acc in snpsds[0].accessions:
# if acc in phed.accessions:
# accessionMapping.append((phed.accessions.index(acc),i))
# i += 1
# phed.orderAccessions(accessionMapping)
#Negating phenotypic values
if negate:
phed.negateValues(phenotypeIndex)
if logTransform and not phed.isBinary(
phenotypeIndex) and phed.getMinValue(phenotypeIndex) <= 0:
addConstant = 0
#Adding a constant.
if addConstant != -1:
if addConstant == 0:
addConstant = math.sqrt(phed.getVariance(phenotypeIndex)) / 10
addConstant = addConstant - phed.getMinValue(phenotypeIndex)
print "Adding a constant to phenotype:", addConstant
phed.addConstant(phenotypeIndex, addConstant)
#Log-transforming
if logTransform:
print "Log transforming phenotype"
phed.logTransform(phenotypeIndex)
#Converting phenotypes to Ranks
elif phenotypeRanks:
phed.transformToRanks(phenotypeIndex)
if not chr:
snpsDataset = snpsdata.SNPsDataSet(newSnpsds, [1, 2, 3, 4, 5])
kinshipSnpsDataset = snpsdata.SNPsDataSet(kinshipSnpsds,
[1, 2, 3, 4, 5])
else:
snpsDataset = snpsdata.SNPsDataSet(newSnpsds, [chr])
kinshipSnpsDataset = snpsdata.SNPsDataSet(kinshipSnpsds, [chr])
phenotypeName = phed.getPhenotypeName(phenotypeIndex)
sys.stdout.flush()
if testRobustness:
print "Starting a robustness test"
allSNPs = []
for snpsd in snpsDataset.snpsDataList:
allSNPs += snpsd.snps
phenVals = phed.getPhenVals(phenotypeIndex)
_robustness_test_(allSNPs, phenVals, rFile, filter=permutationFilter)
sys.exit(0)
if useLinearRegress:
phenVals = phed.getPhenVals(phenotypeIndex)
d0 = {}
d0["phen"] = phenVals
dh = {}
dh["phen"] = phenVals
import rpy, gc
if regressionCofactors: #Adds ler and col as cofactors
import pickle
f = open(regressionCofactors, "r")
co_factors = pickle.load(f)
f.close()
#inserting co factors into model
for factor in co_factors:
d[factor] = co_factors[factor]
import analyzeHaplotype as ah
(ler_factor, col_factor) = ah.getLerAndColAccessions(newSnpsds, True)
if FriColAsCofactor:
d0["col"] = col_factor
dh["col"] = col_factor
if FriLerAsCofactor:
d0["ler"] = ler_factor
dh["ler"] = ler_factor
chr_pos_pvals = []
stats = []
sys.stdout.write("Applying the linear model")
sys.stdout.flush()
for i in range(0, len(newSnpsds)): #[3]:#
snpsd = newSnpsds[i]
sys.stdout.write("|")
sys.stdout.flush()
gc.collect(
) #Calling garbage collector, in an attempt to clean up memory..
for j in range(0, len(snpsd.snps)):
if j % 5000 == 0:
sys.stdout.write(".")
sys.stdout.flush()
#if snpsd.positions[j]>1700000:
# break
snp = snpsd.snps[j]
d0["snp"] = snp
try:
rpy.set_default_mode(rpy.NO_CONVERSION)
aov0 = rpy.r.aov(r("phen ~ ."), data=d0)
aovh = rpy.r.aov(r("phen ~ ."), data=dh)
rpy.set_default_mode(rpy.BASIC_CONVERSION)
s0 = rpy.r.summary(aov0)
sh = rpy.r.summary(aovh)
#print s0,sh
rss_0 = s0['Sum Sq'][-1]
if type(sh['Sum Sq']) != float:
rss_h = sh['Sum Sq'][-1]
else:
rss_h = sh['Sum Sq']
f = (rss_h - rss_0) / (rss_0 /
(len(phenVals) - len(d0) + 1))
pval = rpy.r.pf(f, 1, len(phenVals), lower_tail=False)
except Exception, err_str:
print "Calculating p-value failed" #,err_str
pval = 1.0
#print "dh:",dh
#print "d0:",d0
#print "rss_h,rss_0:",rss_h,rss_0
#print "f,p:",f,pval
chr_pos_pvals.append([i + 1, snpsd.positions[j], pval])
mafc = min(snp.count(snp[0]), len(snp) - snp.count(snp[0]))
maf = mafc / float(len(snp))
stats.append([maf, mafc])
sys.stdout.write("\n")
#Write out to a result file
sys.stdout.write("Writing results to file\n")
sys.stdout.flush()
pvalFile = rFile + ".pvals"
f = open(pvalFile, "w")
f.write("Chromosome,position,p-value,marf,maf\n")
for i in range(0, len(chr_pos_pvals)):
chr_pos_pval = chr_pos_pvals[i]
stat = stats[i]
f.write(
str(chr_pos_pval[0]) + "," + str(chr_pos_pval[1]) + "," +
str(chr_pos_pval[2]) + "," + str(stat[0]) + "," +
str(stat[1]) + "\n")
f.close()
#Plot results
print "Generating a GW plot."
phenotypeName = phed.getPhenotypeName(phenotypeIndex)
res = gwaResults.Result(pvalFile,
name="LM_" + phenotypeName,
phenotypeID=phenotypeIndex)
res.negLogTransform()
pngFile = pvalFile + ".png"
plotResults.plotResult(res,
pngFile=pngFile,
percentile=90,
type="pvals",
ylab="$-$log$_{10}(p)$",
plotBonferroni=True,
usePylab=False)
def _run_():
if len(sys.argv)==1:
print __doc__
sys.exit(2)
long_options_list=["outputFile=", "delim=", "missingval=", "phenotypeFileType=",
"help", "parallel=", "parallelAll", "addToDB",
"callMethodID=", "comment=", "onlyOriginal192","onlyOriginal96", "subSample=" ,
"subSampleLikePhenotype=", "subsampleTest=", "complement", "onlyBelowLatidue=",
"onlyAboveLatidue=", "srInput=", "sr","srOutput=", "srPar=","srSkipFirstRun",
"permTest=", "savePermutations", "permutationFilter=", "testRobustness",
"memReq=","walltimeReq=",]
try:
opts, args=getopt.getopt(sys.argv[1:], "o:c:d:m:h", long_options_list)
except:
traceback.print_exc()
print sys.exc_info()
print __doc__
sys.exit(2)
phenotypeFileType=1
outputFile=None
delim=","
missingVal="NA"
help=0
parallel=None
parallelAll=False
addToDB=False
callMethodID=None
comment=""
subSample=None
onlyOriginal96=False
onlyOriginal192 = False
subSampleLikePhenotype = None
subsampleTest = False
numSubSamples = None
complement = False
onlyBelowLatidue = None
onlyAboveLatidue = None
sr = False
srOutput = False
srInput = False
srSkipFirstRun = False
srTopQuantile = 0.95
srWindowSize = 30000
permTest = None
savePermutations = False
permutationFilter = 1.0
testRobustness = False
memReq = "5g"
walltimeReq = "100:00:00"
for opt, arg in opts:
if opt in ("-h", "--help"):
help=1
print __doc__
elif opt in ("-o", "--outputFile"):
outputFile=arg
elif opt in ("--phenotypeFileType"):
phenotypeFileType=int(arg)
elif opt in ("--parallel"):
parallel=arg
elif opt in ("--parallelAll"):
parallelAll=True
elif opt in ("--addToDB"):
addToDB=True
elif opt in ("--onlyOriginal96"):
onlyOriginal96=True
elif opt in ("--onlyOriginal192"):
onlyOriginal192=True
elif opt in ("--complement"):
complement=True
elif opt in ("--subSample"):
subSample=int(arg)
elif opt in ("--subsampleTest"):
subsampleTest = True
l = arg.split(",")
subSample=int(l[0])
numSubSamples=int(l[1])
elif opt in ("--onlyBelowLatidue"):
onlyBelowLatidue=float(arg)
elif opt in ("--onlyAboveLatidue"):
onlyAboveLatidue=float(arg)
elif opt in ("--subSampleLikePhenotype"):
subSampleLikePhenotype=int(arg)
elif opt in ("--callMethodID"):
callMethodID=int(arg)
elif opt in ("--comment"):
comment=arg
elif opt in ("-d", "--delim"):
delim=arg
elif opt in ("-m", "--missingval"):
missingVal=arg
elif opt in ("--sr"):
sr = True
elif opt in ("--testRobustness"):
testRobustness = True
elif opt in ("--permTest"):
permTest = int(arg)
elif opt in ("--savePermutations"):
savePermutations = True
elif opt in ("--permutationFilter"):
permutationFilter = float(arg)
elif opt in ("--srSkipFirstRun"):
srSkipFirstRun = True
elif opt in ("--srInput"):
srInput = arg
elif opt in ("--srOutput"):
srOutput = arg
elif opt in ("--srPar"):
vals = arg.split(",")
srTopQuantile = float(vals[0])
srWindowSize = int(vals[1])
elif opt in ("--memReq"):
memReq=arg
elif opt in ("--walltimeReq"):
walltimeReq=arg
else:
if help==0:
print "Unkown option!!\n"
print __doc__
sys.exit(2)
if len(args)<3 and not parallel:
if help==0:
print "Arguments are missing!!\n"
print __doc__
sys.exit(2)
snpsDataFile=args[0]
phenotypeDataFile=args[1]
print "Kruskal-Wallis is being set up with the following parameters:"
print "phenotypeDataFile:",phenotypeDataFile
print "snpsDataFile:",snpsDataFile
print "parallel:",parallel
print "parallelAll:",parallelAll
print "onlyOriginal96:",onlyOriginal96
print "onlyOriginal192:",onlyOriginal192
print "onlyBelowLatidue:",onlyBelowLatidue
print "onlyAboveLatidue:",onlyAboveLatidue
print "complement:",complement
print "subSampleLikePhenotype:",subSampleLikePhenotype
print "subsampleTest:",subsampleTest
print "numSubSamples:",numSubSamples
print "subSample:",subSample
print "sr:",sr
print "srSkipFirstRun:",srSkipFirstRun
print "srInput:",srInput
print "srOutput:",srOutput
print "srTopQuantile:",srTopQuantile
print "srWindowSize:",srWindowSize
print "permTest:",permTest
print "savePermutations:",savePermutations
print "permutationFilter:",permutationFilter
print "testRobustness:",testRobustness
print "walltimeReq:",walltimeReq
print "memReq:",memReq
def runParallel(phenotypeIndex,id=""):
#Cluster specific parameters
phed=phenotypeData.readPhenotypeFile(phenotypeDataFile, delimiter = '\t') #Get Phenotype data
phenName=phed.getPhenotypeName(phenotypeIndex)
print phenName
outputFile=resultDir+"KW_"+parallel+"_"+phenName+id
shstr = "#!/bin/csh\n"
shstr += "#PBS -l walltime="+walltimeReq+"\n"
shstr += "#PBS -l mem="+memReq+"\n"
shstr +="#PBS -q cmb\n"
shstr+="#PBS -N K"+phenName+"_"+parallel+"\n"
shstr+="set phenotypeName="+parallel+"\n"
shstr+="set phenotype="+str(phenotypeIndex)+"\n"
shstr+="(python "+scriptDir+"KW.py -o "+outputFile+" "
if subSample:
shstr+=" --subSample="+str(subSample)+" "
elif onlyOriginal96:
shstr+=" --onlyOriginal96 "
elif onlyOriginal192:
shstr+=" --onlyOriginal192 "
if onlyBelowLatidue:
shstr+=" --onlyBelowLatidue="+str(onlyBelowLatidue)+" "
elif onlyAboveLatidue:
shstr+=" --onlyAboveLatidue="+str(onlyAboveLatidue)+" "
if complement:
shstr+=" --complement "
if permTest:
shstr+=" --permTest="+str(permTest)+" "
if savePermutations:
shstr+=" --savePermutations "
shstr+=" --permutationFilter="+str(permutationFilter)+" "
if testRobustness:
shstr+=" --testRobustness "
if sr:
shstr += " --sr "
if not srOutput:
output = resultDir+"KW_"+parallel+"_"+phenName+".sr.pvals"
shstr += " --srOutput="+str(output)+" "
if srSkipFirstRun:
if not srInput:
output = resultDir+"KW_"+parallel+"_"+phenName+".pvals"
shstr += " --srInput="+str(output)+" "
shstr += " --srSkipFirstRun "
shstr += " --srPar="+str(srTopQuantile)+","+str(srWindowSize)+" "
shstr+=snpsDataFile+" "+phenotypeDataFile+" "+str(phenotypeIndex)+" "
shstr+="> "+outputFile+"_job"+".out) >& "+outputFile+"_job"+".err\n"
f=open(parallel+".sh", 'w')
f.write(shstr)
f.close()
#Execute qsub script
os.system("qsub "+parallel+".sh ")
if parallel: #Running on the cluster..
if parallelAll:
phed=phenotypeData.readPhenotypeFile(phenotypeDataFile, delimiter = '\t') #Get Phenotype data
for phenotypeIndex in phed.phenIds:
runParallel(phenotypeIndex)
elif subsampleTest:
phenotypeIndex=int(args[2])
for i in range(0,numSubSamples):
runParallel(phenotypeIndex,id="_r"+str(subSample)+"_"+str(i))
else:
phenotypeIndex=int(args[2])
runParallel(phenotypeIndex)
return
else:
phenotypeIndex=int(args[2])
print "phenotypeIndex:",phenotypeIndex
print "output:",outputFile
print "\nStarting program now!\n"
#Load phenotype file
phed=phenotypeData.readPhenotypeFile(phenotypeDataFile, delimiter = '\t') #Get Phenotype data
#If onlyOriginal96, then remove all other phenotypes..
if onlyOriginal96:
print "Filtering for the first 96 accessions"
original_96_ecotypes = phenotypeData._getFirst96Ecotypes_()
original_96_ecotypes = map(str,original_96_ecotypes)
keepEcotypes = []
if complement:
for acc in phed.accessions:
if not acc in original_96_ecotypes:
keepEcotypes.append(acc)
else:
keepEcotypes = original_96_ecotypes
phed.filterAccessions(keepEcotypes)
print "len(phed.accessions)", len(phed.accessions)
if onlyOriginal192:
print "Filtering for the first 192 accessions"
original_192_ecotypes = phenotypeData._getFirst192Ecotypes_()
original_192_ecotypes = map(str,original_192_ecotypes)
keepEcotypes = []
if complement:
for acc in phed.accessions:
if not acc in original_192_ecotypes:
keepEcotypes.append(acc)
else:
keepEcotypes = original_192_ecotypes
phed.filterAccessions(keepEcotypes)
print "len(phed.accessions)", len(phed.accessions)
if onlyBelowLatidue:
print "Filtering for the accessions which orginate below latitude",onlyBelowLatidue
eiDict = phenotypeData._getEcotypeIdInfoDict_()
print eiDict
keepEcotypes = []
for acc in phed.accessions:
acc = int(acc)
if eiDict.has_key(acc) and eiDict[acc][2] and eiDict[acc][2]<onlyBelowLatidue:
keepEcotypes.append(str(acc))
elif eiDict.has_key(acc) and eiDict[acc][2]==None:
keepEcotypes.append(str(acc))
phed.filterAccessions(keepEcotypes)
print "len(phed.accessions)", len(phed.accessions)
elif onlyAboveLatidue:
print "Filtering for the accessions which orginate above latitude",onlyAboveLatidue
eiDict = phenotypeData._getEcotypeIdInfoDict_()
print eiDict
keepEcotypes = []
for acc in phed.accessions:
acc = int(acc)
if eiDict.has_key(acc) and eiDict[acc][2] and eiDict[acc][2]>onlyAboveLatidue:
keepEcotypes.append(str(acc))
elif eiDict.has_key(acc) and eiDict[acc][2]==None:
keepEcotypes.append(str(acc))
phed.filterAccessions(keepEcotypes)
print "len(phed.accessions)", len(phed.accessions)
if subSampleLikePhenotype:
p_name = phed.getPhenotypeName(subSampleLikePhenotype)
print "Picking sample as in",p_name
ecotypes = phed.getNonNAEcotypes(subSampleLikePhenotype)
print ecotypes
phed.filterAccessions(ecotypes)
print "len(phed.accessions)", len(phed.accessions)
if subSample:
sample_ecotypes = []
ecotypes = phed.getNonNAEcotypes(phenotypeIndex)
sample_ecotypes = random.sample(ecotypes,subSample)
phed.filterAccessions(sample_ecotypes)
print "len(phed.accessions)", len(phed.accessions)
sys.stdout.write("Finished prefiltering phenotype accessions.\n")
sys.stdout.flush()
#Load genotype file
snpsds=dataParsers.parseCSVData(snpsDataFile, format = 1, deliminator = delim, missingVal = missingVal)
#Checking overlap between phenotype and genotype accessions.
phenotype=phed.getPhenIndex(phenotypeIndex)
accIndicesToKeep=[]
phenAccIndicesToKeep=[]
numAcc=len(snpsds[0].accessions)
sys.stdout.write("Removing accessions which do not have a phenotype value for "+phed.phenotypeNames[phenotype]+".")
sys.stdout.flush()
for i in range(0, len(snpsds[0].accessions)):
acc1=snpsds[0].accessions[i]
for j in range(0, len(phed.accessions)):
acc2=phed.accessions[j]
if acc1==acc2 and phed.phenotypeValues[j][phenotype]!='NA':
accIndicesToKeep.append(i)
phenAccIndicesToKeep.append(j)
break
#Filter accessions which do not have the phenotype value.
for snpsd in snpsds:
sys.stdout.write(".")
sys.stdout.flush()
snpsd.removeAccessionIndices(accIndicesToKeep)
print ""
print numAcc-len(accIndicesToKeep), "accessions removed, leaving", len(accIndicesToKeep), "accessions in all."
print "Filtering phenotype data."
phed.removeAccessions(phenAccIndicesToKeep) #Removing accessions that don't have genotypes or phenotype values
#Ordering accessions according to the order of accessions in the genotype file
accessionMapping=[]
i=0
for acc in snpsds[0].accessions:
if acc in phed.accessions:
accessionMapping.append((phed.accessions.index(acc), i))
i+=1
phed.orderAccessions(accessionMapping)
#Filtering monomorphic
print "Filtering monomorphic SNPs"
for snpsd in snpsds:
print "Removed", str(snpsd.filterMonoMorphicSnps()), "Snps"
#Converting format to 01
newSnpsds=[]
sys.stdout.write("Converting data format")
for snpsd in snpsds:
sys.stdout.write(".")
sys.stdout.flush()
newSnpsds.append(snpsd.getSnpsData())
print ""
#Double check genotype file:
problems = 0
for i in range(0,len(newSnpsds)):
snpsd = newSnpsds[i]
for j in range(0,len(snpsd.snps)):
snp = snpsd.snps[j]
sc = snp.count(0)
if sc==0 or sc==len(snp):
print "Problem in file found at chr,pos",(i+1),",",snpsd.positions[i]
problems += 1
if problems >0:
print "Genotype file appears to have potential problems"
else:
print "Genotype file appears to be good"
if permTest:
print "Starting a permutation test"
allSNPs = []
for snpsd in newSnpsds:
allSNPs += snpsd.snps
phenVals = phed.getPhenVals(phenotypeIndex)
test_type = "KW"
if phed.isBinary(phenotypeIndex):
test_type = "Fisher"
permTest = 100
_perm_test_(allSNPs,phenVals,permTest,outputFile, test_type=test_type,savePermutations=savePermutations, filter=permutationFilter)
sys.exit(0)
if testRobustness:
print "Starting a robustness test"
allSNPs = []
for snpsd in newSnpsds:
allSNPs += snpsd.snps
phenVals = phed.getPhenVals(phenotypeIndex)
test_type = "KW"
if phed.isBinary(phenotypeIndex):
test_type = "Fisher"
_robustness_test_(allSNPs,phenVals,outputFile, test_type=test_type, filter=permutationFilter)
sys.exit(0)
sys.stdout.flush()
print "sr:",sr, ", srSkipFirstRun:",srSkipFirstRun
if (not sr) or (sr and not srSkipFirstRun):
#Writing files
#phed and phenotype
sd=snpsdata.SNPsDataSet(newSnpsds, [1, 2, 3, 4, 5])
phenotypeName=phed.getPhenotypeName(phenotypeIndex)
if phed.isBinary(phenotypeIndex):
pvals = run_fet(sd.getSnps(),phed.getPhenVals(phenotypeIndex))
else:
snps = sd.getSnps()
phen_vals = phed.getPhenVals(phenotypeIndex)
try:
kw_res = util.kruskal_wallis(snps,phen_vals)
pvals = kw_res['ps']
except:
print snps
print phen_vals
print len(snps),len(snps[0]),len(phen_vals)
raise Exception
res = gwaResults.Result(scores = pvals,name="KW_"+phenotypeName, snpsds=newSnpsds, load_snps=False)
pvalFile=outputFile+".pvals"
res.writeToFile(pvalFile)
print "Generating a GW plot."
res.negLogTransform()
pngFile = pvalFile+".png"
plotResults.plotResult(res,pngFile=pngFile,percentile=90,type="pvals",ylab="$-$log$_{10}(p)$", plotBonferroni=True,usePylab=False)
srInput = pvalFile
else:
print "Skipping first stage analysis."
sys.stdout.flush()
if sr:
_secondRun_(srOutput,srInput,srTopQuantile,srWindowSize,newSnpsds,phed,phenotypeIndex,binary=binary)
print "Generating second run GW plot."
res = gwaResults.Result(srInput,name="KW_"+phenotypeName, phenotypeID=phenotypeIndex)
res.negLogTransform()
srRes = gwaResults.Result(srOutput,name="KW_SR_"+phenotypeName, phenotypeID=phenotypeIndex)
srRes.negLogTransform()
srPngFile = pvalFile+".sr.png"
plotResults.plotResultWithSecondRun(res,srRes,pngFile=srPngFile,ylab="$-$log$_{10}(p)$", plotBonferroni=True)
def _run_():
if len(sys.argv) == 1:
print __doc__
sys.exit(2)
long_options_list = ["rFile=","chr=", "delim=", "missingval=", "withArrayId=", "BoundaryStart=", "removeOutliers=", "addConstant=",
"logTransform", "BoundaryEnd=", "phenotypeFileType=", "help", "parallel=", "parallelAll", "LRT", "minMAF=",
"kinshipDatafile=", "phenotypeRanks", "onlyMissing","onlyOriginal96", "onlyOriginal192", "onlyBelowLatidue=",
"complement", "negate", "srInput=", "sr","srOutput=", "srPar=","srSkipFirstRun", "testRobustness",
"permutationFilter="]
try:
opts, args = getopt.getopt(sys.argv[1:], "o:c:d:m:a:h", long_options_list)
except:
traceback.print_exc()
print sys.exc_info()
print __doc__
sys.exit(2)
phenotypeRanks = False
removeOutliers = None
addConstant = -1
phenotypeFileType = 1
rFile = None
delim = ","
missingVal = "NA"
help = 0
minMAF=0.0
withArrayIds = 1
boundaries = [-1,-1]
chr=None
parallel = None
logTransform = False
negate = False
parallelAll = False
lrt = False
kinshipDatafile = None
onlyMissing = False
onlyOriginal96 = False
onlyOriginal192 = False
onlyBelowLatidue = None
complement = False
sr = False
srOutput = False
srInput = False
srSkipFirstRun = False
srTopQuantile = 0.95
srWindowSize = 30000
testRobustness = False
permutationFilter = 0.002
for opt, arg in opts:
if opt in ("-h", "--help"):
help = 1
print __doc__
elif opt in ("-a","--withArrayId"):
withArrayIds = int(arg)
elif opt in ("-o","--rFile"):
rFile = arg
elif opt in ("--phenotypeFileType"):
phenotypeFileType = int(arg)
elif opt in ("--BoundaryStart"):
boundaries[0] = int(arg)
elif opt in ("--BoundaryEnd"):
boundaries[1] = int(arg)
elif opt in ("--addConstant"):
addConstant = float(arg)
elif opt in ("--parallel"):
parallel = arg
elif opt in ("--minMAF"):
minMAF = float(arg)
elif opt in ("--parallelAll"):
parallelAll = True
elif opt in ("--onlyMissing"):
onlyMissing = True
elif opt in ("--onlyOriginal96"):
onlyOriginal96 = True
elif opt in ("--onlyOriginal192"):
onlyOriginal192 = True
elif opt in ("--onlyBelowLatidue"):
onlyBelowLatidue = float(arg)
elif opt in ("--complement"):
complement = True
elif opt in ("--logTransform"):
logTransform = True
elif opt in ("--negate"):
negate = True
elif opt in ("--removeOutliers"):
removeOutliers = float(arg)
elif opt in ("--LRT"):
lrt = True
elif opt in ("-c","--chr"):
chr = int(arg)
elif opt in ("-d","--delim"):
delim = arg
elif opt in ("-m","--missingval"):
missingVal = arg
elif opt in ("--kinshipDatafile"):
kinshipDatafile = arg
elif opt in ("--phenotypeRanks"):
phenotypeRanks = True
elif opt in ("--sr"):
sr = True
elif opt in ("--srSkipFirstRun"):
srSkipFirstRun = True
elif opt in ("--srInput"):
srInput = arg
elif opt in ("--srOutput"):
srOutput = arg
elif opt in ("--srPar"):
vals = arg.split(",")
srTopQuantile = float(vals[0])
srWindowSize = int(vals[1])
elif opt in ("--testRobustness"):
testRobustness = True
elif opt in ("--permutationFilter"):
permutationFilter = float(arg)
else:
if help==0:
print "Unkown option!!\n"
print __doc__
sys.exit(2)
if len(args)<3 and not parallel:
if help==0:
print "Arguments are missing!!\n"
print __doc__
sys.exit(2)
print "Emma is being set up with the following parameters:"
print "output:",rFile
print "phenotypeRanks:",phenotypeRanks
print "withArrayId:",withArrayIds
print "phenotypeFileType:",phenotypeFileType
print "parallel:",parallel
print "parallelAll:",parallelAll
print "minMAF:",minMAF
print "LRT:",lrt
print "delim:",delim
print "missingval:",missingVal
print "kinshipDatafile:",kinshipDatafile
print "chr:",chr
print "boundaries:",boundaries
print "onlyMissing:",onlyMissing
print "onlyOriginal96:",onlyOriginal96
print "onlyOriginal192:",onlyOriginal192
print "onlyBelowLatidue:",onlyBelowLatidue
print "complement:",complement
print "negate:",negate
print "logTransform:",logTransform
print "addConstant:",addConstant
print "removeOutliers:",removeOutliers
print "sr:",sr
print "srSkipFirstRun:",srSkipFirstRun
print "srInput:",srInput
print "srOutput:",srOutput
print "srTopQuantile:",srTopQuantile
print "srWindowSize:",srWindowSize
print "testRobustness:",testRobustness
print "permutationFilter:",permutationFilter
def runParallel(phenotypeIndex,phed):
#Cluster specific parameters
print phenotypeIndex
phenName = phed.getPhenotypeName(phenotypeIndex)
outFileName = resultDir+"Emma_"+parallel+"_"+phenName
shstr = """#!/bin/csh
#PBS -l walltime=100:00:00
#PBS -l mem=8g
#PBS -q cmb
"""
shstr += "#PBS -N E"+phenName+"_"+parallel+"\n"
shstr += "set phenotypeName="+parallel+"\n"
shstr += "set phenotype="+str(phenotypeIndex)+"\n"
shstr += "(python "+emmadir+"Emma.py -o "+outFileName+" "
if onlyOriginal96:
shstr+=" --onlyOriginal96 "
elif onlyOriginal192:
shstr+=" --onlyOriginal192 "
if onlyBelowLatidue:
shstr+=" --onlyBelowLatidue="+str(onlyBelowLatidue)+" "
if logTransform:
shstr += " --logTransform "
if negate:
shstr += " --negate "
if removeOutliers:
shstr += " --removeOutliers="+str(removeOutliers)+" "
if phenotypeRanks:
shstr += " --phenotypeRanks "
if testRobustness:
shstr+=" --testRobustness "
shstr+=" --permutationFilter="+str(permutationFilter)+" "
if sr:
shstr += " --sr "
if not srOutput:
output = resultDir+"Emma_"+parallel+"_"+phenName+".sr.pvals"
shstr += " --srOutput="+str(output)+" "
if srSkipFirstRun:
if not srInput:
output = resultDir+"Emma_"+parallel+"_"+phenName+".pvals"
shstr += " --srInput="+str(output)+" "
shstr += " --srSkipFirstRun "
shstr += " --srPar="+str(srTopQuantile)+","+str(srWindowSize)+" "
shstr += " -a "+str(withArrayIds)+" "
if kinshipDatafile:
shstr += " --kinshipDatafile="+str(kinshipDatafile)+" "
shstr += " --addConstant="+str(addConstant)+" "
shstr += snpsDataFile+" "+phenotypeDataFile+" "+str(phenotypeIndex)+" "
shstr += "> "+outFileName+"_job"+".out) >& "+outFileName+"_job"+".err\n"
f = open(parallel+".sh",'w')
f.write(shstr)
f.close()
#Execute qsub script
os.system("qsub "+parallel+".sh ")
snpsDataFile = args[0]
phenotypeDataFile = args[1]
if parallel: #Running on the cluster..
phed = phenotypeData.readPhenotypeFile(phenotypeDataFile, delimiter='\t') #Get Phenotype data
if parallelAll:
for phenotypeIndex in phed.phenIds:
if onlyMissing:
phenName = phed.getPhenotypeName(phenotypeIndex)
pvalFile = resultDir+"Emma_"+parallel+"_"+phenName+".pvals"
res = None
try:
res = os.stat(pvalFile)
except Exception:
print "File",pvalFile,"does not exist."
if res and res.st_size>0:
print "File",pvalFile,"already exists, and is non-empty."
if sr:
srInput = resultDir+"Emma_"+parallel+"_"+phenName+".sr.pvals"
srRes = None
try:
srRes = os.stat(srInput)
except Exception:
print "File",srInput,"does not exist."
if srRes and srRes.st_size>0:
print "File",srInput,"already exists, and is non-empty."
else:
runParallel(phenotypeIndex,phed)
else:
print "Setting up the run."
runParallel(phenotypeIndex,phed)
else:
runParallel(phenotypeIndex,phed)
else:
phenotypeIndex = int(args[2])
runParallel(phenotypeIndex,phed)
return
else:
phenotypeIndex = int(args[2])
print "phenotypeIndex:",phenotypeIndex
print "\nStarting program now!\n"
snpsds = dataParsers.parseCSVData(snpsDataFile, format=1, deliminator=delim, missingVal=missingVal, withArrayIds=withArrayIds)
#Load phenotype file
phed = phenotypeData.readPhenotypeFile(phenotypeDataFile, delimiter='\t') #Get Phenotype data
numAcc = len(snpsds[0].accessions)
#Removing outliers
if removeOutliers:
print "Remoing outliers"
phed.naOutliers(phenotypeIndex,removeOutliers)
#If onlyOriginal96, then remove all other phenotypes..
if onlyOriginal96:
print "Filtering for the first 96 accessions"
original_96_ecotypes = phenotypeData._getFirst96Ecotypes_()
original_96_ecotypes = map(str,original_96_ecotypes)
keepEcotypes = []
if complement:
for acc in phed.accessions:
if not acc in original_96_ecotypes:
keepEcotypes.append(acc)
else:
keepEcotypes = original_96_ecotypes
phed.filterAccessions(keepEcotypes)
print "len(phed.accessions)", len(phed.accessions)
if onlyOriginal192:
print "Filtering for the first 192 accessions"
original_192_ecotypes = phenotypeData._getFirst192Ecotypes_()
original_192_ecotypes = map(str,original_192_ecotypes)
keepEcotypes = []
if complement:
for acc in phed.accessions:
if not acc in original_192_ecotypes:
keepEcotypes.append(acc)
else:
keepEcotypes = original_192_ecotypes
phed.filterAccessions(keepEcotypes)
print "len(phed.accessions)", len(phed.accessions)
if onlyBelowLatidue:
print "Filtering for the accessions which orginate below latitude",onlyBelowLatidue
eiDict = phenotypeData._getEcotypeIdInfoDict_()
print eiDict
keepEcotypes = []
for acc in phed.accessions:
acc = int(acc)
if eiDict.has_key(acc) and eiDict[acc][2] and eiDict[acc][2]<onlyBelowLatidue:
keepEcotypes.append(str(acc))
elif eiDict.has_key(acc) and eiDict[acc][2]==None:
keepEcotypes.append(str(acc))
phed.filterAccessions(keepEcotypes)
print "len(phed.accessions)", len(phed.accessions)
sys.stdout.write("Finished prefiltering phenotype accessions.\n")
sys.stdout.flush()
phenotype = phed.getPhenIndex(phenotypeIndex)
accIndicesToKeep = []
phenAccIndicesToKeep = []
#Checking which accessions to keep and which to remove .
for i in range(0,len(snpsds[0].accessions)):
acc1 = snpsds[0].accessions[i]
for j in range(0,len(phed.accessions)):
acc2 = phed.accessions[j]
if acc1==acc2 and phed.phenotypeValues[j][phenotype]!='NA':
accIndicesToKeep.append(i)
phenAccIndicesToKeep.append(j)
break
print "\nFiltering accessions in genotype data:"
#Filter accessions which do not have the phenotype value (from the genotype data).
for snpsd in snpsds:
sys.stdout.write(".")
sys.stdout.flush()
snpsd.removeAccessionIndices(accIndicesToKeep)
print ""
print numAcc-len(accIndicesToKeep),"accessions removed from genotype data, leaving",len(accIndicesToKeep),"accessions in all."
print "\nNow filtering accessions in phenotype data:"
phed.removeAccessions(phenAccIndicesToKeep) #Removing accessions that don't have genotypes or phenotype values
print "Verifying number of accessions: len(phed.accessions)==len(snpsds[0].accessions) is",len(phed.accessions)==len(snpsds[0].accessions)
if len(phed.accessions)!=len(snpsds[0].accessions):
raise Exception
#Filtering monomorphic
print "Filtering monomorphic SNPs"
for snpsd in snpsds:
print "Removed", str(snpsd.filterMonoMorphicSnps()),"Snps"
#Remove minor allele frequencies
if minMAF!=0:
sys.stdout.write("Filterting SNPs with MAF<"+str(minMAF)+".")
for snpsd in snpsds:
sys.stdout.write(".")
sys.stdout.flush()
snpsd.filterMinMAF(minMAF)
#Removing SNPs which are outside of boundaries.
if chr:
print "\nRemoving SNPs which are outside of boundaries."
snpsds[chr-1].filterRegion(boundaries[0],boundaries[1])
snpsds = [snpsds[chr-1]]
#Ordering accessions in genotype data to fit phenotype data.
print "Ordering genotype data accessions."
accessionMapping = []
i = 0
for acc in phed.accessions:
if acc in snpsds[0].accessions:
accessionMapping.append((snpsds[0].accessions.index(acc),i))
i += 1
#print zip(accessionMapping,snpsds[0].accessions)
print "len(snpsds[0].snps)",len(snpsds[0].snps)
for snpsd in snpsds:
sys.stdout.write(".")
sys.stdout.flush()
snpsd.orderAccessions(accessionMapping)
print "\nGenotype data has been ordered."
#Converting format to 01
newSnpsds = []
sys.stdout.write("Converting data format")
for snpsd in snpsds:
sys.stdout.write(".")
sys.stdout.flush()
newSnpsds.append(snpsd.getSnpsData(missingVal=missingVal))
print ""
print "Checking kinshipfile:",kinshipDatafile
if kinshipDatafile: #Is there a special kinship file?
kinshipSnpsds = dataParsers.parseCSVData(kinshipDatafile, format=1, deliminator=delim, missingVal=missingVal, withArrayIds=withArrayIds)
accIndicesToKeep = []
#Checking which accessions to keep and which to remove (genotype data).
sys.stdout.write("Removing accessions which do not have a phenotype value for "+phed.phenotypeNames[phenotype]+".")
sys.stdout.flush()
for i in range(0,len(kinshipSnpsds[0].accessions)):
acc1 = kinshipSnpsds[0].accessions[i]
for j in range(0,len(phed.accessions)):
acc2 = phed.accessions[j]
if acc1==acc2 and phed.phenotypeValues[j][phenotype]!='NA':
accIndicesToKeep.append(i)
break
print accIndicesToKeep
for snpsd in kinshipSnpsds:
sys.stdout.write(".")
sys.stdout.flush()
snpsd.removeAccessionIndices(accIndicesToKeep)
print ""
print numAcc-len(accIndicesToKeep),"accessions removed from kinship genotype data, leaving",len(accIndicesToKeep),"accessions in all."
print "Ordering kinship data accessions."
accessionMapping = []
i = 0
for acc in snpsds[0].accessions:
if acc in kinshipSnpsds[0].accessions:
accessionMapping.append((kinshipSnpsds[0].accessions.index(acc),i))
i += 1
print zip(accessionMapping,snpsds[0].accessions)
print "len(snpsds[0].snps)",len(snpsds[0].snps)
for snpsd in kinshipSnpsds:
sys.stdout.write(".")
sys.stdout.flush()
snpsd.orderAccessions(accessionMapping)
print "Kinship genotype data has been ordered."
newKinshipSnpsds = []
sys.stdout.write("Converting data format")
for snpsd in kinshipSnpsds:
sys.stdout.write(".")
sys.stdout.flush()
newKinshipSnpsds.append(snpsd.getSnpsData(missingVal=missingVal)) #This data might have NAs
print ""
kinshipSnpsds = newKinshipSnpsds
else:
kinshipSnpsds = newSnpsds
print "Found kinship data."
#Ordering accessions according to the order of accessions in the genotype file
# accessionMapping = []
# i = 0
# for acc in snpsds[0].accessions:
# if acc in phed.accessions:
# accessionMapping.append((phed.accessions.index(acc),i))
# i += 1
# phed.orderAccessions(accessionMapping)
#Negating phenotypic values
if negate:
phed.negateValues(phenotypeIndex)
#Adding a constant.
if addConstant!=-1:
if addConstant==0:
addConstant = math.sqrt(phed.getVariance(phenotypeIndex))/10
addConstant = addConstant - phed.getMinValue(phenotypeIndex)
print "Adding a constant to phenotype:",addConstant
phed.addConstant(phenotypeIndex,addConstant)
#Log-transforming
if logTransform:
print "Log transforming phenotype"
phed.logTransform(phenotypeIndex)
#Converting phenotypes to Ranks
elif phenotypeRanks:
phed.transformToRanks(phenotypeIndex)
if not chr:
snpsDataset = snpsdata.SNPsDataSet(newSnpsds,[1,2,3,4,5])
kinshipSnpsDataset = snpsdata.SNPsDataSet(kinshipSnpsds,[1,2,3,4,5])
else:
snpsDataset = snpsdata.SNPsDataSet(newSnpsds,[chr])
kinshipSnpsDataset = snpsdata.SNPsDataSet(kinshipSnpsds,[chr])
phenotypeName = phed.getPhenotypeName(phenotypeIndex)
sys.stdout.flush()
if testRobustness:
print "Starting a robustness test"
allSNPs = []
for snpsd in snpsDataset.snpsDataList:
allSNPs += snpsd.snps
phenVals = phed.getPhenVals(phenotypeIndex)
_robustness_test_(allSNPs,phenVals,rFile,filter=permutationFilter)
sys.exit(0)
if (not sr) or (sr and not srSkipFirstRun):
sys.stdout.write("Running Primary Emma.\n")
sys.stdout.flush()
pvalFile = _runEmmaScript_(snpsDataset, kinshipSnpsDataset, phed, phenotypeIndex, rFile, chr=chr, delim=delim, missingVal=missingVal, boundaries=boundaries, lrt=lrt)
res = gwaResults.Result(pvalFile,name="EMMA_"+phenotypeName, phenotypeID=phenotypeIndex)
res.filterMAF()
res.negLogTransform()
pngFile = pvalFile+".png"
plotResults.plotResult(res,pngFile=pngFile,percentile=90,type="pvals",ylab="$-$log$_{10}(p)$", plotBonferroni=True,usePylab=False)
srInput = pvalFile
if sr:
_secondRun_(srOutput,srInput,srTopQuantile,srWindowSize,newSnpsds,phed,phenotypeIndex,kinshipSnpsDataset)
print "Generating second run GW plot."
res = gwaResults.Result(srInput,name="KW_"+phenotypeName, phenotypeID=phenotypeIndex)
res.filterMAF()
res.negLogTransform()
srRes = gwaResults.Result(srOutput,name="EMMA_SR_"+phenotypeName, phenotypeID=phenotypeIndex)
srRes.filterMAF()
srRes.negLogTransform()
srPngFile = pvalFile+".sr.png"
plotResults.plotResultWithSecondRun(res,srRes,pngFile=srPngFile,ylab="$-$log$_{10}(p)$", plotBonferroni=True)
def _run_():
if len(sys.argv) == 1:
print __doc__
sys.exit(2)
long_options_list = [
"maxError=", "comparisonFile=", "maxMissing=", "removeEcotypeId=",
"removeArrayId=", "first96", "removeIdentical", "onlyCommon", "delim=",
"missingval=", "withArrayId=", "debug", "report", "help",
"heterozygous2NA", "first192", "removeLer", "removeCol"
]
try:
opts, args = getopt.getopt(sys.argv[1:], "o:d:m:a:bh",
long_options_list)
except:
traceback.print_exc()
print sys.exc_info()
print __doc__
sys.exit(2)
inputFile = args[0]
output_fname = None
delim = ","
missingVal = "NA"
comparisonFile = None
maxMissing = 1.0
maxError = 1.0
removeEcotypes = None
removeArray = None
removeIdentical = False
onlyCommon = False
debug = None
report = None
help = 0
withArrayIds = 1
first96 = False
first192 = False
heterozygous2NA = False
removeLer = False
removeCol = False
for opt, arg in opts:
if opt in ('-o'):
output_fname = arg
elif opt in ("-h", "--help"):
help = 1
print __doc__
elif opt in ("-a", "--withArrayId"):
withArrayIds = int(arg)
elif opt in ("--comparisonFile"):
comparisonFile = arg
elif opt in ("--maxError"):
maxError = float(arg)
elif opt in ("--maxMissing"):
maxMissing = float(arg)
elif opt in ("--heterozygous2NA"):
heterozygous2NA = True
elif opt in ("--removeEcotypeId"):
removeEcotypes = arg.split(",")
removeEcotypes = map(int, removeEcotypes)
elif opt in ("--removeArrayId"):
removeArray = int(arg)
elif opt in ("--removeIdentical"):
removeIdentical = True
elif opt in ("--onlyCommon"):
onlyCommon = True
elif opt in ("--first96"):
first96 = True
elif opt in ("--first192"):
first192 = True
elif opt in ("--removeLer"):
removeLer = True
elif opt in ("--removeCol"):
removeCol = True
elif opt in ("-d", "--delim"):
delim = arg
elif opt in ("-m", "--missingval"):
missingVal = arg
elif opt in ("-b", "--debug"):
debug = 1
elif opt in ("-r", "--report"):
report = 1
else:
if help == 0:
print "Unkown option!!\n"
print __doc__
sys.exit(2)
if not output_fname:
output_fname
if help == 0:
print "Output file missing!!\n"
print __doc__
sys.exit(2)
waid1 = withArrayIds == 1 or withArrayIds == 2
waid2 = withArrayIds == 2 or withArrayIds == 3
import dataParsers
snpsds = dataParsers.parseCSVData(inputFile,
format=1,
deliminator=delim,
missingVal=missingVal,
withArrayIds=waid1)
accessionsToRemove = []
arraysToRemove = None
if first96:
import dataParsers
d = dataParsers.getEcotypeToAccessionDictionary(defaultValue='-1',
user="******",
passwd="bamboo123")
ecotd = dataParsers.getEcotypeToNameDictionary(defaultValue='-1',
user="******",
passwd="bamboo123")
print "Dictionaries loaded"
names = []
first96Names = []
for i in range(0, len(snpsds[0].accessions)):
ecotype = snpsds[0].accessions[i]
arrayID = snpsds[0].arrayIds[i]
names.append((arrayID, ecotd[ecotype], ecotype))
if int(d[ecotype][0]) > 97 or int(d[ecotype][0]) < 0:
accessionsToRemove.append(ecotype)
else:
first96Names.append(
(arrayID, d[ecotype][1], d[ecotype][0], ecotype))
first96Names.sort()
print "First 96 accessions, len:", len(first96Names), ":"
for name in first96Names:
print name
names.sort()
print "All accessions:"
for name in names:
print name
elif first192:
import phenotypeData
ecotypes_192 = map(str, phenotypeData._getFirst192Ecotypes_())
print ecotypes_192, snpsds[0].accessions
for acc in snpsds[0].accessions:
if acc not in ecotypes_192:
accessionsToRemove.append(acc)
print "found", len(ecotypes_192), '"192" ecotypes... removing', len(
accessionsToRemove), "ecotypes."
if removeLer:
import analyzeHaplotype as ah
accessionsToRemove += ah.getLerAndColAccessions(snpsds)[0]
if removeCol:
import analyzeHaplotype as ah
accessionsToRemove += ah.getLerAndColAccessions(snpsds)[1]
#Retrieve comparison list of accessions. (Error rates for accessions)
if (removeIdentical or maxError < 1.0) and comparisonFile:
sys.stderr.write("Loading comparison file:")
snpsds2 = dataParsers.parseCSVData(comparisonFile,
format=1,
deliminator=delim,
missingVal=missingVal,
withArrayIds=waid2)
res = []
sys.stderr.write("Comparing accessions.")
for i in range(0, len(snpsds)):
res.append(snpsds[i].compareWith(snpsds2[i],
withArrayIds=withArrayIds,
verbose=False,
heterozygous2NA=heterozygous2NA))
sys.stderr.write(".")
sys.stderr.write("\n")
totalAccessionCounts = [0] * len(res[0][2])
accErrorRate = [0] * len(res[0][2])
for i in range(0, len(snpsds)):
r = res[i]
for j in range(0, len(r[2])):
totalAccessionCounts[j] += r[6][j]
accErrorRate[j] += r[3][j] * float(r[6][j])
for i in range(0, len(accErrorRate)):
accErrorRate[i] = accErrorRate[i] / float(totalAccessionCounts[i])
accErrAndID = []
if 0 < withArrayIds < 3:
for i in range(0, len(r[2])):
accErrAndID.append((accErrorRate[i], r[2][i], r[5][i]))
else:
for i in range(0, len(r[2])):
accErrAndID.append((accErrorRate[i], r[2][i]))
accErrAndID.sort()
accErrAndID.reverse()
#Figure out which accessions are too erroraneous
if maxError < 1.0 and comparisonFile:
if withArrayIds:
arraysToRemove = []
for (error, ecotype, array) in accErrAndID:
if error > maxError:
accessionsToRemove.append(ecotype)
arraysToRemove.append(array)
else:
for (error, ecotype) in accErrAndID:
if error > maxError:
accessionsToRemove.append(ecotype)
if removeIdentical and comparisonFile and withArrayIds:
print "Locating identical accessions"
accErrAndID.sort()
if not arraysToRemove:
arraysToRemove = []
for accession in set(snpsds[0].accessions):
if snpsds[0].accessions.count(accession) > 1:
found = 0
for (error, ecotype, array) in accErrAndID:
if ecotype == accession:
if found > 0:
accessionsToRemove.append(ecotype)
arraysToRemove.append(array)
found += 1
if onlyCommon and comparisonFile:
print "Locating accessions which are not shared"
snpsds2 = dataParsers.parseCSVData(comparisonFile,
format=1,
deliminator=delim,
missingVal=missingVal,
withArrayIds=waid2)
#print snpsds2[0].accessions,'\n',snpsds[0].accessions,'\n',len(set(snpsds2[0].accessions).intersection(set(snpsds[0].accessions)))
if not arraysToRemove:
arraysToRemove = []
for i in range(0, len(snpsds[0].accessions)):
acc = snpsds[0].accessions[i]
if not acc in snpsds2[0].accessions:
accessionsToRemove.append(acc)
if 0 < withArrayIds < 3:
arraysToRemove.append(snpsds[0].arrayIds[i])
if maxMissing < 1.0:
missingCounts = [0] * len(snpsds[0].accessions)
numSnps = 0
for snpsd in snpsds:
mc = snpsd.accessionsMissingCounts()
numSnps += len(snpsd.positions)
for i in range(0, len(snpsds[0].accessions)):
missingCounts[i] += mc[i]
missingRates = []
if withArrayIds:
arraysToRemove = []
for i in range(0, len(snpsds[0].accessions)):
missingRates.append(
(missingCounts[i] / float(numSnps),
snpsds[0].accessions[i], snpsds[0].arrayIds[i]))
missingRates.sort()
missingRates.reverse()
for (mrate, ecotype, array) in missingRates:
if mrate > maxMissing:
accessionsToRemove.append(ecotype)
arraysToRemove.append(array)
else:
for i in range(0, len(snpsds[0].accessions)):
missingRates.append((missingCounts[i] / float(numSnps),
snpsds[0].accessions[i]))
missingRates.sort()
missingRates.reverse()
for (mrate, ecotype) in missingRates:
if mrate > maxMissing:
accessionsToRemove.append(ecotype)
if removeEcotypes:
for removeEcotype in removeEcotypes:
accessionsToRemove.append(str(int(removeEcotype)))
print "Removing", len(accessionsToRemove), "accessions."
if removeArray:
if not arraysToRemove:
arraysToRemove = []
arraysToRemove.append(str(removeArray))
print "Removing", len(arraysToRemove), " arrays."
numAccessions = len(snpsds[0].accessions)
sys.stderr.write("Removing accessions.")
for snpsd in snpsds:
snpsd.removeAccessions(accessionsToRemove, arrayIds=arraysToRemove)
sys.stderr.write(".")
print "\n", (
numAccessions - len(snpsds[0].accessions)
), "accessions out of " + str(numAccessions) + " were removed."
import snpsdata
snpsdata.writeRawSnpsDatasToFile(output_fname,
snpsds,
chromosomes=[1, 2, 3, 4, 5],
deliminator=delim,
missingVal=missingVal,
withArrayIds=waid1)
def _run_():
if len(sys.argv)==1:
print __doc__
sys.exit(2)
long_options_list=["outputFile=", "delim=", "missingval=", "withArrayId=", "phenotypeFileType=",
"help", "parallel=", "parallelAll", "addToDB",
"callMethodID=", "comment=", "onlyOriginal192","onlyOriginal96", "subSample=" ,
"subSampleLikePhenotype=", "subsampleTest=", "complement", "onlyBelowLatidue=",
"onlyAboveLatidue=", "srInput=", "sr","srOutput=", "srPar=","srSkipFirstRun",
"permTest=", "savePermutations", "permutationFilter=", "testRobustness"]
try:
opts, args=getopt.getopt(sys.argv[1:], "o:c:d:m:a:h", long_options_list)
except:
traceback.print_exc()
print sys.exc_info()
print __doc__
sys.exit(2)
phenotypeFileType=1
outputFile=None
delim=","
missingVal="NA"
help=0
withArrayIds=1
parallel=None
parallelAll=False
addToDB=False
callMethodID=None
comment=""
subSample=None
onlyOriginal96=False
onlyOriginal192 = False
subSampleLikePhenotype = None
subsampleTest = False
numSubSamples = None
complement = False
onlyBelowLatidue = None
onlyAboveLatidue = None
sr = False
srOutput = False
srInput = False
srSkipFirstRun = False
srTopQuantile = 0.95
srWindowSize = 30000
permTest = None
savePermutations = False
permutationFilter = 1.0
testRobustness = False
for opt, arg in opts:
if opt in ("-h", "--help"):
help=1
print __doc__
elif opt in ("-a", "--withArrayId"):
withArrayIds=int(arg)
elif opt in ("-o", "--outputFile"):
outputFile=arg
elif opt in ("--phenotypeFileType"):
phenotypeFileType=int(arg)
elif opt in ("--parallel"):
parallel=arg
elif opt in ("--parallelAll"):
parallelAll=True
elif opt in ("--addToDB"):
addToDB=True
elif opt in ("--onlyOriginal96"):
onlyOriginal96=True
elif opt in ("--onlyOriginal192"):
onlyOriginal192=True
elif opt in ("--complement"):
complement=True
elif opt in ("--subSample"):
subSample=int(arg)
elif opt in ("--subsampleTest"):
subsampleTest = True
l = arg.split(",")
subSample=int(l[0])
numSubSamples=int(l[1])
elif opt in ("--onlyBelowLatidue"):
onlyBelowLatidue=float(arg)
elif opt in ("--onlyAboveLatidue"):
onlyAboveLatidue=float(arg)
elif opt in ("--subSampleLikePhenotype"):
subSampleLikePhenotype=int(arg)
elif opt in ("--callMethodID"):
callMethodID=int(arg)
elif opt in ("--comment"):
comment=arg
elif opt in ("-d", "--delim"):
delim=arg
elif opt in ("-m", "--missingval"):
missingVal=arg
elif opt in ("--sr"):
sr = True
elif opt in ("--testRobustness"):
testRobustness = True
elif opt in ("--permTest"):
permTest = int(arg)
elif opt in ("--savePermutations"):
savePermutations = True
elif opt in ("--permutationFilter"):
permutationFilter = float(arg)
elif opt in ("--srSkipFirstRun"):
srSkipFirstRun = True
elif opt in ("--srInput"):
srInput = arg
elif opt in ("--srOutput"):
srOutput = arg
elif opt in ("--srPar"):
vals = arg.split(",")
srTopQuantile = float(vals[0])
srWindowSize = int(vals[1])
else:
if help==0:
print "Unkown option!!\n"
print __doc__
sys.exit(2)
if len(args)<3 and not parallel:
if help==0:
print "Arguments are missing!!\n"
print __doc__
sys.exit(2)
snpsDataFile=args[0]
phenotypeDataFile=args[1]
print "Kruskal-Wallis is being set up with the following parameters:"
print "phenotypeDataFile:",phenotypeDataFile
print "snpsDataFile:",snpsDataFile
print "parallel:",parallel
print "parallelAll:",parallelAll
print "onlyOriginal96:",onlyOriginal96
print "onlyOriginal192:",onlyOriginal192
print "onlyBelowLatidue:",onlyBelowLatidue
print "onlyAboveLatidue:",onlyAboveLatidue
print "subSampleLikePhenotype:",subSampleLikePhenotype
print "subsampleTest:",subsampleTest
print "numSubSamples:",numSubSamples
print "subSample:",subSample
print "sr:",sr
print "srSkipFirstRun:",srSkipFirstRun
print "srInput:",srInput
print "srOutput:",srOutput
print "srTopQuantile:",srTopQuantile
print "srWindowSize:",srWindowSize
print "permTest:",permTest
print "savePermutations:",savePermutations
print "permutationFilter:",permutationFilter
print "testRobustness:",testRobustness
def runParallel(phenotypeIndex,id=""):
#Cluster specific parameters
phed=phenotypeData.readPhenotypeFile(phenotypeDataFile, delimiter = '\t') #Get Phenotype data
phenName=phed.getPhenotypeName(phenotypeIndex)
phenName=phenName.replace("/", "_div_")
phenName=phenName.replace("*", "_star_")
outputFile=resultDir+"KW_"+parallel+"_"+phenName+id
shstr="""#!/bin/csh
#PBS -l walltime=100:00:00
#PBS -l mem=4g
#PBS -q cmb
"""
shstr+="#PBS -N K"+phenName+"_"+parallel+"\n"
shstr+="set phenotypeName="+parallel+"\n"
shstr+="set phenotype="+str(phenotypeIndex)+"\n"
shstr+="(python "+scriptDir+"KW.py -o "+outputFile+" "
shstr+=" -a "+str(withArrayIds)+" "
if subSample:
shstr+=" --subSample="+str(subSample)+" "
elif onlyOriginal96:
shstr+=" --onlyOriginal96 "
elif onlyOriginal192:
shstr+=" --onlyOriginal192 "
if onlyBelowLatidue:
shstr+=" --onlyBelowLatidue="+str(onlyBelowLatidue)+" "
elif onlyAboveLatidue:
shstr+=" --onlyAboveLatidue="+str(onlyAboveLatidue)+" "
if complement:
shstr+=" --complement "
if permTest:
shstr+=" --permTest="+str(permTest)+" "
if savePermutations:
shstr+=" --savePermutations "
shstr+=" --permutationFilter="+str(permutationFilter)+" "
if testRobustness:
shstr+=" --testRobustness "
if sr:
shstr += " --sr "
if not srOutput:
output = resultDir+"KW_"+parallel+"_"+phenName+".sr.pvals"
shstr += " --srOutput="+str(output)+" "
if srSkipFirstRun:
if not srInput:
output = resultDir+"KW_"+parallel+"_"+phenName+".pvals"
shstr += " --srInput="+str(output)+" "
shstr += " --srSkipFirstRun "
shstr += " --srPar="+str(srTopQuantile)+","+str(srWindowSize)+" "
shstr+=snpsDataFile+" "+phenotypeDataFile+" "+str(phenotypeIndex)+" "
shstr+="> "+outputFile+"_job"+".out) >& "+outputFile+"_job"+".err\n"
f=open(parallel+".sh", 'w')
f.write(shstr)
f.close()
#Execute qsub script
os.system("qsub "+parallel+".sh ")
if parallel: #Running on the cluster..
if parallelAll:
phed=phenotypeData.readPhenotypeFile(phenotypeDataFile, delimiter = '\t') #Get Phenotype data
for phenotypeIndex in phed.phenIds:
runParallel(phenotypeIndex)
elif subsampleTest:
phenotypeIndex=int(args[2])
for i in range(0,numSubSamples):
runParallel(phenotypeIndex,id="_r"+str(subSample)+"_"+str(i))
else:
phenotypeIndex=int(args[2])
runParallel(phenotypeIndex)
return
else:
phenotypeIndex=int(args[2])
print "phenotypeIndex:",phenotypeIndex
print "output:",outputFile
print "\nStarting program now!\n"
#Load phenotype file
phed=phenotypeData.readPhenotypeFile(phenotypeDataFile, delimiter = '\t') #Get Phenotype data
#If onlyOriginal96, then remove all other phenotypes..
if onlyOriginal96:
print "Filtering for the first 96 accessions"
original_96_ecotypes = phenotypeData._getFirst96Ecotypes_()
original_96_ecotypes = map(str,original_96_ecotypes)
keepEcotypes = []
if complement:
for acc in phed.accessions:
if not acc in original_96_ecotypes:
keepEcotypes.append(acc)
else:
keepEcotypes = original_96_ecotypes
phed.filterAccessions(keepEcotypes)
print "len(phed.accessions)", len(phed.accessions)
if onlyOriginal192:
print "Filtering for the first 192 accessions"
original_192_ecotypes = phenotypeData._getFirst192Ecotypes_()
original_192_ecotypes = map(str,original_192_ecotypes)
keepEcotypes = []
if complement:
for acc in phed.accessions:
if not acc in original_192_ecotypes:
keepEcotypes.append(acc)
else:
keepEcotypes = original_192_ecotypes
phed.filterAccessions(keepEcotypes)
print "len(phed.accessions)", len(phed.accessions)
if onlyBelowLatidue:
print "Filtering for the accessions which orginate below latitude",onlyBelowLatidue
eiDict = phenotypeData._getEcotypeIdInfoDict_()
print eiDict
keepEcotypes = []
for acc in phed.accessions:
acc = int(acc)
if eiDict.has_key(acc) and eiDict[acc][2] and eiDict[acc][2]<onlyBelowLatidue:
keepEcotypes.append(str(acc))
elif eiDict.has_key(acc) and eiDict[acc][2]==None:
keepEcotypes.append(str(acc))
phed.filterAccessions(keepEcotypes)
print "len(phed.accessions)", len(phed.accessions)
elif onlyAboveLatidue:
print "Filtering for the accessions which orginate above latitude",onlyAboveLatidue
eiDict = phenotypeData._getEcotypeIdInfoDict_()
print eiDict
keepEcotypes = []
for acc in phed.accessions:
acc = int(acc)
if eiDict.has_key(acc) and eiDict[acc][2] and eiDict[acc][2]>onlyAboveLatidue:
keepEcotypes.append(str(acc))
elif eiDict.has_key(acc) and eiDict[acc][2]==None:
keepEcotypes.append(str(acc))
phed.filterAccessions(keepEcotypes)
print "len(phed.accessions)", len(phed.accessions)
if subSampleLikePhenotype:
p_name = phed.getPhenotypeName(subSampleLikePhenotype)
print "Picking sample as in",p_name
ecotypes = phed.getNonNAEcotypes(subSampleLikePhenotype)
print ecotypes
phed.filterAccessions(ecotypes)
print "len(phed.accessions)", len(phed.accessions)
if subSample:
sample_ecotypes = []
ecotypes = phed.getNonNAEcotypes(phenotypeIndex)
sample_ecotypes = random.sample(ecotypes,subSample)
phed.filterAccessions(sample_ecotypes)
print "len(phed.accessions)", len(phed.accessions)
sys.stdout.write("Finished prefiltering phenotype accessions.\n")
sys.stdout.flush()
#Load genotype file
snpsds=dataParsers.parseCSVData(snpsDataFile, format = 1, deliminator = delim, missingVal = missingVal, withArrayIds = withArrayIds)
#Checking overlap between phenotype and genotype accessions.
phenotype=phed.getPhenIndex(phenotypeIndex)
accIndicesToKeep=[]
phenAccIndicesToKeep=[]
numAcc=len(snpsds[0].accessions)
sys.stdout.write("Removing accessions which do not have a phenotype value for "+phed.phenotypeNames[phenotype]+".")
sys.stdout.flush()
for i in range(0, len(snpsds[0].accessions)):
acc1=snpsds[0].accessions[i]
for j in range(0, len(phed.accessions)):
acc2=phed.accessions[j]
if acc1==acc2 and phed.phenotypeValues[j][phenotype]!='NA':
accIndicesToKeep.append(i)
phenAccIndicesToKeep.append(j)
break
#Filter accessions which do not have the phenotype value.
for snpsd in snpsds:
sys.stdout.write(".")
sys.stdout.flush()
snpsd.removeAccessionIndices(accIndicesToKeep)
print ""
print numAcc-len(accIndicesToKeep), "accessions removed, leaving", len(accIndicesToKeep), "accessions in all."
print "Filtering phenotype data."
phed.removeAccessions(phenAccIndicesToKeep) #Removing accessions that don't have genotypes or phenotype values
#Ordering accessions according to the order of accessions in the genotype file
accessionMapping=[]
i=0
for acc in snpsds[0].accessions:
if acc in phed.accessions:
accessionMapping.append((phed.accessions.index(acc), i))
i+=1
phed.orderAccessions(accessionMapping)
#Filtering monomorphic
print "Filtering monomorphic SNPs"
for snpsd in snpsds:
print "Removed", str(snpsd.filterMonoMorphicSnps()), "Snps"
#Converting format to 01
newSnpsds=[]
sys.stdout.write("Converting data format")
for snpsd in snpsds:
sys.stdout.write(".")
sys.stdout.flush()
newSnpsds.append(snpsd.getSnpsData())
print ""
#Double check genotype file:
problems = 0
for i in range(0,len(newSnpsds)):
snpsd = newSnpsds[i]
for j in range(0,len(snpsd.snps)):
snp = snpsd.snps[j]
sc = snp.count(0)
if sc==0 or sc==len(snp):
print "Problem in file found at chr,pos",(i+1),",",snpsd.positions[i]
problems += 1
if problems >0:
print "Genotype file appears to have potential problems"
else:
print "Genotype file appears to be good"
if permTest:
print "Starting a permutation test"
allSNPs = []
for snpsd in newSnpsds:
allSNPs += snpsd.snps
phenVals = phed.getPhenVals(phenotypeIndex)
test_type = "KW"
if phed.isBinary(phenotypeIndex):
test_type = "Fisher"
permTest = 100
_perm_test_(allSNPs,phenVals,permTest,outputFile, test_type=test_type,savePermutations=savePermutations, filter=permutationFilter)
sys.exit(0)
if testRobustness:
print "Starting a robustness test"
allSNPs = []
for snpsd in newSnpsds:
allSNPs += snpsd.snps
phenVals = phed.getPhenVals(phenotypeIndex)
test_type = "KW"
if phed.isBinary(phenotypeIndex):
test_type = "Fisher"
_robustness_test_(allSNPs,phenVals,outputFile, test_type=test_type, filter=permutationFilter)
sys.exit(0)
sys.stdout.flush()
print "sr:",sr, ", srSkipFirstRun:",srSkipFirstRun
if (not sr) or (sr and not srSkipFirstRun):
#Writing files
if env.user=="bjarni":
tempfile.tempdir='/tmp'
(fId, phenotypeTempFile)=tempfile.mkstemp()
os.close(fId)
(fId, genotypeTempFile)=tempfile.mkstemp()
os.close(fId)
phed.writeToFile(phenotypeTempFile, [phenotype])
sys.stdout.write("Phenotype file written\n")
sys.stdout.flush()
snpsDataset=snpsdata.SNPsDataSet(newSnpsds, [1, 2, 3, 4, 5])
decoder={1:1, 0:0,-1:'NA'}
snpsDataset.writeToFile(genotypeTempFile, deliminator = delim, missingVal = missingVal, withArrayIds = 0, decoder = decoder)
sys.stdout.write("Genotype file written\n")
sys.stdout.flush()
phenotypeName=phed.getPhenotypeName(phenotypeIndex)
rDataFile=outputFile+".rData"
pvalFile=outputFile+".pvals"
#Is the phenotype binary?
binary=phed.isBinary(phenotypeIndex)
rstr=_generateRScript_(genotypeTempFile, phenotypeTempFile, rDataFile, pvalFile, name = phenotypeName, binary = binary)
rFileName=outputFile+".r"
f=open(rFileName, 'w')
f.write(rstr)
f.close()
outRfile=rFileName+".out"
errRfile=rFileName+".err"
print "Running R file:"
cmdStr="(R --vanilla < "+rFileName+" > "+outRfile+") >& "+errRfile
sys.stdout.write(cmdStr+"\n")
sys.stdout.flush()
gc.collect()
os.system(cmdStr)
#print "Emma output saved in R format in", rDataFile
print "Generating a GW plot."
res = gwaResults.Result(pvalFile,name="KW_"+phenotypeName, phenotypeID=phenotypeIndex)
res.negLogTransform()
pngFile = pvalFile+".png"
plotResults.plotResult(res,pngFile=pngFile,percentile=90,type="pvals",ylab="$-$log$_{10}(p)$", plotBonferroni=True,usePylab=False)
srInput = pvalFile
else:
print "Skipping first stage analysis."
sys.stdout.flush()
if sr:
_secondRun_(srOutput,srInput,srTopQuantile,srWindowSize,newSnpsds,phed,phenotypeIndex,binary=binary)
print "Generating second run GW plot."
res = gwaResults.Result(srInput,name="KW_"+phenotypeName, phenotypeID=phenotypeIndex)
res.negLogTransform()
srRes = gwaResults.Result(srOutput,name="KW_SR_"+phenotypeName, phenotypeID=phenotypeIndex)
srRes.negLogTransform()
srPngFile = pvalFile+".sr.png"
plotResults.plotResultWithSecondRun(res,srRes,pngFile=srPngFile,ylab="$-$log$_{10}(p)$", plotBonferroni=True)
