def main():
# index reference
refIndex = indexRef(REFERENCE)
if PAIRED_END:
N_HANDLING = ('random',FRAGMENT_SIZE)
else:
N_HANDLING = ('ignore',READLEN)
indices_by_refName = {refIndex[n][0]:n for n in xrange(len(refIndex))}
# parse input variants, if present
inputVariants = []
if INPUT_VCF != None:
if CANCER:
(sampNames, inputVariants) = parseVCF(INPUT_VCF,tumorNormal=True,ploidy=PLOIDS)
tumorInd = sampNames.index('TUMOR')
normalInd = sampNames.index('NORMAL')
else:
(sampNames, inputVariants) = parseVCF(INPUT_VCF,ploidy=PLOIDS)
for k in sorted(inputVariants.keys()):
inputVariants[k].sort()
# parse input targeted regions, if present
inputRegions = {}
if INPUT_BED != None:
with open(INPUT_BED,'r') as f:
for line in f:
[myChr,pos1,pos2] = line.strip().split('\t')[:3]
if myChr not in inputRegions:
inputRegions[myChr] = [-1]
inputRegions[myChr].extend([int(pos1),int(pos2)])
# parse input mutation rate rescaling regions, if present
mutRateRegions = {}
mutRateValues = {}
if MUT_BED != None:
with open(MUT_BED,'r') as f:
for line in f:
[myChr,pos1,pos2,metaData] = line.strip().split('\t')[:4]
mutStr = re.findall(r"MUT_RATE=.*?(?=;)",metaData+';')
(pos1,pos2) = (int(pos1),int(pos2))
if len(mutStr) and (pos2-pos1) > 1:
# mutRate = #_mutations / length_of_region, let's bound it by a reasonable amount
mutRate = max([0.0,min([float(mutStr[0][9:]),0.3])])
if myChr not in inputRegions:
mutRateRegions[myChr] = [-1]
mutRateValues[myChr] = [0.0]
mutRateRegions[myChr].extend([pos1,pos2])
mutRateValues.extend([mutRate*(pos2-pos1)]*2)
# initialize output files (part I)
bamHeader = None
if SAVE_BAM:
bamHeader = [copy.deepcopy(refIndex)]
vcfHeader = None
if SAVE_VCF:
vcfHeader = [REFERENCE]
# If processing jobs in parallel, precompute the independent regions that can be process separately
if NJOBS > 1:
parallelRegionList = getAllRefRegions(REFERENCE,refIndex,N_HANDLING,saveOutput=SAVE_NON_N)
(myRefs, myRegions) = partitionRefRegions(parallelRegionList,refIndex,MYJOB,NJOBS)
if not len(myRegions):
print 'This job id has no regions to process, exiting...'
exit(1)
for i in xrange(len(refIndex)-1,-1,-1): # delete reference not used in our job
if not refIndex[i][0] in myRefs:
del refIndex[i]
# if value of NJOBS is too high, let's change it to the maximum possible, to avoid output filename confusion
corrected_nJobs = min([NJOBS,sum([len(n) for n in parallelRegionList.values()])])
else:
corrected_nJobs = 1
# initialize output files (part II)
if CANCER:
OFW = OutputFileWriter(OUT_PREFIX+'_normal',paired=PAIRED_END,BAM_header=bamHeader,VCF_header=vcfHeader,gzipped=GZIPPED_OUT)
OFW_CANCER = OutputFileWriter(OUT_PREFIX+'_tumor',paired=PAIRED_END,BAM_header=bamHeader,VCF_header=vcfHeader,gzipped=GZIPPED_OUT,jobTuple=(MYJOB,corrected_nJobs))
else:
OFW = OutputFileWriter(OUT_PREFIX,paired=PAIRED_END,BAM_header=bamHeader,VCF_header=vcfHeader,gzipped=GZIPPED_OUT,jobTuple=(MYJOB,corrected_nJobs))
OUT_PREFIX_NAME = OUT_PREFIX.split('/')[-1]
"""************************************************
**** LET'S GET THIS PARTY STARTED...
************************************************"""
readNameCount = 1 # keep track of the number of reads we've sampled, for read-names
for RI in xrange(len(refIndex)):
# read in reference sequence and notate blocks of Ns
(refSequence,N_regions) = readRef(REFERENCE,refIndex[RI],N_HANDLING)
# if we're processing jobs in parallel only take the regions relevant for the current job
if NJOBS > 1:
for i in xrange(len(N_regions['non_N'])-1,-1,-1):
if not (refIndex[RI][0],N_regions['non_N'][i][0],N_regions['non_N'][i][1]) in myRegions:
del N_regions['non_N'][i]
# count total bp we'll be spanning so we can get an idea of how far along we are (for printing progress indicators)
total_bp_span = sum([n[1]-n[0] for n in N_regions['non_N']])
currentProgress = 0
currentPercent = 0
# prune invalid input variants, e.g variants that:
# - try to delete or alter any N characters
# - don't match the reference base at their specified position
# - any alt allele contains anything other than allowed characters
validVariants = []
nSkipped = [0,0,0]
if refIndex[RI][0] in inputVariants:
for n in inputVariants[refIndex[RI][0]]:
span = (n[0],n[0]+len(n[1]))
rseq = str(refSequence[span[0]-1:span[1]-1]) # -1 because going from VCF coords to array coords
anyBadChr = any((nn not in ALLOWED_NUCL) for nn in [item for sublist in n[2] for item in sublist])
if rseq != n[1]:
nSkipped[0] += 1
continue
elif 'N' in rseq:
nSkipped[1] += 1
continue
elif anyBadChr:
nSkipped[2] += 1
continue
#if bisect.bisect(N_regions['big'],span[0])%2 or bisect.bisect(N_regions['big'],span[1])%2:
# continue
validVariants.append(n)
print 'found',len(validVariants),'valid variants for '+refIndex[RI][0]+' in input VCF...'
if any(nSkipped):
print sum(nSkipped),'variants skipped...'
print ' - ['+str(nSkipped[0])+'] ref allele does not match reference'
print ' - ['+str(nSkipped[1])+'] attempting to insert into N-region'
print ' - ['+str(nSkipped[2])+'] alt allele contains non-ACGT characters'
# add large random structural variants
#
# TBD!!!
# determine which structural variants will affect our sampling window positions
structuralVars = []
for n in validVariants:
bufferNeeded = max([max([len(n[1])-len(alt_allele),1]) for alt_allele in n[2]])
structuralVars.append((n[0]-1,bufferNeeded)) # -1 because going from VCF coords to array coords
# determine sampling windows based on read length, large N regions, and structural mutations.
# in order to obtain uniform coverage, windows should overlap by:
# - READLEN, if single-end reads
# - FRAGMENT_SIZE (mean), if paired-end reads
# ploidy is fixed per large sampling window,
# coverage distributions due to GC% and targeted regions are specified within these windows
samplingWindows = []
ALL_VARIANTS_OUT = {}
sequences = None
if PAIRED_END:
targSize = WINDOW_TARGET_SCALE*FRAGMENT_SIZE
overlap = FRAGMENT_SIZE
else:
targSize = WINDOW_TARGET_SCALE*READLEN
overlap = READLEN
print '--------------------------------'
print 'sampling reads...'
for i in xrange(len(N_regions['non_N'])):
(pi,pf) = N_regions['non_N'][i]
nTargWindows = max([1,(pf-pi)/targSize])
bpd = int((pf-pi)/float(nTargWindows))
bpd += GC_WINDOW_SIZE - bpd%GC_WINDOW_SIZE
#print len(refSequence), (pi,pf), nTargWindows
#print structuralVars
# if for some reason our region is too small to process, skip it! (sorry)
if nTargWindows == 1 and (pf-pi) < overlap-1:
#print 'Does this ever happen?'
continue
start = pi
end = min([start+bpd,pf])
#print '------------------RAWR:', (pi,pf), bpd
currentVariantInd = 0
varsFromPrevOverlap = []
varsCancerFromPrevOverlap = []
vindFromPrev = 0
isLastTime = False
while True:
####print (start,end)
# adjust end-position of window based on inserted structural mutations
relevantVars = []
if len(structuralVars) and currentVariantInd < len(structuralVars):
prevVarInd = currentVariantInd
while structuralVars[currentVariantInd][0] <= end:
delta = (end-1) - (structuralVars[currentVariantInd][0] + structuralVars[currentVariantInd][1])
if delta <= 0:
####print 'DELTA:', delta
end -= (delta-1)
currentVariantInd += 1
if currentVariantInd == len(structuralVars):
break
relevantVars = structuralVars[prevVarInd:currentVariantInd]
next_start = end-overlap
next_end = min([next_start+bpd,pf])
if next_end-next_start < bpd:
end = next_end
isLastTime = True
# print progress indicator
#print 'PROCESSING WINDOW:',(start,end)
currentProgress += end-start
newPercent = int((currentProgress*100)/float(total_bp_span))
if newPercent > currentPercent:
sys.stdout.write(str(newPercent)+'% ')
sys.stdout.flush()
currentPercent = newPercent
# which inserted variants are in this window?
varsInWindow = []
updated = False
for j in xrange(vindFromPrev,len(validVariants)):
vPos = validVariants[j][0]
if vPos >= start and vPos < end:
varsInWindow.append(tuple([vPos-1]+list(validVariants[j][1:]))) # vcf --> array coords
if vPos >= end-overlap-1 and updated == False:
updated = True
vindFromPrev = j
if vPos >= end:
break
# if computing only VCF, we can skip this...
if ONLY_VCF:
coverage_dat = None
coverage_avg = None
else:
# pre-compute gc-bias and targeted sequencing coverage modifiers
nSubWindows = (end-start)/GC_WINDOW_SIZE
coverage_dat = (GC_WINDOW_SIZE,[])
for j in xrange(nSubWindows):
rInd = start + j*GC_WINDOW_SIZE
if INPUT_BED == None: tCov = True
else: tCov = not(bisect.bisect(inputRegions[myChr],rInd)%2) or not(bisect.bisect(inputRegions[myChr],rInd+GC_WINDOW_SIZE)%2)
if tCov: tScl = 1.0
else: tScl = OFFTARGET_SCALAR
gc_v = refSequence[rInd:rInd+GC_WINDOW_SIZE].count('G') + refSequence[rInd:rInd+GC_WINDOW_SIZE].count('C')
gScl = GC_SCALE_VAL[gc_v]
coverage_dat[1].append(1.0*tScl*gScl)
coverage_avg = np.mean(coverage_dat[1])
# pre-compute mutation rate tracks
# PROVIDED MUTATION RATES OVERRIDE AVERAGE VALUE
# construct sequence data that we will sample reads from
if sequences == None:
sequences = SequenceContainer(start,refSequence[start:end],PLOIDS,overlap,READLEN,[MUT_MODEL]*PLOIDS,MUT_RATE,coverage_dat,onlyVCF=ONLY_VCF)
else:
sequences.update(start,refSequence[start:end],PLOIDS,overlap,READLEN,[MUT_MODEL]*PLOIDS,MUT_RATE,coverage_dat)
# adjust position of all inserted variants to match current window offset
#variants_to_insert = []
#for n in varsFromPrevOverlap:
# ln = [n[0]-start] + list(n[1:])
# variants_to_insert.append(tuple(ln))
#for n in varsInWindow:
# ln = [n[0]-start] + list(n[1:])
# variants_to_insert.append(tuple(ln))
#sequences.insert_mutations(variants_to_insert)
sequences.insert_mutations(varsFromPrevOverlap + varsInWindow)
all_inserted_variants = sequences.random_mutations()
#print all_inserted_variants
if CANCER:
tumor_sequences = SequenceContainer(start,refSequence[start:end],PLOIDS,overlap,READLEN,[CANCER_MODEL]*PLOIDS,MUT_RATE,coverage_dat)
tumor_sequences.insert_mutations(varsCancerFromPrevOverlap + all_inserted_variants)
all_cancer_variants = tumor_sequences.random_mutations()
# which variants do we need to keep for next time (because of window overlap)?
varsFromPrevOverlap = []
varsCancerFromPrevOverlap = []
for n in all_inserted_variants:
if n[0] >= end-overlap-1:
varsFromPrevOverlap.append(n)
if CANCER:
for n in all_cancer_variants:
if n[0] >= end-overlap-1:
varsCancerFromPrevOverlap.append(n)
# if we're only producing VCF, no need to go through the hassle of generating reads
if ONLY_VCF:
pass
else:
# for each sampling window, construct sub-windows with coverage information
covWindows = [COVERAGE for n in xrange((end-start)/SMALL_WINDOW)]
if (end-start)%SMALL_WINDOW:
covWindows.append(COVERAGE)
meanCov = sum(covWindows)/float(len(covWindows))
if PAIRED_END:
readsToSample = int(((end-start)*meanCov*coverage_avg)/(2*READLEN))+1
else:
readsToSample = int(((end-start)*meanCov*coverage_avg)/(READLEN))+1
# sample reads from altered reference
for i in xrange(readsToSample):
if PAIRED_END:
myFraglen = FRAGLEN_DISTRIBUTION.sample()
myReadData = sequences.sample_read(SE_CLASS,myFraglen)
myReadData[0][0] += start # adjust mapping position based on window start
myReadData[1][0] += start
else:
myReadData = sequences.sample_read(SE_CLASS)
myReadData[0][0] += start # adjust mapping position based on window start
if NJOBS > 1:
myReadName = OUT_PREFIX_NAME+'-j'+str(MYJOB)+'-'+refIndex[RI][0]+'-r'+str(readNameCount)
else:
myReadName = OUT_PREFIX_NAME+'-'+refIndex[RI][0]+'-'+str(readNameCount)
readNameCount += len(myReadData)
# if desired, replace all low-quality bases with Ns
if N_MAX_QUAL > -1:
for j in xrange(len(myReadData)):
myReadString = [n for n in myReadData[j][2]]
for k in xrange(len(myReadData[j][3])):
adjusted_qual = ord(myReadData[j][3][k])-SE_CLASS.offQ
if adjusted_qual <= N_MAX_QUAL:
myReadString[k] = 'N'
myReadData[j][2] = ''.join(myReadString)
# write read data out to FASTQ and BAM files, bypass FASTQ if option specified
myRefIndex = indices_by_refName[refIndex[RI][0]]
if len(myReadData) == 1:
if NO_FASTQ != True:
OFW.writeFASTQRecord(myReadName,myReadData[0][2],myReadData[0][3])
if SAVE_BAM:
OFW.writeBAMRecord(myRefIndex, myReadName+'/1', myReadData[0][0], myReadData[0][1], myReadData[0][2], myReadData[0][3], samFlag=0)
elif len(myReadData) == 2:
if NO_FASTQ != True:
OFW.writeFASTQRecord(myReadName,myReadData[0][2],myReadData[0][3],read2=myReadData[1][2],qual2=myReadData[1][3])
if SAVE_BAM:
OFW.writeBAMRecord(myRefIndex, myReadName+'/1', myReadData[0][0], myReadData[0][1], myReadData[0][2], myReadData[0][3], samFlag=99, matePos=myReadData[1][0])
OFW.writeBAMRecord(myRefIndex, myReadName+'/2', myReadData[1][0], myReadData[1][1], myReadData[1][2], myReadData[1][3], samFlag=147, matePos=myReadData[0][0])
else:
print '\nError: Unexpected number of reads generated...\n'
exit(1)
# tally up all the variants that got successfully introduced
for n in all_inserted_variants:
ALL_VARIANTS_OUT[n] = True
# prepare indices of next window
start = next_start
end = next_end
if isLastTime:
break
if end >= pf:
isLastTime = True
if currentPercent != 100:
print '100%'
else:
print ''
# write all output variants for this reference
if SAVE_VCF:
for k in sorted(ALL_VARIANTS_OUT.keys()):
currentRef = refIndex[RI][0]
myID = '.'
myQual = '.'
myFilt = 'PASS'
# k[0] + 1 because we're going back to 1-based vcf coords
OFW.writeVCFRecord(currentRef, str(int(k[0])+1), myID, k[1], k[2], myQual, myFilt, k[4])
#break
# close output files
OFW.closeFiles()
if CANCER:
OFW_CANCER.closeFiles()
def main():
# index reference
refIndex = indexRef(REFERENCE)
if PAIRED_END:
N_HANDLING = ('random',FRAGMENT_SIZE)
else:
N_HANDLING = ('ignore',READLEN)
indices_by_refName = {refIndex[n][0]:n for n in xrange(len(refIndex))}
# parse input variants, if present
inputVariants = []
if INPUT_VCF != None:
if CANCER:
(sampNames, inputVariants) = parseVCF(INPUT_VCF,tumorNormal=True,ploidy=PLOIDS)
tumorInd = sampNames.index('TUMOR')
normalInd = sampNames.index('NORMAL')
else:
(sampNames, inputVariants) = parseVCF(INPUT_VCF,ploidy=PLOIDS)
for k in sorted(inputVariants.keys()):
inputVariants[k].sort()
# parse input targeted regions, if present
refList = [n[0] for n in refIndex]
inputRegions = {}
if INPUT_BED != None:
f = open(INPUT_BED,'r')
for line in f:
[myChr,pos1,pos2] = line.strip().split('\t')[:3]
if myChr not in inputRegions:
inputRegions[myChr] = [-1]
inputRegions[myChr].extend([int(pos1),int(pos2)])
f.close()
# some validation
nInBedOnly = 0
nInRefOnly = 0
for k in refList:
if k not in inputRegions:
nInRefOnly += 1
for k in inputRegions.keys():
if not k in refList:
nInBedOnly += 1
del inputRegions[k]
if nInRefOnly > 0:
print 'Warning: Reference contains sequences not found in targeted regions BED file.'
if nInBedOnly > 0:
print 'Warning: Targeted regions BED file contains sequence names not found in reference (regions ignored).'
# parse discard bed similarly
discardRegions = {}
if DISCARD_BED != None:
f = open(DISCARD_BED,'r')
for line in f:
[myChr,pos1,pos2] = line.strip().split('\t')[:3]
if myChr not in discardRegions:
discardRegions[myChr] = [-1]
discardRegions[myChr].extend([int(pos1),int(pos2)])
f.close()
# parse input mutation rate rescaling regions, if present
mutRateRegions = {}
mutRateValues = {}
if MUT_BED != None:
with open(MUT_BED,'r') as f:
for line in f:
[myChr,pos1,pos2,metaData] = line.strip().split('\t')[:4]
mutStr = re.findall(r"MUT_RATE=.*?(?=;)",metaData+';')
(pos1,pos2) = (int(pos1),int(pos2))
if len(mutStr) and (pos2-pos1) > 1:
# mutRate = #_mutations / length_of_region, let's bound it by a reasonable amount
mutRate = max([0.0,min([float(mutStr[0][9:]),0.3])])
if myChr not in mutRateRegions:
mutRateRegions[myChr] = [-1]
mutRateValues[myChr] = [0.0]
mutRateRegions[myChr].extend([pos1,pos2])
mutRateValues.extend([mutRate*(pos2-pos1)]*2)
# initialize output files (part I)
bamHeader = None
if SAVE_BAM:
bamHeader = [copy.deepcopy(refIndex)]
vcfHeader = None
if SAVE_VCF:
vcfHeader = [REFERENCE]
# If processing jobs in parallel, precompute the independent regions that can be process separately
if NJOBS > 1:
parallelRegionList = getAllRefRegions(REFERENCE,refIndex,N_HANDLING,saveOutput=SAVE_NON_N)
(myRefs, myRegions) = partitionRefRegions(parallelRegionList,refIndex,MYJOB,NJOBS)
if not len(myRegions):
print 'This job id has no regions to process, exiting...'
exit(1)
for i in xrange(len(refIndex)-1,-1,-1): # delete reference not used in our job
if not refIndex[i][0] in myRefs:
del refIndex[i]
# if value of NJOBS is too high, let's change it to the maximum possible, to avoid output filename confusion
corrected_nJobs = min([NJOBS,sum([len(n) for n in parallelRegionList.values()])])
else:
corrected_nJobs = 1
# initialize output files (part II)
if CANCER:
OFW = OutputFileWriter(OUT_PREFIX+'_normal',paired=PAIRED_END,BAM_header=bamHeader,VCF_header=vcfHeader,gzipped=GZIPPED_OUT,noFASTQ=NO_FASTQ,FASTA_instead=FASTA_INSTEAD)
OFW_CANCER = OutputFileWriter(OUT_PREFIX+'_tumor',paired=PAIRED_END,BAM_header=bamHeader,VCF_header=vcfHeader,gzipped=GZIPPED_OUT,jobTuple=(MYJOB,corrected_nJobs),noFASTQ=NO_FASTQ,FASTA_instead=FASTA_INSTEAD)
else:
OFW = OutputFileWriter(OUT_PREFIX,paired=PAIRED_END,BAM_header=bamHeader,VCF_header=vcfHeader,gzipped=GZIPPED_OUT,jobTuple=(MYJOB,corrected_nJobs),noFASTQ=NO_FASTQ,FASTA_instead=FASTA_INSTEAD)
OUT_PREFIX_NAME = OUT_PREFIX.split('/')[-1]
"""************************************************
**** LET'S GET THIS PARTY STARTED...
************************************************"""
readNameCount = 1 # keep track of the number of reads we've sampled, for read-names
unmapped_records = []
for RI in xrange(len(refIndex)):
# read in reference sequence and notate blocks of Ns
(refSequence,N_regions) = readRef(REFERENCE,refIndex[RI],N_HANDLING)
# if we're processing jobs in parallel only take the regions relevant for the current job
if NJOBS > 1:
for i in xrange(len(N_regions['non_N'])-1,-1,-1):
if not (refIndex[RI][0],N_regions['non_N'][i][0],N_regions['non_N'][i][1]) in myRegions:
del N_regions['non_N'][i]
# count total bp we'll be spanning so we can get an idea of how far along we are (for printing progress indicators)
total_bp_span = sum([n[1]-n[0] for n in N_regions['non_N']])
currentProgress = 0
currentPercent = 0
havePrinted100 = False
# prune invalid input variants, e.g variants that:
# - try to delete or alter any N characters
# - don't match the reference base at their specified position
# - any alt allele contains anything other than allowed characters
validVariants = []
nSkipped = [0,0,0]
if refIndex[RI][0] in inputVariants:
for n in inputVariants[refIndex[RI][0]]:
span = (n[0],n[0]+len(n[1]))
rseq = str(refSequence[span[0]-1:span[1]-1]) # -1 because going from VCF coords to array coords
anyBadChr = any((nn not in ALLOWED_NUCL) for nn in [item for sublist in n[2] for item in sublist])
if rseq != n[1]:
nSkipped[0] += 1
continue
elif 'N' in rseq:
nSkipped[1] += 1
continue
elif anyBadChr:
nSkipped[2] += 1
continue
#if bisect.bisect(N_regions['big'],span[0])%2 or bisect.bisect(N_regions['big'],span[1])%2:
# continue
validVariants.append(n)
print 'found',len(validVariants),'valid variants for '+refIndex[RI][0]+' in input VCF...'
if any(nSkipped):
print sum(nSkipped),'variants skipped...'
print ' - ['+str(nSkipped[0])+'] ref allele does not match reference'
print ' - ['+str(nSkipped[1])+'] attempting to insert into N-region'
print ' - ['+str(nSkipped[2])+'] alt allele contains non-ACGT characters'
# add large random structural variants
#
# TBD!!!
# determine sampling windows based on read length, large N regions, and structural mutations.
# in order to obtain uniform coverage, windows should overlap by:
# - READLEN, if single-end reads
# - FRAGMENT_SIZE (mean), if paired-end reads
# ploidy is fixed per large sampling window,
# coverage distributions due to GC% and targeted regions are specified within these windows
samplingWindows = []
ALL_VARIANTS_OUT = {}
sequences = None
if PAIRED_END:
targSize = WINDOW_TARGET_SCALE*FRAGMENT_SIZE
overlap = FRAGMENT_SIZE
overlap_minWindowSize = max(FRAGLEN_DISTRIBUTION.values) + 10
else:
targSize = WINDOW_TARGET_SCALE*READLEN
overlap = READLEN
overlap_minWindowSize = READLEN + 10
print '--------------------------------'
if ONLY_VCF:
print 'generating vcf...'
else:
print 'sampling reads...'
tt = time.time()
for i in xrange(len(N_regions['non_N'])):
(pi,pf) = N_regions['non_N'][i]
nTargWindows = max([1,(pf-pi)/targSize])
bpd = int((pf-pi)/float(nTargWindows))
#bpd += GC_WINDOW_SIZE - bpd%GC_WINDOW_SIZE
#print len(refSequence), (pi,pf), nTargWindows
#print structuralVars
# if for some reason our region is too small to process, skip it! (sorry)
if nTargWindows == 1 and (pf-pi) < overlap_minWindowSize:
#print 'Does this ever happen?'
continue
start = pi
end = min([start+bpd,pf])
#print '------------------RAWR:', (pi,pf), nTargWindows, bpd
varsFromPrevOverlap = []
varsCancerFromPrevOverlap = []
vindFromPrev = 0
isLastTime = False
havePrinted100 = False
while True:
# which inserted variants are in this window?
varsInWindow = []
updated = False
for j in xrange(vindFromPrev,len(validVariants)):
vPos = validVariants[j][0]
if vPos > start and vPos < end: # update: changed >= to >, so variant cannot be inserted in first position
varsInWindow.append(tuple([vPos-1]+list(validVariants[j][1:]))) # vcf --> array coords
if vPos >= end-overlap-1 and updated == False:
updated = True
vindFromPrev = j
if vPos >= end:
break
# determine which structural variants will affect our sampling window positions
structuralVars = []
for n in varsInWindow:
bufferNeeded = max([max([abs(len(n[1])-len(alt_allele)),1]) for alt_allele in n[2]]) # change: added abs() so that insertions are also buffered.
structuralVars.append((n[0]-1,bufferNeeded)) # -1 because going from VCF coords to array coords
# adjust end-position of window based on inserted structural mutations
buffer_added = 0
keepGoing = True
while keepGoing:
keepGoing = False
for n in structuralVars:
# adding "overlap" here to prevent SVs from being introduced in overlap regions
# (which can cause problems if random mutations from the previous window land on top of them)
delta = (end-1) - (n[0] + n[1]) - 2 - overlap
if delta < 0:
#print 'DELTA:', delta, 'END:', end, '-->',
buffer_added = -delta
end += buffer_added
####print end
keepGoing = True
break
next_start = end-overlap
next_end = min([next_start+bpd,pf])
if next_end-next_start < bpd:
end = next_end
isLastTime = True
# print progress indicator
#print 'PROCESSING WINDOW:',(start,end), [buffer_added], 'next:', (next_start,next_end), 'isLastTime:', isLastTime
currentProgress += end-start
newPercent = int((currentProgress*100)/float(total_bp_span))
if newPercent > currentPercent:
if newPercent <= 99 or (newPercent == 100 and not havePrinted100):
sys.stdout.write(str(newPercent)+'% ')
sys.stdout.flush()
currentPercent = newPercent
if currentPercent == 100:
havePrinted100 = True
skip_this_window = False
# compute coverage modifiers
coverage_avg = None
coverage_dat = [GC_WINDOW_SIZE,GC_SCALE_VAL,[]]
target_hits = 0
if INPUT_BED == None:
coverage_dat[2] = [1.0]*(end-start)
else:
if refIndex[RI][0] not in inputRegions:
coverage_dat[2] = [OFFTARGET_SCALAR]*(end-start)
else:
for j in xrange(start,end):
if not(bisect.bisect(inputRegions[refIndex[RI][0]],j)%2):
coverage_dat[2].append(1.0)
target_hits += 1
else:
coverage_dat[2].append(OFFTARGET_SCALAR)
# offtarget and we're not interested?
if OFFTARGET_DISCARD and target_hits <= READLEN:
coverage_avg = 0.0
skip_this_window = True
#print len(coverage_dat[2]), sum(coverage_dat[2])
if sum(coverage_dat[2]) < LOW_COV_THRESH:
coverage_avg = 0.0
skip_this_window = True
# check for small window sizes
if (end-start) < overlap_minWindowSize:
skip_this_window = True
if skip_this_window:
# skip window, save cpu time
start = next_start
end = next_end
if isLastTime:
break
if end >= pf:
isLastTime = True
varsFromPrevOverlap = []
continue
# construct sequence data that we will sample reads from
if sequences == None:
sequences = SequenceContainer(start,refSequence[start:end],PLOIDS,overlap,READLEN,[MUT_MODEL]*PLOIDS,MUT_RATE,onlyVCF=ONLY_VCF)
else:
sequences.update(start,refSequence[start:end],PLOIDS,overlap,READLEN,[MUT_MODEL]*PLOIDS,MUT_RATE)
# insert variants
sequences.insert_mutations(varsFromPrevOverlap + varsInWindow)
all_inserted_variants = sequences.random_mutations()
#print all_inserted_variants
# init coverage
if sum(coverage_dat[2]) >= LOW_COV_THRESH:
if PAIRED_END:
coverage_avg = sequences.init_coverage(tuple(coverage_dat),fragDist=FRAGLEN_DISTRIBUTION)
else:
coverage_avg = sequences.init_coverage(tuple(coverage_dat))
# unused cancer stuff
if CANCER:
tumor_sequences = SequenceContainer(start,refSequence[start:end],PLOIDS,overlap,READLEN,[CANCER_MODEL]*PLOIDS,MUT_RATE,coverage_dat)
tumor_sequences.insert_mutations(varsCancerFromPrevOverlap + all_inserted_variants)
all_cancer_variants = tumor_sequences.random_mutations()
# which variants do we need to keep for next time (because of window overlap)?
varsFromPrevOverlap = []
varsCancerFromPrevOverlap = []
for n in all_inserted_variants:
if n[0] >= end-overlap-1:
varsFromPrevOverlap.append(n)
if CANCER:
for n in all_cancer_variants:
if n[0] >= end-overlap-1:
varsCancerFromPrevOverlap.append(n)
# if we're only producing VCF, no need to go through the hassle of generating reads
if ONLY_VCF:
pass
else:
windowSpan = end-start
if PAIRED_END:
if FORCE_COVERAGE:
readsToSample = int((windowSpan*float(COVERAGE))/(2*READLEN))+1
else:
readsToSample = int((windowSpan*float(COVERAGE)*coverage_avg)/(2*READLEN))+1
else:
if FORCE_COVERAGE:
readsToSample = int((windowSpan*float(COVERAGE))/READLEN)+1
else:
readsToSample = int((windowSpan*float(COVERAGE)*coverage_avg)/READLEN)+1
# if coverage is so low such that no reads are to be sampled, skip region
# (i.e., remove buffer of +1 reads we add to every window)
if readsToSample == 1 and sum(coverage_dat[2]) < LOW_COV_THRESH:
readsToSample = 0
# sample reads
ASDF2_TT = time.time()
for i in xrange(readsToSample):
isUnmapped = []
if PAIRED_END:
myFraglen = FRAGLEN_DISTRIBUTION.sample()
myReadData = sequences.sample_read(SE_CLASS,myFraglen)
if myReadData == None: # skip if we failed to find a valid position to sample read
continue
if myReadData[0][0] == None:
isUnmapped.append(True)
else:
isUnmapped.append(False)
myReadData[0][0] += start # adjust mapping position based on window start
if myReadData[1][0] == None:
isUnmapped.append(True)
else:
isUnmapped.append(False)
myReadData[1][0] += start
else:
myReadData = sequences.sample_read(SE_CLASS)
if myReadData == None: # skip if we failed to find a valid position to sample read
continue
if myReadData[0][0] == None: # unmapped read (lives in large insertion)
isUnmapped = [True]
else:
isUnmapped = [False]
myReadData[0][0] += start # adjust mapping position based on window start
# are we discarding offtargets?
outside_boundaries = []
if OFFTARGET_DISCARD and INPUT_BED != None:
outside_boundaries += [bisect.bisect(inputRegions[refIndex[RI][0]],n[0])%2 for n in myReadData]
outside_boundaries += [bisect.bisect(inputRegions[refIndex[RI][0]],n[0]+len(n[2]))%2 for n in myReadData]
if DISCARD_BED != None:
outside_boundaries += [bisect.bisect(discardRegions[refIndex[RI][0]],n[0])%2 for n in myReadData]
outside_boundaries += [bisect.bisect(discardRegions[refIndex[RI][0]],n[0]+len(n[2]))%2 for n in myReadData]
if len(outside_boundaries) and any(outside_boundaries):
continue
if NJOBS > 1:
myReadName = OUT_PREFIX_NAME+'-j'+str(MYJOB)+'-'+refIndex[RI][0]+'-r'+str(readNameCount)
else:
myReadName = OUT_PREFIX_NAME+'-'+refIndex[RI][0]+'-'+str(readNameCount)
readNameCount += len(myReadData)
# if desired, replace all low-quality bases with Ns
if N_MAX_QUAL > -1:
for j in xrange(len(myReadData)):
myReadString = [n for n in myReadData[j][2]]
for k in xrange(len(myReadData[j][3])):
adjusted_qual = ord(myReadData[j][3][k])-SE_CLASS.offQ
if adjusted_qual <= N_MAX_QUAL:
myReadString[k] = 'N'
myReadData[j][2] = ''.join(myReadString)
# flip a coin, are we forward or reverse strand?
isForward = (random.random() < 0.5)
# if read (or read + mate for PE) are unmapped, put them at end of bam file
if all(isUnmapped):
if PAIRED_END:
if isForward:
flag1 = sam_flag(['paired','unmapped','mate_unmapped','first','mate_reverse'])
flag2 = sam_flag(['paired','unmapped','mate_unmapped','second','reverse'])
else:
flag1 = sam_flag(['paired','unmapped','mate_unmapped','second','mate_reverse'])
flag2 = sam_flag(['paired','unmapped','mate_unmapped','first','reverse'])
unmapped_records.append((myReadName+'/1',myReadData[0],flag1))
unmapped_records.append((myReadName+'/2',myReadData[1],flag2))
else:
flag1 = sam_flag(['unmapped'])
unmapped_records.append((myReadName+'/1',myReadData[0],flag1))
myRefIndex = indices_by_refName[refIndex[RI][0]]
#
# write SE output
#
if len(myReadData) == 1:
if NO_FASTQ != True:
if isForward:
OFW.writeFASTQRecord(myReadName,myReadData[0][2],myReadData[0][3])
else:
OFW.writeFASTQRecord(myReadName,RC(myReadData[0][2]),myReadData[0][3][::-1])
if SAVE_BAM:
if isUnmapped[0] == False:
if isForward:
flag1 = 0
OFW.writeBAMRecord(myRefIndex, myReadName, myReadData[0][0], myReadData[0][1], myReadData[0][2], myReadData[0][3], samFlag=flag1)
else:
flag1 = sam_flag(['reverse'])
OFW.writeBAMRecord(myRefIndex, myReadName, myReadData[0][0], myReadData[0][1], myReadData[0][2], myReadData[0][3], samFlag=flag1)
#
# write PE output
#
elif len(myReadData) == 2:
if NO_FASTQ != True:
OFW.writeFASTQRecord(myReadName,myReadData[0][2],myReadData[0][3],read2=myReadData[1][2],qual2=myReadData[1][3],orientation=isForward)
if SAVE_BAM:
if isUnmapped[0] == False and isUnmapped[1] == False:
if isForward:
flag1 = sam_flag(['paired','proper','first','mate_reverse'])
flag2 = sam_flag(['paired','proper','second','reverse'])
else:
flag1 = sam_flag(['paired','proper','second','mate_reverse'])
flag2 = sam_flag(['paired','proper','first','reverse'])
OFW.writeBAMRecord(myRefIndex, myReadName, myReadData[0][0], myReadData[0][1], myReadData[0][2], myReadData[0][3], samFlag=flag1, matePos=myReadData[1][0])
OFW.writeBAMRecord(myRefIndex, myReadName, myReadData[1][0], myReadData[1][1], myReadData[1][2], myReadData[1][3], samFlag=flag2, matePos=myReadData[0][0])
elif isUnmapped[0] == False and isUnmapped[1] == True:
if isForward:
flag1 = sam_flag(['paired','first', 'mate_unmapped', 'mate_reverse'])
flag2 = sam_flag(['paired','second', 'unmapped', 'reverse'])
else:
flag1 = sam_flag(['paired','second', 'mate_unmapped', 'mate_reverse'])
flag2 = sam_flag(['paired','first', 'unmapped', 'reverse'])
OFW.writeBAMRecord(myRefIndex, myReadName, myReadData[0][0], myReadData[0][1], myReadData[0][2], myReadData[0][3], samFlag=flag1, matePos=myReadData[0][0])
OFW.writeBAMRecord(myRefIndex, myReadName, myReadData[0][0], myReadData[1][1], myReadData[1][2], myReadData[1][3], samFlag=flag2, matePos=myReadData[0][0], alnMapQual=0)
elif isUnmapped[0] == True and isUnmapped[1] == False:
if isForward:
flag1 = sam_flag(['paired','first', 'unmapped', 'mate_reverse'])
flag2 = sam_flag(['paired','second', 'mate_unmapped', 'reverse'])
else:
flag1 = sam_flag(['paired','second', 'unmapped', 'mate_reverse'])
flag2 = sam_flag(['paired','first', 'mate_unmapped', 'reverse'])
OFW.writeBAMRecord(myRefIndex, myReadName, myReadData[1][0], myReadData[0][1], myReadData[0][2], myReadData[0][3], samFlag=flag1, matePos=myReadData[1][0], alnMapQual=0)
OFW.writeBAMRecord(myRefIndex, myReadName, myReadData[1][0], myReadData[1][1], myReadData[1][2], myReadData[1][3], samFlag=flag2, matePos=myReadData[1][0])
else:
print '\nError: Unexpected number of reads generated...\n'
exit(1)
#print 'READS:',time.time()-ASDF2_TT
if not isLastTime:
OFW.flushBuffers(bamMax=next_start)
else:
OFW.flushBuffers(bamMax=end+1)
# tally up all the variants that got successfully introduced
for n in all_inserted_variants:
ALL_VARIANTS_OUT[n] = True
# prepare indices of next window
start = next_start
end = next_end
if isLastTime:
break
if end >= pf:
isLastTime = True
if currentPercent != 100 and not havePrinted100:
print '100%'
else:
print ''
if ONLY_VCF:
print 'VCF generation completed in',
else:
print 'Read sampling completed in',
print int(time.time()-tt),'(sec)'
# write all output variants for this reference
if SAVE_VCF:
print 'Writing output VCF...'
for k in sorted(ALL_VARIANTS_OUT.keys()):
currentRef = refIndex[RI][0]
myID = '.'
myQual = '.'
myFilt = 'PASS'
# k[0] + 1 because we're going back to 1-based vcf coords
OFW.writeVCFRecord(currentRef, str(int(k[0])+1), myID, k[1], k[2], myQual, myFilt, k[4])
#break
# write unmapped reads to bam file
if SAVE_BAM and len(unmapped_records):
print 'writing unmapped reads to bam file...'
for umr in unmapped_records:
if PAIRED_END:
OFW.writeBAMRecord(-1, umr[0], 0, umr[1][1], umr[1][2], umr[1][3], samFlag=umr[2], matePos=0, alnMapQual=0)
else:
OFW.writeBAMRecord(-1, umr[0], 0, umr[1][1], umr[1][2], umr[1][3], samFlag=umr[2], alnMapQual=0)
# close output files
OFW.closeFiles()
if CANCER:
OFW_CANCER.closeFiles()
def main():
# index reference
refIndex = indexRef(REFERENCE)
if PAIRED_END:
N_HANDLING = ('random',FRAGMENT_SIZE)
else:
N_HANDLING = ('ignore',READLEN)
indices_by_refName = {refIndex[n][0]:n for n in xrange(len(refIndex))}
# parse input variants, if present
inputVariants = []
if INPUT_VCF != None:
if CANCER:
(sampNames, inputVariants) = parseVCF(INPUT_VCF,tumorNormal=True,ploidy=PLOIDS)
tumorInd = sampNames.index('TUMOR')
normalInd = sampNames.index('NORMAL')
else:
(sampNames, inputVariants) = parseVCF(INPUT_VCF,ploidy=PLOIDS)
for k in sorted(inputVariants.keys()):
inputVariants[k].sort()
# parse input targeted regions, if present
inputRegions = {}
if INPUT_BED != None:
with open(INPUT_BED,'r') as f:
for line in f:
[myChr,pos1,pos2] = line.strip().split('\t')[:3]
if myChr not in inputRegions:
inputRegions[myChr] = [-1]
inputRegions[myChr].extend([int(pos1),int(pos2)])
# parse input mutation rate rescaling regions, if present
mutRateRegions = {}
mutRateValues = {}
if MUT_BED != None:
with open(MUT_BED,'r') as f:
for line in f:
[myChr,pos1,pos2,metaData] = line.strip().split('\t')[:4]
mutStr = re.findall(r"MUT_RATE=.*?(?=;)",metaData+';')
(pos1,pos2) = (int(pos1),int(pos2))
if len(mutStr) and (pos2-pos1) > 1:
# mutRate = #_mutations / length_of_region, let's bound it by a reasonable amount
mutRate = max([0.0,min([float(mutStr[0][9:]),0.3])])
if myChr not in mutRateRegions:
mutRateRegions[myChr] = [-1]
mutRateValues[myChr] = [0.0]
mutRateRegions[myChr].extend([pos1,pos2])
mutRateValues.extend([mutRate*(pos2-pos1)]*2)
# initialize output files (part I)
bamHeader = None
if SAVE_BAM:
bamHeader = [copy.deepcopy(refIndex)]
vcfHeader = None
if SAVE_VCF:
vcfHeader = [REFERENCE]
# If processing jobs in parallel, precompute the independent regions that can be process separately
if NJOBS > 1:
parallelRegionList = getAllRefRegions(REFERENCE,refIndex,N_HANDLING,saveOutput=SAVE_NON_N)
(myRefs, myRegions) = partitionRefRegions(parallelRegionList,refIndex,MYJOB,NJOBS)
if not len(myRegions):
print 'This job id has no regions to process, exiting...'
exit(1)
for i in xrange(len(refIndex)-1,-1,-1): # delete reference not used in our job
if not refIndex[i][0] in myRefs:
del refIndex[i]
# if value of NJOBS is too high, let's change it to the maximum possible, to avoid output filename confusion
corrected_nJobs = min([NJOBS,sum([len(n) for n in parallelRegionList.values()])])
else:
corrected_nJobs = 1
# initialize output files (part II)
if CANCER:
OFW = OutputFileWriter(OUT_PREFIX+'_normal',paired=PAIRED_END,BAM_header=bamHeader,VCF_header=vcfHeader,gzipped=GZIPPED_OUT)
OFW_CANCER = OutputFileWriter(OUT_PREFIX+'_tumor',paired=PAIRED_END,BAM_header=bamHeader,VCF_header=vcfHeader,gzipped=GZIPPED_OUT,jobTuple=(MYJOB,corrected_nJobs))
else:
OFW = OutputFileWriter(OUT_PREFIX,paired=PAIRED_END,BAM_header=bamHeader,VCF_header=vcfHeader,gzipped=GZIPPED_OUT,jobTuple=(MYJOB,corrected_nJobs))
OUT_PREFIX_NAME = OUT_PREFIX.split('/')[-1]
"""************************************************
**** LET'S GET THIS PARTY STARTED...
************************************************"""
readNameCount = 1 # keep track of the number of reads we've sampled, for read-names
for RI in xrange(len(refIndex)):
# read in reference sequence and notate blocks of Ns
(refSequence,N_regions) = readRef(REFERENCE,refIndex[RI],N_HANDLING)
# if we're processing jobs in parallel only take the regions relevant for the current job
if NJOBS > 1:
for i in xrange(len(N_regions['non_N'])-1,-1,-1):
if not (refIndex[RI][0],N_regions['non_N'][i][0],N_regions['non_N'][i][1]) in myRegions:
del N_regions['non_N'][i]
# count total bp we'll be spanning so we can get an idea of how far along we are (for printing progress indicators)
total_bp_span = sum([n[1]-n[0] for n in N_regions['non_N']])
currentProgress = 0
currentPercent = 0
# prune invalid input variants, e.g variants that:
# - try to delete or alter any N characters
# - don't match the reference base at their specified position
# - any alt allele contains anything other than allowed characters
validVariants = []
nSkipped = [0,0,0]
if refIndex[RI][0] in inputVariants:
for n in inputVariants[refIndex[RI][0]]:
span = (n[0],n[0]+len(n[1]))
rseq = str(refSequence[span[0]-1:span[1]-1]) # -1 because going from VCF coords to array coords
anyBadChr = any((nn not in ALLOWED_NUCL) for nn in [item for sublist in n[2] for item in sublist])
if rseq != n[1]:
nSkipped[0] += 1
continue
elif 'N' in rseq:
nSkipped[1] += 1
continue
elif anyBadChr:
nSkipped[2] += 1
continue
#if bisect.bisect(N_regions['big'],span[0])%2 or bisect.bisect(N_regions['big'],span[1])%2:
# continue
validVariants.append(n)
print 'found',len(validVariants),'valid variants for '+refIndex[RI][0]+' in input VCF...'
if any(nSkipped):
print sum(nSkipped),'variants skipped...'
print ' - ['+str(nSkipped[0])+'] ref allele does not match reference'
print ' - ['+str(nSkipped[1])+'] attempting to insert into N-region'
print ' - ['+str(nSkipped[2])+'] alt allele contains non-ACGT characters'
# add large random structural variants
#
# TBD!!!
# determine which structural variants will affect our sampling window positions
structuralVars = []
for n in validVariants:
bufferNeeded = max([max([len(n[1])-len(alt_allele),1]) for alt_allele in n[2]])
structuralVars.append((n[0]-1,bufferNeeded)) # -1 because going from VCF coords to array coords
# determine sampling windows based on read length, large N regions, and structural mutations.
# in order to obtain uniform coverage, windows should overlap by:
# - READLEN, if single-end reads
# - FRAGMENT_SIZE (mean), if paired-end reads
# ploidy is fixed per large sampling window,
# coverage distributions due to GC% and targeted regions are specified within these windows
samplingWindows = []
ALL_VARIANTS_OUT = {}
sequences = None
if PAIRED_END:
targSize = WINDOW_TARGET_SCALE*FRAGMENT_SIZE
overlap = FRAGMENT_SIZE
else:
targSize = WINDOW_TARGET_SCALE*READLEN
overlap = READLEN
print '--------------------------------'
print 'sampling reads...'
for i in xrange(len(N_regions['non_N'])):
(pi,pf) = N_regions['non_N'][i]
nTargWindows = max([1,(pf-pi)/targSize])
bpd = int((pf-pi)/float(nTargWindows))
bpd += GC_WINDOW_SIZE - bpd%GC_WINDOW_SIZE
#print len(refSequence), (pi,pf), nTargWindows
#print structuralVars
# if for some reason our region is too small to process, skip it! (sorry)
if nTargWindows == 1 and (pf-pi) < overlap-1:
#print 'Does this ever happen?'
continue
start = pi
end = min([start+bpd,pf])
#print '------------------RAWR:', (pi,pf), bpd
currentVariantInd = 0
varsFromPrevOverlap = []
varsCancerFromPrevOverlap = []
vindFromPrev = 0
isLastTime = False
while True:
####print (start,end)
# adjust end-position of window based on inserted structural mutations
relevantVars = []
if len(structuralVars) and currentVariantInd < len(structuralVars):
prevVarInd = currentVariantInd
while structuralVars[currentVariantInd][0] <= end:
delta = (end-1) - (structuralVars[currentVariantInd][0] + structuralVars[currentVariantInd][1])
if delta <= 0:
####print 'DELTA:', delta
end -= (delta-1)
currentVariantInd += 1
if currentVariantInd == len(structuralVars):
break
relevantVars = structuralVars[prevVarInd:currentVariantInd]
next_start = end-overlap
next_end = min([next_start+bpd,pf])
if next_end-next_start < bpd:
end = next_end
isLastTime = True
# print progress indicator
#print 'PROCESSING WINDOW:',(start,end)
currentProgress += end-start
newPercent = int((currentProgress*100)/float(total_bp_span))
if newPercent > currentPercent:
sys.stdout.write(str(newPercent)+'% ')
sys.stdout.flush()
currentPercent = newPercent
# which inserted variants are in this window?
varsInWindow = []
updated = False
for j in xrange(vindFromPrev,len(validVariants)):
vPos = validVariants[j][0]
if vPos >= start and vPos < end:
varsInWindow.append(tuple([vPos-1]+list(validVariants[j][1:]))) # vcf --> array coords
if vPos >= end-overlap-1 and updated == False:
updated = True
vindFromPrev = j
if vPos >= end:
break
# if computing only VCF, we can skip this...
if ONLY_VCF:
coverage_dat = None
coverage_avg = None
else:
# pre-compute gc-bias and targeted sequencing coverage modifiers
nSubWindows = (end-start)/GC_WINDOW_SIZE
coverage_dat = (GC_WINDOW_SIZE,[])
for j in xrange(nSubWindows):
rInd = start + j*GC_WINDOW_SIZE
if INPUT_BED == None: tCov = True
else: tCov = not(bisect.bisect(inputRegions[myChr],rInd)%2) or not(bisect.bisect(inputRegions[myChr],rInd+GC_WINDOW_SIZE)%2)
if tCov: tScl = 1.0
else: tScl = OFFTARGET_SCALAR
gc_v = refSequence[rInd:rInd+GC_WINDOW_SIZE].count('G') + refSequence[rInd:rInd+GC_WINDOW_SIZE].count('C')
gScl = GC_SCALE_VAL[gc_v]
coverage_dat[1].append(1.0*tScl*gScl)
coverage_avg = np.mean(coverage_dat[1])
# pre-compute mutation rate tracks
# PROVIDED MUTATION RATES OVERRIDE AVERAGE VALUE
# construct sequence data that we will sample reads from
if sequences == None:
sequences = SequenceContainer(start,refSequence[start:end],PLOIDS,overlap,READLEN,[MUT_MODEL]*PLOIDS,MUT_RATE,coverage_dat,onlyVCF=ONLY_VCF)
else:
sequences.update(start,refSequence[start:end],PLOIDS,overlap,READLEN,[MUT_MODEL]*PLOIDS,MUT_RATE,coverage_dat)
# adjust position of all inserted variants to match current window offset
#variants_to_insert = []
#for n in varsFromPrevOverlap:
# ln = [n[0]-start] + list(n[1:])
# variants_to_insert.append(tuple(ln))
#for n in varsInWindow:
# ln = [n[0]-start] + list(n[1:])
# variants_to_insert.append(tuple(ln))
#sequences.insert_mutations(variants_to_insert)
sequences.insert_mutations(varsFromPrevOverlap + varsInWindow)
all_inserted_variants = sequences.random_mutations()
#print all_inserted_variants
if CANCER:
tumor_sequences = SequenceContainer(start,refSequence[start:end],PLOIDS,overlap,READLEN,[CANCER_MODEL]*PLOIDS,MUT_RATE,coverage_dat)
tumor_sequences.insert_mutations(varsCancerFromPrevOverlap + all_inserted_variants)
all_cancer_variants = tumor_sequences.random_mutations()
# which variants do we need to keep for next time (because of window overlap)?
varsFromPrevOverlap = []
varsCancerFromPrevOverlap = []
for n in all_inserted_variants:
if n[0] >= end-overlap-1:
varsFromPrevOverlap.append(n)
if CANCER:
for n in all_cancer_variants:
if n[0] >= end-overlap-1:
varsCancerFromPrevOverlap.append(n)
# if we're only producing VCF, no need to go through the hassle of generating reads
if ONLY_VCF:
pass
else:
# for each sampling window, construct sub-windows with coverage information
covWindows = [COVERAGE for n in xrange((end-start)/SMALL_WINDOW)]
if (end-start)%SMALL_WINDOW:
covWindows.append(COVERAGE)
meanCov = sum(covWindows)/float(len(covWindows))
if PAIRED_END:
readsToSample = int(((end-start)*meanCov*coverage_avg)/(2*READLEN))+1
else:
readsToSample = int(((end-start)*meanCov*coverage_avg)/(READLEN))+1
# sample reads from altered reference
for i in xrange(readsToSample):
if PAIRED_END:
myFraglen = FRAGLEN_DISTRIBUTION.sample()
myReadData = sequences.sample_read(SE_CLASS,myFraglen)
myReadData[0][0] += start # adjust mapping position based on window start
myReadData[1][0] += start
else:
myReadData = sequences.sample_read(SE_CLASS)
myReadData[0][0] += start # adjust mapping position based on window start
if NJOBS > 1:
myReadName = OUT_PREFIX_NAME+'-j'+str(MYJOB)+'-'+refIndex[RI][0]+'-r'+str(readNameCount)
else:
myReadName = OUT_PREFIX_NAME+'-'+refIndex[RI][0]+'-'+str(readNameCount)
readNameCount += len(myReadData)
# if desired, replace all low-quality bases with Ns
if N_MAX_QUAL > -1:
for j in xrange(len(myReadData)):
myReadString = [n for n in myReadData[j][2]]
for k in xrange(len(myReadData[j][3])):
adjusted_qual = ord(myReadData[j][3][k])-SE_CLASS.offQ
if adjusted_qual <= N_MAX_QUAL:
myReadString[k] = 'N'
myReadData[j][2] = ''.join(myReadString)
# write read data out to FASTQ and BAM files, bypass FASTQ if option specified
myRefIndex = indices_by_refName[refIndex[RI][0]]
if len(myReadData) == 1:
if NO_FASTQ != True:
OFW.writeFASTQRecord(myReadName,myReadData[0][2],myReadData[0][3])
if SAVE_BAM:
OFW.writeBAMRecord(myRefIndex, myReadName+'/1', myReadData[0][0], myReadData[0][1], myReadData[0][2], myReadData[0][3], samFlag=0)
elif len(myReadData) == 2:
if NO_FASTQ != True:
OFW.writeFASTQRecord(myReadName,myReadData[0][2],myReadData[0][3],read2=myReadData[1][2],qual2=myReadData[1][3])
if SAVE_BAM:
OFW.writeBAMRecord(myRefIndex, myReadName+'/1', myReadData[0][0], myReadData[0][1], myReadData[0][2], myReadData[0][3], samFlag=99, matePos=myReadData[1][0])
OFW.writeBAMRecord(myRefIndex, myReadName+'/2', myReadData[1][0], myReadData[1][1], myReadData[1][2], myReadData[1][3], samFlag=147, matePos=myReadData[0][0])
else:
print '\nError: Unexpected number of reads generated...\n'
exit(1)
# tally up all the variants that got successfully introduced
for n in all_inserted_variants:
ALL_VARIANTS_OUT[n] = True
# prepare indices of next window
start = next_start
end = next_end
if isLastTime:
break
if end >= pf:
isLastTime = True
if currentPercent != 100:
print '100%'
else:
print ''
# write all output variants for this reference
if SAVE_VCF:
for k in sorted(ALL_VARIANTS_OUT.keys()):
currentRef = refIndex[RI][0]
myID = '.'
myQual = '.'
myFilt = 'PASS'
# k[0] + 1 because we're going back to 1-based vcf coords
OFW.writeVCFRecord(currentRef, str(int(k[0])+1), myID, k[1], k[2], myQual, myFilt, k[4])
#break
# close output files
OFW.closeFiles()
if CANCER:
OFW_CANCER.closeFiles()
