def test_filter_config_file():
config = pd.read_csv(data_file("filters.csv"), sep=None, engine="python")
result = TypingResult(fromfile=data_file("prof/deep-raw.json"))
result.filter(static=5, dynamic=0.02, config=config)
assert len(result.haplotypes("mh01XYZ-1")) == 8
assert len(result.haplotypes("mh02XYZ-2")) == 2
assert len(result.haplotypes("mh02XYZ-3")) == 2
def test_haplotypes():
simprof = SimulatedProfile.populate_from_bed(data_file("gttest.bed.gz"))
typeprof = TypingResult(fromfile=data_file("prof/gttest.json"))
assert simprof.haplotypes("BoGuSlOcUs") == set()
assert typeprof.haplotypes("BoGuSlOcUs") == set()
assert simprof.haplotypes("MHDBL000135") == set(["G,C,T", "G,T,C"])
assert typeprof.haplotypes("MHDBL000135") == set(["G,C,T", "G,T,C"])
assert simprof.haplotypes("MHDBL000135", index=0) == set(["G,C,T"])
assert simprof.haplotypes("MHDBL000135", index=1) == set(["G,T,C"])
assert typeprof.haplotypes("MHDBL000135", index=0) == set()
def test_type_cli_simple(tmp_path):
outfile = str(tmp_path / "typing-result.json")
arglist = [
"type",
"--out",
outfile,
data_file("pashtun-sim/tiny-panel.tsv"),
data_file("pashtun-sim/aligned-reads.bam"),
]
args = microhapulator.cli.get_parser().parse_args(arglist)
microhapulator.cli.type.main(args)
result = TypingResult(fromfile=outfile)
assert result.haplotypes("mh13KK-218") == set()
assert result.data["markers"]["mh13KK-218"]["typing_result"] == {
"C,T,C,G": 1,
"C,T,T,T": 1,
"G,T,C,T": 1,
"T,A,C,T": 1,
"T,G,C,T": 3,
"T,G,T,T": 2,
"T,T,A,T": 5,
"T,T,C,A": 1,
"T,T,C,C": 2,
"T,T,C,G": 2,
"T,T,C,T": 1178,
"T,T,G,T": 2,
"T,T,T,A": 2,
"T,T,T,G": 6,
"T,T,T,T": 1170,
}
assert result.haplotypes("mh21KK-320") == set()
assert result.data["markers"]["mh21KK-320"]["typing_result"] == {
"G,A,A,A": 1,
"G,A,C,A": 3,
"G,A,G,A": 3,
"G,A,T,A": 1075,
"G,A,T,C": 1,
"G,A,T,G": 1,
"G,A,T,T": 2,
"G,C,C,A": 1,
"G,C,T,A": 4,
"G,G,A,A": 2,
"G,G,A,T": 1,
"G,G,C,A": 1075,
"G,G,C,C": 3,
"G,G,C,G": 12,
"G,G,C,T": 5,
"G,G,T,A": 4,
"G,T,C,A": 1,
"T,G,C,A": 1,
}