예제 #1
0
    def test_wrong_cds(self):

        transcript = Transcript()
        transcript.chrom = "15"
        transcript.source = "protein_coding"
        transcript.start = 47631264
        transcript.end = 48051999

        exons = [(47631264, 47631416), (47704590, 47704669),
                 (47762671, 47762742), (47893062, 47893093),
                 (47895572, 47895655), (48051942, 48051999)]

        transcript.strand = "+"
        transcript.add_exons(exons)
        transcript.id = "ENST00000560636"
        transcript.parent = "ENSG00000137872"
        cds_line = "\t".join([
            "15", "protein_coding", "CDS", "48051996", "48051996", ".", "+",
            "0", "ID=ENST00000560636.cds1;Parent=ENST00000560636"
        ])
        cds_line = GffLine(cds_line)
        transcript.add_exon(cds_line)
        logger = Mikado.utilities.log_utils.create_null_logger()
        transcript.logger = logger
        with self.assertLogs("null", level="WARNING"):
            transcript.finalize()

        trimmed = trim_coding(transcript, logger, max_length=50)
        self.assertEqual(trimmed.start, 47631366)
        self.assertEqual(trimmed.end, 48051992)
예제 #2
0
    def test_non_redundant_as(self):

        t2 = Transcript()
        t2.chrom = "Chr1"
        t2.strand = "+"
        t2.score = 20
        t2.id = "G2.1"
        t2.parent = "G2"
        t2.start = 101
        t2.end = 1600

        t2.add_exons([(101, 500), (601, 700), (1001, 1300), (1401, 1460),
                      (1501, 1600)], "exon")
        t2.add_exons([(401, 500), (601, 700), (1001, 1300), (1401, 1440)],
                     "CDS")
        t2.finalize()

        self.locus.add_transcript_to_locus(t2)
        self.assertEqual(len(self.locus.transcripts), 2,
                         self.locus.transcripts)

        t3 = Transcript()
        t3.chrom = "Chr1"
        t3.strand = "+"
        t3.score = 20
        t3.id = "G3.1"
        t3.parent = "G3"
        t3.start = 201
        t3.end = 1630

        t3.add_exons([(201, 500), (601, 670), (1031, 1300), (1401, 1460),
                      (1501, 1630)], "exon")
        t3.add_exons([(401, 500), (601, 670), (1031, 1300), (1401, 1440)],
                     "CDS")
        t3.logger = self.logger
        t3.finalize()

        self.assertEqual(
            self.locus.is_alternative_splicing(t3)[:2], (True, "j"))
        self.locus.add_transcript_to_locus(t3)
        self.assertEqual(len(self.locus.transcripts), 3,
                         self.locus.transcripts)
예제 #3
0
    def test_noCDSOverlap(self):

        self.t1.strip_cds()
        self.assertEqual(self.t1.combined_cds_introns, set())
        self.t1.finalized = False
        self.t1.add_exons([(401, 500), (601, 700), (1001, 1100)], "CDS")
        self.t1.finalize()

        t2 = Transcript()
        t2.logger = self.logger
        t2.chrom = "Chr1"
        t2.strand = "+"
        t2.score = 1
        t2.id = "G2.1"
        t2.parent = "G2"
        t2.start = 101
        t2.end = 1470
        t2.add_exons([(101, 510), (601, 700), (960, 1350), (1421, 1470)])
        t2.add_exons([(1201, 1350), (1421, 1450)], "CDS")
        t2.finalize()

        self.assertTrue(self.t1.is_coding)
        self.assertTrue(t2.is_coding)

        self.assertGreaterEqual(
            0,
            overlap((self.t1.combined_cds_start, self.t1.combined_cds_end),
                    (t2.combined_cds_start, t2.combined_cds_end)),
            [(self.t1.combined_cds_start, self.t1.combined_cds_end),
             (t2.combined_cds_start, t2.combined_cds_end)])

        self.assertTrue(
            MonosublocusHolder.is_intersecting(self.t1, t2,
                                               logger=self.logger))
        self.assertFalse(
            MonosublocusHolder.is_intersecting(self.t1,
                                               t2,
                                               cds_only=True,
                                               logger=self.logger))