with open(args.regionsFile, "rt") as intFile:
intervals = genomics.Intervals(
tuples=[line.split() for line in intFile])
nIntervals = len(intervals.chroms)
sys.stderr.write("Recording SFS for {} intervals\n".format(nIntervals))
else:
intervals = None
nIntervals = 1
'###############################################################################################################'
#parse pop and individual data, if necessary
if args.inputType == "genotypes":
genoFileReader = genomics.GenoFileReader(
inputFile,
headerLine=args.header,
scafCol=args.scafCol,
posCol=args.posCol,
firstSampleCol=args.firstSampleCol)
popDict = {}
popNames = []
if args.pop or args.FSpops:
if args.pop:
for pop in args.pop:
popNames.append(pop[0])
popDict[pop[0]] = [] if len(pop) == 1 else pop[1].split(",")
if args.FSpops:
for pop in [p for pops in args.FSpops for p in pops]:
if pop not in popNames:
popNames.append(pop)
popDict[pop] = []
except:
sys.stderr.write(
"WARNING: Could not parse fai file, vcf header will not contain contig entries...\n"
)
scafs_lengths = None
with gzip.open(args.reference,
"r") if args.reference.endswith(".gz") else open(
args.reference, "r") as ref:
refDict = dict(zip(*genomics.parseFasta(ref.read())))
else:
refDict = None
#########################################################################################
genoFileReader = genomics.GenoFileReader(genoFile)
allNames = genoFileReader.names
if not args.samples: namesToUse = allNames
else: namesToUse = args.samples.split(",")
outFile.write("##fileformat=VCFv4.2\n")
if refDict:
outFile.write("##reference=file:{}\n".format(
args.reference.split("/")[-1]))
if scafs_lengths:
for x in range(len(scafs_lengths)):
outFile.write("##contig=<ID={},length={}>\n".format(
cdsEnds = [geneData[scaffold][mRNA]["cdsEnds"][x] for x in order]
#for each exon we exytract the sequence for all individuals
#and build a dictionary of position and genotype for each individual
for i in range(geneData[scaffold][mRNA]["exons"]):
#extract the sequence data for this exon
genoStream = tabixStream(args.genoFile,
chrom=scaffold,
start=cdsStarts[i],
end=cdsEnds[i],
header=True)
reader = genomics.GenoFileReader(genoStream,
splitPhased=args.split,
ploidy=args.ploidy)
#if this is the first exon, initialise dictionary of genotype for each pos for each seqName
if i == 0:
nSeqs = len(reader.names)
empty = ["N"] * nSeqs
siteGTdict = defaultdict(lambda: empty)
#now update if there is data for this window
for siteData in reader.siteBySite(
asDict=True if args.samples else False):
GTs = [siteData["GTs"][name] for name in args.samples
] if args.samples else siteData["GTs"]
siteGTdict[siteData["position"]] = [
genomics.complement(gt) for gt in GTs
