def testGetTranscriptsAnnot_withoutUTR_threeExons(self):
exon_1 = Exon(10, 40, "+", "chr1", "fwd_exon_1")
exon_2 = Exon(91, 150, "+", "chr1", "fwd_exon_2")
exon_3 = Exon(201, 361, "+", "chr1", "fwd_exon_3")
cds_1 = CDS(10, 40, "+", "chr1", "fwd_cds_1")
cds_2 = CDS(91, 150, "+", "chr1", "fwd_cds_2")
cds_3 = CDS(201, 361, "+", "chr1", "fwd_cds_3")
gene_1 = Gene(10, 350, None, "chr1", "gene_1", {"id": "g_1"})
transcrit_1 = Transcript(None,
None,
None,
"chr1",
"transcrit_1", {"id": "tr_1"},
parent=gene_1,
children=[exon_1, exon_2, exon_3])
protein_1 = Protein(None,
None,
None,
"chr1",
"protein_1",
children=[cds_1, cds_2, cds_3],
transcript=transcrit_1)
queries = [
Region(80, 100, None, "chr1", "query_1",
{"desc": "starts before exon_2 ; ends in exon_2."}),
Region(100, 180, None, "chr1", "query_2",
{"desc": "starts in exon_2 ; ends after exon_2."}),
Region(
91, 150, None, "chr1", "query_3", {
"desc":
"starts at the start of exon_2 ; ends at the end of exon_2."
}),
Region(80, 170, None, "chr1", "query_4",
{"desc": "starts before exon_2 ; ends after exon_2."}),
Region(80, 230, None, "chr1", "query_5",
{"desc": "starts before exon_2 ; ends in exon_3."}),
Region(100, 400, None, "chr1", "query_6",
{"desc": "starts in exon_2 ; ends after exon_3."}),
Region(100, 250, None, "chr1", "query_7",
{"desc": "starts in exon_2 ; ends in exon_3."}),
Region(80, 370, None, "chr1", "query_8",
{"desc": "starts before exon_2 ; ends after exon_3."}),
Region(90, 151, None, "chr1", "query_9", {
"desc":
"starts just before exon_2 ; ends just after exon_2."
})
]
# Expected forward 3 exons
expected = {
"query_1": {
"start_EXON": None,
"start_INTRON": "1/2",
"start_Protein_position": 11,
"end_EXON": "2/3",
"end_INTRON": None,
"end_Protein_position": 14
},
"query_2": {
"start_EXON": "2/3",
"start_INTRON": None,
"start_Protein_position": 14,
"end_EXON": None,
"end_INTRON": "2/2",
"end_Protein_position": 31
},
"query_3": {
"start_EXON": "2/3",
"start_INTRON": None,
"start_Protein_position": 11,
"end_EXON": "2/3",
"end_INTRON": None,
"end_Protein_position": 31
},
"query_4": {
"start_EXON": None,
"start_INTRON": "1/2",
"start_Protein_position": 11,
"end_EXON": None,
"end_INTRON": "2/2",
"end_Protein_position": 31
},
"query_5": {
"start_EXON": None,
"start_INTRON": "1/2",
"start_Protein_position": 11,
"end_EXON": "3/3",
"end_INTRON": None,
"end_Protein_position": 41
},
"query_6": {
"start_EXON": "2/3",
"start_INTRON": None,
"start_Protein_position": 14,
"end_EXON": "3/3",
"end_INTRON": None,
"end_Protein_position": 84
},
"query_7": {
"start_EXON": "2/3",
"start_INTRON": None,
"start_Protein_position": 14,
"end_EXON": "3/3",
"end_INTRON": None,
"end_Protein_position": 47
},
"query_8": {
"start_EXON": None,
"start_INTRON": "1/2",
"start_Protein_position": 11,
"end_EXON": "3/3",
"end_INTRON": None,
"end_Protein_position": 84
},
"query_9": {
"start_EXON": None,
"start_INTRON": "1/2",
"start_Protein_position": 11,
"end_EXON": None,
"end_INTRON": "2/2",
"end_Protein_position": 31
},
}
for query_name, query_res in expected.items():
for key, val in {
"SYMBOL": "gene_1",
"Gene": "g_1",
"Feature": "tr_1",
"Feature_type": "Transcript",
"STRAND": "1"
}.items():
query_res[key] = val
# Apply forward strand
for exon in transcrit_1.children:
exon.strand = "+"
for cds in protein_1.children:
cds.strand = "+"
transcrit_1.sortChildren()
protein_1.sortChildren()
# Assert
for curr_query in queries:
annotations = getTranscriptsAnnot(curr_query, [transcrit_1])
self.assertEqual([expected[curr_query.name]], annotations)
# Expected reverse 3 exons
expected = {
"query_1": {
"start_EXON": "2/3",
"start_INTRON": None,
"start_Protein_position": 71,
"end_EXON": None,
"end_INTRON": "2/2",
"end_Protein_position": 74
},
"query_2": {
"start_EXON": None,
"start_INTRON": "1/2",
"start_Protein_position": 54,
"end_EXON": "2/3",
"end_INTRON": None,
"end_Protein_position": 71
},
"query_3": {
"start_EXON": "2/3",
"start_INTRON": None,
"start_Protein_position": 54,
"end_EXON": "2/3",
"end_INTRON": None,
"end_Protein_position": 74
},
"query_4": {
"start_EXON": None,
"start_INTRON": "1/2",
"start_Protein_position": 54,
"end_EXON": None,
"end_INTRON": "2/2",
"end_Protein_position": 74
},
"query_5": {
"start_EXON": "1/3",
"start_INTRON": None,
"start_Protein_position": 44,
"end_EXON": None,
"end_INTRON": "2/2",
"end_Protein_position": 74
},
"query_6": {
"start_EXON": "1/3",
"start_INTRON": None,
"start_Protein_position": 1,
"end_EXON": "2/3",
"end_INTRON": None,
"end_Protein_position": 71
},
"query_7": {
"start_EXON": "1/3",
"start_INTRON": None,
"start_Protein_position": 38,
"end_EXON": "2/3",
"end_INTRON": None,
"end_Protein_position": 71
},
"query_8": {
"start_EXON": "1/3",
"start_INTRON": None,
"start_Protein_position": 1,
"end_EXON": None,
"end_INTRON": "2/2",
"end_Protein_position": 74
},
"query_9": {
"start_EXON": None,
"start_INTRON": "1/2",
"start_Protein_position": 54,
"end_EXON": None,
"end_INTRON": "2/2",
"end_Protein_position": 74
}
}
for query_name, query_res in expected.items():
for key, val in {
"SYMBOL": "gene_1",
"Gene": "g_1",
"Feature": "tr_1",
"Feature_type": "Transcript",
"STRAND": "-1"
}.items():
query_res[key] = val
# Apply reverse strand
for exon in transcrit_1.children:
exon.strand = "-"
for cds in protein_1.children:
cds.strand = "-"
transcrit_1.sortChildren()
protein_1.sortChildren()
# Asert
for curr_query in queries:
annotations = getTranscriptsAnnot(curr_query, [transcrit_1])
self.assertEqual([expected[curr_query.name]], annotations)