def test_monoexonic(self):
exon = self.gff_lines[1]
transcript_line = self.gff_lines[0]
transcript_line.end = exon.end
model = Transcript(transcript_line)
model.add_exon(exon)
model.finalize()
fasta = self.fasta[model.chrom][model.start - 1:model.end]
tcheck = TranscriptChecker(model.copy(), fasta, strand_specific=False)
tcheck.check_strand()
self.assertIsNone(tcheck.strand)
tcheck = TranscriptChecker(model.copy(), fasta, strand_specific=True)
tcheck.check_strand()
self.assertEqual(tcheck.strand, "+")
neg = model.copy()
neg.strand = "-"
tcheck = TranscriptChecker(neg.copy(), fasta, strand_specific=False)
tcheck.check_strand()
self.assertIsNone(tcheck.strand)
tcheck = TranscriptChecker(neg.copy(), fasta, strand_specific=True)
tcheck.check_strand()
self.assertEqual(tcheck.strand, "-")
def test_monoexonic(self):
exon = self.gff_lines[1]
transcript_line = self.gff_lines[0]
transcript_line.end = exon.end
model = Transcript(transcript_line)
model.add_exon(exon)
model.finalize()
fasta = self.fasta[model.chrom][model.start - 1: model.end]
tcheck = TranscriptChecker(model.copy(), fasta, strand_specific=False)
tcheck.check_strand()
self.assertIsNone(tcheck.strand)
tcheck = TranscriptChecker(model.copy(), fasta, strand_specific=True)
tcheck.check_strand()
self.assertEqual(tcheck.strand, "+")
neg = model.copy()
neg.strand = "-"
tcheck = TranscriptChecker(neg.copy(), fasta, strand_specific=False)
tcheck.check_strand()
self.assertIsNone(tcheck.strand)
tcheck = TranscriptChecker(neg.copy(), fasta, strand_specific=True)
tcheck.check_strand()
self.assertEqual(tcheck.strand, "-")
def test_negative(self):
gtf_lines = """Chr5 Cufflinks transcript 26575364 26578163 1000 - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";exon_number "1";FPKM "2.9700103727";conf_hi "3.260618";frac "0.732092";cov "81.895309";conf_lo "2.679403";
Chr5 Cufflinks exon 26575364 26575410 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26575495 26575620 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26575711 26575797 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26575885 26575944 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26576035 26576134 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26576261 26577069 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26577163 26577288 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26577378 26577449 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26577856 26578163 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";"""
gtf_lines = [GtfLine(line) for line in gtf_lines.split("\n")]
self.assertEqual(len([_ for _ in gtf_lines if _.header]), 0)
transcript = Transcript(gtf_lines[0])
transcript.add_exons(gtf_lines[1:])
transcript.finalize()
fasta_seq = self.fasta[transcript.chrom][transcript.start -
1:transcript.end]
tr_neg = transcript.copy()
tchecker = TranscriptChecker(tr_neg, fasta_seq, strand_specific=False)
self.assertEqual(tchecker.strand, "-")
self.assertEqual(tchecker.fasta_seq, fasta_seq)
tchecker.check_strand()
self.assertEqual(tchecker.strand, "-")
tr_neg = transcript.copy()
tr_neg.strand = "+"
for ss in (False, True):
with self.subTest(ss=ss):
tchecker = TranscriptChecker(tr_neg.copy(),
fasta_seq,
strand_specific=ss)
tchecker.check_strand()
if ss:
self.assertEqual(tchecker.strand, "+")
self.assertTrue(tchecker.suspicious_splicing)
else:
self.assertEqual(tchecker.strand, "-")
def test_negative(self):
gtf_lines = """Chr5 Cufflinks transcript 26575364 26578163 1000 - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";exon_number "1";FPKM "2.9700103727";conf_hi "3.260618";frac "0.732092";cov "81.895309";conf_lo "2.679403";
Chr5 Cufflinks exon 26575364 26575410 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26575495 26575620 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26575711 26575797 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26575885 26575944 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26576035 26576134 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26576261 26577069 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26577163 26577288 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26577378 26577449 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";
Chr5 Cufflinks exon 26577856 26578163 . - . gene_id "cufflinks_star_at.23553";transcript_id "cufflinks_star_at.23553.1";"""
gtf_lines = [GtfLine(line) for line in gtf_lines.split("\n")]
self.assertEqual(len([_ for _ in gtf_lines if _.header]), 0)
transcript = Transcript(gtf_lines[0])
transcript.add_exons(gtf_lines[1:])
transcript.finalize()
fasta_seq = self.fasta[transcript.chrom][transcript.start - 1:transcript.end]
tr_neg = transcript.copy()
tchecker = TranscriptChecker(tr_neg, fasta_seq, strand_specific=False)
self.assertEqual(tchecker.strand, "-")
self.assertEqual(tchecker.fasta_seq, fasta_seq)
tchecker.check_strand()
self.assertEqual(tchecker.strand, "-")
tr_neg = transcript.copy()
tr_neg.strand = "+"
for ss in (False, True):
with self.subTest(ss=ss):
tchecker = TranscriptChecker(tr_neg.copy(), fasta_seq, strand_specific=ss)
tchecker.check_strand()
if ss:
self.assertEqual(tchecker.strand, "+")
self.assertTrue(tchecker.suspicious_splicing)
else:
self.assertEqual(tchecker.strand, "-")