def test_doublet(self):
aln_df = pipeline.call_lineage_groups(
self.doublet,
self.dir_path + "/test_files",
min_umi_per_cell=1,
min_intbc_thresh=0.5,
kinship_thresh=0.5,
inter_doublet_threshold=0.6,
)
expected_rows = {
("A", "XX"): (1, 2),
("B", "XX"): (1, 2),
("D", "XY"): (2, 2),
("E", "XY"): (2, 2),
}
for pair in expected_rows:
expected_lineage = expected_rows[pair]
self.assertEqual(
aln_df.loc[(aln_df["cellBC"] == pair[0])
& (aln_df["intBC"] == pair[1]),
"lineageGrp", ].iloc[0],
expected_lineage[0],
)
self.assertEqual(
aln_df.loc[(aln_df["cellBC"] == pair[0])
& (aln_df["intBC"] == pair[1]), "UMI", ].iloc[0],
expected_lineage[1],
)
def test_reassign(self):
aln_df = pipeline.call_lineage_groups(
self.reassign,
self.dir_path + "/test_files",
min_umi_per_cell=0,
min_intbc_thresh=0.25,
kinship_thresh=0.1,
)
expected_rows = {
("A", "XX"): (1, 2),
("B", "XX"): (1, 2),
("C", "XX"): (1, 2),
("D", "XX"): (1, 1),
("E", "XZ"): (1, 1),
("F", "XZ"): (1, 3),
}
for pair in expected_rows:
expected_lineage = expected_rows[pair]
self.assertEqual(
aln_df.loc[(aln_df["cellBC"] == pair[0])
& (aln_df["intBC"] == pair[1]),
"lineageGrp", ].iloc[0],
expected_lineage[0],
)
self.assertEqual(
aln_df.loc[(aln_df["cellBC"] == pair[0])
& (aln_df["intBC"] == pair[1]), "UMI", ].iloc[0],
expected_lineage[1],
)
def test_format(self):
aln_df = pipeline.call_lineage_groups(
self.doublet,
self.dir_path + "/test_files",
min_umi_per_cell=1,
min_intbc_thresh=0.5,
kinship_thresh=0.5,
inter_doublet_threshold=0.6,
)
expected_columns = [
"cellBC",
"UMI",
"readCount",
"intBC",
"r1",
"r2",
"r3",
"lineageGrp",
]
for column in expected_columns:
self.assertIn(column, aln_df.columns)