parser.add_argument("--ploidy",
help="Ploidy for splitting phased sequences",
action="store",
type=int,
nargs="+",
default=2)
parser.set_defaults(split=True)
args = parser.parse_args()
with gzip.open(args.gff, "rt") if args.gff.endswith(".gz") else open(
args.gff, "rt") as gff:
gffLines = gff.readlines()
sys.stderr.write("Parsing gene data from gff\n")
geneData = genomics.parseGenes(gffLines, targets=args.targets)
if not args.outFile: outFile = sys.stdout
else:
outFile = gzip.open(args.outFile,
"wt") if args.outFile.endswith(".gz") else open(
args.outFile, "wt")
###################################################
#extract each scaffold from the geno file, and the genes for each scaffold and write them out
for scaffold in geneData.keys():
mRNAs = geneData[scaffold].keys()
sys.stderr.write("Extracting " + str(len(mRNAs)) +
" gene sequences from " + scaffold + "\n")
dest='split',
action='store_true')
parser.add_argument('--no-split',
help="Do not split sequences",
dest='split',
action='store_false')
parser.set_defaults(split=True)
args = parser.parse_args()
#args = parser.parse_args(["--gff", "/scratch/shm45/Hmel2/Hmel2.cortex.gff", "-g", "/zoo/disk1/shm45/vcf/rosina/ros10.Hmel2.bwa.default.HC.DP8.Hmel215006.geno.gz"])
with gzip.open(args.gff, "r") if args.gff.endswith(".gz") else open(
args.gff, "r") as gff:
gffLines = gff.readlines()
geneData = genomics.parseGenes(gffLines)
if not args.outFile: outFile = sys.stdout
else:
outFile = gzip.open(args.outFile,
"w") if args.outFile.endswith(".gz") else open(
args.outFile, "w")
###################################################
#extract each scaffold from the geno file, and the genes for each scaffold and write them out
for scaffold in geneData.keys():
mRNAs = geneData[scaffold].keys()
sys.stderr.write("Extracting " + str(len(mRNAs)) +
" gene sequences from " + scaffold + "\n")
parser.add_argument(
"--ignoreConflicts",
help=
"Don't fail if two annotations give conflicting information about the same site",
action='store_true')
args = parser.parse_args()
################################################################################
#get gene data
sys.stderr.write("Parsing annotation\n")
with gzip.open(args.annotation,
"rt") if args.annotation.endswith(".gz") else open(
args.annotation, "rt") as ann:
geneData = genomics.parseGenes(ann.readlines(), fmt=args.format)
#get scaffold names
sys.stderr.write("Loading reference genome\n")
with gzip.open(args.ref, "rt") if args.ref.endswith(".gz") else open(
args.ref, "rt") as ref:
scaffolds, _sequences_ = genomics.parseFasta(ref.read(),
makeUppercase=True)
sequences = {}
for i, scaffold in enumerate(scaffolds):
sequences[scaffold] = _sequences_[i]
#open output
if not args.outFile: outFile = sys.stdout
else:
outFile = gzip.open(args.outFile,