def test_non_coding_negative(self):
tr = Transcript()
tr.chrom = "Chr1"
tr.start = 101
tr.end = 2000
tr.strand = "-"
tr.add_exons([(101, 300), (1701, 2000)])
tr.id = "test1"
tr.parent = "gene1"
tr.finalize()
gff = tr.format("gff", with_introns=True)
self.maxDiff = None
res = """Chr1\tMikado\ttranscript\t101\t2000\t.\t-\t.\tID=test1;Parent=gene1
Chr1\tMikado\texon\t101\t300\t.\t-\t.\tID=test1.exon1;Parent=test1
Chr1\tMikado\tintron\t301\t1700\t.\t-\t.\tID=test1.intron1;Parent=test1
Chr1\tMikado\texon\t1701\t2000\t.\t-\t.\tID=test1.exon2;Parent=test1"""
self.assertEqual(gff, res, "++++\n\n" + "\n+++\n".join([gff, res]))
gtf = tr.format("gtf", with_introns=True)
res = """Chr1\tMikado\ttranscript\t101\t2000\t.\t-\t.\tgene_id "gene1"; transcript_id "test1";
Chr1\tMikado\texon\t101\t300\t.\t-\t.\tgene_id "gene1"; transcript_id "test1";
Chr1\tMikado\tintron\t301\t1700\t.\t-\t.\tgene_id "gene1"; transcript_id "test1";
Chr1\tMikado\texon\t1701\t2000\t.\t-\t.\tgene_id "gene1"; transcript_id "test1";"""
self.assertEqual(gtf, res, "++++\n\n" + "\n+++\n".join([gtf, res]))
def test_coding_negative(self):
tr = Transcript()
tr.chrom = "Chr1"
tr.start = 101
tr.end = 2000
tr.strand = "-"
tr.add_exons([(101, 300), (1701, 2000)])
tr.add_exons([(101, 300), (1701, 2000)], features="CDS")
tr.id = "test1"
tr.parent = "gene1"
# Phase 0, 0 because the first CDS exon is 300bp
gff = tr.format("gff", with_introns=True)
self.maxDiff = None
res = """Chr1\tMikado\tmRNA\t101\t2000\t.\t-\t.\tID=test1;Parent=gene1;Name=test1
Chr1\tMikado\tCDS\t101\t300\t.\t-\t0\tID=test1.CDS1;Parent=test1
Chr1\tMikado\texon\t101\t300\t.\t-\t.\tID=test1.exon1;Parent=test1
Chr1\tMikado\tintron\t301\t1700\t.\t-\t.\tID=test1.intron1;Parent=test1
Chr1\tMikado\tCDS\t1701\t2000\t.\t-\t0\tID=test1.CDS2;Parent=test1
Chr1\tMikado\texon\t1701\t2000\t.\t-\t.\tID=test1.exon2;Parent=test1"""
self.assertEqual(
gff, res, "++++\n\n" + "\n+++\n".join(
[gff, res, ",\t".join([str(_) for _ in tr.internal_orfs])]))
gtf = tr.format("gtf", with_introns=True)
res = """Chr1\tMikado\tmRNA\t101\t2000\t.\t-\t.\tgene_id "gene1"; transcript_id "test1"; Name "test1";
Chr1\tMikado\tCDS\t101\t300\t.\t-\t0\tgene_id "gene1"; transcript_id "test1";
Chr1\tMikado\texon\t101\t300\t.\t-\t.\tgene_id "gene1"; transcript_id "test1";
Chr1\tMikado\tintron\t301\t1700\t.\t-\t.\tgene_id "gene1"; transcript_id "test1";
Chr1\tMikado\tCDS\t1701\t2000\t.\t-\t0\tgene_id "gene1"; transcript_id "test1";
Chr1\tMikado\texon\t1701\t2000\t.\t-\t.\tgene_id "gene1"; transcript_id "test1";"""
self.assertEqual(gtf, res, "++++\n\n" + "\n+++\n".join([gtf, res]))
def test_coding_positive(self):
tr = Transcript()
tr.chrom = "Chr1"
tr.start = 101
tr.end = 2000
tr.strand = "+"
tr.add_exons([(101, 300),
(1701, 2000)])
tr.add_exons([(101, 300),
(1701, 2000)], features="CDS")
tr.id = "test1"
tr.parent = "gene1"
gff = tr.format("gff", with_introns=True)
self.maxDiff = None
res = """Chr1\tMikado\tmRNA\t101\t2000\t.\t+\t.\tID=test1;Parent=gene1;Name=test1
Chr1\tMikado\tCDS\t101\t300\t.\t+\t0\tID=test1.CDS1;Parent=test1
Chr1\tMikado\texon\t101\t300\t.\t+\t.\tID=test1.exon1;Parent=test1
Chr1\tMikado\tintron\t301\t1700\t.\t+\t.\tID=test1.intron1;Parent=test1
Chr1\tMikado\tCDS\t1701\t2000\t.\t+\t1\tID=test1.CDS2;Parent=test1
Chr1\tMikado\texon\t1701\t2000\t.\t+\t.\tID=test1.exon2;Parent=test1"""
self.assertEqual(gff,
res,
"++++\n\n" + "\n+++\n".join([gff, res]))
gtf = tr.format("gtf", with_introns=True)
res = """Chr1\tMikado\tmRNA\t101\t2000\t.\t+\t.\tgene_id "gene1"; transcript_id "test1"; Name "test1";
Chr1\tMikado\tCDS\t101\t300\t.\t+\t0\tgene_id "gene1"; transcript_id "test1";
Chr1\tMikado\texon\t101\t300\t.\t+\t.\tgene_id "gene1"; transcript_id "test1";
Chr1\tMikado\tintron\t301\t1700\t.\t+\t.\tgene_id "gene1"; transcript_id "test1";
Chr1\tMikado\tCDS\t1701\t2000\t.\t+\t2\tgene_id "gene1"; transcript_id "test1";
Chr1\tMikado\texon\t1701\t2000\t.\t+\t.\tgene_id "gene1"; transcript_id "test1";"""
self.assertEqual(gtf, res,
"++++\n\n" + "\n+++\n".join([gtf, res]))
def test_non_coding_negative(self):
tr = Transcript()
tr.chrom = "Chr1"
tr.start = 101
tr.end = 2000
tr.strand = "-"
tr.add_exons([(101, 300),
(1701, 2000)])
tr.id = "test1"
tr.parent = "gene1"
tr.finalize()
gff = tr.format("gff", with_introns=True)
self.maxDiff = None
res = """Chr1\tMikado\ttranscript\t101\t2000\t.\t-\t.\tID=test1;Parent=gene1
Chr1\tMikado\texon\t101\t300\t.\t-\t.\tID=test1.exon1;Parent=test1
Chr1\tMikado\tintron\t301\t1700\t.\t-\t.\tID=test1.intron1;Parent=test1
Chr1\tMikado\texon\t1701\t2000\t.\t-\t.\tID=test1.exon2;Parent=test1"""
self.assertEqual(gff,
res,
"++++\n\n"+"\n+++\n".join([gff, res]))
gtf = tr.format("gtf", with_introns=True)
res = """Chr1\tMikado\ttranscript\t101\t2000\t.\t-\t.\tgene_id "gene1"; transcript_id "test1";
Chr1\tMikado\texon\t101\t300\t.\t-\t.\tgene_id "gene1"; transcript_id "test1";
Chr1\tMikado\tintron\t301\t1700\t.\t-\t.\tgene_id "gene1"; transcript_id "test1";
Chr1\tMikado\texon\t1701\t2000\t.\t-\t.\tgene_id "gene1"; transcript_id "test1";"""
self.assertEqual(gtf, res,
"++++\n\n" + "\n+++\n".join([gtf, res]))
def test_caseNegative(self):
tr = Transcript()
tr.chrom, tr.start, tr.end, tr.strand = "Chr1", 101, 3000, "-"
tr.id = "test1"
tr.add_exons([(101, 300),
(401, 600),
(801, 1200),
(2501, 3000)
])
tr.add_exons([(421, 600), # 180
(801, 1200), # 400
(2501, 2700) # 200 = 780 % 3 == 0
], features="CDS")
with self.assertLogs("null", "DEBUG") as _:
tr.finalize()
self.assertTrue(tr.is_coding)
b12 = tr.as_bed12()
self.assertEqual(b12.thick_start, tr.combined_cds_end)
self.assertEqual(b12.thick_end, tr.combined_cds_start)
self.assertEqual(len(b12.block_sizes), tr.exon_num)
self.assertEqual(b12.block_sizes,
[200, 200, 400, 500],
b12.block_sizes)
self.assertEqual(b12.strand, "-")
self.assertEqual(b12.block_starts,
[0, 300, 700, 2400],
b12.block_starts)
self.assertEqual(tr.format("bed12"), str(b12))
self.assertEqual(str(b12),
"\t".join([str(_) for _ in
["Chr1", 100, 3000, tr.id, 0, tr.strand,
b12.thick_start - 1, b12.thick_end,
0, 4,
",".join([str(__) for __ in [200, 200, 400, 500]]),
",".join([str(___) for ___ in [0, 300, 700, 2400]])]]
))
def main():
parser = argparse.ArgumentParser(__doc__)
parser.add_argument("-mi",
"--max-intron",
default=10000,
dest="max_intron",
type=int,
help="Maximum intron length for UTR introns.")
parser.add_argument("gff", type=parser_factory)
parser.add_argument("out",
default=sys.stdout,
type=argparse.FileType("wt"),
nargs="?")
args = parser.parse_args()
if args.max_intron < 0:
raise ValueError("Max intron length <0 specified! {0}".format(
args.max_intron))
ref_gff = isinstance(args.gff, GFF3)
if ref_gff:
form = "gff3"
else:
form = "gtf"
current = None
current_transcript = None
last_header = []
for record in args.gff:
if record.header is True:
# print(record, file=sys.stderr)
if current is not None:
current = remove_introns(current, args)
print(current.format(form), file=args.out)
print(*last_header, sep="\n", file=args.out, end='')
current = None
current_transcript = None
print(*last_header, sep="\n", end="")
last_header = [record]
continue
if record.feature not in ("gene", "mRNA", "CDS", "exon"):
continue
if record.is_gene is True and ref_gff:
print(record, file=sys.stderr)
last_header = []
if current is not None:
# current = remove_introns(current, args)
print(current.format(form), file=args.out)
print(*last_header, sep="\n", file=args.out, end='')
current = None
current_transcript = None
if record.is_transcript:
if ref_gff is False:
if current_transcript is not None:
# current_transcript = remove_introns_from_transcr(current_transcript,
# args)
assert current_transcript.combined_cds_length > 0
print(current_transcript, file=args.out)
print(*last_header, sep="\n", file=args.out)
last_header = []
elif ref_gff is True:
if current_transcript is not None:
if current is None:
current = Gene(current_transcript)
current.add(current_transcript)
else:
assert current_transcript.parent[0] != current.id
current.add(current_transcript)
# if current.id == current_transcript.parent[0]:
# else:
# current = remove_introns(current, args)
# print(current.format(form), file=args.out)
# print("###", file=args.out)
# current = None
# elif current_transcript is not None:
# current = Gene(current_transcript)
current_transcript = Transcript(record)
elif record.is_exon:
if record.feature not in ("CDS", "exon"):
continue
current_transcript.add_exon(record)
else:
continue
continue
if ref_gff and current is not None:
print(*last_header, sep="\n", file=args.out)
last_header = []
current = remove_introns(current, args)
print(current.format(form), file=args.out)
elif not ref_gff and current_transcript is not None:
current_transcript = remove_introns_from_transcr(
current_transcript, args)
print(current_transcript.format(form), file=args.out)
print(*last_header, sep="\n", file=args.out, end='')
def main():
parser = argparse.ArgumentParser(__doc__)
parser.add_argument("-mi", "--max-intron", default=10000, dest="max_intron",
type=int, help="Maximum intron length for UTR introns.")
parser.add_argument("gff", type=to_gff)
parser.add_argument("out", default=sys.stdout, type=argparse.FileType("wt"), nargs="?")
args = parser.parse_args()
if args.max_intron < 0:
raise ValueError("Max intron length <0 specified! {0}".format(args.max_intron))
ref_gff = isinstance(args.gff, GFF3)
if ref_gff:
form = "gff3"
else:
form = "gtf"
current = None
current_transcript = None
last_header = []
for record in args.gff:
if record.header is True:
# print(record, file=sys.stderr)
if current is not None:
current = remove_introns(current, args)
print(current.format(form), file=args.out)
print(*last_header, sep="\n", file=args.out, end='')
current = None
current_transcript = None
print(*last_header, sep="\n", end="")
last_header = [record]
continue
if record.feature not in ("gene", "mRNA", "CDS", "exon"):
continue
if record.is_gene is True and ref_gff:
print(record, file=sys.stderr)
last_header = []
if current is not None:
# current = remove_introns(current, args)
print(current.format(form), file=args.out)
print(*last_header, sep="\n", file=args.out, end='')
current = None
current_transcript = None
if record.is_transcript:
if ref_gff is False:
if current_transcript is not None:
# current_transcript = remove_introns_from_transcr(current_transcript,
# args)
assert current_transcript.combined_cds_length > 0
print(current_transcript, file=args.out)
print(*last_header, sep="\n", file=args.out)
last_header = []
elif ref_gff is True:
if current_transcript is not None:
if current is None:
current = Gene(current_transcript)
current.add(current_transcript)
else:
assert current_transcript.parent[0] != current.id
current.add(current_transcript)
# if current.id == current_transcript.parent[0]:
# else:
# current = remove_introns(current, args)
# print(current.format(form), file=args.out)
# print("###", file=args.out)
# current = None
# elif current_transcript is not None:
# current = Gene(current_transcript)
current_transcript = Transcript(record)
elif record.is_exon:
if record.feature not in ("CDS", "exon"):
continue
current_transcript.add_exon(record)
else:
continue
continue
if ref_gff and current is not None:
print(*last_header, sep="\n", file=args.out)
last_header = []
current = remove_introns(current, args)
print(current.format(form), file=args.out)
elif not ref_gff and current_transcript is not None:
current_transcript = remove_introns_from_transcr(current_transcript,
args)
print(current_transcript.format(form), file=args.out)
print(*last_header, sep="\n", file=args.out, end='')